Merge 'Fix hang in multishard_writer' from Asias

"
This series fix hang in multishard_writer when error happens. It contains
- multishard_writer: Abort the queue attached to consumers when producer fails
- repair: Fix hang when the writer is dead

Fixes #6241
Refs: #6248
"

* asias-stream_fix_multishard_writer_hang:
  repair: Fix hang when the writer is dead
  mutation_writer_test: Add test_multishard_writer_producer_aborts
  multishard_writer: Abort the queue attached to consumers when producer fails

(cherry picked from commit 8925e00e96)

.clang-format

@@ -1,209 +0,0 @@
----
-Language: Cpp
-AccessModifierOffset: -4
-AlignAfterOpenBracket: DontAlign
-AlignArrayOfStructures: None
-AlignConsecutiveAssignments:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: true
-AlignConsecutiveBitFields:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: false
-AlignConsecutiveDeclarations:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: false
-AlignConsecutiveMacros:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCompound: false
-  PadOperators: false
-AlignConsecutiveShortCaseStatements:
-  Enabled: false
-  AcrossEmptyLines: false
-  AcrossComments: false
-  AlignCaseColons: false
-AlignEscapedNewlines: Right
-AlignOperands: Align
-AlignTrailingComments:
-  Kind: Always
-  OverEmptyLines: 0
-AllowAllArgumentsOnNextLine: true
-AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortBlocksOnASingleLine: Never
-AllowShortCaseLabelsOnASingleLine: false
-AllowShortEnumsOnASingleLine: true
-AllowShortFunctionsOnASingleLine: None
-AllowShortIfStatementsOnASingleLine: Never
-AllowShortLambdasOnASingleLine: Empty
-AllowShortLoopsOnASingleLine: false
-AlwaysBreakAfterDefinitionReturnType: None
-AlwaysBreakAfterReturnType: None
-AlwaysBreakBeforeMultilineStrings: false
-AlwaysBreakTemplateDeclarations: Yes
-AttributeMacros:
-  - __capability
-BinPackArguments: true
-BinPackParameters: true
-BitFieldColonSpacing: Both
-BraceWrapping:
-  AfterCaseLabel: false
-  AfterClass: false
-  AfterControlStatement: Never
-  AfterEnum: false
-  AfterExternBlock: false
-  AfterFunction: false
-  AfterNamespace: false
-  AfterObjCDeclaration: false
-  AfterStruct: false
-  AfterUnion: false
-  BeforeCatch: false
-  BeforeElse: false
-  BeforeLambdaBody: false
-  BeforeWhile: false
-  IndentBraces: false
-  SplitEmptyFunction: true
-  SplitEmptyRecord: true
-  SplitEmptyNamespace: true
-BreakAfterAttributes: Never
-BreakAfterJavaFieldAnnotations: false
-BreakArrays: true
-BreakBeforeBinaryOperators: None
-BreakBeforeConceptDeclarations: Always
-BreakBeforeBraces: Attach
-BreakBeforeInlineASMColon: OnlyMultiline
-BreakBeforeTernaryOperators: true
-BreakConstructorInitializers: BeforeComma
-BreakInheritanceList: BeforeColon
-BreakStringLiterals: true
-ColumnLimit: 160
-CommentPragmas: '^ IWYU pragma:'
-CompactNamespaces: false
-ConstructorInitializerIndentWidth: 4
-ContinuationIndentWidth: 8
-Cpp11BracedListStyle: true
-DerivePointerAlignment: false
-DisableFormat: false
-EmptyLineAfterAccessModifier: Never
-EmptyLineBeforeAccessModifier: LogicalBlock
-ExperimentalAutoDetectBinPacking: false
-FixNamespaceComments: true
-ForEachMacros:
-  - foreach
-  - Q_FOREACH
-  - BOOST_FOREACH
-IfMacros:
-  - KJ_IF_MAYBE
-IndentAccessModifiers: false
-IndentCaseBlocks: false
-IndentCaseLabels: false
-IndentExternBlock: AfterExternBlock
-IndentGotoLabels: true
-IndentPPDirectives: None
-IndentRequiresClause: true
-IndentWidth: 4
-IndentWrappedFunctionNames: false
-InsertBraces: false
-InsertNewlineAtEOF: true
-InsertTrailingCommas: None
-IntegerLiteralSeparator:
-  Binary: 0
-  BinaryMinDigits: 0
-  Decimal: 0
-  DecimalMinDigits: 0
-  Hex: 0
-  HexMinDigits: 0
-JavaScriptQuotes: Leave
-JavaScriptWrapImports: true
-KeepEmptyLinesAtTheStartOfBlocks: true
-KeepEmptyLinesAtEOF: false
-LambdaBodyIndentation: Signature
-LineEnding: DeriveLF
-MacroBlockBegin: ''
-MacroBlockEnd: ''
-MaxEmptyLinesToKeep: 2
-NamespaceIndentation: None
-PackConstructorInitializers: BinPack
-PenaltyBreakAssignment: 2
-PenaltyBreakBeforeFirstCallParameter: 19
-PenaltyBreakComment: 300
-PenaltyBreakFirstLessLess: 120
-PenaltyBreakOpenParenthesis: 0
-PenaltyBreakString: 1000
-PenaltyBreakTemplateDeclaration: 10
-PenaltyExcessCharacter: 1000000
-PenaltyIndentedWhitespace: 0
-PenaltyReturnTypeOnItsOwnLine: 60
-PointerAlignment: Left
-PPIndentWidth: -1
-QualifierAlignment: Leave
-ReferenceAlignment: Pointer
-ReflowComments: true
-RemoveBracesLLVM: false
-RemoveParentheses: Leave
-RemoveSemicolon: false
-RequiresClausePosition: OwnLine
-RequiresExpressionIndentation: OuterScope
-SeparateDefinitionBlocks: Leave
-ShortNamespaceLines: 1
-SortIncludes: Never
-SortJavaStaticImport: Before
-SortUsingDeclarations: Never
-SpaceAfterCStyleCast: false
-SpaceAfterLogicalNot: false
-SpaceAfterTemplateKeyword: true
-SpaceAroundPointerQualifiers: Default
-SpaceBeforeAssignmentOperators: true
-SpaceBeforeCaseColon: false
-SpaceBeforeCpp11BracedList: false
-SpaceBeforeCtorInitializerColon: true
-SpaceBeforeInheritanceColon: true
-SpaceBeforeJsonColon: false
-SpaceBeforeParens: ControlStatements
-SpaceBeforeParensOptions:
-  AfterControlStatements: true
-  AfterForeachMacros: true
-  AfterFunctionDefinitionName: false
-  AfterFunctionDeclarationName: false
-  AfterIfMacros: true
-  AfterOverloadedOperator: false
-  AfterRequiresInClause: false
-  AfterRequiresInExpression: false
-  BeforeNonEmptyParentheses: false
-SpaceBeforeRangeBasedForLoopColon: true
-SpaceBeforeSquareBrackets: false
-SpaceInEmptyBlock: false
-SpacesBeforeTrailingComments: 1
-SpacesInAngles: Never
-SpacesInContainerLiterals: true
-SpacesInLineCommentPrefix:
-  Minimum: 1
-  Maximum: -1
-SpacesInParens: Never
-SpacesInParensOptions:
-  InCStyleCasts: false
-  InConditionalStatements: false
-  InEmptyParentheses: false
-  Other: false
-SpacesInSquareBrackets: false
-Standard: Latest
-TabWidth: 8
-UseTab: Never
-VerilogBreakBetweenInstancePorts: true
-WhitespaceSensitiveMacros:
-  - BOOST_PP_STRINGIZE
-  - CF_SWIFT_NAME
-  - NS_SWIFT_NAME
-  - PP_STRINGIZE
-  - STRINGIZE
-...
-

.dockerignore

@@ -1,4 +1,3 @@
 .git
 build
 seastar/build
-testlog

.gitattributes

@@ -1,5 +1,2 @@
 *.cc diff=cpp
 *.hh diff=cpp
-*.svg binary
-docs/_static/api/js/* binary
-pgo/profiles/** filter=lfs diff=lfs merge=lfs -text

.github/CODEOWNERS

@@ -1,103 +0,0 @@
-# AUTH
-auth/* @nuivall
-
-# CACHE
-row_cache* @tgrabiec
-*mutation* @tgrabiec
-test/boost/mvcc* @tgrabiec
-
-# CDC
-cdc/* @kbr-scylla @elcallio @piodul
-test/cql/cdc_* @kbr-scylla @elcallio @piodul
-test/boost/cdc_* @kbr-scylla @elcallio @piodul
-
-# COMMITLOG / BATCHLOG
-db/commitlog/* @elcallio @eliransin
-db/batch* @elcallio
-
-# COORDINATOR
-service/storage_proxy* @gleb-cloudius
-
-# COMPACTION
-compaction/* @raphaelsc
-
-# CQL TRANSPORT LAYER
-transport/*
-
-# CQL QUERY LANGUAGE
-cql3/* @tgrabiec @nuivall
-
-# COUNTERS
-counters* @nuivall
-tests/counter_test* @nuivall
-
-# DOCS
-docs/* @annastuchlik @tzach
-docs/alternator @annastuchlik @tzach @nyh
-
-# GOSSIP
-gms/* @tgrabiec @asias @kbr-scylla
-
-# DOCKER
-dist/docker/*
-
-# LSA
-utils/logalloc* @tgrabiec
-
-# MATERIALIZED VIEWS
-db/view/* @nyh @piodul
-cql3/statements/*view* @nyh @piodul
-test/boost/view_* @nyh @piodul
-
-# PACKAGING
-dist/* @syuu1228
-
-# REPAIR
-repair/* @tgrabiec @asias
-
-# SCHEMA MANAGEMENT
-db/schema_tables* @tgrabiec
-service/migration* @tgrabiec
-schema* @tgrabiec
-
-# SECONDARY INDEXES
-index/* @nyh @piodul
-cql3/statements/*index* @nyh @piodul
-test/boost/*index* @nyh @piodul
-
-# SSTABLES
-sstables/* @tgrabiec @raphaelsc
-
-# STREAMING
-streaming/* @tgrabiec @asias
-service/storage_service.* @tgrabiec @asias
-
-# ALTERNATOR
-alternator/* @nyh
-test/alternator/* @nyh
-
-# HINTED HANDOFF
-db/hints/* @piodul @vladzcloudius @eliransin
-
-# REDIS
-redis/* @syuu1228
-test/redis/* @syuu1228
-
-# READERS
-reader_* @denesb
-querier* @denesb
-test/boost/mutation_reader_test.cc @denesb
-test/boost/querier_cache_test.cc @denesb
-
-# PYTEST-BASED CQL TESTS
-test/cqlpy/* @nyh
-
-# RAFT
-raft/* @kbr-scylla @gleb-cloudius @kostja
-test/raft/* @kbr-scylla @gleb-cloudius @kostja
-
-# HEAT-WEIGHTED LOAD BALANCING
-db/heat_load_balance.* @nyh @gleb-cloudius
-
-# Tools
-tools/* @denesb

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,15 @@
+This is Scylla's bug tracker, to be used for reporting bugs only.
+If you have a question about Scylla, and not a bug, please ask it in
+our mailing-list at scylladb-dev@googlegroups.com or in our slack channel.
+
+- [] I have read the disclaimer above, and I am reporting a suspected malfunction in Scylla.
+
+*Installation details*
+Scylla version (or git commit hash):
+Cluster size:
+OS (RHEL/CentOS/Ubuntu/AWS AMI):
+
+*Hardware details (for performance issues)*          Delete if unneeded
+Platform (physical/VM/cloud instance type/docker):
+Hardware: sockets= cores= hyperthreading= memory=
+Disks: (SSD/HDD, count)

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,86 +0,0 @@
-name: "Report a bug"
-description: "File a bug report."
-title: "[Bug]: "
-type: "bug"
-labels: bug
-body:
-  - type: checkboxes
-    id: terms
-    attributes:
-      label: Code of Conduct
-      description: "This is Scylla's bug tracker, to be used for reporting bugs only.
-If you have a question about Scylla, and not a bug, please ask it in
-our forum at https://forum.scylladb.com/ or in our slack channel https://slack.scylladb.com/ "
-      options:
-        - label: I have read the disclaimer above and am reporting a suspected malfunction in Scylla.
-          required: true
-
-  - type: input
-    id: product-version
-    attributes:
-      label: product version
-      description: Scylla version (or git commit hash)
-      placeholder: ex. scylla-6.1.1
-    validations:
-      required: true
-      
-  - type: input
-    id: cluster-size
-    attributes:
-      label: Cluster Size
-    validations:
-      required: true  
-      
-  - type: input
-    id: os
-    attributes:
-      label: OS
-      placeholder: RHEL/CentOS/Ubuntu/AWS AMI
-    validations:
-      required: true
-      
-  - type: textarea
-    id: additional-data
-    attributes:
-      label: Additional Environmental Data
-      #description: 
-      placeholder: Add additional data
-      value: "Platform (physical/VM/cloud instance type/docker):\n
-Hardware: sockets=   cores=   hyperthreading=   memory=\n
-Disks: (SSD/HDD, count)"
-    validations:
-      required: false
-      
-  - type: textarea
-    id: reproducer-steps
-    attributes:
-      label: Reproduction Steps
-      placeholder: Describe how to reproduce the problem
-      value: "The steps to reproduce the problem are:"
-    validations:
-      required: true
-      
-  - type: textarea
-    id: the-problem
-    attributes:
-      label: What is the problem?
-      placeholder: Describe the problem you found
-      value: "The problem is that"
-    validations:
-      required: true
-      
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: Expected behavior?
-      placeholder: Describe what should have happened
-      value: "I expected that "
-    validations:
-      required: true
-      
-  - type: textarea
-    id: logs
-    attributes:
-      label: Relevant log output
-      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
-      render: shell

.github/clang-include-cleaner.json

@@ -1,20 +0,0 @@
-{
-    "problemMatcher": [
-        {
-            "owner": "clang-include-cleaner",
-            "severity": "error",
-            "pattern": [
-                {
-                    "regexp": "^([^\\-\\+].*)$",
-                    "file": 1
-                },
-                {
-                    "regexp": "^(-\\s+[^\\s]+)\\s+@Line:(\\d+)$",
-                    "line": 2,
-                    "message": 1,
-                    "loop": true
-                }
-            ]
-        }
-    ]
-}

.github/clang-matcher.json

@@ -1,18 +0,0 @@
-{
-    "problemMatcher": [
-        {
-            "owner": "clang",
-            "pattern": [
-                {
-                    "regexp": "^([^:]+):(\\d+):(\\d+):\\s+(warning|error):\\s+(.*?)\\s+\\[(.*?)\\]$",
-                    "file": 1,
-                    "line": 2,
-                    "column": 3,
-                    "severity": 4,
-                    "message": 5,
-                    "code": 6
-                }
-            ]
-        }
-    ]
-}

.github/copilot-instructions.md

@@ -1,101 +0,0 @@
-# ScyllaDB Development Instructions
-
-## Project Context
-High-performance distributed NoSQL database. Core values: performance, correctness, readability.
-
-## Build System
-
-### Modern Build (configure.py + ninja)
-```bash
-# Configure (run once per mode, or when switching modes)
-./configure.py --mode=<mode>  # mode: dev, debug, release, sanitize
-
-# Build everything
-ninja <mode>-build  # e.g., ninja dev-build
-
-# Build Scylla binary only (sufficient for Python integration tests)
-ninja build/<mode>/scylla
-
-# Build specific test
-ninja build/<mode>/test/boost/<test_name>
-```
-
-## Running Tests
-
-### C++ Unit Tests
-```bash
-# Run all tests in a file
-./test.py --mode=<mode> test/<suite>/<test_name>.cc
-
-# Run a single test case from a file
-./test.py --mode=<mode> test/<suite>/<test_name>.cc::<test_case_name>
-
-# Examples
-./test.py --mode=dev test/boost/memtable_test.cc
-./test.py --mode=dev test/raft/raft_server_test.cc::test_check_abort_on_client_api
-```
-
-**Important:** 
-- Use full path with `.cc` extension (e.g., `test/boost/test_name.cc`, not `boost/test_name`)
-- To run a single test case, append `::<test_case_name>` to the file path
-- If you encounter permission issues with cgroup metric gathering, add `--no-gather-metrics` flag
-
-**Rebuilding Tests:**
-- test.py does NOT automatically rebuild when test source files are modified
-- Many tests are part of composite binaries (e.g., `combined_tests` in test/boost contains multiple test files)
-- To find which binary contains a test, check `configure.py` in the repository root (primary source) or `test/<suite>/CMakeLists.txt`
-- To rebuild a specific test binary: `ninja build/<mode>/test/<suite>/<binary_name>`
-- Examples: 
-  - `ninja build/dev/test/boost/combined_tests` (contains group0_voter_calculator_test.cc and others)
-  - `ninja build/dev/test/raft/replication_test` (standalone Raft test)
-
-### Python Integration Tests
-```bash
-# Only requires Scylla binary (full build usually not needed)
-ninja build/<mode>/scylla
-
-# Run all tests in a file
-./test.py --mode=<mode> test/<suite>/<test_name>.py
-
-# Run a single test case from a file
-./test.py --mode=<mode> test/<suite>/<test_name>.py::<test_function_name>
-
-# Run all tests in a directory
-./test.py --mode=<mode> test/<suite>/
-
-# Examples
-./test.py --mode=dev test/alternator/
-./test.py --mode=dev test/cluster/test_raft_voters.py::test_raft_limited_voters_retain_coordinator
-./test.py --mode=dev test/cqlpy/test_json.py
-
-# Optional flags
-./test.py --mode=dev test/cluster/test_raft_no_quorum.py -v  # Verbose output
-./test.py --mode=dev test/cluster/test_raft_no_quorum.py --repeat 5  # Repeat test 5 times
-```
-
-**Important:**
-- Use full path with `.py` extension (e.g., `test/cluster/test_raft_no_quorum.py`, not `cluster/test_raft_no_quorum`)
-- To run a single test case, append `::<test_function_name>` to the file path
-- Add `-v` for verbose output
-- Add `--repeat <num>` to repeat a test multiple times
-- After modifying C++ source files, only rebuild the Scylla binary for Python tests - building the entire repository is unnecessary
-
-## Code Philosophy
-- Performance matters in hot paths (data read/write, inner loops)
-- Self-documenting code through clear naming
-- Comments explain "why", not "what"
-- Prefer standard library over custom implementations
-- Strive for simplicity and clarity, add complexity only when clearly justified
-- Question requests: don't blindly implement requests - evaluate trade-offs, identify issues, and suggest better alternatives when appropriate
-- Consider different approaches, weigh pros and cons, and recommend the best fit for the specific context
-
-## Test Philosophy
-- Performance matters. Tests should run as quickly as possible. Sleeps in the code are highly discouraged and should be avoided, to reduce run time and flakiness.
-- Stability matters. Tests should be stable. New tests should be executed 100 times at least to ensure they pass 100 out of 100 times. (use --repeat 100 --max-failures 1 when running it)
-- Unit tests should ideally test one thing and one thing only.
-- Tests for bug fixes should run before the fix - and show the failure and after the fix - and show they now pass.
-- Tests for bug fixes should have in their comments which bug fixes (GitHub or JIRA issue) they test.
-- Tests in debug are always slower, so if needed, reduce number of iterations, rows, data used, cycles, etc. in debug mode.
-- Tests should strive to be repeatable, and not use random input that will make their results unpredictable.
-- Tests should consume as little resources as possible. Prefer running tests on a single node if it is sufficient, for example.
-

.github/dependabot.yml

@@ -1,9 +0,0 @@
-version: 2
-updates:
-- package-ecosystem: "uv"
-  directory: "/docs"
-  schedule:
-    interval: "daily"
-  allow:
-  - dependency-name: "sphinx-scylladb-theme"
-  - dependency-name: "sphinx-multiversion-scylla"

.github/instructions/cpp.instructions.md

@@ -1,115 +0,0 @@
----
-applyTo: "**/*.{cc,hh}"
----
-
-# C++ Guidelines
-
-**Important:** Always match the style and conventions of existing code in the file and directory.
-
-## Memory Management
-- Prefer stack allocation whenever possible
-- Use `std::unique_ptr` by default for dynamic allocations
-- `new`/`delete` are forbidden (use RAII)
-- Use `seastar::lw_shared_ptr` or `seastar::shared_ptr` for shared ownership within same shard
-- Use `seastar::foreign_ptr` for cross-shard sharing
-- Avoid `std::shared_ptr` except when interfacing with external C++ APIs
-- Avoid raw pointers except for non-owning references or C API interop
-
-## Seastar Asynchronous Programming
-- Use `seastar::future<T>` for all async operations
-- Prefer coroutines (`co_await`, `co_return`) over `.then()` chains for readability
-- Coroutines are preferred over `seastar::do_with()` for managing temporary state
-- In hot paths where futures are ready, continuations may be more efficient than coroutines
-- Chain futures with `.then()`, don't block with `.get()` (unless in `seastar::thread` context)
-- All I/O must be asynchronous (no blocking calls)
-- Use `seastar::gate` for shutdown coordination
-- Use `seastar::semaphore` for resource limiting (not `std::mutex`)
-- Break long loops with `maybe_yield()` to avoid reactor stalls
-
-## Coroutines
-```cpp
-seastar::future<T> func() {
-    auto result = co_await async_operation();
-    co_return result;
-}
-```
-
-## Error Handling
-- Throw exceptions for errors (futures propagate them automatically)
-- In data path: avoid exceptions, use `std::expected` (or `boost::outcome`) instead
-- Use standard exceptions (`std::runtime_error`, `std::invalid_argument`)
-- Database-specific: throw appropriate schema/query exceptions
-
-## Performance
-- Pass large objects by `const&` or `&&` (move semantics)
-- Use `std::string_view` for non-owning string references
-- Avoid copies: prefer move semantics
-- Use `utils::chunked_vector` instead of `std::vector` for large allocations (>128KB)
-- Minimize dynamic allocations in hot paths
-
-## Database-Specific Types
-- Use `schema_ptr` for schema references
-- Use `mutation` and `mutation_partition` for data modifications
-- Use `partition_key` and `clustering_key` for keys
-- Use `api::timestamp_type` for database timestamps
-- Use `gc_clock` for garbage collection timing
-
-## Style
-- C++23 standard (prefer modern features, especially coroutines)
-- Use `auto` when type is obvious from RHS
-- Avoid `auto` when it obscures the type
-- Use range-based for loops: `for (const auto& item : container)`
-- Use standard algorithms when they clearly simplify code (e.g., replacing 10-line loops)
-- Avoid chaining multiple algorithms if a straightforward loop is clearer
-- Mark functions and variables `const` whenever possible
-- Use scoped enums: `enum class` (not unscoped `enum`)
-
-## Headers
-- Use `#pragma once`
-- Include order: own header, C++ std, Seastar, Boost, project headers
-- Forward declare when possible
-- Never `using namespace` in headers (exception: `using namespace seastar` is globally available via `seastarx.hh`)
-
-## Documentation
-- Public APIs require clear documentation
-- Implementation details should be self-evident from code
-- Use `///` or Doxygen `/** */` for public documentation, `//` for implementation notes - follow the existing style
-
-## Naming
-- `snake_case` for most identifiers (classes, functions, variables, namespaces)
-- Template parameters: `CamelCase` (e.g., `template<typename ValueType>`)
-- Member variables: prefix with `_` (e.g., `int _count;`)
-- Structs (value-only): no `_` prefix on members
-- Constants and `constexpr`: `snake_case` (e.g., `static constexpr int max_size = 100;`)
-- Files: `.hh` for headers, `.cc` for source
-
-## Formatting
-- 4 spaces indentation, never tabs
-- Opening braces on same line as control structure (except namespaces)
-- Space after keywords: `if (`, `while (`, `return `
-- Whitespace around operators matches precedence: `*a + *b` not `* a+* b`
-- Line length: keep reasonable (<160 chars), use continuation lines with double indent if needed
-- Brace all nested scopes, even single statements
-- Minimal patches: only format code you modify, never reformat entire files
-
-## Logging
-- Use structured logging with appropriate levels: DEBUG, INFO, WARN, ERROR
-- Include context in log messages (e.g., request IDs)
-- Never log sensitive data (credentials, PII)
-
-## Forbidden
-- `malloc`/`free`
-- `printf` family (use logging or fmt)
-- Raw pointers for ownership
-- `using namespace` in headers
-- Blocking operations: `std::sleep`, `std::read`, `std::mutex` (use Seastar equivalents)
-- `std::atomic` (reserved for very special circumstances only)
-- Macros (use `inline`, `constexpr`, or templates instead)
-
-## Testing
-When modifying existing code, follow TDD: create/update test first, then implement.
-- Examine existing tests for style and structure
-- Use Boost.Test framework
-- Use `SEASTAR_THREAD_TEST_CASE` for Seastar asynchronous tests
-- Aim for high code coverage, especially for new features and bug fixes
-- Maintain bisectability: all tests must pass in every commit. Mark failing tests with `BOOST_FAIL()` or similar, then fix in subsequent commit

.github/instructions/python.instructions.md

@@ -1,51 +0,0 @@
----
-applyTo: "**/*.py"
----
-
-# Python Guidelines
-
-**Important:** Match existing code style. Some directories (like `test/cqlpy` and `test/alternator`) prefer simplicity over type hints and docstrings.
-
-## Style
-- Follow PEP 8
-- Use type hints for function signatures (unless directory style omits them)
-- Use f-strings for formatting
-- Line length: 160 characters max
-- 4 spaces for indentation
-
-## Imports
-Order: standard library, third-party, local imports
-```python
-import os
-import sys
-
-import pytest
-from cassandra.cluster import Cluster
-
-from test.utils import setup_keyspace
-```
-
-Never use `from module import *`
-
-## Documentation
-All public functions/classes need docstrings (unless the current directory conventions omit them):
-```python
-def my_function(arg1: str, arg2: int) -> bool:
-    """
-    Brief summary of function purpose.
-
-    Args:
-        arg1: Description of first argument.
-        arg2: Description of second argument.
-
-    Returns:
-        Description of return value.
-    """
-    pass
-```
-
-## Testing Best Practices
-- Maintain bisectability: all tests must pass in every commit
-- Mark currently-failing tests with `@pytest.mark.xfail`, unmark when fixed
-- Use descriptive names that convey intent
-- Docstrings/comments should explain what the test verifies and why, and if it reproduces a specific issue or how it fits into the larger test suite

.github/mergify.yml

@@ -1,92 +0,0 @@
-pull_request_rules:
-  - name: put PR in draft if conflicts
-    conditions:
-      - label = conflicts
-      - author = mergify[bot]
-      - head ~= ^mergify/
-    actions:
-      edit:
-         draft: true
-  - name: Delete mergify backport branch
-    conditions:
-      - base~=branch-
-      - or:
-        - merged
-        - closed
-    actions:
-      delete_head_branch:
-  - name: Automate backport pull request 6.2
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/6.2 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 6.2] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-          Refs #{{number}}
-        branches:
-          - branch-6.2
-        assignees:
-          - "{{ author }}"
-  - name: Automate backport pull request 6.1
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/6.1 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 6.1] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-           Refs #{{number}}
-        branches:
-          - branch-6.1
-        assignees:
-          - "{{ author }}"
-  - name: Automate backport pull request 6.0
-    conditions:
-      - or:
-        - closed
-        - merged
-      - or:
-          - base=master
-          - base=next
-      - label=backport/6.0 # The PR must have this label to trigger the backport
-      - label=promoted-to-master
-    actions:
-      copy:
-        title: "[Backport 6.0] {{ title }}"
-        body: |
-          {{ body }}
-
-          {% for c in commits %}
-          (cherry picked from commit {{ c.sha }})
-          {% endfor %}
-
-           Refs #{{number}}
-        branches:
-          - branch-6.0
-        assignees:
-          - "{{ author }}"

.github/pull_request_template.md

@@ -1 +0,0 @@
-**Please replace this line with justification for the backport/\* labels added to this PR**

.github/scripts/auto-backport.py

@@ -1,245 +0,0 @@
-#!/usr/bin/env python3
-
-import argparse
-import os
-import re
-import sys
-import tempfile
-import logging
-
-from github import Github, GithubException
-from git import Repo, GitCommandError
-
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def is_pull_request():
-    return '--pull-request' in sys.argv[1:]
-
-
-def parse_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--repo', type=str, required=True, help='Github repository name')
-    parser.add_argument('--base-branch', type=str, default='refs/heads/master', help='Base branch')
-    parser.add_argument('--commits', default=None, type=str, help='Range of promoted commits.')
-    parser.add_argument('--pull-request', type=int, help='Pull request number to be backported')
-    parser.add_argument('--head-commit', type=str, required=is_pull_request(), help='The HEAD of target branch after the pull request specified by --pull-request is merged')
-    parser.add_argument('--github-event', type=str, help='Get GitHub event type')
-    return parser.parse_args()
-
-
-def create_pull_request(repo, new_branch_name, base_branch_name, pr, backport_pr_title, commits, is_draft, is_collaborator):
-    pr_body = f'{pr.body}\n\n'
-    for commit in commits:
-        pr_body += f'- (cherry picked from commit {commit})\n\n'
-    pr_body += f'Parent PR: #{pr.number}'
-    try:
-        backport_pr = repo.create_pull(
-            title=backport_pr_title,
-            body=pr_body,
-            head=f'scylladbbot:{new_branch_name}',
-            base=base_branch_name,
-            draft=is_draft
-        )
-        logging.info(f"Pull request created: {backport_pr.html_url}")
-        labels_to_add = []
-        priority_labels = {"P0", "P1"}
-        parent_pr_labels = [label.name for label in pr.labels]
-        for label in priority_labels:
-            if label in parent_pr_labels:
-                labels_to_add.append(label)
-                labels_to_add.append("force_on_cloud")
-                logging.info(f"Adding {label} and force_on_cloud labels from parent PR to backport PR")
-                break  # Only apply the highest priority label
-        
-        if is_collaborator:
-            backport_pr.add_to_assignees(pr.user)
-        if is_draft:
-            labels_to_add.append("conflicts")
-            pr_comment = f"@{pr.user.login} - This PR was marked as draft because it has conflicts\n"
-            pr_comment += "Please resolve them and remove the 'conflicts' label. The PR will be made ready for review automatically."
-            backport_pr.create_issue_comment(pr_comment)
-        
-        # Apply all labels at once if we have any
-        if labels_to_add:
-            backport_pr.add_to_labels(*labels_to_add)
-            logging.info(f"Added labels to backport PR: {labels_to_add}")
-
-        logging.info(f"Assigned PR to original author: {pr.user}")
-        return backport_pr
-    except GithubException as e:
-        if 'A pull request already exists' in str(e):
-            logging.warning(f'A pull request already exists for {pr.user}:{new_branch_name}')
-        else:
-            logging.error(f'Failed to create PR: {e}')
-
-
-def get_pr_commits(repo, pr, stable_branch, start_commit=None):
-    commits = []
-    if pr.merged:
-        merge_commit = repo.get_commit(pr.merge_commit_sha)
-        if len(merge_commit.parents) > 1:  # Check if this merge commit includes multiple commits
-            for commit in pr.get_commits():
-                commits.append(commit.sha)
-        else:
-            if start_commit:
-                promoted_commits = repo.compare(start_commit, stable_branch).commits
-            else:
-                promoted_commits = repo.get_commits(sha=stable_branch)
-            for commit in pr.get_commits():
-                for promoted_commit in promoted_commits:
-                    commit_title = commit.commit.message.splitlines()[0]
-                    # In Scylla-pkg and scylla-dtest, for example,
-                    # we don't create a merge commit for a PR with multiple commits,
-                    # according to the GitHub API, the last commit will be the merge commit,
-                    # which is not what we need when backporting (we need all the commits).
-                    # So here, we are validating the correct SHA for each commit so we can cherry-pick
-                    if promoted_commit.commit.message.startswith(commit_title):
-                        commits.append(promoted_commit.sha)
-
-    elif pr.state == 'closed':
-        events = pr.get_issue_events()
-        for event in events:
-            if event.event == 'closed':
-                commits.append(event.commit_id)
-    return commits
-
-
-def backport(repo, pr, version, commits, backport_base_branch, is_collaborator):
-    new_branch_name = f'backport/{pr.number}/to-{version}'
-    backport_pr_title = f'[Backport {version}] {pr.title}'
-    repo_url = f'https://scylladbbot:{github_token}@github.com/{repo.full_name}.git'
-    fork_repo = f'https://scylladbbot:{github_token}@github.com/scylladbbot/{repo.name}.git'
-    with (tempfile.TemporaryDirectory() as local_repo_path):
-        try:
-            repo_local = Repo.clone_from(repo_url, local_repo_path, branch=backport_base_branch)
-            repo_local.git.checkout(b=new_branch_name)
-            is_draft = False
-            for commit in commits:
-                try:
-                    repo_local.git.cherry_pick(commit, '-x')
-                except GitCommandError as e:
-                    logging.warning(f'Cherry-pick conflict on commit {commit}: {e}')
-                    is_draft = True
-                    repo_local.git.add(A=True)
-                    repo_local.git.cherry_pick('--continue')
-            # Check if the branch already exists in the remote fork
-            remote_refs = repo_local.git.ls_remote('--heads', fork_repo, new_branch_name)
-            if not remote_refs:
-                # Branch does not exist, create it with a regular push
-                repo_local.git.push(fork_repo, new_branch_name)
-                create_pull_request(repo, new_branch_name, backport_base_branch, pr, backport_pr_title, commits,
-                                    is_draft, is_collaborator)
-            else:
-                logging.info(f"Remote branch {new_branch_name} already exists in fork. Skipping push.")
-        except GitCommandError as e:
-            logging.warning(f"GitCommandError: {e}")
-
-
-def with_github_keyword_prefix(repo, pr):
-    # GitHub issue pattern: #123, scylladb/scylladb#123, or full GitHub URLs
-    github_pattern = rf"(?:fix(?:|es|ed))\s*:?\s*(?:(?:(?:{repo.full_name})?#)|https://github\.com/{repo.full_name}/issues/)(\d+)"
-    
-    # JIRA issue pattern: PKG-92 or https://scylladb.atlassian.net/browse/PKG-92
-    jira_pattern = r"(?:fix(?:|es|ed))\s*:?\s*(?:(?:https://scylladb\.atlassian\.net/browse/)?([A-Z]+-\d+))"
-    
-    # Check PR body for GitHub issues
-    github_match = re.findall(github_pattern, pr.body, re.IGNORECASE)
-    # Check PR body for JIRA issues
-    jira_match = re.findall(jira_pattern, pr.body, re.IGNORECASE)
-    
-    match = github_match or jira_match
-
-    if match:
-        return True
-
-    for commit in pr.get_commits():
-        github_match = re.findall(github_pattern, commit.commit.message, re.IGNORECASE)
-        jira_match = re.findall(jira_pattern, commit.commit.message, re.IGNORECASE)
-        if github_match or jira_match:
-            print(f'{pr.number} has a valid close reference in commit message {commit.sha}')
-            return True
-
-    print(f'No valid close reference for {pr.number}')
-    return False
-
-def main():
-    args = parse_args()
-    base_branch = args.base_branch.split('/')[2]
-    promoted_label = 'promoted-to-master'
-    repo_name = args.repo
-    fork_repo_name = 'scylladbbot/scylladb'
-    if 'scylla-enterprise' in args.repo:
-        promoted_label = 'promoted-to-enterprise'
-        fork_repo_name = 'scylladbbot/scylla-enterprise'
-    stable_branch = base_branch
-    backport_branch = 'branch-'
-
-    backport_label_pattern = re.compile(r'backport/\d+\.\d+$')
-
-    g = Github(github_token)
-    repo = g.get_repo(repo_name)
-    scylladbbot_repo = g.get_repo(fork_repo_name)
-    closed_prs = []
-    start_commit = None
-    is_collaborator = True
-
-    if args.commits:
-        start_commit, end_commit = args.commits.split('..')
-        commits = repo.compare(start_commit, end_commit).commits
-        for commit in commits:
-            match = re.search(rf"Closes .*#([0-9]+)", commit.commit.message, re.IGNORECASE)
-            if match:
-                pr_number = int(match.group(1))
-                pr = repo.get_pull(pr_number)
-                closed_prs.append(pr)
-    if args.pull_request:
-        start_commit = args.head_commit
-        pr = repo.get_pull(args.pull_request)
-        closed_prs = [pr]
-
-    for pr in closed_prs:
-        labels = [label.name for label in pr.labels]
-        backport_labels = [label for label in labels if backport_label_pattern.match(label)]
-        if promoted_label not in labels:
-            print(f'no {promoted_label} label: {pr.number}')
-            continue
-        if not backport_labels:
-            print(f'no backport label: {pr.number}')
-            continue
-        if not with_github_keyword_prefix(repo, pr) and args.github_event != 'unlabeled':
-            comment = f''':warning:  @{pr.user.login} PR body or PR commits do not contain a Fixes reference to an issue and can not be backported
-            please update PR body with a valid ref to an issue. Then remove `scylladbbot/backport_error` label to re-trigger the backport process
-            '''
-            pr.create_issue_comment(comment)
-            pr.add_to_labels("scylladbbot/backport_error")
-            continue
-        if not repo.private and not scylladbbot_repo.has_in_collaborators(pr.user.login):
-            logging.info(f"Sending an invite to {pr.user.login} to become a collaborator to {scylladbbot_repo.full_name} ")
-            scylladbbot_repo.add_to_collaborators(pr.user.login)
-            comment = f''':warning:  @{pr.user.login} you have been added as collaborator to scylladbbot fork
-            Please check your inbox and approve the invitation, otherwise you will not be able to edit PR branch when needed
-            '''
-            # When a pull request is pending for backport but its author is not yet a collaborator of "scylladbbot",
-            # we attach a "scylladbbot/backport_error" label to the PR.
-            # This prevents the workflow from proceeding with the backport process
-            # until the author has been granted proper permissions
-            # the author should remove the label manually to re-trigger the backport workflow.
-            pr.add_to_labels("scylladbbot/backport_error")
-            pr.create_issue_comment(comment)
-            is_collaborator = False
-        commits = get_pr_commits(repo, pr, stable_branch, start_commit)
-        logging.info(f"Found PR #{pr.number} with commit {commits} and the following labels: {backport_labels}")
-        for backport_label in backport_labels:
-            version = backport_label.replace('backport/', '')
-            backport_base_branch = backport_label.replace('backport/', backport_branch)
-            backport(repo, pr, version, commits, backport_base_branch, is_collaborator)
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/check-license.py

@@ -1,81 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
-# Copyright (C) 2024-present ScyllaDB
-#
-#
-# SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
-#
-
-import argparse
-import sys
-from pathlib import Path
-from typing import Set
-
-
-def parse_args() -> argparse.Namespace:
-    """Parses command-line arguments."""
-    parser = argparse.ArgumentParser(description='Check license headers in files')
-    parser.add_argument('--files', required=True, nargs="+", type=Path,
-                        help='List of files to check')
-    parser.add_argument('--license', required=True,
-                        help='License to check for')
-    parser.add_argument('--check-lines', type=int, default=10,
-                        help='Number of lines to check (default: %(default)s)')
-    parser.add_argument('--extensions', required=True, nargs="+",
-                        help='List of file extensions to check')
-    parser.add_argument('--verbose', action='store_true',
-                        help='Print verbose output (default: %(default)s)')
-    return parser.parse_args()
-
-
-def should_check_file(file_path: Path, allowed_extensions: Set[str]) -> bool:
-    return file_path.suffix in allowed_extensions
-
-
-def check_license_header(file_path: Path, license_header: str, check_lines: int) -> bool:
-    try:
-        with open(file_path, 'r', encoding='utf-8') as f:
-            for _ in range(check_lines):
-                line = f.readline()
-                if license_header in line:
-                    return True
-        return False
-    except (UnicodeDecodeError, StopIteration):
-        # Handle files that can't be read as text or have fewer lines
-        return False
-
-
-def main() -> int:
-    args = parse_args()
-
-    if not args.files:
-        print("No files to check")
-        return 0
-
-    num_errors = 0
-
-    for file_path in args.files:
-        # Skip non-existent files
-        if not file_path.exists():
-            continue
-
-        # Skip files with non-matching extensions
-        if not should_check_file(file_path, args.extensions):
-            print(f"ℹ️ Skipping file with unchecked extension: {file_path}")
-            continue
-
-        # Check license header
-        if check_license_header(file_path, args.license, args.check_lines):
-            if args.verbose:
-                print(f"✅ License header found in: {file_path}")
-        else:
-            print(f"❌ Missing license header in: {file_path}")
-            num_errors += 1
-
-    if num_errors > 0:
-        sys.exit(1)
-
-
-if __name__ == '__main__':
-    main()

.github/scripts/label_promoted_commits.py

@@ -1,89 +0,0 @@
-import argparse
-import re
-import sys
-import os
-from github import Github
-from github.GithubException import UnknownObjectException
-
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def parser():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--repository', type=str, required=True,
-                        help='Github repository name (e.g., scylladb/scylladb)')
-    parser.add_argument('--commits', type=str, required=True, help='Range of promoted commits.')
-    parser.add_argument('--label', type=str, default='promoted-to-master', help='Label to use')
-    parser.add_argument('--ref', type=str, required=True, help='PR target branch')
-    return parser.parse_args()
-
-
-def add_comment_and_close_pr(pr, comment):
-    if pr.state == 'open':
-        pr.create_issue_comment(comment)
-        pr.edit(state="closed")
-
-
-def mark_backport_done(repo, ref_pr_number, branch):
-    pr = repo.get_pull(int(ref_pr_number))
-    label_to_remove = f'backport/{branch}'
-    label_to_add = f'{label_to_remove}-done'
-    current_labels = [label.name for label in pr.get_labels()]
-    if label_to_remove in current_labels:
-        pr.remove_from_labels(label_to_remove)
-    if label_to_add not in current_labels:
-        pr.add_to_labels(label_to_add)
-
-
-def main():
-    # This script is triggered by a push event to either the master branch or a branch named branch-x.y (where x and y represent version numbers). Based on the pushed branch, the script performs the following actions:
-    # - When ref branch is `master`, it will add the `promoted-to-master` label, which we need later for the auto backport process
-    # - When ref branch is `branch-x.y` (which means we backported a patch), it will replace in the original PR the `backport/x.y` label with `backport/x.y-done` and will close the backport PR (Since GitHub close only the one referring to default branch)
-    args = parser()
-    pr_pattern = re.compile(r'Closes .*#([0-9]+)')
-    target_branch = re.search(r'branch-(\d+\.\d+)', args.ref)
-    g = Github(github_token)
-    repo = g.get_repo(args.repository, lazy=False)
-    start_commit, end_commit = args.commits.split('..')
-    commits = repo.compare(start_commit, end_commit).commits
-    processed_prs = set()
-    # Print commit information
-    for commit in commits:
-        print(f'Commit sha is: {commit.sha}')
-        pr_last_line = commit.commit.message.splitlines()
-        for line in reversed(pr_last_line):
-            match = pr_pattern.search(line)
-            if match:
-                pr_number = int(match.group(1))
-                if pr_number in processed_prs:
-                    continue
-                if target_branch:
-                    pr = repo.get_pull(pr_number)
-                    branch_name = target_branch[1]
-                    refs_pr = re.findall(r'Parent PR: (?:#|https.*?)(\d+)', pr.body)
-                    if refs_pr:
-                        print(f'branch-{target_branch.group(1)}, pr number is: {pr_number}')
-                        # 1. change the backport label of the parent PR to note that
-                        #    we've merged the corresponding backport PR
-                        # 2. close the backport PR and leave a comment on it to note
-                        #    that it has been merged with a certain git commit.
-                        ref_pr_number = refs_pr[0]
-                        mark_backport_done(repo, ref_pr_number, branch_name)
-                        comment = f'Closed via {commit.sha}'
-                        add_comment_and_close_pr(pr, comment)
-                else:
-                    try:
-                        pr = repo.get_pull(pr_number)
-                        pr.add_to_labels('promoted-to-master')
-                        print(f'master branch, pr number is: {pr_number}')
-                    except UnknownObjectException:
-                        print(f'{pr_number} is not a PR but an issue, no need to add label')
-                processed_prs.add(pr_number)
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/sync_labels.py

@@ -1,113 +0,0 @@
-#!/usr/bin/env python3
-import argparse
-import os
-import sys
-from github import Github
-import re
-
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def parser():
-    parse = argparse.ArgumentParser()
-    parse.add_argument('--repo', type=str, required=True, help='Github repository name (e.g., scylladb/scylladb)')
-    parse.add_argument('--number', type=int, required=True, help='Pull request or issue number to sync labels from')
-    parse.add_argument('--label', type=str, default=None, help='Label to add/remove from an issue or PR')
-    parse.add_argument('--is_issue', action='store_true', help='Determined if label change is in Issue or not')
-    parse.add_argument('--action', type=str, choices=['opened', 'labeled', 'unlabeled'], required=True, help='Sync labels action')
-    return parse.parse_args()
-
-
-def copy_labels_from_linked_issues(repo, pr_number):
-    pr = repo.get_pull(pr_number)
-    if pr.body:
-        linked_issue_numbers = set(re.findall(r'Fixes:? (?:#|https.*?/issues/)(\d+)', pr.body))
-        for issue_number in linked_issue_numbers:
-            try:
-                issue = repo.get_issue(int(issue_number))
-                for label in issue.labels:
-                    # Copy ALL labels from issues to PR when PR is opened
-                    pr.add_to_labels(label.name)
-                    print(f"Copied label '{label.name}' from issue #{issue_number} to PR #{pr_number}")
-                    if label.name in ['P0', 'P1']:
-                        pr.add_to_labels('force_on_cloud')
-                        print(f"Added force_on_cloud label to PR #{pr_number} due to {label.name} label")
-                print(f"All labels from issue #{issue_number} copied to PR #{pr_number}")
-            except Exception as e:
-                print(f"Error processing issue #{issue_number}: {e}")
-
-
-def get_linked_pr_from_issue_number(repo, number):
-    linked_prs = []
-    for pr in repo.get_pulls(state='all', base='master'):
-        if pr.body and f'{number}' in pr.body:
-            linked_prs.append(pr.number)
-            break
-        else:
-            continue
-    return linked_prs
-
-
-def get_linked_issues_based_on_pr_body(repo, number):
-    pr = repo.get_pull(number)
-    repo_name = repo.full_name
-    pattern = rf"(?:fix(?:|es|ed)|resolve(?:|d|s))\s*:?\s*(?:(?:(?:{repo_name})?#)|https://github\.com/{repo_name}/issues/)(\d+)"
-    issue_number_from_pr_body = []
-    if pr.body is None:
-        return issue_number_from_pr_body
-    matches = re.findall(pattern, pr.body, re.IGNORECASE)
-    if matches:
-        for match in matches:
-            issue_number_from_pr_body.append(match)
-            print(f"Found issue number: {match}")
-    return issue_number_from_pr_body
-
-
-def sync_labels(repo, number, label, action, is_issue=False):
-    if is_issue:
-        linked_prs_or_issues = get_linked_pr_from_issue_number(repo, number)
-    else:
-        linked_prs_or_issues = get_linked_issues_based_on_pr_body(repo, number)
-    for pr_or_issue_number in linked_prs_or_issues:
-        if is_issue:
-            target = repo.get_issue(pr_or_issue_number)
-        else:
-            target = repo.get_issue(int(pr_or_issue_number))
-        if action == 'labeled':
-            target.add_to_labels(label)
-            if label in ['P0', 'P1'] and is_issue:
-                # Only add force_on_cloud to PRs when P0/P1 is added to an issue
-                target.add_to_labels('force_on_cloud')
-                print(f"Added 'force_on_cloud' label to PR #{pr_or_issue_number} due to {label} label")
-            print(f"Label '{label}' successfully added.")
-        elif action == 'unlabeled':
-            target.remove_from_labels(label)
-            if label in ['P0', 'P1'] and is_issue:
-                # Check if any other P0/P1 labels remain before removing force_on_cloud
-                remaining_priority_labels = [l.name for l in target.labels if l.name in ['P0', 'P1']]
-                if not remaining_priority_labels:
-                    try:
-                        target.remove_from_labels('force_on_cloud')
-                        print(f"Removed 'force_on_cloud' label from PR #{pr_or_issue_number} as no P0/P1 labels remain")
-                    except Exception as e:
-                        print(f"Warning: Could not remove force_on_cloud label: {e}")
-            print(f"Label '{label}' successfully removed.")
-        elif action == 'opened':
-            copy_labels_from_linked_issues(repo, number)
-        else:
-            print("Invalid action. Use 'labeled', 'unlabeled' or 'opened'.")
-
-
-def main():
-    args = parser()
-    github = Github(github_token)
-    repo = github.get_repo(args.repo)
-    sync_labels(repo, args.number, args.label, args.action, args.is_issue)
-
-
-if __name__ == "__main__":
-    main()

.github/seastar-bad-include.json

@@ -1,16 +0,0 @@
-{
-    "problemMatcher": [
-        {
-            "owner": "seastar-bad-include",
-            "severity": "error",
-            "pattern": [
-                {
-                    "regexp": "^(.+):(\\d+):(.+)$",
-                    "file": 1,
-                    "line": 2,
-                    "message": 3
-                }
-            ]
-        }
-    ]
-}

.github/workflows/add-label-when-promoted.yaml

@@ -1,83 +0,0 @@
-name: Check if commits are promoted
-
-on:
-  push:
-    branches:
-      - master
-      - branch-*.*
-      - enterprise
-  pull_request_target:
-    types: [labeled, unlabeled]
-    branches: [master, next, enterprise]
-
-jobs:
-  check-commit:
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-      issues: write
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Set Default Branch
-        id: set_branch
-        run: |
-          if [[ "${{ github.repository }}" == *enterprise* ]]; then
-            echo "DEFAULT_BRANCH=enterprise" >> $GITHUB_ENV
-          else
-            echo "DEFAULT_BRANCH=master" >> $GITHUB_ENV
-          fi
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          repository: ${{ github.repository }}
-          ref: ${{ env.DEFAULT_BRANCH }}
-          token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-          fetch-depth: 0  # Fetch all history for all tags and branches
-      - name: Set up Git identity
-        run: |
-          git config --global user.name "GitHub Action"
-          git config --global user.email "action@github.com"
-          git config --global merge.conflictstyle diff3
-      - name: Install dependencies
-        run: sudo apt-get install -y python3-github python3-git
-      - name: Run python script
-        if: github.event_name == 'push'
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-        run: python .github/scripts/label_promoted_commits.py  --commits ${{ github.event.before }}..${{ github.sha }} --repository ${{ github.repository }} --ref ${{ github.ref }}
-      - name: Run auto-backport.py when promotion completed
-        if: ${{ github.event_name == 'push' && github.ref == format('refs/heads/{0}', env.DEFAULT_BRANCH) }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-        run: python .github/scripts/auto-backport.py --repo ${{ github.repository }} --base-branch ${{ github.ref }} --commits ${{ github.event.before }}..${{ github.sha }}
-      - name: Check if a valid backport label exists and no backport_error
-        env:
-          LABELS_JSON: ${{ toJson(github.event.pull_request.labels) }}
-        id: check_label
-        run: |
-          labels_json="$LABELS_JSON"
-          echo "Checking labels:"
-          echo "$labels_json" | jq -r '.[].name'
-
-          # Check if a valid backport label exists
-          if echo "$labels_json" | jq -e 'any(.[] | .name; test("backport/[0-9]+\\.[0-9]+$"))' > /dev/null; then
-            # Ensure scylladbbot/backport_error is NOT present
-            if ! echo "$labels_json" | jq -e '.[] | select(.name == "scylladbbot/backport_error")' > /dev/null; then
-              echo "A matching backport label was found and no backport_error label exists."
-              echo "ready_for_backport=true" >> "$GITHUB_OUTPUT"
-              exit 0
-            else
-              echo "The label 'scylladbbot/backport_error' is present, invalidating backport."
-            fi
-          else
-            echo "No matching backport label found."
-          fi
-          echo "ready_for_backport=false" >> "$GITHUB_OUTPUT"
-      - name: Run auto-backport.py when PR is closed
-        if: ${{ github.event_name == 'pull_request_target' && steps.check_label.outputs.ready_for_backport == 'true' && github.event.pull_request.state == 'closed' }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-        run: python .github/scripts/auto-backport.py --repo ${{ github.repository }} --base-branch ${{ github.ref }} --pull-request ${{ github.event.pull_request.number }} --head-commit ${{ github.event.pull_request.base.sha }} --github-event ${{ github.event.action }}

.github/workflows/backport-pr-fixes-validation.yaml

@@ -1,36 +0,0 @@
-name: Fixes validation for backport PR
-
-on:
-  pull_request:
-    types: [opened, reopened, edited]
-    branches: [branch-*]
-
-jobs:
-  check-fixes-prefix:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - name: Check PR body for "Fixes" prefix patterns
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const body = context.payload.pull_request.body;
-            const repo = context.payload.repository.full_name;
-            
-            // Regular expression pattern to check for "Fixes" prefix
-            // Adjusted to dynamically insert the repository full name
-            const pattern = `Fixes:? ((?:#|${repo.replace('/', '\\/')}#|https://github\\.com/${repo.replace('/', '\\/')}/issues/)(\\d+)|(?:https://scylladb\\.atlassian\\.net/browse/)?([A-Z]+-\\d+))`;
-            const regex = new RegExp(pattern);
-            
-            if (!regex.test(body)) {
-              const error = "PR body does not contain a valid 'Fixes' reference.";
-              core.setFailed(error);
-              await github.rest.issues.createComment({
-                issue_number: context.issue.number,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `:warning: ${error}`
-              });
-            }

.github/workflows/build-scylla.yaml

@@ -1,39 +0,0 @@
-name: Build Scylla
-
-on:
-  workflow_call:
-    inputs:
-      build_mode:
-        description: 'the build mode'
-        type: string
-        required: true
-    outputs:
-      md5sum:
-        description: 'the md5sum for scylla executable'
-        value: ${{ jobs.build.outputs.md5sum }}
-
-jobs:
-  read-toolchain:
-    uses: ./.github/workflows/read-toolchain.yaml
-  build:
-    if: github.repository == 'scylladb/scylladb'
-    needs:
-      - read-toolchain
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    outputs:
-      md5sum: ${{ steps.checksum.outputs.md5sum }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - name: Generate the building system
-        run: |
-          git config --global --add safe.directory $GITHUB_WORKSPACE
-          ./configure.py --mode ${{ inputs.build_mode }} --with scylla
-      - run: |
-          ninja build/${{ inputs.build_mode }}/scylla
-      - id: checksum
-        run: |
-          checksum=$(md5sum build/${{ inputs.build_mode }}/scylla | cut -c -32)
-          echo "md5sum=$checksum" >> $GITHUB_OUTPUT

.github/workflows/call_backport_with_jira.yaml

@@ -1,53 +0,0 @@
-name: Backport with Jira Integration
-
-on:
-  push:
-    branches:
-      - master
-      - next-*.*
-      - branch-*.*
-  pull_request_target:
-    types: [labeled, closed]
-    branches: 
-      - master
-      - next
-      - next-*.*
-      - branch-*.*
-
-jobs:
-  backport-on-push:
-    if: github.event_name == 'push'
-    uses: scylladb/github-automation/.github/workflows/backport-with-jira.yaml@main
-    with:
-      event_type: 'push'
-      base_branch: ${{ github.ref }}
-      commits: ${{ github.event.before }}..${{ github.sha }}
-    secrets:
-      gh_token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-      jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-
-  backport-on-label:
-    if: github.event_name == 'pull_request_target' && github.event.action == 'labeled'
-    uses: scylladb/github-automation/.github/workflows/backport-with-jira.yaml@main
-    with:
-      event_type: 'labeled'
-      base_branch: refs/heads/${{ github.event.pull_request.base.ref }}
-      pull_request_number: ${{ github.event.pull_request.number }}
-      head_commit: ${{ github.event.pull_request.base.sha }}
-      label_name: ${{ github.event.label.name }}
-      pr_state: ${{ github.event.pull_request.state }}
-    secrets:
-      gh_token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-      jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-
-  backport-chain:
-    if: github.event_name == 'pull_request_target' && github.event.action == 'closed' && github.event.pull_request.merged == true
-    uses: scylladb/github-automation/.github/workflows/backport-with-jira.yaml@main
-    with:
-      event_type: 'chain'
-      base_branch: refs/heads/${{ github.event.pull_request.base.ref }}
-      pull_request_number: ${{ github.event.pull_request.number }}
-      pr_body: ${{ github.event.pull_request.body }}
-    secrets:
-      gh_token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-      jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_jira_sync.yml

@@ -1,18 +0,0 @@
-name: Sync Jira Based on PR Events
-
-on:
-  pull_request_target:
-    types: [opened, edited, ready_for_review, review_requested, labeled, unlabeled, closed]
-
-permissions:
-  contents: read
-  pull-requests: write
-  issues: write
-
-jobs:
-  jira-sync:
-    uses: scylladb/github-automation/.github/workflows/main_pr_events_jira_sync.yml@main
-    with:
-      caller_action: ${{ github.event.action }}
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_jira_sync_pr_milestone.yml

@@ -1,22 +0,0 @@
-name: Sync Jira Based on PR Milestone Events
-
-on:
-  pull_request_target:
-    types: [milestoned, demilestoned]
-
-permissions:
-  contents: read
-  pull-requests: read
-
-jobs:
-  jira-sync-milestone-set:
-    if: github.event.action == 'milestoned'
-    uses: scylladb/github-automation/.github/workflows/main_jira_sync_pr_milestone_set.yml@main
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}
-
-  jira-sync-milestone-removed:
-    if: github.event.action == 'demilestoned'
-    uses: scylladb/github-automation/.github/workflows/main_jira_sync_pr_milestone_removed.yml@main
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_sync_milestone_to_jira.yml

@@ -1,14 +0,0 @@
-name: Call Jira release creation for new milestone
-
-on:
-  milestone:
-    types: [created, closed]
-
-jobs:
-  sync-milestone-to-jira:
-    uses: scylladb/github-automation/.github/workflows/main_sync_milestone_to_jira_release.yml@main
-    with:
-      # Comma-separated list of Jira project keys
-      jira_project_keys: "SCYLLADB,CUSTOMER,SMI,RELENG,VECTOR"
-    secrets:
-      caller_jira_auth: ${{ secrets.USER_AND_KEY_FOR_JIRA_AUTOMATION }}

.github/workflows/call_validate_pr_author_email.yml

@@ -1,13 +0,0 @@
-name: validate_pr_author_email
-
-on:
-  pull_request_target:
-    types:
-      - opened
-      - synchronize
-      - reopened
-
-jobs:
-  validate_pr_author_email:
-    uses: scylladb/github-automation/.github/workflows/validate_pr_author_email.yml@main
-

.github/workflows/check-license-header.yaml

@@ -1,52 +0,0 @@
-name: License Header Check
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened]
-    branches: [master]
-
-env:
-  HEADER_CHECK_LINES: 10
-  LICENSE: "LicenseRef-ScyllaDB-Source-Available-1.0"
-  CHECKED_EXTENSIONS: ".cc .hh .py"
-
-jobs:
-  check-license-headers:
-    name: Check License Headers
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Get changed files
-        id: changed-files
-        run: |
-          # Get list of added files comparing with base branch
-          echo "files=$(git diff --name-only --diff-filter=A ${{ github.event.pull_request.base.sha }} ${{ github.sha }} | tr '\n' ' ')" >> $GITHUB_OUTPUT
-
-      - name: Check license headers
-        if: steps.changed-files.outputs.files != ''
-        run: |
-          .github/scripts/check-license.py \
-            --files ${{ steps.changed-files.outputs.files }} \
-            --license "${{ env.LICENSE }}" \
-            --check-lines "${{ env.HEADER_CHECK_LINES }}" \
-            --extensions ${{ env.CHECKED_EXTENSIONS }}
-
-      - name: Comment on PR if check fails
-        if: failure()
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const license = '${{ env.LICENSE }}';
-            await github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `❌ License header check failed. Please ensure all new files include the header within the first ${{ env.HEADER_CHECK_LINES }} lines:\n\`\`\`\n${license}\n\`\`\`\nSee action logs for details.`
-            });

.github/workflows/clang-nightly.yaml

@@ -1,66 +0,0 @@
-name: clang-nightly
-
-on:
-  schedule:
-    # only at 5AM Saturday
-    - cron: '0 5 * * SAT'
-
-env:
-  # use the development branch explicitly
-  CLANG_VERSION: 21
-  BUILD_DIR: build
-
-permissions: {}
-
-# cancel the in-progress run upon a repush
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  clang-dev:
-    name: Build with clang nightly
-    if: github.repository == 'scylladb/scylladb'
-    runs-on: ubuntu-latest
-    container: fedora:40
-    strategy:
-      matrix:
-        build_type:
-          - Debug
-          - RelWithDebInfo
-          - Dev
-    steps:
-      - run: |
-          sudo dnf -y install git
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Install build dependencies
-        run: |
-          # use the copr repo for llvm snapshot builds, see
-          # https://copr.fedorainfracloud.org/coprs/g/fedora-llvm-team/llvm-snapshots/
-          sudo dnf -y install 'dnf-command(copr)'
-          sudo dnf copr enable -y @fedora-llvm-team/llvm-snapshots
-          # do not install java dependencies, which is not only not used here
-          sed -i.orig \
-            -e '/tools\/.*\/install-dependencies.sh/d' \
-            -e 's/(minio_download_jobs)/(true)/' \
-            ./install-dependencies.sh
-          sudo ./install-dependencies.sh
-          sudo dnf -y install lld
-      - name: Generate the building system
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DCMAKE_C_COMPILER=clang-$CLANG_VERSION     \
-            -DCMAKE_CXX_COMPILER=clang++-$CLANG_VERSION \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      # see https://github.com/actions/toolkit/blob/main/docs/problem-matchers.md
-      - run: |
-          echo "::add-matcher::.github/clang-matcher.json"
-      - run: |
-          cmake --build $BUILD_DIR --target scylla
-      - run: |
-          echo "::remove-matcher owner=clang::"

.github/workflows/clang-tidy.yaml

@@ -1,69 +0,0 @@
-name: clang-tidy
-
-on:
-  pull_request:
-    branches:
-      - master
-    paths-ignore:
-      - '**/*.rst'
-      - '**/*.md'
-      - 'docs/**'
-      - '.github/**'
-  workflow_dispatch:
-  issue_comment:
-    types:
-      - created
-
-env:
-  BUILD_TYPE: RelWithDebInfo
-  BUILD_DIR: build
-  CLANG_TIDY_CHECKS: '-*,bugprone-use-after-move'
-
-permissions: {}
-
-# cancel the in-progress run upon a repush
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  read-toolchain:
-    if: github.event_name == 'pull_request' || (github.event.issue.pull_request && startsWith(github.event.comment.body, '/clang-tidy'))
-    uses: ./.github/workflows/read-toolchain.yaml
-  clang-tidy:
-    name: Run clang-tidy
-    needs:
-      - read-toolchain
-    if: "${{ needs.read-toolchain.result == 'success' }}"
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    steps:
-      - env:
-          IMAGE: ${{ needs.read-toolchain.image }}
-        run: |
-          echo ${{ needs.read-toolchain.image }}
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - run: |
-          sudo dnf -y install clang-tools-extra
-      - name: Generate the building system
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=$BUILD_TYPE              \
-            -DCMAKE_C_COMPILER=clang                    \
-            -DScylla_USE_LINKER=ld.lld                  \
-            -DCMAKE_CXX_COMPILER=clang++                \
-            -DCMAKE_EXPORT_COMPILE_COMMANDS=ON          \
-            -DCMAKE_CXX_CLANG_TIDY="clang-tidy;--checks=$CLANG_TIDY_CHECKS" \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      # see https://github.com/actions/toolkit/blob/main/docs/problem-matchers.md
-      - run: |
-          echo "::add-matcher::.github/clang-matcher.json"
-      - name: Build with clang-tidy enabled
-        run: |
-          cmake --build $BUILD_DIR --target scylla
-      - run: |
-          echo "::remove-matcher owner=clang::"

.github/workflows/close_issue_for_scylla_associate.yml

@@ -1,62 +0,0 @@
-name: Close issues created by Scylla associates
-
-on:
-  issues:
-    types: [opened, reopened]
-
-permissions:
-  issues: write
-
-jobs:
-  comment-and-close:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Comment and close if author email is scylladb.com
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const issue = context.payload.issue;
-            const actor = context.actor;
-
-            // Get user data (only public email is available)
-            const { data: user } = await github.rest.users.getByUsername({
-              username: actor,
-            });
-
-            const email = user.email || "";
-            console.log(`Actor: ${actor}, public email: ${email || "<none>"}`);
-
-            // Only continue if email exists and ends with @scylladb.com
-            if (!email || !email.toLowerCase().endsWith("@scylladb.com")) {
-              console.log("User is not a scylladb.com email (or email not public); skipping.");
-              return;
-            }
-
-            const owner = context.repo.owner;
-            const repo = context.repo.repo;
-            const issue_number = issue.number;
-
-            const body = "Issues in this repository are closed automatically. Scylla associates should use Jira to manage issues.\nPlease move this issue to Jira https://scylladb.atlassian.net/jira/software/c/projects/SCYLLADB/list";
-
-            // Add the comment
-            await github.rest.issues.createComment({
-              owner,
-              repo,
-              issue_number,
-              body,
-            });
-
-            console.log(`Comment added to #${issue_number}`);
-
-            // Close the issue
-            await github.rest.issues.update({
-              owner,
-              repo,
-              issue_number,
-              state: "closed",
-              state_reason: "not_planned"
-            });
-
-            console.log(`Issue #${issue_number} closed.`);

.github/workflows/codespell.yaml

@@ -1,17 +0,0 @@
-name: codespell
-on:
-  pull_request:
-    branches:
-      - master
-permissions: {}
-jobs:
-  codespell:
-    name: Check for spelling errors
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: codespell-project/actions-codespell@master
-        with:
-          only_warn: 1
-          ignore_words_list: "ans,datas,fo,ser,ue,crate,nd,reenable,strat,stap,te,raison,iif,tread"
-          skip: "./.git,./build,./tools,*.js,*.lock,./test,./licenses,./redis/lolwut.cc,*.svg"

.github/workflows/conflict_reminder.yaml

@@ -1,154 +0,0 @@
-name: Notify PR Authors of Conflicts
-
-permissions:
-  issues: write
-  pull-requests: write
-
-on:
-  push:
-    branches:
-      - 'master'
-      - 'branch-*'
-  schedule:
-    - cron: '0 10 * * 1'  # Runs every Monday at 10:00am
-
-jobs:
-  notify_conflict_prs:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Notify PR Authors of Conflicts
-        uses: actions/github-script@v7
-        with:
-          script: |
-            console.log("Starting conflict reminder script...");
-            // Print trigger event
-            if (process.env.GITHUB_EVENT_NAME) {
-              console.log(`Workflow triggered by: ${process.env.GITHUB_EVENT_NAME}`);
-            } else {
-              console.log("Could not determine workflow trigger event.");
-            }
-            const isPushEvent = process.env.GITHUB_EVENT_NAME === 'push';
-            console.log(`isPushEvent: ${isPushEvent}`);
-            const twoMonthsAgo = new Date();
-            twoMonthsAgo.setMonth(twoMonthsAgo.getMonth() - 2);
-            const prs = await github.paginate(github.rest.pulls.list, {
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              state: 'open',
-              per_page: 100
-            });
-            console.log(`Fetched ${prs.length} open PRs`);
-            const recentPrs = prs.filter(pr => new Date(pr.created_at) >= twoMonthsAgo);
-            const validBaseBranches = ['master'];
-            const branchPrefix = 'branch-';
-            const oneWeekAgo = new Date();
-            const conflictLabel = 'conflicts';
-            oneWeekAgo.setDate(oneWeekAgo.getDate() - 7);
-            console.log(`One week ago: ${oneWeekAgo.toISOString()}`);
-
-            for (const pr of recentPrs) {
-              console.log(`Checking PR #${pr.number} on base branch '${pr.base.ref}'`);
-              const isBranchX = pr.base.ref.startsWith(branchPrefix);
-              const isMaster = validBaseBranches.includes(pr.base.ref);
-              if (!(isBranchX || isMaster)) {
-                console.log(`PR #${pr.number} skipped: base branch is not 'master' or does not start with '${branchPrefix}'`);
-                continue;
-              }
-              const updatedDate = new Date(pr.updated_at);
-              console.log(`PR #${pr.number} last updated at: ${updatedDate.toISOString()}`);
-              if (!isPushEvent && updatedDate >= oneWeekAgo) {
-                console.log(`PR #${pr.number} skipped: updated within last week`);
-                continue;
-              }
-              if (pr.assignee === null) {
-                console.log(`PR #${pr.number} skipped: no assignee`);
-                continue;
-              }
-
-              // Fetch PR details to check mergeability
-              let { data: prDetails } = await github.rest.pulls.get({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                pull_number: pr.number,
-              });
-              console.log(`PR #${pr.number} mergeable: ${prDetails.mergeable}`);
-
-              // Wait and re-fetch if mergeable is null
-              if (prDetails.mergeable === null) {
-                console.log(`PR #${pr.number} mergeable is null, waiting 2 seconds and retrying...`);
-                await new Promise(resolve => setTimeout(resolve, 2000)); // wait 2 seconds
-                prDetails = (await github.rest.pulls.get({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  pull_number: pr.number,
-                })).data;
-                console.log(`PR #${pr.number} mergeable after retry: ${prDetails.mergeable}`);
-              }
-
-              if (prDetails.mergeable === false) {
-                const hasConflictLabel = pr.labels.some(label => label.name === conflictLabel);
-                console.log(`PR #${pr.number} has conflict label: ${hasConflictLabel}`);
-
-                // Fetch comments to check for existing notifications
-                const comments = await github.paginate(github.rest.issues.listComments, {
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: pr.number,
-                  per_page: 100,
-                });
-                
-                // Find last notification comment from the bot
-                const notificationPrefix = `@${pr.assignee.login}, this PR has merge conflicts with the base branch.`;
-                const lastNotification = comments
-                  .filter(c =>
-                    c.user.type === "Bot" &&
-                    c.body.startsWith(notificationPrefix)
-                  )
-                  .sort((a, b) => new Date(b.created_at) - new Date(a.created_at))[0];
-
-                // Check if we should skip notification based on recent notification
-                let shouldSkipNotification = false;
-                if (lastNotification) {
-                  const lastNotified = new Date(lastNotification.created_at);
-                  if (lastNotified >= oneWeekAgo) {
-                    console.log(`PR #${pr.number} skipped: last notification was less than 1 week ago`);
-                    shouldSkipNotification = true;
-                  }
-                }
-
-                // Additional check for push events on draft PRs with conflict labels
-                if (
-                  isPushEvent &&
-                  pr.draft === true &&
-                  hasConflictLabel &&
-                  shouldSkipNotification
-                ) {
-                  continue;
-                }
-
-                if (!hasConflictLabel) {
-                  await github.rest.issues.addLabels({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: pr.number,
-                    labels: [conflictLabel],
-                  });
-                  console.log(`Added 'conflicts' label to PR #${pr.number}`);
-                }
-                
-                const assignee = pr.assignee.login;
-                if (assignee && !shouldSkipNotification) {
-                  await github.rest.issues.createComment({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: pr.number,
-                    body: `@${assignee}, this PR has merge conflicts with the base branch. Please resolve the conflicts so we can merge it.`,
-                  });
-                  console.log(`Notified @${assignee} for PR #${pr.number}`);
-                }
-              } else {
-                console.log(`PR #${pr.number} is mergeable, no action needed.`);
-              }
-            }
-            console.log(`Total PRs checked: ${prs.length}`);

.github/workflows/differential-shellcheck.yaml

@@ -1,32 +0,0 @@
----
-# https://github.com/redhat-plumbers-in-action/differential-shellcheck#readme
-
-name: Differential ShellCheck
-on:
-  push:
-    branches:
-      - master
-  pull_request:
-    branches:
-      - master
-
-permissions:
-  contents: read
-
-jobs:
-  lint:
-    runs-on: ubuntu-latest
-
-    permissions:
-      security-events: write
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Differential ShellCheck
-        uses: redhat-plumbers-in-action/differential-shellcheck@v5
-        with:
-          severity: warning
-          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pages.yaml

@@ -1,49 +0,0 @@
-name: "Docs / Publish"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-  DEFAULT_BRANCH: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'master' }}
-
-on:
-  push:
-    branches:
-      - 'master'
-      - 'enterprise'
-      - 'branch-**'
-    paths:
-      - "docs/**"
-  workflow_dispatch:
-
-jobs:
-  release:
-    permissions:
-      pages: write
-      id-token: write
-      contents: write
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ env.DEFAULT_BRANCH }}
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
-      - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
-      - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" multiversion
-      - name: Build redirects
-        run: make -C docs FLAG="${{ env.FLAG }}" redirects
-      - name: Deploy docs to GitHub Pages
-        run: ./docs/_utils/deploy.sh
-        if: (github.ref_name == 'master' && env.FLAG == 'opensource') || (github.ref_name == 'enterprise' && env.FLAG == 'enterprise')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pr.yaml

@@ -1,38 +0,0 @@
-name: "Docs / Build PR"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-permissions:
-  contents: read
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-
-on:
-  pull_request:
-    branches:
-      - master
-      - enterprise
-    paths:
-      - "docs/**"
-      - "db/config.hh"
-      - "db/config.cc"
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-      - name: Install uv
-        uses: astral-sh/setup-uv@v6
-      - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
-      - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" test

.github/workflows/docs-validate-metrics.yml

@@ -1,37 +0,0 @@
-name: Docs / Validate metrics
-
-permissions:
-  contents: read
-
-on:
-  pull_request:
-    branches:
-      - master
-      - enterprise
-    paths:
-      - '**/*.cc'
-      - 'scripts/metrics-config.yml'
-      - 'scripts/get_description.py'
-      - 'docs/_ext/scylladb_metrics.py'
-
-jobs:
-  validate-metrics:
-    runs-on: ubuntu-latest
-    name: Check metrics documentation coverage
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        submodules: true
-
-    - name: Set up Python
-      uses: actions/setup-python@v6
-      with:
-        python-version: '3.10'
-
-    - name: Install dependencies
-      run: pip install PyYAML
-
-    - name: Validate metrics
-      run: python3 scripts/get_description.py --validate -c scripts/metrics-config.yml

.github/workflows/iwyu.yaml

@@ -1,103 +0,0 @@
-name: iwyu
-
-on:
-  pull_request:
-    branches:
-      - master
-
-env:
-  BUILD_TYPE: RelWithDebInfo
-  BUILD_DIR: build
-  CLEANER_OUTPUT_PATH: build/clang-include-cleaner.log
-  # the "idl" subdirectory does not contain C++ source code. the .hh files in it are
-  # supposed to be processed by idl-compiler.py, so we don't check them using the cleaner
-  CLEANER_DIRS: test/unit exceptions alternator api auth cdc compaction db dht gms index lang message mutation mutation_writer node_ops raft redis replica service
-  SEASTAR_BAD_INCLUDE_OUTPUT_PATH: build/seastar-bad-include.log
-
-permissions:
-  contents: read
-
-# cancel the in-progress run upon a repush
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  read-toolchain:
-    uses: ./.github/workflows/read-toolchain.yaml
-  clang-include-cleaner:
-    name: "Analyze #includes in source files"
-    needs:
-      - read-toolchain
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Generate compilation database
-        run: |
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=$BUILD_TYPE              \
-            -DCMAKE_C_COMPILER=clang                    \
-            -DCMAKE_CXX_COMPILER=clang++                \
-            -DCMAKE_EXPORT_COMPILE_COMMANDS=ON          \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      - run: |
-          cmake                       \
-          --build $BUILD_DIR          \
-          --target wasmtime_bindings
-      - name: Build headers
-        run: |
-          swagger_targets=''
-          for f in api/api-doc/*.json; do
-            if test "${f#*.}" = json; then
-              name=$(basename "$f" .json)
-              if test $name != swagger20_header; then
-                swagger_targets+=" scylla_swagger_gen_$name"
-              fi
-            fi
-          done
-          cmake                                         \
-            --build build                               \
-             --target seastar_http_request_parser       \
-             --target idl-sources                       \
-             --target $swagger_targets
-      - run: |
-          echo "::add-matcher::.github/clang-include-cleaner.json"
-      - name: clang-include-cleaner
-        run: |
-          for d in $CLEANER_DIRS; do
-            find $d -name '*.cc' -o -name '*.hh'          \
-              -exec echo {} \;                            \
-              -exec clang-include-cleaner                 \
-                --ignore-headers=seastarx.hh              \
-                --print=changes                           \
-                -p $BUILD_DIR                             \
-                {} \; | tee --append $CLEANER_OUTPUT_PATH
-          done
-      - run: |
-          echo "::remove-matcher owner=clang-include-cleaner::"
-      - run: |
-          echo "::add-matcher::.github/seastar-bad-include.json"
-      - name: check for seastar includes
-        run: |
-          git -c safe.directory="$PWD"    \
-            grep -nE '#include +"seastar/' \
-            | tee "$SEASTAR_BAD_INCLUDE_OUTPUT_PATH"
-      - run: |
-          echo "::remove-matcher owner=seastar-bad-include::"
-      - uses: actions/upload-artifact@v4
-        with:
-          name: Logs
-          path: |
-            ${{ env.CLEANER_OUTPUT_PATH }}
-            ${{ env.SEASTAR_BAD_INCLUDE_OUTPUT_PATH }}
-      - name: fail if seastar headers are included as an internal library
-        run: |
-          if [ -s "$SEASTAR_BAD_INCLUDE_OUTPUT_PATH" ]; then
-            echo "::error::Found #include \"seastar/ in the source code. Use angle brackets instead."
-            exit 1
-          fi

.github/workflows/make-pr-ready-for-review.yaml

@@ -1,29 +0,0 @@
-name: Mark PR as Ready When Conflicts Label is Removed
-
-on:
-  pull_request_target:
-    types:
-      - unlabeled
-
-env:
-  DEFAULT_BRANCH: 'master'
-
-jobs:
-  mark-ready:
-    if: github.event.label.name == 'conflicts'
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          repository: ${{ github.repository }}
-          ref: ${{ env.DEFAULT_BRANCH }}
-          token: ${{ secrets.AUTO_BACKPORT_TOKEN }}
-          fetch-depth: 1
-      - name: Mark pull request as ready for review
-        run:  gh pr ready "${{ github.event.pull_request.number }}"
-        env:
-          GITHUB_TOKEN: ${{ secrets.AUTO_BACKPORT_TOKEN }}

.github/workflows/pr-require-backport-label.yaml

@@ -1,24 +0,0 @@
-name: PR require backport label
-on:
-  pull_request:
-    types: [opened, labeled, unlabeled, synchronize]
-    branches:
-      - master
-      - next
-jobs:
-  label:
-    if: github.event.pull_request.draft == false
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
-    steps:
-      - name: Wait for label to be added
-        run: sleep 1m
-      - uses: mheap/github-action-required-labels@v5
-        with:
-          mode: minimum
-          count: 1
-          labels: "backport/none\nbackport/\\d{4}\\.\\d+\nbackport/\\d+\\.\\d+"
-          use_regex: true
-          add_comment: false

.github/workflows/read-toolchain.yaml

@@ -1,25 +0,0 @@
-name: Read Toolchain
-
-on:
-  workflow_call:
-    outputs:
-      image:
-        description: "the toolchain docker image"
-        value: ${{ jobs.read-toolchain.outputs.image }}
-
-jobs:
-  read-toolchain:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-    outputs:
-      image: ${{ steps.read.outputs.image }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          sparse-checkout: tools/toolchain/image
-          sparse-checkout-cone-mode: false
-      - id: read
-        run: |
-          image=$(cat tools/toolchain/image)
-          echo "image=$image" >> $GITHUB_OUTPUT

.github/workflows/reproducible-build.yaml

@@ -1,35 +0,0 @@
-name: Check Reproducible Build
-
-on:
-  schedule:
-    # 5AM every friday
-    - cron: '0 5 * * FRI'
-
-permissions: {}
-
-env:
-  BUILD_MODE: release
-jobs:
-  build-a:
-    uses: ./.github/workflows/build-scylla.yaml
-    with:
-      build_mode: release
-  build-b:
-    uses: ./.github/workflows/build-scylla.yaml
-    with:
-      build_mode: release
-  compare-checksum:
-    if: github.repository == 'scylladb/scylladb'
-    runs-on: ubuntu-latest
-    needs:
-      - build-a
-      - build-b
-    steps:
-      - env:
-          CHECKSUM_A: ${{needs.build-a.outputs.md5sum}}
-          CHECKSUM_B: ${{needs.build-b.outputs.md5sum}}
-        run: |
-          if [ $CHECKSUM_A != $CHECKSUM_B ]; then                             \
-            echo "::error::mismatched checksums: $CHECKSUM_A != $CHECKSUM_B"; \
-            exit 1;                                                           \
-          fi

.github/workflows/seastar.yaml

@@ -1,53 +0,0 @@
-name: Build with the latest Seastar
-
-on:
-  schedule:
-    # 5AM everyday
-    - cron: '0 5 * * *'
-
-permissions: {}
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-env:
-  BUILD_DIR: build
-
-jobs:
-  read-toolchain:
-    uses: ./.github/workflows/read-toolchain.yaml
-  build-with-the-latest-seastar:
-    needs:
-      - read-toolchain
-    runs-on: ubuntu-latest
-    container: ${{ needs.read-toolchain.outputs.image }}
-    strategy:
-      matrix:
-        build_type:
-          - Debug
-          - RelWithDebInfo
-          - Dev
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-      - run: |
-          rm -rf seastar
-      - uses: actions/checkout@v4
-        with:
-          repository: scylladb/seastar
-          submodules: true
-          path: seastar
-      - name: Generate the building system
-        run: |
-          git config --global --add safe.directory $GITHUB_WORKSPACE
-          cmake                                         \
-            -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-            -DCMAKE_C_COMPILER=clang                    \
-            -DCMAKE_CXX_COMPILER=clang++                \
-            -G Ninja                                    \
-            -B $BUILD_DIR                               \
-            -S .
-      - run: |
-          cmake --build $BUILD_DIR --target scylla

.github/workflows/sync-labels.yaml

@@ -1,49 +0,0 @@
-name: Sync labels
-
-on:
-  pull_request_target:
-    types: [opened, labeled, unlabeled]
-    branches: [master, next]
-  issues:
-    types: [labeled, unlabeled]
-
-jobs:
-  label-sync:
-    if: ${{ github.repository == 'scylladb/scylladb' }}
-    name:  Synchronize labels between PR and the issue(s) fixed by it
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-      issues: write
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          sparse-checkout: |
-            .github/scripts/sync_labels.py
-          sparse-checkout-cone-mode: false
-
-      - name: Install dependencies
-        run: sudo apt-get install -y python3-github
-
-      - name: Pull request opened event
-        if: ${{ github.event.action == 'opened' }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/sync_labels.py --repo ${{ github.repository }} --number ${{ github.event.number }} --action ${{ github.event.action }}
-
-      - name: Pull request labeled or unlabeled event
-        if: github.event_name == 'pull_request_target' && (startsWith(github.event.label.name, 'backport/') || github.event.label.name == 'P0' || github.event.label.name == 'P1')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/sync_labels.py --repo ${{ github.repository }} --number ${{ github.event.number }} --action ${{ github.event.action }} --label ${{ github.event.label.name }}
-
-      - name: Issue labeled or unlabeled event
-        if: github.event_name == 'issues' && (startsWith(github.event.label.name, 'backport/') || github.event.label.name == 'P0' || github.event.label.name == 'P1')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/sync_labels.py --repo ${{ github.repository }} --number ${{ github.event.issue.number }} --action ${{ github.event.action }} --is_issue --label ${{ github.event.label.name }}

.github/workflows/trigger-scylla-ci.yaml

@@ -1,66 +0,0 @@
-name: Trigger Scylla CI Route
-permissions:
-  contents: read
-
-on:
-  issue_comment:
-    types: [created]
-  pull_request_target:
-    types:
-      - unlabeled
-
-jobs:
-  trigger-jenkins:
-    if: (github.event_name == 'issue_comment' && github.event.comment.user.login != 'scylladbbot') || github.event.label.name == 'conflicts'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Verify Org Membership
-        id: verify_author
-        env:
-          EVENT_NAME: ${{ github.event_name }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-          PR_ASSOCIATION: ${{ github.event.pull_request.author_association }}
-          COMMENT_AUTHOR: ${{ github.event.comment.user.login }}
-          COMMENT_ASSOCIATION: ${{ github.event.comment.author_association }}
-        shell: bash
-        run: |
-          if [[ "$EVENT_NAME" == "pull_request_target" ]]; then
-            AUTHOR="$PR_AUTHOR"
-            ASSOCIATION="$PR_ASSOCIATION"
-          else
-            AUTHOR="$COMMENT_AUTHOR"
-            ASSOCIATION="$COMMENT_ASSOCIATION"
-          fi
-          if [[ "$ASSOCIATION" == "MEMBER" || "$ASSOCIATION" == "OWNER" ]]; then
-            echo "member=true" >> $GITHUB_OUTPUT
-          else
-            echo "::warning::${AUTHOR} is not a member of scylladb (association: ${ASSOCIATION}); skipping CI trigger."
-            echo "member=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Validate Comment Trigger
-        if: github.event_name == 'issue_comment'
-        id: verify_comment
-        env:
-          COMMENT_BODY: ${{ github.event.comment.body }}
-        shell: bash
-        run: |
-          CLEAN_BODY=$(echo "$COMMENT_BODY" | grep -v '^[[:space:]]*>')
-
-          if echo "$CLEAN_BODY" | grep -qi '@scylladbbot' && echo "$CLEAN_BODY" | grep -qi 'trigger-ci'; then
-            echo "trigger=true" >> $GITHUB_OUTPUT
-          else
-            echo "trigger=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Trigger Scylla-CI-Route Jenkins Job
-        if: steps.verify_author.outputs.member == 'true' && (github.event_name == 'pull_request_target' || steps.verify_comment.outputs.trigger == 'true')
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-          PR_NUMBER: "${{ github.event.issue.number || github.event.pull_request.number }}"
-          PR_REPO_NAME: "${{ github.event.repository.full_name }}"
-        run: |
-          curl -X POST "$JENKINS_URL/job/releng/job/Scylla-CI-Route/buildWithParameters?PR_NUMBER=$PR_NUMBER&PR_REPO_NAME=$PR_REPO_NAME" \
-            --user "$JENKINS_USER:$JENKINS_API_TOKEN" --fail

.github/workflows/trigger_ci.yaml

@@ -1,242 +0,0 @@
-name: Trigger next gating
-
-on:
-  pull_request_target:
-    types: [opened, reopened, synchronize]
-  issue_comment:
-    types: [created]
-    
-jobs:
-  trigger-ci:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Checkout PR code
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0  # Needed to access full history
-          ref: ${{ github.event.pull_request.head.ref }}
-
-      - name: Fetch before commit if needed
-        run: |
-          if ! git cat-file -e ${{ github.event.before }} 2>/dev/null; then
-            echo "Fetching before commit ${{ github.event.before }}"
-            git fetch --depth=1 origin ${{ github.event.before }}
-          fi
-
-      - name: Compare commits for file changes
-        if: github.action == 'synchronize'
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          echo "Base: ${{ github.event.before }}"
-          echo "Head: ${{ github.event.after }}"
-
-          TREE_BEFORE=$(git show -s --format=%T ${{ github.event.before }})
-          TREE_AFTER=$(git show -s --format=%T ${{ github.event.after }})
-          
-          echo "TREE_BEFORE=$TREE_BEFORE" >> $GITHUB_ENV
-          echo "TREE_AFTER=$TREE_AFTER" >> $GITHUB_ENV
-
-      - name: Check if last push has file changes
-        run: |
-          if [[ "${{ env.TREE_BEFORE }}" == "${{ env.TREE_AFTER }}" ]]; then
-            echo "No file changes detected in the last push, only commit message edit."
-            echo "has_file_changes=false" >> $GITHUB_ENV
-          else
-            echo "File changes detected in the last push."
-            echo "has_file_changes=true" >> $GITHUB_ENV
-          fi
-
-      - name: Rule 1 - Check PR draft or conflict status
-        run: |
-          # Check if PR is in draft mode
-          IS_DRAFT="${{ github.event.pull_request.draft }}"
-          
-          # Check if PR has 'conflict' label
-          HAS_CONFLICT_LABEL="false"
-          LABELS='${{ toJson(github.event.pull_request.labels) }}'
-          if echo "$LABELS" | jq -r '.[].name' | grep -q "^conflict$"; then
-            HAS_CONFLICT_LABEL="true"
-          fi
-          
-          # Set draft_or_conflict variable
-          if [[ "$IS_DRAFT" == "true" || "$HAS_CONFLICT_LABEL" == "true" ]]; then
-            echo "draft_or_conflict=true" >> $GITHUB_ENV
-            echo "✅ Rule 1: PR is in draft mode or has conflict label - setting draft_or_conflict=true"
-          else
-            echo "draft_or_conflict=false" >> $GITHUB_ENV
-            echo "✅ Rule 1: PR is ready and has no conflict label - setting draft_or_conflict=false"
-          fi
-          
-          echo "Draft status: $IS_DRAFT"
-          echo "Has conflict label: $HAS_CONFLICT_LABEL"
-          echo "Result: draft_or_conflict = $draft_or_conflict"
-
-      - name: Rule 2 - Check labels
-        run: |
-          # Check if PR has P0 or P1 labels
-          HAS_P0_P1_LABEL="false"
-          LABELS='${{ toJson(github.event.pull_request.labels) }}'
-          if echo "$LABELS" | jq -r '.[].name' | grep -E "^(P0|P1)$" > /dev/null; then
-            HAS_P0_P1_LABEL="true"
-          fi
-          
-          # Check if PR already has force_on_cloud label
-          echo "HAS_FORCE_ON_CLOUD_LABEL=false" >> $GITHUB_ENV
-          if echo "$LABELS" | jq -r '.[].name' | grep -q "^force_on_cloud$"; then
-            HAS_FORCE_ON_CLOUD_LABEL="true"
-            echo "HAS_FORCE_ON_CLOUD_LABEL=true" >> $GITHUB_ENV
-          fi
-          
-          echo "Has P0/P1 label: $HAS_P0_P1_LABEL"
-          echo "Has force_on_cloud label: $HAS_FORCE_ON_CLOUD_LABEL"
-          
-          # Add force_on_cloud label if PR has P0/P1 and doesn't already have force_on_cloud
-          if [[ "$HAS_P0_P1_LABEL" == "true" && "$HAS_FORCE_ON_CLOUD_LABEL" == "false" ]]; then
-            echo "✅ Rule 2: PR has P0 or P1 label - adding force_on_cloud label"
-            curl -X POST \
-              -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
-              -H "Accept: application/vnd.github.v3+json" \
-              "https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/labels" \
-              -d '{"labels":["force_on_cloud"]}'
-          elif [[ "$HAS_P0_P1_LABEL" == "true" && "$HAS_FORCE_ON_CLOUD_LABEL" == "true" ]]; then
-            echo "✅ Rule 2: PR has P0 or P1 label and already has force_on_cloud label - no action needed"
-          else
-            echo "✅ Rule 2: PR does not have P0 or P1 label - no force_on_cloud label needed"
-          fi
-
-          SKIP_UNIT_TEST_CUSTOM="false"
-          if echo "$LABELS" | jq -r '.[].name' | grep -q "^ci/skip_unit-tests_custom$"; then
-            SKIP_UNIT_TEST_CUSTOM="true"
-          fi
-          echo "SKIP_UNIT_TEST_CUSTOM=$SKIP_UNIT_TEST_CUSTOM" >> $GITHUB_ENV
-
-      - name: Rule 3 - Analyze changed files and set build requirements
-        run: |
-          # Get list of changed files
-          CHANGED_FILES=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }})
-          echo "Changed files:"
-          echo "$CHANGED_FILES"
-          echo ""
-          
-          # Initialize all requirements to false
-          REQUIRE_BUILD="false"
-          REQUIRE_DTEST="false"
-          REQUIRE_UNITTEST="false"
-          REQUIRE_ARTIFACTS="false"
-          REQUIRE_SCYLLA_GDB="false"
-          
-          # Check each file against patterns
-          while IFS= read -r file; do
-            if [[ -n "$file" ]]; then
-              echo "Checking file: $file"
-              
-              # Build pattern: ^(?!scripts\/pull_github_pr.sh).*$
-              # Everything except scripts/pull_github_pr.sh
-              if [[ "$file" != "scripts/pull_github_pr.sh" ]]; then
-                REQUIRE_BUILD="true"
-                echo "  ✓ Matches build pattern"
-              fi
-              
-              # Dtest pattern: ^(?!test(.py|\/)|dist\/docker\/|dist\/common\/scripts\/).*$
-              # Everything except test files, dist/docker/, dist/common/scripts/
-              if [[ ! "$file" =~ ^test\.(py|/).*$ ]] && [[ ! "$file" =~ ^dist/docker/.*$ ]] && [[ ! "$file" =~ ^dist/common/scripts/.*$ ]]; then
-                REQUIRE_DTEST="true"
-                echo "  ✓ Matches dtest pattern"
-              fi
-              
-              # Unittest pattern: ^(?!dist\/docker\/|dist\/common\/scripts).*$
-              # Everything except dist/docker/, dist/common/scripts/
-              if [[ ! "$file" =~ ^dist/docker/.*$ ]] && [[ ! "$file" =~ ^dist/common/scripts.*$ ]]; then
-                REQUIRE_UNITTEST="true"
-                echo "  ✓ Matches unittest pattern"
-              fi
-              
-              # Artifacts pattern: ^(?:dist|tools\/toolchain).*$
-              # Files starting with dist or tools/toolchain
-              if [[ "$file" =~ ^dist.*$ ]] || [[ "$file" =~ ^tools/toolchain.*$ ]]; then
-                REQUIRE_ARTIFACTS="true"
-                echo "  ✓ Matches artifacts pattern"
-              fi
-              
-              # Scylla GDB pattern: ^(scylla-gdb.py).*$
-              # Files starting with scylla-gdb.py
-              if [[ "$file" =~ ^scylla-gdb\.py.*$ ]]; then
-                REQUIRE_SCYLLA_GDB="true"
-                echo "  ✓ Matches scylla_gdb pattern"
-              fi
-            fi
-          done <<< "$CHANGED_FILES"
-          
-          # Set environment variables
-          echo "requireBuild=$REQUIRE_BUILD" >> $GITHUB_ENV
-          echo "requireDtest=$REQUIRE_DTEST" >> $GITHUB_ENV
-          echo "requireUnittest=$REQUIRE_UNITTEST" >> $GITHUB_ENV
-          echo "requireArtifacts=$REQUIRE_ARTIFACTS" >> $GITHUB_ENV
-          echo "requireScyllaGdb=$REQUIRE_SCYLLA_GDB" >> $GITHUB_ENV
-          
-          echo ""
-          echo "✅ Rule 3: File analysis complete"
-          echo "Build required: $REQUIRE_BUILD"
-          echo "Dtest required: $REQUIRE_DTEST"
-          echo "Unittest required: $REQUIRE_UNITTEST"
-          echo "Artifacts required: $REQUIRE_ARTIFACTS"
-          echo "Scylla GDB required: $REQUIRE_SCYLLA_GDB"
-
-      - name: Determine Jenkins Job Name
-        run: |
-          if [[ "${{ github.ref_name }}" == "next" ]]; then
-            FOLDER_NAME="scylla-master"
-          elif [[ "${{ github.ref_name }}" == "next-enterprise" ]]; then
-            FOLDER_NAME="scylla-enterprise"
-          else
-            VERSION=$(echo "${{ github.ref_name }}" | awk -F'-' '{print $2}')
-            if [[ "$VERSION" =~ ^202[0-4]\.[0-9]+$ ]]; then
-              FOLDER_NAME="enterprise-$VERSION"
-            elif [[ "$VERSION" =~ ^[0-9]+\.[0-9]+$ ]]; then
-              FOLDER_NAME="scylla-$VERSION"
-            fi
-          fi
-          echo "JOB_NAME=${FOLDER_NAME}/job/scylla-ci" >> $GITHUB_ENV
-
-      - name: Trigger Jenkins Job
-        if: env.draft_or_conflict == 'false' && env.has_file_changes == 'true' && github.action == 'opened' || github.action == 'reopened'
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-        run: |
-          PR_NUMBER=${{ github.event.issue.number }}
-          PR_REPO_NAME=${{ github.event.repository.full_name }}
-          echo "Triggering Jenkins Job: $JOB_NAME"
-          curl -X POST \
-            "$JENKINS_URL/job/$JOB_NAME/buildWithParameters? \
-            PR_NUMBER=$PR_NUMBER& \
-            RUN_DTEST=$REQUIRE_DTEST& \
-            RUN_ONLY_SCYLLA_GDB=$REQUIRE_SCYLLA_GDB& \
-            RUN_UNIT_TEST=$REQUIRE_UNITTEST& \
-            FORCE_ON_CLOUD=$HAS_FORCE_ON_CLOUD_LABEL& \
-            SKIP_UNIT_TEST_CUSTOM=$SKIP_UNIT_TEST_CUSTOM& \
-            RUN_ARTIFACT_TESTS=$REQUIRE_ARTIFACTS" \
-            --fail \
-            --user "$JENKINS_USER:$JENKINS_API_TOKEN" \
-            -i -v
-  trigger-ci-via-comment:
-    if: github.event.comment.user.login != 'scylladbbot' && contains(github.event.comment.body, '@scylladbbot') && contains(github.event.comment.body, 'trigger-ci')
-    runs-on: ubuntu-latest
-    steps:
-      - name: Trigger Scylla-CI Jenkins Job
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-        run: |
-          PR_NUMBER=${{ github.event.issue.number }}
-          PR_REPO_NAME=${{ github.event.repository.full_name }}
-          curl -X POST "$JENKINS_URL/job/$JOB_NAME/buildWithParameters?PR_NUMBER=$PR_NUMBER" \
-          --user "$JENKINS_USER:$JENKINS_API_TOKEN" --fail -i -v

.github/workflows/trigger_jenkins.yaml

@@ -1,53 +0,0 @@
-name: Trigger next gating
-
-permissions:
-  contents: read
-
-on:
-  push:
-    branches:
-      - next**
-
-jobs:
-  trigger-jenkins:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Determine Jenkins Job Name
-        run: |
-          if [[ "${{ github.ref_name }}" == "next" ]]; then
-            FOLDER_NAME="scylla-master"
-          elif [[ "${{ github.ref_name }}" == "next-enterprise" ]]; then
-            FOLDER_NAME="scylla-enterprise"
-          else
-            VERSION=$(echo "${{ github.ref_name }}" | awk -F'-' '{print $2}')
-            if [[ "$VERSION" =~ ^202[0-4]\.[0-9]+$ ]]; then
-              FOLDER_NAME="enterprise-$VERSION"
-            elif [[ "$VERSION" =~ ^[0-9]+\.[0-9]+$ ]]; then
-              FOLDER_NAME="scylla-$VERSION"
-            fi
-          fi
-          echo "JOB_NAME=${FOLDER_NAME}/job/next" >> $GITHUB_ENV
-
-      - name: Trigger Jenkins Job
-        env:
-          JENKINS_USER: ${{ secrets.JENKINS_USERNAME }}
-          JENKINS_API_TOKEN: ${{ secrets.JENKINS_TOKEN }}
-          JENKINS_URL: "https://jenkins.scylladb.com"
-          SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-        run: |
-          echo "Triggering Jenkins Job: $JOB_NAME"
-          if ! curl -X POST "$JENKINS_URL/job/$JOB_NAME/buildWithParameters" --fail --user "$JENKINS_USER:$JENKINS_API_TOKEN" -i -v; then
-            echo "Error: Jenkins job trigger failed"
-
-            # Send Slack message
-            curl -X POST -H 'Content-type: application/json' \
-              -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
-              --data '{
-                "channel": "#releng-team",
-                "text": "🚨 @here '$JOB_NAME' failed to be triggered, please check https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }} for more details",
-                "icon_emoji": ":warning:"
-              }' \
-              https://slack.com/api/chat.postMessage
-
-            exit 1
-          fi

.github/workflows/urgent_issue_reminder.yml

@@ -1,58 +0,0 @@
-name: Urgent Issue Reminder
-
-on:
-  schedule:
-    - cron: '10 8 * * *' # Runs daily at 8 AM
-
-jobs:
-  reminder:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Send reminders
-      uses: actions/github-script@v7
-      with:
-        script: |
-          const labelFilters = ['P0', 'P1', 'Field-Tier1','status/release blocker', 'status/regression']; 
-          const excludingLabelFilters = ['documentation'];
-          const daysInactive = 7;
-          const now = new Date();
-
-          // Fetch open issues
-          const issues = await github.rest.issues.listForRepo({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            state: 'open'
-          });
-          console.log("Looking for issues with labels:"+labelFilters+", excluding labels:"+excludingLabelFilters+ ", inactive for more than "+daysInactive+" days.");
-          for (const issue of issues.data) {
-            // Check if issue has any of the specified labels
-            const hasFilteredLabel = issue.labels.some(label => labelFilters.includes(label.name));
-            const hasExcludingLabel = issue.labels.some(label => excludingLabelFilters.includes(label.name));
-            if (hasExcludingLabel) continue;
-            if (!hasFilteredLabel) continue;
-
-            // Check for inactivity
-            const lastUpdated = new Date(issue.updated_at);
-            const diffInDays = (now - lastUpdated) / (1000 * 60 * 60 * 24);
-            console.log("Issue #"+issue.number+"; Days inactive:"+diffInDays);
-            if (diffInDays > daysInactive) {
-              if (issue.assignees.length > 0) {
-                console.log("==>> Alert about issue #"+issue.number);
-                const assigneesLogins = issue.assignees.map(assignee => `@${assignee.login}`).join(', ');
-                await github.rest.issues.createComment({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issue.number,
-                  body: `${assigneesLogins}, This urgent issue had no activity for more than ${daysInactive} days. Please check its status.\n CC @mykaul @dani-tweig`
-                });
-              } else {
-                await github.rest.issues.createComment({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issue.number,
-                  body: `This urgent issue had no activity for more than ${daysInactive} days. Please check its status.\n CC @mykaul @dani-tweig`
-                });
-              }
-            }
-          }

.gitignore

@@ -3,8 +3,6 @@
 .settings
 build
 build.ninja
-cmake-build-*
-build.ninja.new
 cscope.*
 /debian/
 dist/ami/files/*.rpm
@@ -14,26 +12,13 @@ dist/ami/scylla_deploy.sh
 Cql.tokens
 .kdev4
 *.kdev4
-.idea
 CMakeLists.txt.user
 .cache
 .tox
 *.egg-info
 __pycache__CMakeLists.txt.user
 .gdbinit
-/resources
+resources
 .pytest_cache
 /expressions.tokens
 tags
-!db/tags/
-testlog
-test/*/*.reject
-.vscode
-compile_commands.json
-.ccls-cache/
-.mypy_cache
-.envrc
-clang_build
-.idea/
-nuke
-rust/target

.gitmodules

@@ -1,17 +1,17 @@
 [submodule "seastar"]
 	path = seastar
-	url = ../seastar
+	url = ../scylla-seastar
 	ignore = dirty
 [submodule "swagger-ui"]
 	path = swagger-ui
 	url = ../scylla-swagger-ui
 	ignore = dirty
-[submodule "abseil"]
-	path = abseil
-	url = ../abseil-cpp
-[submodule "scylla-python3"]
-	path = tools/python3
-	url = ../scylla-python3
-[submodule "tools/cqlsh"]
-	path = tools/cqlsh
-	url = ../scylla-cqlsh
+[submodule "xxHash"]
+	path = xxHash
+	url = ../xxHash
+[submodule "libdeflate"]
+	path = libdeflate
+	url = ../libdeflate
+[submodule "zstd"]
+	path = zstd
+	url = ../zstd

.mailmap

@@ -1,3 +0,0 @@
-Avi Kivity <avi@scylladb.com> Avi Kivity' via ScyllaDB development <scylladb-dev@googlegroups.com>
-Raphael S. Carvalho <raphaelsc@scylladb.com> Raphael S. Carvalho' via ScyllaDB development <scylladb-dev@googlegroups.com>
-Pavel Emelyanov <xemul@scylladb.com> Pavel Emelyanov' via ScyllaDB development <scylladb-dev@googlegroups.com>

CMakeLists.txt

@@ -1,397 +1,142 @@
-cmake_minimum_required(VERSION 3.27)
+##
+## For best results, first compile the project using the Ninja build-system.
+##
 
+cmake_minimum_required(VERSION 3.7)
 project(scylla)
 
-list(APPEND CMAKE_MODULE_PATH
-  ${CMAKE_CURRENT_SOURCE_DIR}/cmake
-  ${CMAKE_CURRENT_SOURCE_DIR}/seastar/cmake)
+if (NOT DEFINED FOR_IDE AND NOT DEFINED ENV{FOR_IDE} AND NOT DEFINED ENV{CLION_IDE})
+    message(FATAL_ERROR "This CMakeLists.txt file is only valid for use in IDEs, please define FOR_IDE to acknowledge this.")
+endif()
 
-# Set the possible values of build type for cmake-gui
-set(scylla_build_types
-    "Debug" "RelWithDebInfo" "Dev" "Sanitize" "Coverage")
-if(DEFINED CMAKE_BUILD_TYPE)
-    set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
-     ${scylla_build_types})
-    if(NOT CMAKE_BUILD_TYPE)
-        set(CMAKE_BUILD_TYPE "RelWithDebInfo" CACHE
-            STRING "Choose the type of build." FORCE)
-        message(WARNING "CMAKE_BUILD_TYPE not specified, Using 'RelWithDebInfo'")
-    elseif(NOT CMAKE_BUILD_TYPE IN_LIST scylla_build_types)
-        message(FATAL_ERROR "Unknown CMAKE_BUILD_TYPE: ${CMAKE_BUILD_TYPE}. "
-            "Following types are supported: ${scylla_build_types}")
-    endif()
-endif(DEFINED CMAKE_BUILD_TYPE)
+# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
+set(SEASTAR_INCLUDE_DIRS "seastar")
 
-option(Scylla_ENABLE_LTO "Turn on link-time optimization for the 'release' mode." ON)
+# These paths are always available, since they're included in the repository. Additional DPDK headers are placed while
+# Seastar is built, and are captured in `SEASTAR_INCLUDE_DIRS` through parsing the Seastar pkg-config file (below).
+set(SEASTAR_DPDK_INCLUDE_DIRS
+        seastar/dpdk/lib/librte_eal/common/include
+        seastar/dpdk/lib/librte_eal/common/include/generic
+        seastar/dpdk/lib/librte_eal/common/include/x86
+        seastar/dpdk/lib/librte_ether)
 
-include(mode.common)
-get_property(is_multi_config GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
-if(is_multi_config)
-    foreach(config ${CMAKE_CONFIGURATION_TYPES})
-        include(mode.${config})
-        list(APPEND scylla_build_modes ${scylla_build_mode_${config}})
+find_package(PkgConfig REQUIRED)
+
+set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
+pkg_check_modules(SEASTAR seastar)
+
+find_package(Boost COMPONENTS filesystem program_options system thread)
+
+##
+## Populate the names of all source and header files in the indicated paths in a designated variable.
+##
+## When RECURSIVE is specified, directories are traversed recursively.
+##
+## Use: scan_scylla_source_directories(VAR my_result_var [RECURSIVE] PATHS [path1 path2 ...])
+##
+function (scan_scylla_source_directories)
+    set(options RECURSIVE)
+    set(oneValueArgs VAR)
+    set(multiValueArgs PATHS)
+    cmake_parse_arguments(args "${options}" "${oneValueArgs}" "${multiValueArgs}" "${ARGN}")
+
+    set(globs "")
+
+    foreach (dir ${args_PATHS})
+        list(APPEND globs "${dir}/*.cc" "${dir}/*.hh")
     endforeach()
-    add_custom_target(mode_list
-        COMMAND ${CMAKE_COMMAND} -E echo "$<JOIN:${scylla_build_modes}, >"
-        COMMENT "List configured modes"
-        BYPRODUCTS mode-list.phony.stamp
-        COMMAND_EXPAND_LISTS)
-else()
-    include(mode.${CMAKE_BUILD_TYPE})
-    add_custom_target(mode_list
-        ${CMAKE_COMMAND} -E echo "${scylla_build_mode}"
-        COMMENT "List configured modes")
-endif()
 
-include(limit_jobs)
-
-# Configure Seastar compile options to align with Scylla
-set(CMAKE_CXX_STANDARD "23" CACHE INTERNAL "")
-set(CMAKE_CXX_EXTENSIONS ON CACHE INTERNAL "")
-set(CMAKE_CXX_SCAN_FOR_MODULES OFF CACHE INTERNAL "")
-set(CMAKE_VISIBILITY_INLINES_HIDDEN ON)
-
-if(is_multi_config)
-    find_package(Seastar)
-    # this is atypical compared to standard ExternalProject usage:
-    # - Seastar's build system should already be configured at this point.
-    # - We maintain separate project variants for each configuration type.
-    #
-    # Benefits of this approach:
-    # - Allows the parent project to consume the compile options exposed by
-    #   .pc file. as the compile options vary from one config to another.
-    # - Allows application of config-specific settings
-    # - Enables building Seastar within the parent project's build system
-    # - Facilitates linking of artifacts with the external project target,
-    #   establishing proper dependencies between them
-    include(ExternalProject)
-
-    # should be consistent with configure_seastar() in configure.py
-    set(seastar_build_dir "${CMAKE_BINARY_DIR}/$<CONFIG>/seastar")
-    ExternalProject_Add(Seastar
-        SOURCE_DIR "${PROJECT_SOURCE_DIR}/seastar"
-        CONFIGURE_COMMAND ""
-        BUILD_COMMAND ${CMAKE_COMMAND} --build "${seastar_build_dir}"
-          --target seastar
-          --target seastar_testing
-          --target seastar_perf_testing
-          --target app_iotune
-        BUILD_ALWAYS ON
-        BUILD_BYPRODUCTS
-          ${seastar_build_dir}/libseastar.$<IF:$<CONFIG:Debug,Dev>,so,a>
-          ${seastar_build_dir}/libseastar_testing.$<IF:$<CONFIG:Debug,Dev>,so,a>
-          ${seastar_build_dir}/libseastar_perf_testing.$<IF:$<CONFIG:Debug,Dev>,so,a>
-          ${seastar_build_dir}/apps/iotune/iotune
-          ${seastar_build_dir}/gen/include/seastar/http/chunk_parsers.hh
-          ${seastar_build_dir}/gen/include/seastar/http/request_parser.hh
-          ${seastar_build_dir}/gen/include/seastar/http/response_parser.hh
-        INSTALL_COMMAND "")
-    add_dependencies(Seastar::seastar Seastar)
-    add_dependencies(Seastar::seastar_testing Seastar)
-else()
-    set(Seastar_TESTING ON CACHE BOOL "" FORCE)
-    set(Seastar_API_LEVEL 9 CACHE STRING "" FORCE)
-    set(Seastar_DEPRECATED_OSTREAM_FORMATTERS OFF CACHE BOOL "" FORCE)
-    set(Seastar_APPS ON CACHE BOOL "" FORCE)
-    set(Seastar_EXCLUDE_APPS_FROM_ALL ON CACHE BOOL "" FORCE)
-    set(Seastar_EXCLUDE_TESTS_FROM_ALL ON CACHE BOOL "" FORCE)
-    set(Seastar_IO_URING ON CACHE BOOL "" FORCE)
-    set(Seastar_SCHEDULING_GROUPS_COUNT 21 CACHE STRING "" FORCE)
-    set(Seastar_UNUSED_RESULT_ERROR ON CACHE BOOL "" FORCE)
-    add_subdirectory(seastar)
-    target_compile_definitions (seastar
-      PRIVATE
-        SEASTAR_NO_EXCEPTION_HACK)
-endif()
-
-set(ABSL_PROPAGATE_CXX_STD ON CACHE BOOL "" FORCE)
-
-if(Scylla_ENABLE_LTO)
-    list(APPEND absl_cxx_flags $<$<CONFIG:RelWithDebInfo>:${CMAKE_CXX_COMPILE_OPTIONS_IPO};-ffat-lto-objects>)
-endif()
-
-find_package(Sanitizers QUIET)
-list(APPEND absl_cxx_flags
-    $<$<CONFIG:Debug,Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_COMPILE_OPTIONS>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_COMPILE_OPTIONS>>)
-if(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
-    list(APPEND ABSL_GCC_FLAGS ${absl_cxx_flags})
-elseif(CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
-    list(APPEND absl_cxx_flags "-Wno-deprecated-builtins")
-    list(APPEND ABSL_LLVM_FLAGS ${absl_cxx_flags})
-endif()
-set(ABSL_DEFAULT_LINKOPTS
-    $<$<CONFIG:Debug,Sanitize>:$<TARGET_PROPERTY:Sanitizers::address,INTERFACE_LINK_LIBRARIES>;$<TARGET_PROPERTY:Sanitizers::undefined_behavior,INTERFACE_LINK_LIBRARIES>>)
-add_subdirectory(abseil)
-add_library(absl-headers INTERFACE)
-target_include_directories(absl-headers SYSTEM INTERFACE
-    "${PROJECT_SOURCE_DIR}/abseil")
-add_library(absl::headers ALIAS absl-headers)
-
-# Exclude absl::strerror from the default "all" target since it's not
-# used in Scylla build and, moreover, makes use of deprecated glibc APIs,
-# such as sys_nerr, which are not exposed from "stdio.h" since glibc 2.32,
-# which happens to be the case for recent Fedora distribution versions.
-#
-# Need to use the internal "absl_strerror" target name instead of namespaced
-# variant because `set_target_properties` does not understand the latter form,
-# unfortunately.
-set_target_properties(absl_strerror PROPERTIES EXCLUDE_FROM_ALL TRUE)
-
-# System libraries dependencies
-find_package(Boost REQUIRED
-    COMPONENTS filesystem program_options system thread regex unit_test_framework)
-target_link_libraries(Boost::regex
-  INTERFACE
-    ICU::i18n
-    ICU::uc)
-find_package(Lua REQUIRED)
-find_package(ZLIB REQUIRED)
-find_package(ICU COMPONENTS uc i18n REQUIRED)
-find_package(fmt 10.0.0 REQUIRED)
-find_package(libdeflate REQUIRED)
-find_package(libxcrypt REQUIRED)
-find_package(p11-kit REQUIRED)
-find_package(Snappy REQUIRED)
-find_package(RapidJSON REQUIRED)
-find_package(xxHash REQUIRED)
-find_package(yaml-cpp REQUIRED)
-find_package(zstd REQUIRED)
-find_package(lz4 REQUIRED)
-
-set(scylla_gen_build_dir "${CMAKE_BINARY_DIR}/gen")
-file(MAKE_DIRECTORY "${scylla_gen_build_dir}")
-
-include(add_version_library)
-generate_scylla_version()
-
-option(Scylla_USE_PRECOMPILED_HEADER "Use precompiled header for Scylla" ON)
-add_library(scylla-precompiled-header STATIC exported_templates.cc)
-target_link_libraries(scylla-precompiled-header PRIVATE
-    absl::headers
-    absl::btree
-    absl::hash
-    absl::raw_hash_set
-    Seastar::seastar
-    Snappy::snappy
-    systemd
-    ZLIB::ZLIB
-    lz4::lz4_static
-    zstd::zstd_static)
-if (Scylla_USE_PRECOMPILED_HEADER)
-  set(Scylla_USE_PRECOMPILED_HEADER_USE ON)
-  find_program(DISTCC_EXEC NAMES distcc OPTIONAL)
-  if (DISTCC_EXEC)
-    if(DEFINED ENV{DISTCC_HOSTS})
-      set(Scylla_USE_PRECOMPILED_HEADER_USE OFF)
-      message(STATUS "Disabling precompiled header usage because distcc exists and DISTCC_HOSTS is set, assuming you're using distributed compilation.")
+    if (args_RECURSIVE)
+        set(glob_kind GLOB_RECURSE)
     else()
-      file(REAL_PATH "~/.distcc/hosts" DIST_CC_HOSTS_PATH EXPAND_TILDE)
-      if (EXISTS ${DIST_CC_HOSTS_PATH})
-        set(Scylla_USE_PRECOMPILED_HEADER_USE OFF)
-        message(STATUS "Disabling precompiled header usage because distcc and ~/.distcc/hosts exists, assuming you're using distributed compilation.")
-      endif()
+        set(glob_kind GLOB)
     endif()
-  endif()
-  if (Scylla_USE_PRECOMPILED_HEADER_USE)
-    message(STATUS "Using precompiled header for Scylla - remember to add `sloppiness = pch_defines,time_macros` to ccache.conf, if you're using ccache.")
-    target_precompile_headers(scylla-precompiled-header PRIVATE "stdafx.hh")
-    target_compile_definitions(scylla-precompiled-header PRIVATE SCYLLA_USE_PRECOMPILED_HEADER)
-  endif()
-else()
-  set(Scylla_USE_PRECOMPILED_HEADER_USE OFF)
-endif()
 
-add_library(scylla-main STATIC)
+    file(${glob_kind} var
+            ${globs})
 
-target_sources(scylla-main
-  PRIVATE
-    absl-flat_hash_map.cc
-    bytes.cc
-    client_data.cc
-    clocks-impl.cc
-    sstable_dict_autotrainer.cc
-    exceptions/exceptions.cc
-    debug.cc
-    init.cc
-    keys/keys.cc
-    mutation_query.cc
-    node_ops/task_manager_module.cc
-    partition_slice_builder.cc
-    query/query.cc
-    query_ranges_to_vnodes.cc
-    query/query-result-set.cc
-    tombstone_gc_options.cc
-    tombstone_gc.cc
-    reader_concurrency_semaphore.cc
-    reader_concurrency_semaphore_group.cc
-    serializer.cc
-    service/direct_failure_detector/failure_detector.cc
-    sstables_loader.cc
-    table_helper.cc
-    tasks/task_handler.cc
-    tasks/task_manager.cc
-    timeout_config.cc
-    unimplemented.cc
-    validation.cc
-    vint-serialization.cc)
-target_link_libraries(scylla-main
-  PRIVATE
-    db
-    absl::headers
-    absl::btree
-    absl::hash
-    absl::raw_hash_set
-    Seastar::seastar
-    Snappy::snappy
-    systemd
-    ZLIB::ZLIB
-    lz4::lz4_static
-    zstd::zstd_static
-    scylla-precompiled-header
-)
+    set(${args_VAR} ${var} PARENT_SCOPE)
+endfunction()
 
-option(Scylla_CHECK_HEADERS
-  "Add check-headers target for checking the self-containness of headers")
-if(Scylla_CHECK_HEADERS)
-    add_custom_target(check-headers)
-    # compatibility target used by CI, which builds "check-headers" only for
-    # the "Dev" mode.
-    # our CI currently builds "dev-headers" using ninja without specify a build
-    # mode. where "dev" is actually a prefix encoded in the target name for the
-    # underlying "headers" target. while we don't have this convention in CMake
-    # targets. in contrast, the "check-headers" which is built for all
-    # configurations defined by "CMAKE_DEFAULT_CONFIGS". however, we only need
-    # to build "check-headers" for the "Dev" configuration. Therefore, before
-    # updating the CI to use build "check-headers:Dev", let's add a new target
-    # that specifically builds "check-headers" only for Dev configuration. The
-    # new target will do nothing for other configurations.
-    add_custom_target(dev-headers
-        COMMAND ${CMAKE_COMMAND}
-          "$<IF:$<CONFIG:Dev>,--build;${CMAKE_BINARY_DIR};--config;$<CONFIG>;--target;check-headers,-E;echo;skipping;dev-headers;in;$<CONFIG>>"
-        COMMAND_EXPAND_LISTS)
-endif()
+## Although Seastar is an external project, it is common enough to explore the sources while doing
+## Scylla development that we'll treat the Seastar sources as part of this project for easier navigation.
+scan_scylla_source_directories(
+        VAR SEASTAR_SOURCE_FILES
+        RECURSIVE
 
-include(check_headers)
-check_headers(check-headers scylla-main
-  GLOB ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)
+        PATHS
+          seastar/core
+          seastar/http
+          seastar/json
+          seastar/net
+          seastar/rpc
+          seastar/tests
+          seastar/util)
 
-option(Scylla_DIST
-  "Build dist targets"
-  ON)
+scan_scylla_source_directories(
+        VAR SCYLLA_ROOT_SOURCE_FILES
+        PATHS .)
 
-add_custom_target(compiler-training)
+scan_scylla_source_directories(
+        VAR SCYLLA_SUB_SOURCE_FILES
+        RECURSIVE
 
-add_subdirectory(api)
-add_subdirectory(alternator)
-add_subdirectory(audit)
-add_subdirectory(db)
-add_subdirectory(auth)
-add_subdirectory(cdc)
-add_subdirectory(compaction)
-add_subdirectory(cql3)
-add_subdirectory(data_dictionary)
-add_subdirectory(dht)
-add_subdirectory(ent)
-add_subdirectory(gms)
-add_subdirectory(idl)
-add_subdirectory(index)
-add_subdirectory(lang)
-add_subdirectory(locator)
-add_subdirectory(message)
-add_subdirectory(mutation)
-add_subdirectory(mutation_writer)
-add_subdirectory(readers)
-add_subdirectory(replica)
-add_subdirectory(raft)
-add_subdirectory(repair)
-add_subdirectory(rust)
-add_subdirectory(schema)
-add_subdirectory(service)
-add_subdirectory(sstables)
-add_subdirectory(streaming)
-add_subdirectory(test)
-add_subdirectory(tools)
-add_subdirectory(tracing)
-add_subdirectory(transport)
-add_subdirectory(types)
-add_subdirectory(utils)
-add_subdirectory(vector_search)
-add_version_library(scylla_version
-    release.cc)
+        PATHS
+          api
+          auth
+          cql3
+          db
+          dht
+          exceptions
+          gms
+          index
+          io
+          locator
+          message
+          repair
+          service
+          sstables
+          streaming
+          tests
+          thrift
+          tracing
+          transport
+          utils)
+
+scan_scylla_source_directories(
+        VAR SCYLLA_GEN_SOURCE_FILES
+        RECURSIVE
+        PATHS build/release/gen)
+
+set(SCYLLA_SOURCE_FILES
+        ${SCYLLA_ROOT_SOURCE_FILES}
+        ${SCYLLA_GEN_SOURCE_FILES}
+        ${SCYLLA_SUB_SOURCE_FILES})
 
 add_executable(scylla
-  main.cc)
-set(scylla_libs
-    audit
-    scylla-main
-    api
-    auth
-    alternator
-    db
-    cdc
-    compaction
-    cql3
-    data_dictionary
-    dht
-    encryption
-    gms
-    idl
-    index
-    lang
-    ldap
-    locator
-    message
-    mutation
-    mutation_writer
-    raft
-    readers
-    repair
-    replica
-    schema
-    scylla_version
-    service
-    sstables
-    streaming
-    test-perf
-    tools
-    tracing
-    transport
-    types
-    utils
-    vector_search)
-target_link_libraries(scylla PRIVATE
-    ${scylla_libs})
+        ${SEASTAR_SOURCE_FILES}
+        ${SCYLLA_SOURCE_FILES})
 
-if(Scylla_ENABLE_LTO)
-  include(enable_lto)
-  foreach(target scylla ${scylla_libs})
-    enable_lto(${target})
-  endforeach()
-endif()
+# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
+# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
+list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
 
-target_link_libraries(scylla PRIVATE
-    p11-kit::p11-kit
-    Seastar::seastar
-    absl::headers
-    yaml-cpp::yaml-cpp
-    Boost::program_options)
+# If the Seastar pkg-config information is available, append to the default flags.
+#
+# For ease of browsing the source code, we always pretend that DPDK is enabled.
+target_compile_options(scylla PUBLIC
+        -std=gnu++1z
+        -DHAVE_DPDK
+        -DHAVE_HWLOC
+        "${SEASTAR_CFLAGS}")
 
-target_include_directories(scylla PRIVATE
-    "${CMAKE_CURRENT_SOURCE_DIR}"
-    "${scylla_gen_build_dir}")
-
-add_custom_target(maybe-scylla
-  DEPENDS $<$<CONFIG:Dev>:$<TARGET_FILE:scylla>>)
-add_dependencies(compiler-training
-  maybe-scylla)
-
-if(Scylla_DIST)
-  add_subdirectory(dist)
-endif()
-
-if(Scylla_BUILD_INSTRUMENTED)
-  add_subdirectory(pgo)
-endif()
-
-add_executable(patchelf
-  tools/patchelf.cc)
+# The order matters here: prefer the "static" DPDK directories to any dynamic paths from pkg-config. Some files are only
+# available dynamically, though.
+target_include_directories(scylla PUBLIC
+        .
+        ${SEASTAR_DPDK_INCLUDE_DIRS}
+        ${SEASTAR_INCLUDE_DIRS}
+        ${Boost_INCLUDE_DIRS}
+        xxhash
+        libdeflate
+        build/release/gen)

CONTRIBUTING.md

@@ -1,22 +1,11 @@
-# Contributing to Scylla
+# Asking questions or requesting help
 
-## Asking questions or requesting help
+Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
 
-Use the [ScyllaDB Community Forum](https://forum.scylladb.com) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+# Reporting an issue
 
-Join the [Scylla Developers mailing list](https://groups.google.com/g/scylladb-dev) for deeper technical discussions and to discuss your ideas for contributions.
+Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to report issues.  Fill in as much information as you can in the issue template, especially for performance problems.
 
-## Reporting an issue
+# Contributing Code to Scylla
 
-Please use the [issue tracker](https://github.com/scylladb/scylla/issues/) to report issues or to suggest features. Fill in as much information as you can in the issue template, especially for performance problems.
-
-## Contributing code to Scylla
-
-Before you can contribute code to Scylla for the first time, you should sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send the signed form to cla@scylladb.com. You can then submit your changes as patches to the [scylladb-dev mailing list](https://groups.google.com/forum/#!forum/scylladb-dev) or as a pull request to the [Scylla project on github](https://github.com/scylladb/scylla).
-If you need help formatting or sending patches, [check out these instructions](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches).
-
-The Scylla C++ source code uses the [Seastar coding style](https://github.com/scylladb/seastar/blob/master/coding-style.md) so please adhere to that in your patches. Note that Scylla code is written with `using namespace seastar`, so should not explicitly add the `seastar::` prefix to Seastar symbols. You will usually not need to add `using namespace seastar` to new source files, because most Scylla header files have `#include "seastarx.hh"`, which does this.
-
-Header files in Scylla must be self-contained, i.e., each can be included without having to include specific other headers first. To verify that your change did not break this property, run `ninja dev-headers`. If you added or removed header files, you must `touch configure.py` first - this will cause `configure.py` to be automatically re-run to generate a fresh list of header files.
-
-For more criteria on what reviewers consider good code, see the [review checklist](https://github.com/scylladb/scylla/blob/master/docs/dev/review-checklist.md).
+To contribute code to Scylla, you need to sign the [Contributor License Agreement](http://www.scylladb.com/opensource/cla/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.

HACKING.md

@@ -18,41 +18,23 @@ $ git submodule update --init --recursive
 
 ### Dependencies
 
-Scylla is fairly fussy about its build environment, requiring a very recent
-version of the C++23 compiler and numerous tools and libraries to build.
+Scylla depends on the system package manager for its development dependencies.
 
-Run `./install-dependencies.sh` (as root) to use your Linux distributions's
-package manager to install the appropriate packages on your build machine.
-However, this will only work on very recent distributions. For example,
-currently Fedora users must upgrade to Fedora 32 otherwise the C++ compiler
-will be too old, and not support the new C++23 standard that Scylla uses.
+Running `./install-dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
 
-Alternatively, to avoid having to upgrade your build machine or install
-various packages on it, we provide another option - the **frozen toolchain**.
-This is a script, `./tools/toolchain/dbuild`, that can execute build or run
-commands inside a container that contains exactly the right build tools and
-libraries. The `dbuild` technique is useful for beginners, but is also the way
-in which ScyllaDB produces official releases, so it is highly recommended.
+On Ubuntu and Debian based Linux distributions, some packages
+required to build Scylla are missing in the official upstream:
 
-To use `dbuild`, you simply prefix any build or run command with it. Building
-and running Scylla becomes as easy as:
+- libthrift-dev and libthrift
+- antlr3-c++-dev
 
-```bash
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
-$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
-```
-
-Note: do not mix environments - either perform all your work with dbuild, or natively on the host.
-Note2: you can get to an interactive shell within dbuild by running it without any parameters:
-```bash
-$ ./tools/toolchain/dbuild
-```
+Try running ```sudo ./scripts/scylla_current_repo``` to add Scylla upstream,
+and get the missing packages from it.
 
 ### Build system
 
 **Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
-thread, and up to 3 GB per native thread while linking. GCC >= 10 is
+thread, and up to 3 GB per native thread while linking. GCC >= 8.1.1. is
 required.
 
 Scylla is built with [Ninja](https://ninja-build.org/), a low-level rule-based system. A Python script, `configure.py`, generates a Ninja file (`build.ninja`) based on configuration options.
@@ -91,7 +73,7 @@ You can also specify a single mode. For example
 $ ninja-build release
 ```
 
-Will build everything in release mode. The valid modes are
+Will build everytihng in release mode. The valid modes are
 
 * Debug: Enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer)
   and other sanity checks. It has no optimizations, which allows for debugging with tools like
@@ -122,13 +104,6 @@ Run all tests through the test execution wrapper with
 $ ./test.py --mode={debug,release}
 ```
 
-or, if you are using `dbuild`, you need to build the code and the tests and then you can run them at will:
-
-```bash
-$ ./tools/toolchain/dbuild ninja {debug,release,dev}-build
-$ ./tools/toolchain/dbuild ./test.py --mode {debug,release,dev}
-```
-
 The `--name` argument can be specified to run a particular test.
 
 Alternatively, you can execute the test executable directly. For example,
@@ -166,7 +141,7 @@ In v3:
 "Tests: unit ({mode}), dtest ({smp})"
 ```
 
-The usual is "Tests: unit (dev)", although running debug tests is encouraged.
+The usual is "Tests: unit (release)", although running debug tests is encouraged.
 
 5. When answering review comments, prefer inline quotes as they make it easier to track the conversation across multiple e-mails.
 
@@ -185,8 +160,12 @@ and you will get output like this:
 ```
 CQL QUERY LANGUAGE
   Tomasz Grabiec <tgrabiec@scylladb.com>   [maintainer]
+  Pekka Enberg <penberg@scylladb.com>      [maintainer]
 MATERIALIZED VIEWS
+  Pekka Enberg <penberg@scylladb.com>      [maintainer]
+  Duarte Nunes <duarte@scylladb.com>       [maintainer]
   Nadav Har'El <nyh@scylladb.com>          [reviewer]
+  Duarte Nunes <duarte@scylladb.com>       [reviewer]
 ```
 
 ### Running Scylla
@@ -208,11 +187,11 @@ $ # Edit configuration options as appropriate
 $ SCYLLA_HOME=$HOME/scylla build/release/scylla
 ```
 
-The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories`, `commitlog_directory` and `schema_commitlog_directory` fields as appropriate.
+The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories` and `commitlog_directory` fields as appropriate.
 
 Scylla has a number of requirements for the file-system and operating system to operate ideally and at peak performance. However, during development, these requirements can be relaxed with the `--developer-mode` flag.
 
-Additionally, when running on under-powered platforms like portable laptops, the `--overprovisioned` flag is useful.
+Additionally, when running on under-powered platforms like portable laptops, the `--overprovisined` flag is useful.
 
 On a development machine, one might run Scylla as
 
@@ -220,9 +199,28 @@ On a development machine, one might run Scylla as
 $ SCYLLA_HOME=$HOME/scylla build/release/scylla --overprovisioned --developer-mode=yes
 ```
 
-To interact with scylla it is recommended to build our version of
-cqlsh. It is available at
-https://github.com/scylladb/scylla-cqlsh and is available as a submodule.
+To interact with scylla it is recommended to build our versions of
+cqlsh and nodetool. They are available at
+https://github.com/scylladb/scylla-tools-java and can be built with
+
+```bash
+$ sudo ./install-dependencies.sh
+$ ant jar
+```
+
+cqlsh should work out of the box, but nodetool depends on a running
+scylla-jmx (https://github.com/scylladb/scylla-jmx). It can be build
+with
+
+```bash
+$ mvn package
+```
+
+and must be started with
+
+```bash
+$ ./scripts/scylla-jmx
+```
 
 ### Branches and tags
 
@@ -261,45 +259,21 @@ Once the patch set is ready to be reviewed, push the branch to the public remote
 
 ### Development environment and source code navigation
 
-Scylla includes a [CMake](https://cmake.org/) file, `CMakeLists.txt` that can be used with development environments so
-that they can properly analyze the source code. However, building with CMake is not yet officially supported.
+Scylla includes a [CMake](https://cmake.org/) file, `CMakeLists.txt`, for use only with development environments (not for building) so that they can properly analyze the source code.
 
-Good IDEs that have support for CMake build toolchain are [CLion](https://www.jetbrains.com/clion/),
-[KDevelop](https://www.kdevelop.org/) and [QtCreator](https://wiki.qt.io/Qt_Creator).
+[CLion](https://www.jetbrains.com/clion/) is a commercial IDE offers reasonably good source code navigation and advice for code hygiene, though its C++ parser sometimes makes errors and flags false issues.
 
-[Eclipse](https://eclipse.org/cdt/) is another open-source option. It doesn't natively work with CMake projects and its
-C++ parser has many issues.
+Other good options that directly parse CMake files are [KDevelop](https://www.kdevelop.org/) and [QtCreator](https://wiki.qt.io/Qt_Creator).
 
-#### CLion
+To use the `CMakeLists.txt` file with these programs, define the `FOR_IDE` CMake variable or shell environmental variable.
 
-[CLion](https://www.jetbrains.com/clion/) is a commercial IDE offers reasonably good source code navigation and advice
-for code hygiene, though its C++ parser sometimes makes errors and flags false issues. In order to enable proper code
-analysis in CLion, the following steps are needed:
-
-1. Get the ScyllaDB source code by following the [Getting the source code](#getting-the-source-code).
-2. Follow the steps in [Dependencies](#dependencies) in order to install the required tools natively into your system.
-   **Don't** follow the *frozen toolchain* part described there, since CMake checks for the build dependencies installed
-   in the system, not in the container image provided by the toolchain.
-3. In CLion, select `File`→`Open` and select the main ScyllaDB directory in order to open the CMake project there. The
-   project should open and fail to process the `CMakeLists.txt`. That's expected.
-4. In CLion, open `File`→`Settings`.
-5. Find and click on `Toolchains` (type *toolchains* into search box).
-6. Select the toolchain you will use, for instance the `Default` one.
-7. Type in the following system-installed tools to be used:
-    - `CMake`: *cmake*
-    - `Build Tool`: *ninja*
-    - `C Compiler`: *clang*
-    - `C++ Compiler`: *clang*
-8. On the `CMake` panel/tab, click on `Reload CMake Project`
-
-After that, CLion should successfully initialize the CMake project (marked by `[Finished]` in the console) and the
-source code editor should provide code analysis support normally from now on.
+[Eclipse](https://eclipse.org/cdt/) is another open-source option. It doesn't natively work with CMake projects, and its C++ parser has many similar issues as CLion.
 
 ### Distributed compilation: `distcc` and `ccache`
 
 Scylla's compilations times can be long. Two tools help somewhat:
 
-- [ccache](https://ccache.samba.org/) caches compiled object files on disk and reuses them when possible
+- [ccache](https://ccache.samba.org/) caches compiled object files on disk and re-uses them when possible
 - [distcc](https://github.com/distcc/distcc) distributes compilation jobs to remote machines
 
 A reasonably-powered laptop acts as the coordinator for compilation. A second, more powerful, machine acts as a passive compilation server.
@@ -361,7 +335,7 @@ avoid that the gold linker can be told to create an index with
 
 More info at https://gcc.gnu.org/wiki/DebugFission.
 
-Both options can be enabled by passing `--split-dwarf` to configure.py.
+Both options can be enable by passing `--split-dwarf` to configure.py.
 
 Note that distcc is *not* compatible with it, but icecream
 (https://github.com/icecc/icecream) is.
@@ -370,7 +344,7 @@ Note that distcc is *not* compatible with it, but icecream
 
 Sometimes Scylla development is closely tied with a feature being developed in Seastar. It can be useful to compile Scylla with a particular check-out of Seastar.
 
-One way to do this is to create a local remote for the Seastar submodule in the Scylla repository:
+One way to do this it to create a local remote for the Seastar submodule in the Scylla repository:
 
 ```bash
 $ cd $HOME/src/scylla
@@ -380,61 +354,7 @@ $ git remote update
 $ git checkout -t local/my_local_seastar_branch
 ```
 
-### Generating code coverage report
-
-Install dependencies:
-
-    $ dnf install llvm # for llvm-profdata and llvm-cov
-    $ dnf install lcov # for genhtml
-
-Instruct `configure.py` to generate build files for `coverage` mode:
-
-    $ ./configure.py --mode=coverage
-
-Build the tests you want to run, then run them via `test.py` (important!):
-
-    $ ./test.py --mode=coverage [...]
-
-Alternatively, you can run individual tests via `./scripts/coverage.py --run`.
-
-Open the link printed at the end. Be horrified. Go and write more tests.
-
-For more details see `./scripts/coverage.py --help`.
-
-### Resolving stack backtraces
-
-Scylla may print stack backtraces to the log for several reasons.
-For example:
-- When aborting (e.g. due to assertion failure, internal error, or segfault)
-- When detecting seastar reactor stalls (where a seastar task runs for a long time without yielding the cpu to other tasks on that shard)
-
-The backtraces contain code pointers so they are not very helpful without resolving into code locations.
-To resolve the backtraces, one needs the scylla relocatable package that contains the scylla binary (with debug information),
-as well as the dynamic libraries it is linked against.
-
-Builds from our automated build system are uploaded to the cloud
-and can be searched on http://backtrace.scylladb.com/
-
-Make sure you have the scylla server exact `build-id` to locate
-its respective relocatable package, required for decoding backtraces it prints.
-
-The build-id is printed to the system log when scylla starts.
-It can also be found by executing `scylla --build-id`, or
-by using the `file` utility, for example:
-```
-$ scylla --build-id
-4cba12e6eb290a406bfa4930918db23941fd4be3
-
-$ file scylla
-scylla: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked, interpreter /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////lib64/ld-linux-x86-64.so.2, for GNU/Linux 3.2.0, BuildID[sha1]=4cba12e6eb290a406bfa4930918db23941fd4be3, with debug_info, not stripped, too many notes (256)
-```
-
-To find the build-id of a coredump, use the `eu-unstrip` utility as follows:
-```
-$ eu-unstrip -n --core <coredump> | awk '/scylla$/ { s=$2; sub(/@.*$/, "", s); print s; exit(0); }'
-4cba12e6eb290a406bfa4930918db23941fd4be3
-```
-
 ### Core dump debugging
 
-See [debugging.md](docs/dev/debugging.md).
+Slides:
+2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

LICENSE-ScyllaDB-Source-Available.md

@@ -1,62 +0,0 @@
-## **SCYLLADB SOFTWARE LICENSE AGREEMENT**
-
-| Version: | 1.0 |
-| :---- | :---- |
-| Last updated: | December 18, 2024 |
-
-**Your Acceptance**
-
-By utilizing or accessing the Software in any manner, You hereby confirm and agree to be bound by this ScyllaDB Software License Agreement (the "**Agreement**"), which sets forth the terms and conditions on which ScyllaDB Ltd. ("**Licensor**") makes the Software available to You, as the Licensee. If Licensee does not agree to the terms of this Agreement or cannot otherwise comply with the Agreement, Licensee shall not utilize or access the Software.
-
-The terms "**You**" or "**Licensee**" refer to any individual accessing or using the Software under this Agreement ("**Use**"). In case that such individual is Using the Software on behalf of a legal entity, You hereby irrevocably represents and warrants that You have full legal capacity and authority to enter into this Agreement on behalf of such entity as well as bind such entity to this Agreement, and in such case, the term "You" or "Licensee" in this Agreement will refer to such entity.
-
-**Grant of License**
-
-* **Software Definitions:** Software means the ScyllaDB software provided by Licensor, including the source code, object code, and any accompanying documentation or tools, or any part thereof, as made available under this Agreement.
-* **Grant of License:** Subject to the terms and conditions of this Agreement, Licensor grants You a limited, non-exclusive, revocable, non-sublicensable, non-transferable, royalty free license to Use the Software, in each case solely for the purposes of:
-  1) Copying, distributing, evaluating (including performing benchmarking or comparative tests or evaluations , subject to the limitations below) and improving the Software and ScyllaDB; and
-  2) create a modified version of the Software (each, a "**Licensed Work**"); provided however, that each such Licensed Work keeps all or substantially all of the functions and features of the Software, and/or using all or substantially all of the source code of the Software. You hereby agree that all the Licensed Work are, upon creation, considered Licensed Work of the Licensor, shall be the sole property of the Licensor and its assignees, and the Licensor and its assignees shall be the sole owner of all rights of any kind or nature, in connection with such Licensed Work. You hereby irrevocably and unconditionally assign to the Licensor all the Licensed Work and any part thereof.  This License applies separately for each version of the Licensed Work, which shall be considered "Software" for the purpose of this Agreement.
-
-
-**License Limitations, Restrictions and Obligations:** The license grant above is subject to the following limitations, restrictions, and obligations. If Licensee’s Use of the Software does not comply with the above license grant or the terms of this section (including exceeding the Usage Limit set forth below), Licensee must: (i) refrain from any Use of the Software; and (ii) purchase a [commercial paid license](https://www.scylladb.com/scylladb-proprietary-software-license-agreement/) from the Licensor.
-
-* **Updates:** You shall be solely responsible for providing all equipment, systems, assets, access, and ancillary goods and services needed to access and Use the Software.  Licensor may modify or update the Software at any time, without notification, in its sole and absolute discretion.  After the effective date of each such update, Licensor shall bear no obligation to run, provide or support legacy versions of the Software.
-* **"Usage Limit":** Licensee's total overall available storage across all deployments and clusters of the Software and the Licensed Work under this License shall not exceed 10TB and/or an upper limit of 50 VCPUs (hyper threads).
-* **IP Markings:** Licensee must retain all copyright, trademark, and other proprietary notices contained in the Software. You will not modify, delete, alter, remove, or obscure any intellectual property, including without limitations licensing, copyright, trademark, or any other notices of Licensor in the Software.
-* **License Reproduction:** You must conspicuously display this Agreement on each copy of the Software. If You receive the Software from a third party, this Agreement still applies to Your Use of the Software. You will be responsible for any breach of this Agreement by any such third-party.
-* Distribution of any Licensed Works is permitted, provided that: (i) You must include in any Licensed Work prominent notices stating that You have modified the Software, (ii) You include a copy of this Agreement with the Licensed Work, and (iii) You clearly identify all modifications made in the Licensed Work and provides attribution to the Licensor as the original author(s) of the Software.
-* **Commercial Use Restrictions:** Licensee may not offer the Software as a software-as-a-service (SaaS) or commercial database-as-as-service (dBaaS) offering.  Licensee may not use the Software to compete with Licensor's existing or future products or services. If your Use of the Software does not comply with the requirements currently in effect as described in this License, you must purchase a commercial license from the Licensor, its affiliated entities, or you must refrain from using the Software and all Licensed Work. Furthermore, if You make any written claim of patent infringement relating to the Software, Your patent license for the Software granted under this Agreement terminates immediately.
-* Notwithstanding anything to the contrary, under the License granted hereunder, You shall not and shall not permit others to: (i) transfer the Software or any portions thereof to any other party except as expressly permitted herein; (ii) attempt to circumvent or overcome any technological protection measures incorporated into the Software; (iii) incorporate the Software into the structure, machinery or controls of any aircraft, other aerial device, military vehicle, hovercraft, waterborne craft or any medical equipment of any kind; or (iv) use the Software or any part thereof in any unlawful, harmful or illegal manner, or in a manner which infringes third parties’ rights in any way, including intellectual property rights.
-
-**Monitoring; Audit**
-
-* **License Key:** Licensor may implement a method of authentication, e.g., a unique license token ("License Key") as a condition of accessing or using the Software. Upon the implementation of such License Key, Licensee agrees to comply with Licensor terms and requirements with regards to such License Key
-* **Monitoring & Data Sharing:** Licensor do not collect customer data from its database. Notwithstanding, Licensee acknowledges and agrees that the License Key and Software may share telemetry metrics and information regarding the execution volume and statistics with Licensor regarding Licensee’s use of the same. Any disclosure or use of such information shall be subject to, and in accordance with, Licensor’s Privacy Policy and Data Processing Agreement, which can be found at [https://www.scylladb.com/policies-agreements](https://www.scylladb.com/policies-agreements).
-* **Information Requests; Audits:**  Licensee shall keep accurate records of its access to and use of any Software, and shall promptly respond to any Licensor requests for information regarding the same.  To ensure compliance with the terms of this Agreement, during the term of this Agreement and for a period of one (1) year thereafter, Licensor (or an agent bound by customary confidentiality undertakings on its behalf) may audit Licensee’s records which are related to its access to or use of the Software. The cost of such audit shall be borne by Licensor unless it is determined that Licensee has materially breached this Agreement.
-
-**Termination**
-
-* **Termination:** Licensor may immediately terminate this Agreement will automatically terminate if You for any reason, including without limitation for (i) Licensee’s breach of any term, condition, or restriction of this Agreement, unless such breach was cured to Licensor’s satisfaction within no more than 15 days from the date of the breach. Notwithstanding the foregoing, intentional; or (ii) if Licensee brings any claim, demand or repeated breaches lawsuit against Licensor.
-* **Obligations on Termination:**  Upon termination of this Agreement by You will cause Your licenses to terminate automatically and permanently, at Licensor’s sole discretion, Licensee must (i) immediately stop using any Software, (ii) return all copies of any tools or documentation provided by Licensor; and (iii) pay amount due to Licensor hereunder (e.g., audit costs).  All obligations which by their nature must survive the termination of this Agreement shall so survive.
-
-**Indemnity; Disclaimer; Limitation of Liability**
-
-* **Indemnity:** Licensee hereby agrees to indemnify, defend and hold harmless Licensor and its affiliates from any losses or damages incurred due to a third party claim arising out of: (i) Licensee’s breach of this Agreement; (ii) Licensee’s negligence, willful misconduct or violation of law, or (iii) Licensee’s products or services.
-* DISCLAIMER OF WARRANTIES:  LICENSEE AGREES THAT LICENSOR HAS MADE NO EXPRESS WARRANTIES REGARDING THE SOFTWARE AND THAT THE SOFTWARE IS BEING PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND. LICENSOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THE SOFTWARE, EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION, ANY IMPLIED WARRANTIES OF FITNESS FOR A PARTICULAR PURPOSE; TITLE; MERCHANTABILITY;  OR NON-INFRINGEMENT OF THIRD PARTY RIGHTS. LICENSOR DOES NOT WARRANT THAT THE SOFTWARE WILL OPERATE UNINTERRUPTED OR ERROR FREE, OR THAT ALL ERRORS WILL BE CORRECTED.  LICENSOR DOES NOT GUARANTEE ANY PARTICULAR RESULTS FROM THE USE OF THE SOFTWARE, AND DOES NOT WARRANT THAT THE SOFTWARE IS FIT FOR ANY PARTICULAR PURPOSE.
-* LIMITATION OF LIABILITY:  TO THE FULLEST EXTENT PERMISSIBLE UNDER APPLICABLE LAW, IN NO EVENT WILL LICENSOR AND/OR ITS AFFILIATES, EMPLOYEES, OFFICERS AND DIRECTORS BE LIABLE TO LICENSEE FOR (I) ANY LOSS OF USE OR DATA; INTERRUPTION OF BUSINESS; OR ANY INDIRECT; SPECIAL; INCIDENTAL; OR CONSEQUENTIAL DAMAGES OF ANY KIND (INCLUDING LOST PROFITS); AND (II) ANY DIRECT DAMAGES EXCEEDING THE TOTAL AMOUNT OF ONE THOUSAND US DOLLARS ($1,000).  THE FOREGOING PROVISIONS LIMITING THE LIABILITY OF LICENSOR SHALL APPLY REGARDLESS OF THE FORM OR CAUSE OF ACTION, WHETHER IN STRICT LIABILITY, CONTRACT OR TORT.
-
-**Proprietary Rights; No Other Rights**
-
-* **Ownership:** Licensor retains sole and exclusive ownership of all rights, interests and title in the Software and any scripts, processes, techniques, methodologies, inventions, know-how, concepts, formatting, arrangements, visual attributes, ideas, database rights, copyrights, patents, trade secrets, and other intellectual property related thereto, and all derivatives, enhancements, modifications and improvements thereof. Except for the limited license rights granted herein, Licensee has no rights in or to the Software and/ or Licensor’s trademarks, logo, or branding and You acknowledge that such Software, trademarks, logo, or branding is the sole property of Licensor.
-* **Feedback:** Licensee is not required to provide any suggestions, enhancement requests, recommendations or other feedback regarding the Software ("Feedback").  If, notwithstanding this policy, Licensee submits Feedback, Licensee understands and acknowledges that such Feedback is not submitted in confidence and Licensor assumes no obligation, expressed or implied, by considering it.  All right in any trademark or logo of Licensor or its affiliates and You shall make no claim of right to the Software or any part thereof to be supplied by Licensor hereunder and acknowledges that as between Licensor and You, such Software is the sole proprietary, title and interest in and to Licensor.such Feedback shall be assigned to, and shall become the sole and exclusive property of, Licensor upon its creation.
-* Except for the rights expressly granted to You under this Agreement, You are not granted any other licenses or rights in the Software or otherwise. This Agreement constitutes the entire agreement between You and the Licensor with respect to the subject matter hereof and supersedes all prior or contemporaneous communications, representations, or agreements, whether oral or written.
-* **Third-Party Software:** Customer acknowledges that the Software may contain open and closed source components (“OSS Components”) that are governed separately by certain licenses, in each case as further provided by Company upon request. Any applicable OSS Component license is solely between Licensee and the applicable licensor of the OSS Component and Licensee shall comply with the applicable OSS Component license.
-* If any provision of this Agreement is held to be invalid or unenforceable, such provision shall be struck and the remaining provisions shall remain in full force and effect.
-
-**Miscellaneous**
-
-* **Miscellaneous:** This Agreement may be modified at any time by Licensor, and constitutes the entire agreement between the parties with respect to the subject matter hereof. Licensee may not assign or subcontract its rights or obligations under this Agreement.  This Agreement does not, and shall not be construed to create any relationship, partnership, joint venture, employer-employee, agency, or franchisor-franchisee relationship between the parties.
-* **Governing Law & Jurisdiction:** This Agreement shall be governed and construed in accordance with the laws of Israel, without giving effect to their respective conflicts of laws provisions, and the competent courts situated in Tel Aviv, Israel, shall have sole and exclusive jurisdiction over the parties and any conflict and/or dispute arising out of, or in connection to, this Agreement
-
-\[*End of ScyllaDB Software License Agreement*\]
-

LICENSE.AGPL

@@ -0,0 +1,661 @@
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU Affero General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<http://www.gnu.org/licenses/>.

MAINTAINERS

@@ -0,0 +1,131 @@
+M: Maintainer with commit access
+R: Reviewer with subsystem expertise
+F: Filename, directory, or pattern for the subsystem
+
+---
+
+AUTH
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Calle Wilund <calle@scylladb.com>
+R: Vlad Zolotarov <vladz@scylladb.com>
+R: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
+F: auth/*
+
+CACHE
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Paweł Dziepak <pdziepak@scylladb.com>
+R: Piotr Jastrzebski <piotr@scylladb.com>
+F: row_cache*
+F: *mutation*
+F: tests/mvcc*
+
+COMMITLOG / BATCHLOGa
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Calle Wilund <calle@scylladb.com>
+F: db/commitlog/*
+F: db/batch*
+
+COORDINATOR
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Gleb Natapov <gleb@scylladb.com>
+F: service/storage_proxy*
+
+COMPACTION
+R: Raphael S. Carvalho <raphaelsc@scylladb.com>
+R: Glauber Costa <glauber@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+F: sstables/compaction*
+
+CQL TRANSPORT LAYER
+M: Pekka Enberg <penberg@scylladb.com>
+F: transport/*
+
+CQL QUERY LANGUAGE
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Pekka Enberg <penberg@scylladb.com>
+F: cql3/*
+
+COUNTERS
+M: Paweł Dziepak <pdziepak@scylladb.com>
+F: counters*
+F: tests/counter_test*
+
+GOSSIP
+M: Duarte Nunes <duarte@scylladb.com>
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+R: Asias He <asias@scylladb.com>
+F: gms/*
+
+DOCKER
+M: Pekka Enberg <penberg@scylladb.com>
+F: dist/docker/*
+
+LSA
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Paweł Dziepak <pdziepak@scylladb.com>
+F: utils/logalloc*
+
+MATERIALIZED VIEWS
+M: Duarte Nunes <duarte@scylladb.com>
+M: Pekka Enberg <penberg@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+R: Duarte Nunes <duarte@scylladb.com>
+F: db/view/*
+F: cql3/statements/*view*
+
+PACKAGING
+R: Takuya ASADA <syuu@scylladb.com>
+F: dist/*
+
+REPAIR
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Asias He <asias@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+F: repair/*
+
+SCHEMA MANAGEMENT
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+M: Pekka Enberg <penberg@scylladb.com>
+F: db/schema_tables*
+F: db/legacy_schema_migrator*
+F: service/migration*
+F: schema*
+
+SECONDARY INDEXES
+M: Pekka Enberg <penberg@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+R: Pekka Enberg <penberg@scylladb.com>
+F: db/index/*
+F: cql3/statements/*index*
+
+SSTABLES
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Raphael S. Carvalho <raphaelsc@scylladb.com>
+R: Glauber Costa <glauber@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+F: sstables/*
+
+STREAMING
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Asias He <asias@scylladb.com>
+F: streaming/*
+F: service/storage_service.*
+
+THRIFT TRANSPORT LAYER
+M: Duarte Nunes <duarte@scylladb.com>
+F: thrift/*
+
+THE REST
+M: Avi Kivity <avi@scylladb.com>
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+F: *

NOTICE.txt

@@ -1,8 +1,5 @@
 This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
 especially Apache Cassandra.
 
-It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)
-
-It includes modified tests from https://github.com/etcd-io/etcd.git (owned by The etcd Authors)
-
-It includes files from https://github.com/bytecodealliance/wasmtime-cpp (owned by Bytecode Alliance), licensed with Apache License 2.0.
+It also includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
+These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.

README.md

@@ -1,112 +1,103 @@
 # Scylla
 
-[![Slack](https://img.shields.io/badge/slack-scylla-brightgreen.svg?logo=slack)](http://slack.scylladb.com)
-[![Twitter](https://img.shields.io/twitter/follow/ScyllaDB.svg?style=social&label=Follow)](https://twitter.com/intent/follow?screen_name=ScyllaDB)
+## Quick-start
 
-## What is Scylla?
-
-Scylla is the real-time big data database that is API-compatible with Apache Cassandra and Amazon DynamoDB.
-Scylla embraces a shared-nothing approach that increases throughput and storage capacity to realize order-of-magnitude performance improvements and reduce hardware costs.
-
-For more information, please see the [ScyllaDB web site].
-
-[ScyllaDB web site]: https://www.scylladb.com
-
-## Build Prerequisites
-
-Scylla is fairly fussy about its build environment, requiring very recent
-versions of the C++23 compiler and of many libraries to build. The document
-[HACKING.md](HACKING.md) includes detailed information on building and
-developing Scylla, but to get Scylla building quickly on (almost) any build
-machine, Scylla offers a [frozen toolchain](tools/toolchain/README.md).
-This is a pre-configured Docker image which includes recent versions of all
-the required compilers, libraries and build tools. Using the frozen toolchain
-allows you to avoid changing anything in your build machine to meet Scylla's
-requirements - you just need to meet the frozen toolchain's prerequisites
-(mostly, Docker or Podman being available).
-
-## Building Scylla
-
-Building Scylla with the frozen toolchain `dbuild` is as easy as:
+To get the build going quickly, Scylla offers a [frozen toolchain](tools/toolchain/README.md)
+which would build and run Scylla using a pre-configured Docker image.
+Using the frozen toolchain will also isolate all of the installed
+dependencies in a Docker container.
+Assuming you have met the toolchain prerequisites, which is running
+Docker in user mode, building and running is as easy as:
 
 ```bash
-$ git submodule update --init --force --recursive
 $ ./tools/toolchain/dbuild ./configure.py
 $ ./tools/toolchain/dbuild ninja build/release/scylla
-```
+$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
+ ```
 
-For further information, please see:
+Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
 
-* [Developer documentation] for more information on building Scylla.
-* [Build documentation] on how to build Scylla binaries, tests, and packages.
-* [Docker image build documentation] for information on how to build Docker images.
-
-[developer documentation]: HACKING.md
-[build documentation]: docs/dev/building.md
-[docker image build documentation]: dist/docker/redhat/README.md
+**Note**: GCC >= 8.1.1 is required to compile Scylla.
 
 ## Running Scylla
 
-To start Scylla server, run:
+* Run Scylla
+```
+./build/release/scylla
 
-```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --workdir tmp --smp 1 --developer-mode 1
 ```
 
-This will start a Scylla node with one CPU core allocated to it and data files stored in the `tmp` directory.
-The `--developer-mode` is needed to disable the various checks Scylla performs at startup to ensure the machine is configured for maximum performance (not relevant on development workstations).
-Please note that you need to run Scylla with `dbuild` if you built it with the frozen toolchain.
+* run Scylla with one CPU and ./tmp as data directory
 
-For more run options, run:
-
-```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --help
+```
+./build/release/scylla --datadir tmp --commitlog-directory tmp --smp 1
 ```
 
-## Testing
-
-[![Build with the latest Seastar](https://github.com/scylladb/scylladb/actions/workflows/seastar.yaml/badge.svg)](https://github.com/scylladb/scylladb/actions/workflows/seastar.yaml) [![Check Reproducible Build](https://github.com/scylladb/scylladb/actions/workflows/reproducible-build.yaml/badge.svg)](https://github.com/scylladb/scylladb/actions/workflows/reproducible-build.yaml) [![clang-nightly](https://github.com/scylladb/scylladb/actions/workflows/clang-nightly.yaml/badge.svg)](https://github.com/scylladb/scylladb/actions/workflows/clang-nightly.yaml)
-
-See [test.py manual](docs/dev/testing.md).
+* For more run options:
+```
+./build/release/scylla --help
+```
 
 ## Scylla APIs and compatibility
-By default, Scylla is compatible with Apache Cassandra and its API - CQL.
-There is also support for the API of Amazon DynamoDB™,
-which needs to be enabled and configured in order to be used. For more
-information on how to enable the DynamoDB™ API in Scylla,
-and the current compatibility of this feature as well as Scylla-specific extensions, see
+By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
+Thrift. There is also experimental support for the API of Amazon DynamoDB,
+but being experimental it needs to be explicitly enabled to be used. For more
+information on how to enable the experimental DynamoDB compatibility in Scylla,
+and the current limitations of this feature, see
 [Alternator](docs/alternator/alternator.md) and
 [Getting started with Alternator](docs/alternator/getting-started.md).
 
 ## Documentation
 
-Documentation can be found [here](docs/dev/README.md).
+Documentation can be found in [./docs](./docs) and on the
+[wiki](https://github.com/scylladb/scylla/wiki). There is currently no clear
+definition of what goes where, so when looking for something be sure to check
+both.
 Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
 User documentation can be found [here](https://docs.scylladb.com/).
 
-## Training
+## Building Fedora RPM
 
-Training material and online courses can be found at [Scylla University](https://university.scylladb.com/).
-The courses are free, self-paced and include hands-on examples. They cover a variety of topics including Scylla data modeling,
-administration, architecture, basic NoSQL concepts, using drivers for application development, Scylla setup, failover, compactions,
-multi-datacenters and how Scylla integrates with third-party applications.
+As a pre-requisite, you need to install [Mock](https://fedoraproject.org/wiki/Mock) on your machine:
+
+```
+# Install mock:
+sudo yum install mock
+
+# Add user to the "mock" group:
+usermod -a -G mock $USER && newgrp mock
+```
+
+Then, to build an RPM, run:
+
+```
+./dist/redhat/build_rpm.sh
+```
+
+The built RPM is stored in ``/var/lib/mock/<configuration>/result`` directory.
+For example, on Fedora 21 mock reports the following:
+
+```
+INFO: Done(scylla-server-0.00-1.fc21.src.rpm) Config(default) 20 minutes 7 seconds
+INFO: Results and/or logs in: /var/lib/mock/fedora-21-x86_64/result
+```
+
+## Building Fedora-based Docker image
+
+Build a Docker image with:
+
+```
+cd dist/docker
+docker build -t <image-name> .
+```
+
+Run the image with:
+
+```
+docker run -p $(hostname -i):9042:9042 -i -t <image name>
+```
 
 ## Contributing to Scylla
 
-If you want to report a bug or submit a pull request or a patch, please read the [contribution guidelines].
-
-If you are a developer working on Scylla, please read the [developer guidelines].
-
-[contribution guidelines]: CONTRIBUTING.md
-[developer guidelines]: HACKING.md
-
-## Contact
-
-* The [community forum] and [Slack channel] are for users to discuss configuration, management, and operations of ScyllaDB.
-* The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
-
-[Community forum]: https://forum.scylladb.com/
-
-[Slack channel]: http://slack.scylladb.com/
-
-[Developers mailing list]: https://groups.google.com/forum/#!forum/scylladb-dev
+[Hacking howto](HACKING.md)
+[Guidelines for contributing](CONTRIBUTING.md)

SCYLLA-VERSION-GEN

@@ -1,119 +1,26 @@
 #!/bin/sh
 
-USAGE=$(cat <<-END
-Usage: $(basename "$0") [-h|--help] [-o|--output-dir PATH] [--date-stamp DATE] -- generate Scylla version and build information files.
-
-Options:
-  -h|--help show this help message.
-  -o|--output-dir PATH specify destination path at which the version files are to be created.
-  -d|--date-stamp DATE manually set date for release parameter
-  -v|--verbose also print out the version number
-
-By default, the script will attempt to parse 'version' file
-in the current directory, which should contain a string of
-'\$version-\$release' form.
-
-Otherwise, it will call 'git log' on the source tree (the
-directory, which contains the script) to obtain current
-commit hash and use it for building the version and release
-strings.
-
-The script assumes that it's called from the Scylla source
-tree.
-
-The files created are:
-  SCYLLA-VERSION-FILE
-  SCYLLA-RELEASE-FILE
-  SCYLLA-PRODUCT-FILE
-
-By default, these files are created in the 'build'
-subdirectory under the directory containing the script.
-The destination directory can be overridden by
-using '-o PATH' option.
-END
-)
-
-DATE=""
-PRINT_VERSION=false
-
-while [ $# -gt 0 ]; do
-	opt="$1"
-	case $opt in
-		-h|--help)
-			echo "$USAGE"
-			exit 0
-			;;
-		-o|--output-dir)
-			OUTPUT_DIR="$2"
-			shift
-			shift
-			;;
-		--date-stamp)
-			DATE="$2"
-			shift
-			shift
-			;;
-		-v|--verbose)
-			PRINT_VERSION=true
-			shift
-			;;
-		*)
-			echo "Unexpected argument found: $1"
-			echo
-			echo "$USAGE"
-			exit 1
-			;;
-	esac
-done
-
-SCRIPT_DIR="$(dirname "$0")"
-
-if [ -z "$OUTPUT_DIR" ]; then
-	OUTPUT_DIR="$SCRIPT_DIR/build"
-fi
-
-if [ -z "$DATE" ]; then
-  DATE=$(date --utc +%Y%m%d)
-fi
-
-# Default scylla product/version tags
 PRODUCT=scylla
-VERSION=2026.2.0-dev
+VERSION=3.2.5
 
 if test -f version
 then
 	SCYLLA_VERSION=$(cat version | awk -F'-' '{print $1}')
 	SCYLLA_RELEASE=$(cat version | awk -F'-' '{print $2}')
 else
+	DATE=$(date +%Y%m%d)
+	GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
 	SCYLLA_VERSION=$VERSION
-	if [ -z "$SCYLLA_RELEASE" ]; then
-		GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1 --abbrev=12)
-		# For custom package builds, replace "0" with "counter.yourname",
-		# where counter starts at 1 and increments for successive versions.
-		# This ensures that the package manager will select your custom
-		# package over the standard release.
-		# Do not use any special characters like - or _ in the name above!
-		# These characters either have special meaning or are illegal in
-		# version strings.
-		SCYLLA_BUILD=0
-		SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
-	elif [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-		echo "setting SCYLLA_RELEASE only makes sense in clean builds" 1>&2
-		exit 1
-	fi
+	# For custom package builds, replace "0" with "counter.your_name",
+	# where counter starts at 1 and increments for successive versions.
+	# This ensures that the package manager will select your custom
+	# package over the standard release.
+	SCYLLA_BUILD=0
+	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi
 
-if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" | rev | cut -d . -f 1 | rev)
-	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
-		exit 0
-	fi
-fi
-
-if $PRINT_VERSION; then
-	echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
-fi
-mkdir -p "$OUTPUT_DIR"
-echo "$SCYLLA_VERSION" > "$OUTPUT_DIR/SCYLLA-VERSION-FILE"
-echo "$SCYLLA_RELEASE" > "$OUTPUT_DIR/SCYLLA-RELEASE-FILE"
-echo "$PRODUCT" > "$OUTPUT_DIR/SCYLLA-PRODUCT-FILE"
+echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
+mkdir -p build
+echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
+echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE
+echo "$PRODUCT" > build/SCYLLA-PRODUCT-FILE

absl-flat_hash_map.cc

@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "absl-flat_hash_map.hh"
-
-size_t sstring_hash::operator()(std::string_view v) const noexcept {
-    return absl::Hash<std::string_view>{}(v);
-}

absl-flat_hash_map.hh

@@ -1,34 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <absl/container/flat_hash_map.h>
-#include <seastar/core/sstring.hh>
-
-using namespace seastar;
-
-struct sstring_hash {
-    using is_transparent = void;
-    size_t operator()(std::string_view v) const noexcept;
-};
-
-struct sstring_eq {
-    using is_transparent = void;
-    bool operator()(std::string_view a, std::string_view b) const noexcept {
-        return a == b;
-    }
-};
-
-template <typename K, typename V, typename... Ts>
-struct flat_hash_map : public absl::flat_hash_map<K, V, Ts...> {
-};
-
-template <typename V>
-struct flat_hash_map<sstring, V>
-    : public absl::flat_hash_map<sstring, V, sstring_hash, sstring_eq> {};

alternator-test/README.md

@@ -0,0 +1,78 @@
+Tests for Alternator that should also pass, identically, against DynamoDB.
+
+Tests use the boto3 library for AWS API, and the pytest frameworks
+(both are available from Linux distributions, or with "pip install").
+
+To run all tests against the local installation of Alternator on
+http://localhost:8000, just run `pytest`.
+
+Some additional pytest options:
+* To run all tests in a single file, do `pytest test_table.py`.
+* To run a single specific test, do `pytest test_table.py::test_create_table_unsupported_names`.
+* Additional useful pytest options, especially useful for debugging tests:
+  * -v: show the names of each individual test running instead of just dots.
+  * -s: show the full output of running tests (by default, pytest captures the test's output and only displays it if a test fails)
+
+Add the `--aws` option to test against AWS instead of the local installation.
+For example - `pytest --aws test_item.py` or `pytest --aws`.
+
+If you plan to run tests against AWS and not just a local Scylla installation,
+the files ~/.aws/credentials should be configured with your AWS key:
+
+```
+[default]
+aws_access_key_id = XXXXXXXXXXXXXXXXXXXX
+aws_secret_access_key = xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+```
+
+and ~/.aws/config with the default region to use in the test:
+```
+[default]
+region = us-east-1
+```
+
+## HTTPS support
+
+In order to run tests with HTTPS, run pytest with `--https` parameter. Note that the Scylla cluster needs to be provided
+with alternator\_https\_port configuration option in order to initialize a HTTPS server.
+Moreover, running an instance of a HTTPS server requires a certificate. Here's how to easily generate
+a key and a self-signed certificate, which is sufficient to run `--https` tests:
+
+```
+openssl genrsa 2048 > scylla.key
+openssl req -new -x509 -nodes -sha256 -days 365 -key scylla.key -out scylla.crt
+```
+
+If this pair is put into `conf/` directory, it will be enough
+to allow the alternator HTTPS server to think it's been authorized and properly certified.
+Still, boto3 library issues warnings that the certificate used for communication is self-signed,
+and thus should not be trusted. For the sake of running local tests this warning is explicitly ignored.
+
+
+## Authorization
+
+By default, boto3 prepares a properly signed Authorization header with every request.
+In order to confirm the authorization, the server recomputes the signature by using
+user credentials (user-provided username + a secret key known by the server),
+and then checks if it matches the signature from the header.
+Early alternator code did not verify signatures at all, which is also allowed by the protocol.
+A partial implementation of the authorization verification can be allowed by providing a Scylla
+configuration parameter:
+```yaml
+  alternator_enforce_authorization: true
+```
+The implementation is currently coupled with Scylla's system\_auth.roles table,
+which means that an additional step needs to be performed when setting up Scylla
+as the test environment. Tests will use the following credentials:
+Username: `alternator`
+Secret key: `secret_pass`
+
+With CQLSH, it can be achieved by executing this snipped:
+
+```bash
+cqlsh -x "INSERT INTO system_auth.roles (role, salted_hash) VALUES ('alternator', 'secret_pass')"
+```
+
+Most tests expect the authorization to succeed, so they will pass even with `alternator_enforce_authorization`
+turned off. However, test cases from `test_authorization.py` may require this option to be turned on,
+so it's advised.

alternator-test/conftest.py

@@ -0,0 +1,179 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# This file contains "test fixtures", a pytest concept described in
+# https://docs.pytest.org/en/latest/fixture.html.
+# A "fixture" is some sort of setup which an invididual test requires to run.
+# The fixture has setup code and teardown code, and if multiple tests
+# require the same fixture, it can be set up only once - while still allowing
+# the user to run individual tests and automatically set up the fixtures they need.
+
+import pytest
+import boto3
+from util import create_test_table
+
+# Test that the Boto libraries are new enough. These tests want to test a
+# large variety of DynamoDB API features, and to do this we need a new-enough
+# version of the the Boto libraries (boto3 and botocore) so that they can
+# access all these API features.
+# In particular, the BillingMode feature was added in botocore 1.12.54.
+import botocore
+import sys
+from distutils.version import LooseVersion
+if (LooseVersion(botocore.__version__) < LooseVersion('1.12.54')):
+    pytest.exit("Your Boto library is too old. Please upgrade it,\ne.g. using:\n    sudo pip{} install --upgrade boto3".format(sys.version_info[0]))
+
+# By default, tests run against a local Scylla installation on localhost:8080/.
+# The "--aws" option can be used to run against Amazon DynamoDB in the us-east-1
+# region.
+def pytest_addoption(parser):
+    parser.addoption("--aws", action="store_true",
+        help="run against AWS instead of a local Scylla installation")
+    parser.addoption("--https", action="store_true",
+        help="communicate via HTTPS protocol on port 8043 instead of HTTP when"
+            " running against a local Scylla installation")
+
+# "dynamodb" fixture: set up client object for communicating with the DynamoDB
+# API. Currently this chooses either Amazon's DynamoDB in the default region
+# or a local Alternator installation on http://localhost:8080 - depending on the
+# existence of the "--aws" option. In the future we should provide options
+# for choosing other Amazon regions or local installations.
+# We use scope="session" so that all tests will reuse the same client object.
+@pytest.fixture(scope="session")
+def dynamodb(request):
+    if request.config.getoption('aws'):
+        return boto3.resource('dynamodb')
+    else:
+        # Even though we connect to the local installation, Boto3 still
+        # requires us to specify dummy region and credential parameters,
+        # otherwise the user is forced to properly configure ~/.aws even
+        # for local runs.
+        local_url = 'https://localhost:8043' if request.config.getoption('https') else 'http://localhost:8000'
+        # Disable verifying in order to be able to use self-signed TLS certificates
+        verify = not request.config.getoption('https')
+        # Silencing the 'Unverified HTTPS request warning'
+        if request.config.getoption('https'):
+            import urllib3
+            urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        return boto3.resource('dynamodb', endpoint_url=local_url, verify=verify,
+            region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass')
+
+# "test_table" fixture: Create and return a temporary table to be used in tests
+# that need a table to work on. The table is automatically deleted at the end.
+# We use scope="session" so that all tests will reuse the same client object.
+# This "test_table" creates a table which has a specific key schema: both a
+# partition key and a sort key, and both are strings. Other fixtures (below)
+# can be used to create different types of tables.
+#
+# TODO: Although we are careful about deleting temporary tables when the
+# fixture is torn down, in some cases (e.g., interrupted tests) we can be left
+# with some tables not deleted, and they will never be deleted. Because all
+# our temporary tables have the same test_table_prefix, we can actually find
+# and remove these old tables with this prefix. We can have a fixture, which
+# test_table will require, which on teardown will delete all remaining tables
+# (possibly from an older run). Because the table's name includes the current
+# time, we can also remove just tables older than a particular age. Such
+# mechanism will allow running tests in parallel, without the risk of deleting
+# a parallel run's temporary tables.
+@pytest.fixture(scope="session")
+def test_table(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ])
+    yield table
+    # We get back here when this fixture is torn down. We ask Dynamo to delete
+    # this table, but not wait for the deletion to complete. The next time
+    # we create a test_table fixture, we'll choose a different table name
+    # anyway.
+    table.delete()
+
+# The following fixtures test_table_* are similar to test_table but create
+# tables with different key schemas.
+@pytest.fixture(scope="session")
+def test_table_s(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ])
+    yield table
+    table.delete()
+@pytest.fixture(scope="session")
+def test_table_b(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'B' } ])
+    yield table
+    table.delete()
+@pytest.fixture(scope="session")
+def test_table_sb(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'B' } ])
+    yield table
+    table.delete()
+@pytest.fixture(scope="session")
+def test_table_sn(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'N' } ])
+    yield table
+    table.delete()
+
+# "filled_test_table" fixture:  Create a temporary table to be used in tests
+# that involve reading data - GetItem, Scan, etc. The table is filled with
+# 328 items - each consisting of a partition key, clustering key and two
+# string attributes. 164 of the items are in a single partition (with the
+# partition key 'long') and the 164 other items are each in a separate
+# partition. Finally, a 329th item is added with different attributes.
+# This table is supposed to be read from, not updated nor overwritten.
+# This fixture returns both a table object and the description of all items
+# inserted into it.
+@pytest.fixture(scope="session")
+def filled_test_table(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ])
+    count = 164
+    items = [{
+        'p': str(i),
+        'c': str(i),
+        'attribute': "x" * 7,
+        'another': "y" * 16
+    } for i in range(count)]
+    items = items + [{
+        'p': 'long',
+        'c': str(i),
+        'attribute': "x" * (1 + i % 7),
+        'another': "y" * (1 + i % 16)
+    } for i in range(count)]
+    items.append({'p': 'hello', 'c': 'world', 'str': 'and now for something completely different'})
+
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+
+    yield table, items
+    table.delete()

alternator-test/test_authorization.py

@@ -0,0 +1,74 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for authorization
+
+import pytest
+import botocore
+from botocore.exceptions import ClientError
+import boto3
+import requests
+
+# Test that trying to perform an operation signed with a wrong key
+# will not succeed
+def test_wrong_key_access(request, dynamodb):
+    print("Please make sure authorization is enforced in your Scylla installation: alternator_enforce_authorization: true")
+    url = dynamodb.meta.client._endpoint.host
+    with pytest.raises(ClientError, match='UnrecognizedClientException'):
+        if url.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url, aws_access_key_id='wrong_id', aws_secret_access_key='').describe_endpoints()
+        else:
+            verify = not url.startswith('https')
+            boto3.client('dynamodb',endpoint_url=url, region_name='us-east-1', aws_access_key_id='whatever', aws_secret_access_key='', verify=verify).describe_endpoints()
+
+# A similar test, but this time the user is expected to exist in the database (for local tests)
+def test_wrong_password(request, dynamodb):
+    print("Please make sure authorization is enforced in your Scylla installation: alternator_enforce_authorization: true")
+    url = dynamodb.meta.client._endpoint.host
+    with pytest.raises(ClientError, match='UnrecognizedClientException'):
+        if url.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url, aws_access_key_id='alternator', aws_secret_access_key='wrong_key').describe_endpoints()
+        else:
+            verify = not url.startswith('https')
+            boto3.client('dynamodb',endpoint_url=url, region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='wrong_key', verify=verify).describe_endpoints()
+
+# A test ensuring that expired signatures are not accepted
+def test_expired_signature(dynamodb, test_table):
+    url = dynamodb.meta.client._endpoint.host
+    print(url)
+    headers = {'Content-Type': 'application/x-amz-json-1.0',
+               'X-Amz-Date': '20170101T010101Z',
+               'X-Amz-Target': 'DynamoDB_20120810.DescribeEndpoints',
+               'Authorization': 'AWS4-HMAC-SHA256 Credential=alternator/2/3/4/aws4_request SignedHeaders=x-amz-date;host Signature=123'
+    }
+    response = requests.post(url, headers=headers)
+    assert not response.ok
+    assert "InvalidSignatureException" in response.text and "Signature expired" in response.text
+
+# A test ensuring that signatures that exceed current time too much are not accepted.
+# Watch out - this test is valid only for around next 1000 years, it needs to be updated later.
+def test_signature_too_futuristic(dynamodb, test_table):
+    url = dynamodb.meta.client._endpoint.host
+    print(url)
+    headers = {'Content-Type': 'application/x-amz-json-1.0',
+               'X-Amz-Date': '30200101T010101Z',
+               'X-Amz-Target': 'DynamoDB_20120810.DescribeEndpoints',
+               'Authorization': 'AWS4-HMAC-SHA256 Credential=alternator/2/3/4/aws4_request SignedHeaders=x-amz-date;host Signature=123'
+    }
+    response = requests.post(url, headers=headers)
+    assert not response.ok
+    assert "InvalidSignatureException" in response.text and "Signature not yet current" in response.text

alternator-test/test_batch.py

@@ -0,0 +1,253 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for batch operations - BatchWriteItem, BatchReadItem.
+# Note that various other tests in other files also use these operations,
+# so they are actually tested by other tests as well.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string, full_scan, full_query, multiset
+
+# Test ensuring that items inserted by a batched statement can be properly extracted
+# via GetItem. Schema has both hash and sort keys.
+def test_basic_batch_write_item(test_table):
+    count = 7
+
+    with test_table.batch_writer() as batch:
+        for i in range(count):
+            batch.put_item(Item={
+                'p': "batch{}".format(i),
+                'c': "batch_ck{}".format(i),
+                'attribute': str(i),
+                'another': 'xyz'
+            })
+
+    for i in range(count):
+        item = test_table.get_item(Key={'p': "batch{}".format(i), 'c': "batch_ck{}".format(i)}, ConsistentRead=True)['Item']
+        assert item['p'] == "batch{}".format(i)
+        assert item['c'] == "batch_ck{}".format(i)
+        assert item['attribute'] == str(i)
+        assert item['another'] == 'xyz' 
+
+# Test batch write to a table with only a hash key
+def test_batch_write_hash_only(test_table_s):
+    items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for item in items:
+        assert test_table_s.get_item(Key={'p': item['p']}, ConsistentRead=True)['Item'] == item
+
+# Test batch delete operation (DeleteRequest): We create a bunch of items, and
+# then delete them all.
+def test_batch_write_delete(test_table_s):
+    items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for item in items:
+        assert test_table_s.get_item(Key={'p': item['p']}, ConsistentRead=True)['Item'] == item
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.delete_item(Key={'p': item['p']})
+    # Verify that all items are now missing:
+    for item in items:
+        assert not 'Item' in test_table_s.get_item(Key={'p': item['p']}, ConsistentRead=True)
+
+# Test the same batch including both writes and delete. Should be fine.
+def test_batch_write_and_delete(test_table_s):
+    p1 = random_string()
+    p2 = random_string()
+    test_table_s.put_item(Item={'p': p1})
+    assert 'Item' in test_table_s.get_item(Key={'p': p1}, ConsistentRead=True)
+    assert not 'Item' in test_table_s.get_item(Key={'p': p2}, ConsistentRead=True)
+    with test_table_s.batch_writer() as batch:
+        batch.put_item({'p': p2})
+        batch.delete_item(Key={'p': p1})
+    assert not 'Item' in test_table_s.get_item(Key={'p': p1}, ConsistentRead=True)
+    assert 'Item' in test_table_s.get_item(Key={'p': p2}, ConsistentRead=True)
+
+# It is forbidden to update the same key twice in the same batch.
+# DynamoDB says "Provided list of item keys contains duplicates".
+def test_batch_write_duplicate_write(test_table_s, test_table):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table_s.batch_writer() as batch:
+            batch.put_item({'p': p})
+            batch.put_item({'p': p})
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table.batch_writer() as batch:
+            batch.put_item({'p': p, 'c': c})
+            batch.put_item({'p': p, 'c': c})
+    # But it is fine to touch items with one component the same, but the other not.
+    other = random_string()
+    with test_table.batch_writer() as batch:
+        batch.put_item({'p': p, 'c': c})
+        batch.put_item({'p': p, 'c': other})
+        batch.put_item({'p': other, 'c': c})
+
+def test_batch_write_duplicate_delete(test_table_s, test_table):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table_s.batch_writer() as batch:
+            batch.delete_item(Key={'p': p})
+            batch.delete_item(Key={'p': p})
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table.batch_writer() as batch:
+            batch.delete_item(Key={'p': p, 'c': c})
+            batch.delete_item(Key={'p': p, 'c': c})
+    # But it is fine to touch items with one component the same, but the other not.
+    other = random_string()
+    with test_table.batch_writer() as batch:
+        batch.delete_item(Key={'p': p, 'c': c})
+        batch.delete_item(Key={'p': p, 'c': other})
+        batch.delete_item(Key={'p': other, 'c': c})
+
+def test_batch_write_duplicate_write_and_delete(test_table_s, test_table):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table_s.batch_writer() as batch:
+            batch.delete_item(Key={'p': p})
+            batch.put_item({'p': p})
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table.batch_writer() as batch:
+            batch.delete_item(Key={'p': p, 'c': c})
+            batch.put_item({'p': p, 'c': c})
+    # But it is fine to touch items with one component the same, but the other not.
+    other = random_string()
+    with test_table.batch_writer() as batch:
+        batch.delete_item(Key={'p': p, 'c': c})
+        batch.put_item({'p': p, 'c': other})
+        batch.put_item({'p': other, 'c': c})
+
+# Test that BatchWriteItem's PutRequest completely replaces an existing item.
+# It shouldn't merge it with a previously existing value. See also the same
+# test for PutItem - test_put_item_replace().
+def test_batch_put_item_replace(test_table_s, test_table):
+    p = random_string()
+    with test_table_s.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'a': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hi'}
+    with test_table_s.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'b': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
+    c = random_string()
+    with test_table.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'c': c, 'a': 'hi'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 'hi'}
+    with test_table.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'c': c, 'b': 'hello'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'b': 'hello'}
+
+# Test that if one of the batch's operations is invalid, because a key
+# column is missing or has the wrong type, the entire batch is rejected
+# before any write is done.
+def test_batch_write_invalid_operation(test_table_s):
+    # test key attribute with wrong type:
+    p1 = random_string()
+    p2 = random_string()
+    items = [{'p': p1}, {'p': 3}, {'p': p2}]
+    with pytest.raises(ClientError, match='ValidationException'):
+        with test_table_s.batch_writer() as batch:
+            for item in items:
+                batch.put_item(item)
+    for p in [p1, p2]:
+        assert not 'item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+    # test missing key attribute:
+    p1 = random_string()
+    p2 = random_string()
+    items = [{'p': p1}, {'x': 'whatever'}, {'p': p2}]
+    with pytest.raises(ClientError, match='ValidationException'):
+        with test_table_s.batch_writer() as batch:
+            for item in items:
+                batch.put_item(item)
+    for p in [p1, p2]:
+        assert not 'item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+
+# Basic test for BatchGetItem, reading several entire items.
+# Schema has both hash and sort keys.
+def test_batch_get_item(test_table):
+    items = [{'p': random_string(), 'c': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p', 'c')} for x in items]
+    # We use the low-level batch_get_item API for lack of a more convenient
+    # API. At least it spares us the need to encode the key's types...
+    reply = test_table.meta.client.batch_get_item(RequestItems = {test_table.name: {'Keys': keys, 'ConsistentRead': True}})
+    print(reply)
+    got_items = reply['Responses'][test_table.name]
+    assert multiset(got_items) == multiset(items)
+
+# Same, with schema has just hash key.
+def test_batch_get_item_hash(test_table_s):
+    items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p')} for x in items]
+    reply = test_table_s.meta.client.batch_get_item(RequestItems = {test_table_s.name: {'Keys': keys, 'ConsistentRead': True}})
+    got_items = reply['Responses'][test_table_s.name]
+    assert multiset(got_items) == multiset(items)
+
+# Test what do we get if we try to read two *missing* values in addition to
+# an existing one. It turns out the missing items are simply not returned,
+# with no sign they are missing.
+def test_batch_get_item_missing(test_table_s):
+    p = random_string();
+    test_table_s.put_item(Item={'p': p})
+    reply = test_table_s.meta.client.batch_get_item(RequestItems = {test_table_s.name: {'Keys': [{'p': random_string()}, {'p': random_string()}, {'p': p}], 'ConsistentRead': True}})
+    got_items = reply['Responses'][test_table_s.name]
+    assert got_items == [{'p' : p}]
+
+# If all the keys requested from a particular table are missing, we still
+# get a response array for that table - it's just empty.
+def test_batch_get_item_completely_missing(test_table_s):
+    reply = test_table_s.meta.client.batch_get_item(RequestItems = {test_table_s.name: {'Keys': [{'p': random_string()}], 'ConsistentRead': True}})
+    got_items = reply['Responses'][test_table_s.name]
+    assert got_items == []
+
+# Test GetItem with AttributesToGet
+def test_batch_get_item_attributes_to_get(test_table):
+    items = [{'p': random_string(), 'c': random_string(), 'val1': random_string(), 'val2': random_string()} for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p', 'c')} for x in items]
+    for wanted in [['p'], ['p', 'c'], ['val1'], ['p', 'val2']]:
+        reply = test_table.meta.client.batch_get_item(RequestItems = {test_table.name: {'Keys': keys, 'AttributesToGet': wanted, 'ConsistentRead': True}})
+        got_items = reply['Responses'][test_table.name]
+        expected_items = [{k: item[k] for k in wanted if k in item} for item in items]
+        assert multiset(got_items) == multiset(expected_items)
+
+# Test GetItem with ProjectionExpression (just a simple one, with
+# top-level attributes)
+def test_batch_get_item_projection_expression(test_table):
+    items = [{'p': random_string(), 'c': random_string(), 'val1': random_string(), 'val2': random_string()} for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p', 'c')} for x in items]
+    for wanted in [['p'], ['p', 'c'], ['val1'], ['p', 'val2']]:
+        reply = test_table.meta.client.batch_get_item(RequestItems = {test_table.name: {'Keys': keys, 'ProjectionExpression': ",".join(wanted), 'ConsistentRead': True}})
+        got_items = reply['Responses'][test_table.name]
+        expected_items = [{k: item[k] for k in wanted if k in item} for item in items]
+        assert multiset(got_items) == multiset(expected_items)

alternator-test/test_condition_expression.py

@@ -0,0 +1,40 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the ConditionExpression parameter
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string
+
+# Test that ConditionExpression works as expected
+@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
+def test_update_condition_expression(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1',
+        ExpressionAttributeValues={':val1': 4})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1',
+        ConditionExpression='b = :oldval',
+        ExpressionAttributeValues={':val1': 6, ':oldval': 4})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException.*'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1',
+            ConditionExpression='b = :oldval',
+            ExpressionAttributeValues={':val1': 8, ':oldval': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 6}

alternator-test/test_describe_endpoints.py

@@ -0,0 +1,49 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Test for the DescribeEndpoints operation
+
+import boto3
+
+# Test that the DescribeEndpoints operation works as expected: that it
+# returns one endpoint (it may return more, but it never does this in
+# Amazon), and this endpoint can be used to make more requests.
+def test_describe_endpoints(request, dynamodb):
+    endpoints = dynamodb.meta.client.describe_endpoints()['Endpoints']
+    # It is not strictly necessary that only a single endpoint be returned,
+    # but this is what Amazon DynamoDB does today (and so does Alternator).
+    assert len(endpoints) == 1
+    for endpoint in endpoints:
+        assert 'CachePeriodInMinutes' in endpoint.keys()
+        address = endpoint['Address']
+        # Check that the address is a valid endpoint by checking that we can
+        # send it another describe_endpoints() request ;-) Note that the
+        # address does not include the "http://" or "https://" prefix, and
+        # we need to choose one manually.
+        prefix = "https://" if request.config.getoption('https') else "http://"
+        verify = not request.config.getoption('https')
+        url = prefix + address
+        if address.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url, verify=verify).describe_endpoints()
+        else:
+            # Even though we connect to the local installation, Boto3 still
+            # requires us to specify dummy region and credential parameters,
+            # otherwise the user is forced to properly configure ~/.aws even
+            # for local runs.
+            boto3.client('dynamodb',endpoint_url=url, region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass', verify=verify).describe_endpoints()
+        # Nothing to check here - if the above call failed with an exception,
+        # the test would fail.

alternator-test/test_describe_table.py

@@ -0,0 +1,170 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the DescribeTable operation.
+# Some attributes used only by a specific major feature will be tested
+# elsewhere:
+#  1. Tests for describing tables with global or local secondary indexes
+#     (the GlobalSecondaryIndexes and LocalSecondaryIndexes attributes)
+#     are in test_gsi.py and test_lsi.py.
+#  2. Tests for the stream feature (LatestStreamArn, LatestStreamLabel,
+#     StreamSpecification) will be in the tests devoted to the stream
+#     feature.
+#  3. Tests for describing a restored table (RestoreSummary, TableId)
+#     will be together with tests devoted to the backup/restore feature.
+
+import pytest
+from botocore.exceptions import ClientError
+import re
+import time
+from util import multiset
+
+# Test that DescribeTable correctly returns the table's name and state
+def test_describe_table_basic(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert got['TableName'] == test_table.name
+    assert got['TableStatus'] == 'ACTIVE'
+
+# Test that DescribeTable correctly returns the table's schema, in
+# AttributeDefinitions and KeySchema attributes
+@pytest.mark.xfail(reason="DescribeTable does not yet return schema")
+def test_describe_table_schema(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    expected = { # Copied from test_table()'s fixture
+        'KeySchema': [ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        'AttributeDefinitions': [
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ]
+    }
+    assert got['KeySchema'] == expected['KeySchema']
+    # The list of attribute definitions may be arbitrarily reordered
+    assert multiset(got['AttributeDefinitions']) == multiset(expected['AttributeDefinitions'])
+
+# Test that DescribeTable correctly returns the table's billing mode,
+# in the BillingModeSummary attribute.
+def test_describe_table_billing(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert got['BillingModeSummary']['BillingMode'] == 'PAY_PER_REQUEST'
+    # The BillingModeSummary should also contain a
+    # LastUpdateToPayPerRequestDateTime attribute, which is a date.
+    # We don't know what date this is supposed to be, but something we
+    # do know is that the test table was created already with this billing
+    # mode, so the table creation date should be the same as the billing
+    # mode setting date.
+    assert 'LastUpdateToPayPerRequestDateTime' in got['BillingModeSummary']
+    assert got['BillingModeSummary']['LastUpdateToPayPerRequestDateTime'] == got['CreationDateTime']
+
+# Test that DescribeTable correctly returns the table's creation time.
+# We don't know what this creation time is supposed to be, so this test
+# cannot be very thorough... We currently just tests against something we
+# know to be wrong - returning the *current* time, which changes on every
+# call.
+@pytest.mark.xfail(reason="DescribeTable does not return table creation time")
+def test_describe_table_creation_time(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert 'CreationDateTime' in got
+    time1 = got['CreationDateTime']
+    time.sleep(1) 
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    time2 = got['CreationDateTime']
+    assert time1 == time2
+
+# Test that DescribeTable returns the table's estimated item count
+# in the ItemCount attribute. Unfortunately, there's not much we can
+# really test here... The documentation says that the count can be
+# delayed by six hours, so the number we get here may have no relation
+# to the current number of items in the test table. The attribute should exist,
+# though. This test does NOT verify that ItemCount isn't always returned as
+# zero - such stub implementation will pass this test.
+@pytest.mark.xfail(reason="DescribeTable does not return table item count")
+def test_describe_table_item_count(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert 'ItemCount' in got
+
+# Similar test for estimated size in bytes - TableSizeBytes - which again,
+# may reflect the size as long as six hours ago.
+@pytest.mark.xfail(reason="DescribeTable does not return table size")
+def test_describe_table_size(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert 'TableSizeBytes' in got
+
+# Test the ProvisionedThroughput attribute returned by DescribeTable.
+# This is a very partial test: Our test table is configured without
+# provisioned throughput, so obviously it will not have interesting settings
+# for it. DynamoDB returns zeros for some of the attributes, even though
+# the documentation suggests missing values should have been fine too.
+@pytest.mark.xfail(reason="DescribeTable does not return provisioned throughput")
+def test_describe_table_provisioned_throughput(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert got['ProvisionedThroughput']['NumberOfDecreasesToday'] == 0
+    assert got['ProvisionedThroughput']['WriteCapacityUnits'] == 0
+    assert got['ProvisionedThroughput']['ReadCapacityUnits'] == 0
+
+# This is a silly test for the RestoreSummary attribute in DescribeTable -
+# it should not exist in a table not created by a restore. When testing
+# the backup/restore feature, we will have more meaninful tests for the
+# value of this attribute in that case.
+def test_describe_table_restore_summary(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert not 'RestoreSummary' in got
+
+# This is a silly test for the SSEDescription attribute in DescribeTable -
+# by default, a table is encrypted with AWS-owned keys, not using client-
+# owned keys, and the SSEDescription attribute is not returned at all.
+def test_describe_table_encryption(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert not 'SSEDescription' in got
+
+# This is a silly test for the StreamSpecification attribute in DescribeTable -
+# when there are no streams, this attribute should be missing.
+def test_describe_table_stream_specification(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert not 'StreamSpecification' in got
+
+# Test that the table has an ARN, a unique identifier for the table which
+# includes which zone it is on, which account, and of course the table's
+# name. The ARN format is described in
+# https://docs.aws.amazon.com/general/latest/gr/aws-arns-and-namespaces.html#genref-arns
+@pytest.mark.xfail(reason="DescribeTable does not return ARN")
+def test_describe_table_arn(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert 'TableArn' in got and got['TableArn'].startswith('arn:')
+
+# Test that the table has a TableId.
+# TODO: Figure out what is this TableId supposed to be, it is just a
+# unique id that is created with the table and never changes? Or anything
+# else?
+@pytest.mark.xfail(reason="DescribeTable does not return TableId")
+def test_describe_table_id(test_table):
+    got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
+    assert 'TableId' in got
+
+# DescribeTable error path: trying to describe a non-existent table should
+# result in a ResourceNotFoundException.
+def test_describe_table_non_existent_table(dynamodb):
+    with pytest.raises(ClientError, match='ResourceNotFoundException') as einfo:
+        dynamodb.meta.client.describe_table(TableName='non_existent_table')
+    # As one of the first error-path tests that we wrote, let's test in more
+    # detail that the error reply has the appropriate fields:
+    response = einfo.value.response
+    print(response)
+    err = response['Error']
+    assert err['Code'] == 'ResourceNotFoundException'
+    assert re.match(err['Message'], 'Requested resource not found: Table: non_existent_table not found')

alternator-test/test_expected.py

@@ -1,6 +1,19 @@
-# Copyright 2019-present ScyllaDB
+# Copyright 2019 ScyllaDB
 #
-# SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 
 # Tests for the "Expected" parameter used to make certain operations (PutItem,
 # UpdateItem and DeleteItem) conditional on the existing attribute values.
@@ -9,7 +22,7 @@
 
 import pytest
 from botocore.exceptions import ClientError
-from test.alternator.util import random_string
+from util import random_string
 
 # Most of the tests in this file check that the "Expected" parameter works for
 # the UpdateItem operation. It should also work the same for the PutItem and
@@ -73,6 +86,7 @@ def test_update_expected_1_eq_true(test_table_s):
 # Check that set equality is checked correctly. Unlike string equality (for
 # example), it cannot be done with just naive string comparison of the JSON
 # representation, and we need to allow for any order.
+@pytest.mark.xfail(reason="bug in EQ test of sets")
 def test_update_expected_1_eq_set(test_table_s):
     p = random_string()
     # Because boto3 sorts the set values we give it, in order to generate a
@@ -157,6 +171,7 @@ def test_update_expected_1_ne_false(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "LE":
+@pytest.mark.xfail(reason="ComparisonOperator=LE in Expected not yet implemented")
 def test_update_expected_1_le(test_table_s):
     p = random_string()
     # LE should work for string, number, and binary type
@@ -224,30 +239,6 @@ def test_update_expected_1_le(test_table_s):
                             'AttributeValueList': [2, 3]}}
         )
 
-# Comparison operators like le work only on numbers, strings or bytes.
-# As noted in issue #8043, if any other type is included in *the query*,
-# the result should be a ValidationException, but if the wrong type appears
-# in the item, not the query, the result is a failed condition.
-def test_update_expected_1_le_validation(test_table_s):
-    p = random_string()
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
-                          'b': {'Value': [1,2], 'Action': 'PUT'}})
-    # Bad type (a list) in the query. Result is ValidationException.
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'a': {'ComparisonOperator': 'LE',
-                            'AttributeValueList': [[1,2,3]]}}
-        )
-    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'b': {'ComparisonOperator': 'LE',
-                            'AttributeValueList': [3]}}
-        )
-    assert not 'z' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']
-
 # Tests for Expected with ComparisonOperator = "LT":
 def test_update_expected_1_lt(test_table_s):
     p = random_string()
@@ -317,6 +308,7 @@ def test_update_expected_1_lt(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "GE":
+@pytest.mark.xfail(reason="ComparisonOperator=GE in Expected not yet implemented")
 def test_update_expected_1_ge(test_table_s):
     p = random_string()
     # GE should work for string, number, and binary type
@@ -533,16 +525,8 @@ def test_update_expected_1_null(test_table_s):
             Expected={'a': {'ComparisonOperator': 'NULL', 'AttributeValueList': [2]}}
         )
 
-# When ComparisonOperator = "NULL", AttributeValueList should be empty if it
-# exists, but as this test verifies, it may also be missing completely.
-def test_update_expected_1_null_missing_list(test_table_s):
-    p = random_string()
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 2, 'Action': 'PUT'}},
-        Expected={'a': {'ComparisonOperator': 'NULL'}})
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
-
 # Tests for Expected with ComparisonOperator = "CONTAINS":
+@pytest.mark.xfail(reason="ComparisonOperator=CONTAINS in Expected not yet implemented")
 def test_update_expected_1_contains(test_table_s):
     # true cases. CONTAINS can be used for two unrelated things: check substrings
     # (in string or binary) and membership (in set or list).
@@ -618,10 +602,6 @@ def test_update_expected_1_contains(test_table_s):
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'CONTAINS', 'AttributeValueList': []}}
         )
-    # Strangely, while ConditionExpression's contains() allows the argument
-    # to be of any type and checks if the attribute is perhaps a list
-    # containing that item, Expected's "CONTAINS" is more limited, and
-    # refuses a list as the argument (to be searched in a list of lists)
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
@@ -629,6 +609,7 @@ def test_update_expected_1_contains(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "NOT_CONTAINS":
+@pytest.mark.xfail(reason="ComparisonOperator=NOT_CONTAINS in Expected not yet implemented")
 def test_update_expected_1_not_contains(test_table_s):
     # true cases. NOT_CONTAINS can be used for two unrelated things: check substrings
     # (in string or binary) and membership (in set or list).
@@ -708,10 +689,6 @@ def test_update_expected_1_not_contains(test_table_s):
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'NOT_CONTAINS', 'AttributeValueList': []}}
         )
-    # Strangely, while ConditionExpression's contains() allows the argument
-    # to be of any type and checks if the attribute is perhaps a list
-    # containing that item, Expected's "CONTAINS" is more limited, and
-    # refuses a list as the argument (to be searched in a list of lists)
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
@@ -722,21 +699,14 @@ def test_update_expected_1_not_contains(test_table_s):
 def test_update_expected_1_begins_with_true(test_table_s):
     p = random_string()
     test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'},
-                          'd': {'Value': bytearray('hi there', 'utf-8'), 'Action': 'PUT'}})
+        AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'}})
     # Case where expected and update are on different attribute:
     test_table_s.update_item(Key={'p': p},
         AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
         Expected={'a': {'ComparisonOperator': 'BEGINS_WITH',
                         'AttributeValueList': ['hell']}}
     )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 3
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'b': {'Value': 4, 'Action': 'PUT'}},
-        Expected={'d': {'ComparisonOperator': 'BEGINS_WITH',
-                        'AttributeValueList': [bytearray('hi', 'utf-8')]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 4
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 3}
     # For BEGINS_WITH, AttributeValueList must have a single element
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
@@ -828,13 +798,13 @@ def test_update_expected_1_in(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "BETWEEN":
+@pytest.mark.xfail(reason="ComparisonOperator=BETWEEN in Expected not yet implemented")
 def test_update_expected_1_between(test_table_s):
     p = random_string()
     test_table_s.update_item(Key={'p': p},
         AttributeUpdates={'a': {'Value': 2, 'Action': 'PUT'},
                           'b': {'Value': 'cat', 'Action': 'PUT'},
-                          'c': {'Value': bytearray('cat', 'utf-8'), 'Action': 'PUT'},
-                          'd': {'Value': set([2, 4, 7]), 'Action': 'PUT'}})
+                          'c': {'Value': bytearray('cat', 'utf-8'), 'Action': 'PUT'}})
     # true cases:
     test_table_s.update_item(Key={'p': p},
         AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
@@ -872,10 +842,6 @@ def test_update_expected_1_between(test_table_s):
             AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': ['cat', 'dog']}}
         )
-    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-            Expected={'q': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [0, 100]}})
     assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 6
     # The given AttributeValueList array must contain exactly two items of the
     # same type, and in the right order. Any other input is considered a validation
@@ -892,46 +858,10 @@ def test_update_expected_1_between(test_table_s):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [4, 3]}})
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-            Expected={'b': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': ['dog', 'aardvark']}})
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [4, 'dog']}})
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-            Expected={'d': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [set([1]), set([2])]}})
-
-# BETWEEN work only on numbers, strings or bytes. As noted in issue #8043,
-# if any other type is included in *the query*, the result should be a
-# ValidationException, but if the wrong type appears in the item, not the
-# query, the result is a failed condition.
-# BETWEEN should also generate ValidationException if the two ends of the
-# range are not of the same type or not in the correct order, but this
-# already is tested in the test above (test_update_expected_1_between).
-def test_update_expected_1_between_validation(test_table_s):
-    p = random_string()
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
-                          'b': {'Value': [1,2], 'Action': 'PUT'}})
-    # Bad type (a list) in the query. Result is ValidationException.
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'a': {'ComparisonOperator': 'BETWEEN',
-                            'AttributeValueList': [[1,2,3], [2,3,4]]}}
-        )
-    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'b': {'ComparisonOperator': 'BETWEEN',
-                            'AttributeValueList': [1,2]}}
-        )
-    assert not 'z' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']
-
 
 ##############################################################################
 # Instead of ComparisonOperator and AttributeValueList, one can specify either
@@ -1108,19 +1038,6 @@ def test_update_expected_empty(test_table_s):
             AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
             Expected={}, ConditionalOperator='AND')
 
-# Specifying ConditionalOperator is forbidden if the "Expected" Attribute
-# is missing:
-def test_conditional_operator_expected_missing(test_table_s):
-    p = random_string()
-    with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
-            ConditionalOperator='OR')
-    with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
-            ConditionalOperator='AND')
-
 # All of the above tests tested "Expected" with the UpdateItem operation.
 # We now want to test that it works also with the PutItem and DeleteItems
 # operations. We don't need to check again all the different sub-cases tested
@@ -1146,42 +1063,3 @@ def test_put_item_expected(test_table_s):
     assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 2}
     with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
         test_table_s.put_item(Item={'p': p, 'a': 3}, Expected={'a': {'Value': 1}})
-
-# Reproducer for issue #6573: binary strings should be ordered as unsigned
-# bytes, i.e., byte 128 comes after 127, not before as with signed bytes.
-# Test the five ordering operators: LT, LE, GT, GE, BETWEEN
-def test_update_expected_unsigned_bytes(test_table_s):
-    p = random_string()
-    test_table_s.put_item(Item={'p': p, 'b': bytearray([127])})
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 1, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'LT',
-                        'AttributeValueList': [bytearray([128])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 1
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'LE',
-                        'AttributeValueList': [bytearray([128])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 2
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 3, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'BETWEEN',
-                        'AttributeValueList': [bytearray([126]), bytearray([128])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 3
-
-    test_table_s.put_item(Item={'p': p, 'b': bytearray([128])})
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'GT',
-                        'AttributeValueList': [bytearray([127])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 4
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 5, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'GE',
-                        'AttributeValueList': [bytearray([127])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 5

alternator-test/test_gsi.py

@@ -0,0 +1,801 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests of GSI (Global Secondary Indexes)
+#
+# Note that many of these tests are slower than usual, because many of them
+# need to create new tables and/or new GSIs of different types, operations
+# which are extremely slow in DynamoDB, often taking minutes (!).
+
+import pytest
+import time
+from botocore.exceptions import ClientError, ParamValidationError
+from util import create_test_table, random_string, full_scan, full_query, multiset, list_tables
+
+# GSIs only support eventually consistent reads, so tests that involve
+# writing to a table and then expect to read something from it cannot be
+# guaranteed to succeed without retrying the read. The following utility
+# functions make it easy to write such tests.
+# Note that in practice, there repeated reads are almost never necessary:
+# Amazon claims that "Changes to the table data are propagated to the global
+# secondary indexes within a fraction of a second, under normal conditions"
+# and indeed, in practice, the tests here almost always succeed without a
+# retry.
+def assert_index_query(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_query retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
+
+def assert_index_scan(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_scan retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
+
+# Although quite silly, it is actually allowed to create an index which is
+# identical to the base table.
+def test_gsi_identical(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
+        AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    items = [{'p': random_string(), 'x': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert multiset(items) == multiset(full_scan(table))
+    assert_index_scan(table, 'hello', items)
+    # We can't scan a non-existant index
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_scan(table, IndexName='wrong')
+    table.delete()
+
+# One of the simplest forms of a non-trivial GSI: The base table has a hash
+# and sort key, and the index reverses those roles. Other attributes are just
+# copied.
+@pytest.fixture(scope="session")
+def test_table_gsi_1(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ],
+        )
+    yield table
+    table.delete()
+
+def test_gsi_simple(test_table_gsi_1):
+    items = [{'p': random_string(), 'c': random_string(), 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    c = items[0]['c']
+    # The index allows a query on just a specific sort key, which isn't
+    # allowed on the base table.
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table_gsi_1, KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    expected_items = [x for x in items if x['c'] == c]
+    assert_index_query(test_table_gsi_1, 'hello', expected_items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert_index_scan(test_table_gsi_1, 'hello', full_scan(test_table_gsi_1))
+
+def test_gsi_same_key(test_table_gsi_1):
+    c = random_string();
+    # All these items have the same sort key 'c' but different hash key 'p'
+    items = [{'p': random_string(), 'c': c, 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_1, 'hello', items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+
+# Check we get an appropriate error when trying to read a non-existing index
+# of an existing table. Although the documentation specifies that a
+# ResourceNotFoundException should be returned if "The operation tried to
+# access a nonexistent table or index", in fact in the specific case that
+# the table does exist but an index does not - we get a ValidationException.
+def test_gsi_missing_index(test_table_gsi_1):
+    with pytest.raises(ClientError, match='ValidationException.*wrong_name'):
+        full_query(test_table_gsi_1, IndexName='wrong_name',
+            KeyConditions={'x': {'AttributeValueList': [1], 'ComparisonOperator': 'EQ'}})
+    with pytest.raises(ClientError, match='ValidationException.*wrong_name'):
+        full_scan(test_table_gsi_1, IndexName='wrong_name')
+
+# Nevertheless, if the table itself does not exist, a query should return
+# a ResourceNotFoundException, not ValidationException:
+def test_gsi_missing_table(dynamodb):
+    with pytest.raises(ClientError, match='ResourceNotFoundException'):
+        dynamodb.meta.client.query(TableName='nonexistent_table', IndexName='any_name', KeyConditions={'x': {'AttributeValueList': [1], 'ComparisonOperator': 'EQ'}})
+    with pytest.raises(ClientError, match='ResourceNotFoundException'):
+        dynamodb.meta.client.scan(TableName='nonexistent_table', IndexName='any_name')
+
+# Verify that strongly-consistent reads on GSI are *not* allowed.
+@pytest.mark.xfail(reason="GSI strong consistency not checked")
+def test_gsi_strong_consistency(test_table_gsi_1):
+    with pytest.raises(ClientError, match='ValidationException.*Consistent'):
+        full_query(test_table_gsi_1, KeyConditions={'c': {'AttributeValueList': ['hi'], 'ComparisonOperator': 'EQ'}}, IndexName='hello', ConsistentRead=True)
+    with pytest.raises(ClientError, match='ValidationException.*Consistent'):
+        full_scan(test_table_gsi_1, IndexName='hello', ConsistentRead=True)
+
+# Verify that a GSI is correctly listed in describe_table
+@pytest.mark.xfail(reason="DescribeTable provides index names only, no size or item count")
+def test_gsi_describe(test_table_gsi_1):
+    desc = test_table_gsi_1.meta.client.describe_table(TableName=test_table_gsi_1.name)
+    assert 'Table' in desc
+    assert 'GlobalSecondaryIndexes' in desc['Table']
+    gsis = desc['Table']['GlobalSecondaryIndexes']
+    assert len(gsis) == 1
+    gsi = gsis[0]
+    assert gsi['IndexName'] == 'hello'
+    assert 'IndexSizeBytes' in gsi     # actual size depends on content
+    assert 'ItemCount' in gsi
+    assert gsi['Projection'] == {'ProjectionType': 'ALL'}
+    assert gsi['IndexStatus'] == 'ACTIVE'
+    assert gsi['KeySchema'] == [{'KeyType': 'HASH', 'AttributeName': 'c'},
+                                {'KeyType': 'RANGE', 'AttributeName': 'p'}]
+    # TODO: check also ProvisionedThroughput, IndexArn
+
+# When a GSI's key includes an attribute not in the base table's key, we
+# need to remember to add its type to AttributeDefinitions.
+def test_gsi_missing_attribute_definition(dynamodb):
+    with pytest.raises(ClientError, match='ValidationException.*AttributeDefinitions'):
+        create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ],
+            GlobalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [ { 'AttributeName': 'c', 'KeyType': 'HASH' } ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+
+# test_table_gsi_1_hash_only is a variant of test_table_gsi_1: It's another
+# case where the index doesn't involve non-key attributes. Again the base
+# table has a hash and sort key, but in this case the index has *only* a
+# hash key (which is the base's hash key). In the materialized-view-based
+# implementation, we need to remember the other part of the base key as a
+# clustering key.
+@pytest.fixture(scope="session")
+def test_table_gsi_1_hash_only(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ],
+        )
+    yield table
+    table.delete()
+
+def test_gsi_key_not_in_index(test_table_gsi_1_hash_only):
+    # Test with items with different 'c' values:
+    items = [{'p': random_string(), 'c': random_string(), 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1_hash_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    c = items[0]['c']
+    expected_items = [x for x in items if x['c'] == c]
+    assert_index_query(test_table_gsi_1_hash_only, 'hello', expected_items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    # Test items with the same sort key 'c' but different hash key 'p'
+    c = random_string();
+    items = [{'p': random_string(), 'c': c, 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1_hash_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_1_hash_only, 'hello', items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert_index_scan(test_table_gsi_1_hash_only, 'hello', full_scan(test_table_gsi_1_hash_only))
+
+
+# A second scenario of GSI. Base table has just hash key, Index has a
+# different hash key - one of the non-key attributes from the base table.
+@pytest.fixture(scope="session")
+def test_table_gsi_2(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_gsi_2(test_table_gsi_2):
+    items1 = [{'p': random_string(), 'x': random_string()} for i in range(10)]
+    x1 = items1[0]['x']
+    x2 = random_string()
+    items2 = [{'p': random_string(), 'x': x2} for i in range(10)]
+    items = items1 + items2
+    with test_table_gsi_2.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['x'] == x1]
+    assert_index_query(test_table_gsi_2, 'hello', expected_items,
+        KeyConditions={'x': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
+    expected_items = [i for i in items if i['x'] == x2]
+    assert_index_query(test_table_gsi_2, 'hello', expected_items,
+        KeyConditions={'x': {'AttributeValueList': [x2], 'ComparisonOperator': 'EQ'}})
+
+# Test that when a table has a GSI, if the indexed attribute is missing, the
+# item is added to the base table but not the index.
+def test_gsi_missing_attribute(test_table_gsi_2):
+    p1 = random_string()
+    x1 = random_string()
+    test_table_gsi_2.put_item(Item={'p':  p1, 'x': x1})
+    p2 = random_string()
+    test_table_gsi_2.put_item(Item={'p':  p2})
+
+    # Both items are now in the base table:
+    assert test_table_gsi_2.get_item(Key={'p':  p1})['Item'] == {'p': p1, 'x': x1}
+    assert test_table_gsi_2.get_item(Key={'p':  p2})['Item'] == {'p': p2}
+
+    # But only the first item is in the index: It can be found using a
+    # Query, and a scan of the index won't find it (but a scan on the base
+    # will).
+    assert_index_query(test_table_gsi_2, 'hello', [{'p': p1, 'x': x1}],
+        KeyConditions={'x': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
+    assert any([i['p'] == p1 for i in full_scan(test_table_gsi_2)])
+    # Note: with eventually consistent read, we can't really be sure that
+    # and item will "never" appear in the index. We do this test last,
+    # so if we had a bug and such item did appear, hopefully we had enough
+    # time for the bug to become visible. At least sometimes.
+    assert not any([i['p'] == p2 for i in full_scan(test_table_gsi_2, IndexName='hello')])
+
+# Test when a table has a GSI, if the indexed attribute has the wrong type,
+# the update operation is rejected, and is added to neither base table nor
+# index. This is different from the case of a *missing* attribute, where
+# the item is added to the base table but not index.
+# The following three tests test_gsi_wrong_type_attribute_{put,update,batch}
+# test updates using PutItem, UpdateItem, and BatchWriteItem respectively.
+def test_gsi_wrong_type_attribute_put(test_table_gsi_2):
+    # PutItem with wrong type for 'x' is rejected, item isn't created even
+    # in the base table.
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*mismatch'):
+        test_table_gsi_2.put_item(Item={'p':  p, 'x': 3})
+    assert not 'Item' in test_table_gsi_2.get_item(Key={'p': p}, ConsistentRead=True)
+
+def test_gsi_wrong_type_attribute_update(test_table_gsi_2):
+    # An UpdateItem with wrong type for 'x' is also rejected, but naturally
+    # if the item already existed, it remains as it was.
+    p = random_string()
+    x = random_string()
+    test_table_gsi_2.put_item(Item={'p':  p, 'x': x})
+    with pytest.raises(ClientError, match='ValidationException.*mismatch'):
+        test_table_gsi_2.update_item(Key={'p':  p}, AttributeUpdates={'x': {'Value': 3, 'Action': 'PUT'}})
+    assert test_table_gsi_2.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'x': x}
+
+def test_gsi_wrong_type_attribute_batch(test_table_gsi_2):
+    # In a BatchWriteItem, if any update is forbidden, the entire batch is
+    # rejected, and none of the updates happen at all.
+    p1 = random_string()
+    p2 = random_string()
+    p3 = random_string()
+    items = [{'p': p1, 'x': random_string()},
+             {'p': p2, 'x': 3},
+             {'p': p3, 'x': random_string()}]
+    with pytest.raises(ClientError, match='ValidationException.*mismatch'):
+        with test_table_gsi_2.batch_writer() as batch:
+            for item in items:
+                batch.put_item(item)
+    for p in [p1, p2, p3]:
+        assert not 'Item' in test_table_gsi_2.get_item(Key={'p': p}, ConsistentRead=True)
+
+# A third scenario of GSI. Index has a hash key and a sort key, both are
+# non-key attributes from the base table. This scenario may be very
+# difficult to implement in Alternator because Scylla's materialized-views
+# implementation only allows one new key column in the view, and here
+# we need two (which, also, aren't actual columns, but map items).
+@pytest.fixture(scope="session")
+def test_table_gsi_3(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'a', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' }
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'a', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'b', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_gsi_3(test_table_gsi_3):
+    items = [{'p': random_string(), 'a': random_string(), 'b': random_string()} for i in range(10)]
+    with test_table_gsi_3.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_3, 'hello', [items[3]],
+        KeyConditions={'a': {'AttributeValueList': [items[3]['a']], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [items[3]['b']], 'ComparisonOperator': 'EQ'}})
+
+@pytest.mark.xfail(reason="GSI in alternator currently have a bug on updating the second regular base column")
+def test_gsi_update_second_regular_base_column(test_table_gsi_3):
+    items = [{'p': random_string(), 'a': random_string(), 'b': random_string(), 'd': random_string()} for i in range(10)]
+    with test_table_gsi_3.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    items[3]['b'] = 'updated'
+    test_table_gsi_3.update_item(Key={'p':  items[3]['p']}, AttributeUpdates={'b': {'Value': 'updated', 'Action': 'PUT'}})
+    assert_index_query(test_table_gsi_3, 'hello', [items[3]],
+        KeyConditions={'a': {'AttributeValueList': [items[3]['a']], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [items[3]['b']], 'ComparisonOperator': 'EQ'}})
+
+
+# A fourth scenario of GSI. Two GSIs on a single base table.
+@pytest.fixture(scope="session")
+def test_table_gsi_4(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'a', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' }
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello_a',
+                'KeySchema': [
+                    { 'AttributeName': 'a', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            },
+            {   'IndexName': 'hello_b',
+                'KeySchema': [
+                    { 'AttributeName': 'b', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+# Test that a base table with two GSIs updates both as expected.
+def test_gsi_4(test_table_gsi_4):
+    items = [{'p': random_string(), 'a': random_string(), 'b': random_string()} for i in range(10)]
+    with test_table_gsi_4.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_4, 'hello_a', [items[3]],
+        KeyConditions={'a': {'AttributeValueList': [items[3]['a']], 'ComparisonOperator': 'EQ'}})
+    assert_index_query(test_table_gsi_4, 'hello_b', [items[3]],
+        KeyConditions={'b': {'AttributeValueList': [items[3]['b']], 'ComparisonOperator': 'EQ'}})
+
+# Verify that describe_table lists the two GSIs.
+def test_gsi_4_describe(test_table_gsi_4):
+    desc = test_table_gsi_4.meta.client.describe_table(TableName=test_table_gsi_4.name)
+    assert 'Table' in desc
+    assert 'GlobalSecondaryIndexes' in desc['Table']
+    gsis = desc['Table']['GlobalSecondaryIndexes']
+    assert len(gsis) == 2
+    assert multiset([g['IndexName'] for g in gsis]) == multiset(['hello_a', 'hello_b'])
+
+# A scenario for GSI in which the table has both hash and sort key
+@pytest.fixture(scope="session")
+def test_table_gsi_5(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'x', 'KeyType': 'RANGE' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_gsi_5(test_table_gsi_5):
+    items1 = [{'p': random_string(), 'c': random_string(), 'x': random_string()} for i in range(10)]
+    p1, x1 = items1[0]['p'], items1[0]['x']
+    p2, x2 = random_string(), random_string()
+    items2 = [{'p': p2, 'c': random_string(), 'x': x2} for i in range(10)]
+    items = items1 + items2
+    with test_table_gsi_5.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['x'] == x1]
+    assert_index_query(test_table_gsi_5, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'x': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
+    expected_items = [i for i in items if i['p'] == p2 and i['x'] == x2]
+    assert_index_query(test_table_gsi_5, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'x': {'AttributeValueList': [x2], 'ComparisonOperator': 'EQ'}})
+
+# All tests above involved "ProjectionType: ALL". This test checks how
+# "ProjectionType:: KEYS_ONLY" works. We note that it projects both
+# the index's key, *and* the base table's key. So items which had different
+# base-table keys cannot suddenly become the same item in the index.
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_projection_keys_only(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ])
+    items = [{'p': random_string(), 'x': random_string(), 'y': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    wanted = ['p', 'x']
+    expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+    assert_index_scan(table, 'hello', expected_items)
+    table.delete()
+
+# Test for "ProjectionType:: INCLUDE". The secondary table includes the
+# its own and the base's keys (as in KEYS_ONLY) plus the extra keys given
+# in NonKeyAttributes.
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_projection_include(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'INCLUDE',
+                                'NonKeyAttributes': ['a', 'b'] }
+            }
+        ])
+    # Some items have the projected attributes a,b and some don't:
+    items = [{'p': random_string(), 'x': random_string(), 'a': random_string(), 'b': random_string(), 'y': random_string()} for i in range(10)]
+    items = items + [{'p': random_string(), 'x': random_string(), 'y': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    wanted = ['p', 'x', 'a', 'b']
+    expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+    assert_index_scan(table, 'hello', expected_items)
+    print(len(expected_items))
+    table.delete()
+
+# DynamoDB's says the "Projection" argument of GlobalSecondaryIndexes is
+# mandatory, and indeed Boto3 enforces that it must be passed. The
+# documentation then goes on to claim that the "ProjectionType" member of
+# "Projection" is optional - and Boto3 allows it to be missing. But in
+# fact, it is not allowed to be missing: DynamoDB complains: "Unknown
+# ProjectionType: null".
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_missing_projection_type(dynamodb):
+    with pytest.raises(ClientError, match='ValidationException.*ProjectionType'):
+        create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
+            AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }],
+            GlobalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+                    'Projection': {}
+                }
+            ])
+
+# update_table() for creating a GSI is an asynchronous operation.
+# The table's TableStatus changes from ACTIVE to UPDATING for a short while
+# and then goes back to ACTIVE, but the new GSI's IndexStatus appears as
+# CREATING, until eventually (after a *long* time...) it becomes ACTIVE.
+# During the CREATING phase, at some point the Backfilling attribute also
+# appears, until it eventually disappears. We need to wait until all three
+# markers indicate completion.
+# Unfortunately, while boto3 has a client.get_waiter('table_exists') to
+# wait for a table to exists, there is no such function to wait for an
+# index to come up, so we need to code it ourselves.
+def wait_for_gsi(table, gsi_name):
+    start_time = time.time()
+    # Surprisingly, even for tiny tables this can take a very long time
+    # on DynamoDB - often many minutes!
+    for i in range(300):
+        time.sleep(1)
+        desc = table.meta.client.describe_table(TableName=table.name)
+        table_status = desc['Table']['TableStatus']
+        if table_status != 'ACTIVE':
+            print('%d Table status still %s' % (i, table_status))
+            continue
+        index_desc = [x for x in desc['Table']['GlobalSecondaryIndexes'] if x['IndexName'] == gsi_name]
+        assert len(index_desc) == 1
+        index_status = index_desc[0]['IndexStatus']
+        if index_status != 'ACTIVE':
+            print('%d Index status still %s' % (i, index_status))
+            continue
+        # When the index is ACTIVE, this must be after backfilling completed
+        assert not 'Backfilling' in index_desc[0]
+        print('wait_for_gsi took %d seconds' % (time.time() - start_time))
+        return
+    raise AssertionError("wait_for_gsi did not complete")
+
+# Similarly to how wait_for_gsi() waits for a GSI to finish adding,
+# this function waits for a GSI to be finally deleted.
+def wait_for_gsi_gone(table, gsi_name):
+    start_time = time.time()
+    for i in range(300):
+        time.sleep(1)
+        desc = table.meta.client.describe_table(TableName=table.name)
+        table_status = desc['Table']['TableStatus']
+        if table_status != 'ACTIVE':
+            print('%d Table status still %s' % (i, table_status))
+            continue
+        if 'GlobalSecondaryIndexes' in desc['Table']:
+            index_desc = [x for x in desc['Table']['GlobalSecondaryIndexes'] if x['IndexName'] == gsi_name]
+            if len(index_desc) != 0:
+                index_status = index_desc[0]['IndexStatus']
+                print('%d Index status still %s' % (i, index_status))
+                continue
+        print('wait_for_gsi_gone took %d seconds' % (time.time() - start_time))
+        return
+    raise AssertionError("wait_for_gsi_gone did not complete")
+
+# All tests above involved creating a new table with a GSI up-front. This
+# test will test creating a base table *without* a GSI, putting data in
+# it, and then adding a GSI with the UpdateTable operation. This starts
+# a backfilling stage - where data is copied to the index - and when this
+# stage is done, the index is usable. Items whose indexed column contains
+# the wrong type are silently ignored and not added to the index (it would
+# not have been possible to add such items if the GSI was already configured
+# when they were added).
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_backfill(dynamodb):
+    # First create, and fill, a table without GSI. The items in items1
+    # will have the appropriate string type for 'x' and will later get
+    # indexed. Items in item2 have no value for 'x', and in item3 'x' is in
+    # not a string; So the items in items2 and items3 will be missing
+    # in the index we'll create later.
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ])
+    items1 = [{'p': random_string(), 'x': random_string(), 'y': random_string()} for i in range(10)]
+    items2 = [{'p': random_string(), 'y': random_string()} for i in range(10)]
+    items3 = [{'p': random_string(), 'x': i} for i in range(10)]
+    items = items1 + items2 + items3
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert multiset(items) == multiset(full_scan(table))
+    # Now use UpdateTable to create the GSI
+    dynamodb.meta.client.update_table(TableName=table.name,
+        AttributeDefinitions=[{ 'AttributeName': 'x', 'AttributeType': 'S' }],
+        GlobalSecondaryIndexUpdates=[ {  'Create':
+            {  'IndexName': 'hello',
+                'KeySchema': [{ 'AttributeName': 'x', 'KeyType': 'HASH' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }}])
+    # update_table is an asynchronous operation. We need to wait until it
+    # finishes and the table is backfilled.
+    wait_for_gsi(table, 'hello')
+    # As explained above, only items in items1 got copied to the gsi,
+    # and Scan on them works as expected.
+    # Note that we don't need to retry the reads here (i.e., use the
+    # assert_index_scan() or assert_index_query() functions) because after
+    # we waited for backfilling to complete, we know all the pre-existing
+    # data is already in the index.
+    assert multiset(items1) == multiset(full_scan(table, IndexName='hello'))
+    # We can also use Query on the new GSI, to search on the attribute x:
+    assert multiset([items1[3]]) == multiset(full_query(table,
+        IndexName='hello',
+        KeyConditions={'x': {'AttributeValueList': [items1[3]['x']], 'ComparisonOperator': 'EQ'}}))
+    # Let's also test that we cannot add another index with the same name
+    # that already exists
+    with pytest.raises(ClientError, match='ValidationException.*already exists'):
+        dynamodb.meta.client.update_table(TableName=table.name,
+            AttributeDefinitions=[{ 'AttributeName': 'y', 'AttributeType': 'S' }],
+            GlobalSecondaryIndexUpdates=[ {  'Create':
+                {  'IndexName': 'hello',
+                    'KeySchema': [{ 'AttributeName': 'y', 'KeyType': 'HASH' }],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }}])
+    table.delete()
+
+# Test deleting an existing GSI using UpdateTable
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_delete(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    items = [{'p': random_string(), 'x': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # So far, we have the index for "x" and can use it:
+    assert_index_query(table, 'hello', [items[3]],
+        KeyConditions={'x': {'AttributeValueList': [items[3]['x']], 'ComparisonOperator': 'EQ'}})
+    # Now use UpdateTable to delete the GSI for "x"
+    dynamodb.meta.client.update_table(TableName=table.name,
+        GlobalSecondaryIndexUpdates=[{  'Delete':
+            { 'IndexName': 'hello' } }])
+    # update_table is an asynchronous operation. We need to wait until it
+    # finishes and the GSI is removed.
+    wait_for_gsi_gone(table, 'hello')
+    # Now index is gone. We cannot query using it.
+    with pytest.raises(ClientError, match='ValidationException.*hello'):
+        full_query(table, IndexName='hello',
+            KeyConditions={'x': {'AttributeValueList': [items[3]['x']], 'ComparisonOperator': 'EQ'}})
+    table.delete()
+
+# Utility function for creating a new table a GSI with the given name,
+# and, if creation was successful, delete it. Useful for testing which
+# GSI names work.
+def create_gsi(dynamodb, index_name):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
+        AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': index_name,
+                'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    # Verify that the GSI wasn't just ignored, as Scylla originally did ;-)
+    assert 'GlobalSecondaryIndexes' in table.meta.client.describe_table(TableName=table.name)['Table']
+    table.delete()
+
+# Like table names (tested in test_table.py), index names must must also
+# be 3-255 characters and match the regex [a-zA-Z0-9._-]+. This test
+# is similar to test_create_table_unsupported_names(), but for GSI names.
+# Note that Scylla is actually more limited in the length of the index
+# names, because both table name and index name, together, have to fit in
+# 221 characters. But we don't verify here this specific limitation.
+def test_gsi_unsupported_names(dynamodb):
+    # Unfortunately, the boto library tests for names shorter than the
+    # minimum length (3 characters) immediately, and failure results in
+    # ParamValidationError. But the other invalid names are passed to
+    # DynamoDB, which returns an HTTP response code, which results in a
+    # CientError exception.
+    with pytest.raises(ParamValidationError):
+        create_gsi(dynamodb, 'n')
+    with pytest.raises(ParamValidationError):
+        create_gsi(dynamodb, 'nn')
+    with pytest.raises(ClientError, match='ValidationException.*nnnnn'):
+        create_gsi(dynamodb, 'n' * 256)
+    with pytest.raises(ClientError, match='ValidationException.*nyh'):
+        create_gsi(dynamodb, 'nyh@test')
+
+# On the other hand, names following the above rules should be accepted. Even
+# names which the Scylla rules forbid, such as a name starting with .
+def test_gsi_non_scylla_name(dynamodb):
+    create_gsi(dynamodb, '.alternator_test')
+
+# Index names with 255 characters are allowed in Dynamo. In Scylla, the
+# limit is different - the sum of both table and index length cannot
+# exceed 211 characters. So we test a much shorter limit.
+# (compare test_create_and_delete_table_very_long_name()).
+def test_gsi_very_long_name(dynamodb):
+    #create_gsi(dynamodb, 'n' * 255)   # works on DynamoDB, but not on Scylla
+    create_gsi(dynamodb, 'n' * 190)
+
+# Verify that ListTables does not list materialized views used for indexes.
+# This is hard to test, because we don't really know which table names
+# should be listed beyond those we created, and don't want to assume that
+# no other test runs in parallel with us. So the method we chose is to use a
+# unique random name for an index, and check that no table contains this
+# name. This assumes that materialized-view names are composed using the
+# index's name (which is currently what we do).
+
+@pytest.fixture(scope="session")
+def test_table_gsi_random_name(dynamodb):
+    index_name = random_string()
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': index_name,
+                'KeySchema': [
+                    { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ],
+        )
+    yield [table, index_name]
+    table.delete()
+
+def test_gsi_list_tables(dynamodb, test_table_gsi_random_name):
+    table, index_name = test_table_gsi_random_name
+    # Check that the random "index_name" isn't a substring of any table name:
+    tables = list_tables(dynamodb)
+    for name in tables:
+        assert not index_name in name
+    # But of course, the table's name should be in the list:
+    assert table.name in tables

alternator-test/test_health.py

@@ -0,0 +1,34 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the health check
+
+import requests
+
+# Test that a health check can be performed with a GET packet
+def test_health_works(dynamodb):
+    url = dynamodb.meta.client._endpoint.host
+    response = requests.get(url)
+    assert response.ok
+    assert response.content.decode('utf-8').strip()  == 'healthy: {}'.format(url.replace('https://', '').replace('http://', ''))
+
+# Test that a health check only works for the root URL ('/')
+def test_health_only_works_for_root_path(dynamodb):
+    url = dynamodb.meta.client._endpoint.host
+    for suffix in ['/abc', '/..', '/-', '/index.htm', '/health']:
+        response = requests.get(url + suffix)
+        assert response.status_code in range(400, 405)

alternator-test/test_item.py

@@ -0,0 +1,402 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the CRUD item operations: PutItem, GetItem, UpdateItem, DeleteItem
+
+import pytest
+from botocore.exceptions import ClientError
+from decimal import Decimal
+from util import random_string, random_bytes
+
+# Basic test for creating a new item with a random name, and reading it back
+# with strong consistency.
+# Only the string type is used for keys and attributes. None of the various
+# optional PutItem features (Expected, ReturnValues, ReturnConsumedCapacity,
+# ReturnItemCollectionMetrics, ConditionalOperator, ConditionExpression,
+# ExpressionAttributeNames, ExpressionAttributeValues) are used, and
+# for GetItem strong consistency is requested as well as all attributes,
+# but no other optional features (AttributesToGet, ReturnConsumedCapacity,
+# ProjectionExpression, ExpressionAttributeNames)
+def test_basic_string_put_and_get(test_table):
+    p = random_string()
+    c = random_string()
+    val = random_string()
+    val2 = random_string()
+    test_table.put_item(Item={'p': p, 'c': c, 'attribute': val, 'another': val2})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item['p'] == p
+    assert item['c'] == c
+    assert item['attribute'] == val
+    assert item['another'] == val2
+
+# Similar to test_basic_string_put_and_get, just uses UpdateItem instead of
+# PutItem. Because the item does not yet exist, it should work the same.
+def test_basic_string_update_and_get(test_table):
+    p = random_string()
+    c = random_string()
+    val = random_string()
+    val2 = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'attribute': {'Value': val, 'Action': 'PUT'}, 'another': {'Value': val2, 'Action': 'PUT'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item['p'] == p
+    assert item['c'] == c
+    assert item['attribute'] == val
+    assert item['another'] == val2
+
+# Test put_item and get_item of various types for the *attributes*,
+# including both scalars as well as nested documents, lists and sets.
+# The full list of types tested here:
+#    number, boolean, bytes, null, list, map, string set, number set,
+#    binary set.
+# The keys are still strings.
+# Note that only top-level attributes are written and read in this test -
+# this test does not attempt to modify *nested* attributes.
+# See https://boto3.amazonaws.com/v1/documentation/api/latest/reference/customizations/dynamodb.html
+# on how to pass these various types to Boto3's put_item().
+def test_put_and_get_attribute_types(test_table):
+    key = {'p': random_string(), 'c': random_string()}
+    test_items = [
+        Decimal("12.345"),
+        42,
+        True,
+        False,
+        b'xyz',
+        None,
+        ['hello', 'world', 42],
+        {'hello': 'world', 'life': 42},
+        {'hello': {'test': 'hi', 'hello': True, 'list': [1, 2, 'hi']}},
+        set(['hello', 'world', 'hi']),
+        set([1, 42, Decimal("3.14")]),
+        set([b'xyz', b'hi']),
+    ]
+    item = { str(i) : test_items[i] for i in range(len(test_items)) }
+    item.update(key)
+    test_table.put_item(Item=item)
+    got_item = test_table.get_item(Key=key, ConsistentRead=True)['Item']
+    assert item == got_item
+
+# The test_empty_* tests below verify support for empty items, with no
+# attributes except the key. This is a difficult case for Scylla, because
+# for an empty row to exist, Scylla needs to add a "CQL row marker".
+# There are several ways to create empty items - via PutItem, UpdateItem
+# and deleting attributes from non-empty items, and we need to check them
+# all, in several test_empty_* tests:
+def test_empty_put(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.put_item(Item={'p': p, 'c': c})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+def test_empty_put_delete(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.put_item(Item={'p': p, 'c': c, 'hello': 'world'})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'hello': {'Action': 'DELETE'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+def test_empty_update(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+def test_empty_update_delete(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'hello': {'Value': 'world', 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'hello': {'Action': 'DELETE'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+
+# Test error handling of UpdateItem passed a bad "Action" field.
+def test_update_bad_action(test_table):
+    p = random_string()
+    c = random_string()
+    val = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'attribute': {'Value': val, 'Action': 'NONEXISTENT'}})
+
+# A more elaborate UpdateItem test, updating different attributes at different
+# times. Includes PUT and DELETE operations.
+def test_basic_string_more_update(test_table):
+    p = random_string()
+    c = random_string()
+    val1 = random_string()
+    val2 = random_string()
+    val3 = random_string()
+    val4 = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a3': {'Value': val1, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a1': {'Value': val1, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a2': {'Value': val2, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a1': {'Value': val3, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a3': {'Action': 'DELETE'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item['p'] == p
+    assert item['c'] == c
+    assert item['a1'] == val3
+    assert item['a2'] == val2
+    assert not 'a3' in item
+
+# Test that item operations on a non-existant table name fail with correct
+# error code.
+def test_item_operations_nonexistent_table(dynamodb):
+    with pytest.raises(ClientError, match='ResourceNotFoundException'):
+        dynamodb.meta.client.put_item(TableName='non_existent_table',
+            Item={'a':{'S':'b'}})
+
+# Fetching a non-existant item. According to the DynamoDB doc, "If there is no
+# matching item, GetItem does not return any data and there will be no Item
+# element in the response."
+def test_get_item_missing_item(test_table):
+    p = random_string()
+    c = random_string()
+    assert not "Item" in test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)
+
+# Test that if we have a table with string hash and sort keys, we can't read
+# or write items with other key types to it.
+def test_put_item_wrong_key_type(test_table):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types)
+    test_table.put_item(Item={'p': s, 'c': s})
+    assert test_table.get_item(Key={'p': s, 'c': s}, ConsistentRead=True)['Item'] == {'p': s, 'c': s}
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': b, 'c': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': n, 'c': s})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': s, 'c': b})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': s, 'c': n})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'c': s})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': s})
+def test_update_item_wrong_key_type(test_table, test_table_s):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types)
+    test_table.update_item(Key={'p': s, 'c': s}, AttributeUpdates={})
+    assert test_table.get_item(Key={'p': s, 'c': s}, ConsistentRead=True)['Item'] == {'p': s, 'c': s}
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': b, 'c': s}, AttributeUpdates={})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': n, 'c': s}, AttributeUpdates={})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': s, 'c': b}, AttributeUpdates={})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': s, 'c': n}, AttributeUpdates={})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'c': s}, AttributeUpdates={})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': s}, AttributeUpdates={})
+    # Should fail (spurious key columns)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': s, 'spurious': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': s, 'c': s})
+def test_get_item_wrong_key_type(test_table, test_table_s):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types) but have empty result
+    assert not "Item" in test_table.get_item(Key={'p': s, 'c': s}, ConsistentRead=True)
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': b, 'c': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': n, 'c': s})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': b})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': n})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'c': s})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s})
+    # Should fail (spurious key columns)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': s, 'spurious': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': s, 'c': s})
+def test_delete_item_wrong_key_type(test_table, test_table_s):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types)
+    test_table.delete_item(Key={'p': s, 'c': s})
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': b, 'c': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': n, 'c': s})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s, 'c': b})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s, 'c': n})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'c': s})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s})
+    # Should fail (spurious key columns)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s, 'c': s, 'spurious': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.delete_item(Key={'p': s, 'c': s})
+
+# Most of the tests here arbitrarily used a table with both hash and sort keys
+# (both strings). Let's check that a table with *only* a hash key works ok
+# too, for PutItem, GetItem, and UpdateItem.
+def test_only_hash_key(test_table_s):
+    s = random_string()
+    test_table_s.put_item(Item={'p': s, 'hello': 'world'})
+    assert test_table_s.get_item(Key={'p': s}, ConsistentRead=True)['Item'] == {'p': s, 'hello': 'world'}
+    test_table_s.update_item(Key={'p': s}, AttributeUpdates={'hi': {'Value': 'there', 'Action': 'PUT'}})
+    assert test_table_s.get_item(Key={'p': s}, ConsistentRead=True)['Item'] == {'p': s, 'hello': 'world', 'hi': 'there'}
+
+# Tests for item operations in tables with non-string hash or sort keys.
+# These tests focus only on the type of the key - everything else is as
+# simple as we can (string attributes, no special options for GetItem
+# and PutItem). These tests also focus on individual items only, and
+# not about the sort order of sort keys - this should be verified in
+# test_query.py, for example.
+def test_bytes_hash_key(test_table_b):
+    # Bytes values are passed using base64 encoding, which has weird cases
+    # depending on len%3 and len%4. So let's try various lengths.
+    for len in range(10,18):
+        p = random_bytes(len)
+        val = random_string()
+        test_table_b.put_item(Item={'p': p, 'attribute': val})
+        assert test_table_b.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'attribute': val}
+def test_bytes_sort_key(test_table_sb):
+    p = random_string()
+    c = random_bytes()
+    val = random_string()
+    test_table_sb.put_item(Item={'p': p, 'c': c, 'attribute': val})
+    assert test_table_sb.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'attribute': val}
+
+# Tests for using a large binary blob as hash key, sort key, or attribute.
+# DynamoDB strictly limits the size of the binary hash key to 2048 bytes,
+# and binary sort key to 1024 bytes, and refuses anything larger. The total
+# size of an item is limited to 400KB, which also limits the size of the
+# largest attributes. For more details on these limits, see
+# https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Limits.html
+# Alternator currently does *not* have these limitations, and can accept much
+# larger keys and attributes, but what we do in the following tests is to verify
+# that items up to DynamoDB's maximum sizes also work well in Alternator.
+def test_large_blob_hash_key(test_table_b):
+    b = random_bytes(2048)
+    test_table_b.put_item(Item={'p': b})
+    assert test_table_b.get_item(Key={'p': b}, ConsistentRead=True)['Item'] == {'p': b}
+def test_large_blob_sort_key(test_table_sb):
+    s = random_string()
+    b = random_bytes(1024)
+    test_table_sb.put_item(Item={'p': s, 'c': b})
+    assert test_table_sb.get_item(Key={'p': s, 'c': b}, ConsistentRead=True)['Item'] == {'p': s, 'c': b}
+def test_large_blob_attribute(test_table):
+    p = random_string()
+    c = random_string()
+    b = random_bytes(409500)  # a bit less than 400KB
+    test_table.put_item(Item={'p': p, 'c': c, 'attribute': b })
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'attribute': b}
+
+# Checks what it is not allowed to use in a single UpdateItem request both
+# old-style AttributeUpdates and new-style UpdateExpression.
+def test_update_item_two_update_methods(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'a': {'Value': 3, 'Action': 'PUT'}},
+            UpdateExpression='SET b = :val1',
+            ExpressionAttributeValues={':val1': 4})
+
+# Verify that having neither AttributeUpdates nor UpdateExpression is
+# allowed, and results in creation of an empty item.
+def test_update_item_no_update_method(test_table_s):
+    p = random_string()
+    assert not "Item" in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+    test_table_s.update_item(Key={'p': p})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p}
+
+# Test GetItem with the AttributesToGet parameter. Result should include the
+# selected attributes only - if one wants the key attributes as well, one
+# needs to select them explicitly. When no key attributes are selected,
+# some items may have *none* of the selected attributes. Those items are
+# returned too, as empty items - they are not outright missing.
+def test_getitem_attributes_to_get(dynamodb, test_table):
+    p = random_string()
+    c = random_string()
+    item = {'p': p, 'c': c, 'a': 'hello', 'b': 'hi'}
+    test_table.put_item(Item=item)
+    for wanted in [ ['a'],             # only non-key attribute
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # Our item doesn't have this
+                   ]:
+        got_item = test_table.get_item(Key={'p': p, 'c': c}, AttributesToGet=wanted, ConsistentRead=True)['Item']
+        expected_item = {k: item[k] for k in wanted if k in item}
+        assert expected_item == got_item
+
+# Basic test for DeleteItem, with hash key only
+def test_delete_item_hash(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p})
+    assert 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+    test_table_s.delete_item(Key={'p': p})
+    assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+
+# Basic test for DeleteItem, with hash and sort key
+def test_delete_item_sort(test_table):
+    p = random_string()
+    c = random_string()
+    key = {'p': p, 'c': c}
+    test_table.put_item(Item=key)
+    assert 'Item' in test_table.get_item(Key=key, ConsistentRead=True)
+    test_table.delete_item(Key=key)
+    assert not 'Item' in test_table.get_item(Key=key, ConsistentRead=True)
+
+# Test that PutItem completely replaces an existing item. It shouldn't merge
+# it with a previously existing value, as UpdateItem does!
+# We test for a table with just hash key, and for a table with both hash and
+# sort keys.
+def test_put_item_replace(test_table_s, test_table):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hi'}
+    test_table_s.put_item(Item={'p': p, 'b': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
+    c = random_string()
+    test_table.put_item(Item={'p': p, 'c': c, 'a': 'hi'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 'hi'}
+    test_table.put_item(Item={'p': p, 'c': c, 'b': 'hello'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'b': 'hello'}

alternator-test/test_lsi.py

@@ -0,0 +1,365 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests of LSI (Local Secondary Indexes)
+#
+# Note that many of these tests are slower than usual, because many of them
+# need to create new tables and/or new LSIs of different types, operations
+# which are extremely slow in DynamoDB, often taking minutes (!).
+
+import pytest
+import time
+from botocore.exceptions import ClientError, ParamValidationError
+from util import create_test_table, random_string, full_scan, full_query, multiset, list_tables
+
+# Currently, Alternator's LSIs only support eventually consistent reads, so tests
+# that involve writing to a table and then expect to read something from it cannot
+# be guaranteed to succeed without retrying the read. The following utility
+# functions make it easy to write such tests.
+def assert_index_query(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_query retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
+
+def assert_index_scan(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_scan retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
+
+# Although quite silly, it is actually allowed to create an index which is
+# identical to the base table.
+def test_lsi_identical(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' }],
+        AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'S' }],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    items = [{'p': random_string(), 'c': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert multiset(items) == multiset(full_scan(table))
+    assert_index_scan(table, 'hello', items)
+    # We can't scan a non-existant index
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_scan(table, IndexName='wrong')
+    table.delete()
+
+# Checks that providing a hash key different than the base table is not allowed,
+# and so is providing duplicated keys or no sort key at all
+def test_lsi_wrong(dynamodb):
+    with pytest.raises(ClientError, match='ValidationException.*'):
+        table = create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[
+                        { 'AttributeName': 'p', 'AttributeType': 'S' },
+                        { 'AttributeName': 'a', 'AttributeType': 'S' },
+                        { 'AttributeName': 'b', 'AttributeType': 'S' }
+            ],
+            LocalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [
+                        { 'AttributeName': 'b', 'KeyType': 'HASH' },
+                        { 'AttributeName': 'p', 'KeyType': 'RANGE' }
+                    ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+        table.delete()
+    with pytest.raises(ClientError, match='ValidationException.*'):
+        table = create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[
+                        { 'AttributeName': 'p', 'AttributeType': 'S' },
+                        { 'AttributeName': 'a', 'AttributeType': 'S' },
+                        { 'AttributeName': 'b', 'AttributeType': 'S' }
+            ],
+            LocalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [
+                        { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                        { 'AttributeName': 'p', 'KeyType': 'RANGE' }
+                    ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+        table.delete()
+    with pytest.raises(ClientError, match='ValidationException.*'):
+        table = create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[
+                        { 'AttributeName': 'p', 'AttributeType': 'S' },
+                        { 'AttributeName': 'a', 'AttributeType': 'S' },
+                        { 'AttributeName': 'b', 'AttributeType': 'S' }
+            ],
+            LocalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [
+                        { 'AttributeName': 'p', 'KeyType': 'HASH' }
+                    ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+        table.delete()
+
+# A simple scenario for LSI. Base table has just hash key, Index has an
+# additional sort key - one of the non-key attributes from the base table.
+@pytest.fixture(scope="session")
+def test_table_lsi_1(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' },
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'b', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_lsi_1(test_table_lsi_1):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string()} for i in range(10)]
+    p1, b1 = items1[0]['p'], items1[0]['b']
+    p2, b2 = random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2}]
+    items = items1 + items2
+    with test_table_lsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}})
+    expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}})
+
+# A second scenario of LSI. Base table has both hash and sort keys,
+# a local index is created on each non-key parameter
+@pytest.fixture(scope="session")
+def test_table_lsi_4(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x1', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x2', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x3', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x4', 'AttributeType': 'S' },
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello_' + column,
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': column, 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            } for column in ['x1','x2','x3','x4']
+        ])
+    yield table
+    table.delete()
+
+def test_lsi_4(test_table_lsi_4):
+    items1 = [{'p': random_string(), 'c': random_string(),
+               'x1': random_string(), 'x2': random_string(), 'x3': random_string(), 'x4': random_string()} for i in range(10)]
+    i_values = items1[0]
+    i5 = random_string()
+    items2 = [{'p': i5, 'c': i5, 'x1': i5, 'x2': i5, 'x3': i5, 'x4': i5}]
+    items = items1 + items2
+    with test_table_lsi_4.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for column in ['x1', 'x2', 'x3', 'x4']:
+        expected_items = [i for i in items if (i['p'], i[column]) == (i_values['p'], i_values[column])]
+        assert_index_query(test_table_lsi_4, 'hello_' + column, expected_items,
+            KeyConditions={'p': {'AttributeValueList': [i_values['p']], 'ComparisonOperator': 'EQ'},
+                           column: {'AttributeValueList': [i_values[column]], 'ComparisonOperator': 'EQ'}})
+        expected_items = [i for i in items if (i['p'], i[column]) == (i5, i5)]
+        assert_index_query(test_table_lsi_4, 'hello_' + column, expected_items,
+            KeyConditions={'p': {'AttributeValueList': [i5], 'ComparisonOperator': 'EQ'},
+                           column: {'AttributeValueList': [i5], 'ComparisonOperator': 'EQ'}})
+
+def test_lsi_describe(test_table_lsi_4):
+    desc = test_table_lsi_4.meta.client.describe_table(TableName=test_table_lsi_4.name)
+    assert 'Table' in desc
+    assert 'LocalSecondaryIndexes' in desc['Table']
+    lsis = desc['Table']['LocalSecondaryIndexes']
+    assert(sorted([lsi['IndexName'] for lsi in lsis]) == ['hello_x1', 'hello_x2', 'hello_x3', 'hello_x4'])
+    # TODO: check projection and key params
+    # TODO: check also ProvisionedThroughput, IndexArn
+
+# A table with selective projection - only keys are projected into the index
+@pytest.fixture(scope="session")
+def test_table_lsi_keys_only(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' }
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'b', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ])
+    yield table
+    table.delete()
+
+# Check that it's possible to extract a non-projected attribute from the index,
+# as the documentation promises
+def test_lsi_get_not_projected_attribute(test_table_lsi_keys_only):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string(), 'd': random_string()} for i in range(10)]
+    p1, b1, d1 = items1[0]['p'], items1[0]['b'], items1[0]['d']
+    p2, b2, d2 = random_string(), random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2, 'd': d2}]
+    items = items1 + items2
+    with test_table_lsi_keys_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1 and i['d'] == d1]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}},
+        Select='ALL_ATTRIBUTES')
+    expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2 and i['d'] == d2]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
+        Select='ALL_ATTRIBUTES')
+    expected_items = [{'d': i['d']} for i in items if i['p'] == p2 and i['b'] == b2 and i['d'] == d2]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
+        Select='SPECIFIC_ATTRIBUTES', AttributesToGet=['d'])
+
+# Check that only projected attributes can be extracted
+@pytest.mark.xfail(reason="LSI in alternator currently only implement full projections")
+def test_lsi_get_all_projected_attributes(test_table_lsi_keys_only):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string(), 'd': random_string()} for i in range(10)]
+    p1, b1, d1 = items1[0]['p'], items1[0]['b'], items1[0]['d']
+    p2, b2, d2 = random_string(), random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2, 'd': d2}]
+    items = items1 + items2
+    with test_table_lsi_keys_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [{'p': i['p'], 'c': i['c'],'b': i['b']} for i in items if i['p'] == p1 and i['b'] == b1]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}})
+
+# Check that strongly consistent reads are allowed for LSI
+def test_lsi_consistent_read(test_table_lsi_1):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string()} for i in range(10)]
+    p1, b1 = items1[0]['p'], items1[0]['b']
+    p2, b2 = random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2}]
+    items = items1 + items2
+    with test_table_lsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}},
+        ConsistentRead=True)
+    expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
+        ConsistentRead=True)
+
+# A table with both gsi and lsi present
+@pytest.fixture(scope="session")
+def test_table_lsi_gsi(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x1', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello_g1',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'x1', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello_l1',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'x1', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ])
+    yield table
+    table.delete()
+
+# Test that GSI and LSI can coexist, even if they're identical
+def test_lsi_and_gsi(test_table_lsi_gsi):
+    desc = test_table_lsi_gsi.meta.client.describe_table(TableName=test_table_lsi_gsi.name)
+    assert 'Table' in desc
+    assert 'LocalSecondaryIndexes' in desc['Table']
+    assert 'GlobalSecondaryIndexes' in desc['Table']
+    lsis = desc['Table']['LocalSecondaryIndexes']
+    gsis = desc['Table']['GlobalSecondaryIndexes']
+    assert(sorted([lsi['IndexName'] for lsi in lsis]) == ['hello_l1'])
+    assert(sorted([gsi['IndexName'] for gsi in gsis]) == ['hello_g1'])
+
+    items = [{'p': random_string(), 'c': random_string(), 'x1': random_string()} for i in range(17)]
+    p1, c1, x1 = items[0]['p'], items[0]['c'], items[0]['x1']
+    with test_table_lsi_gsi.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+
+    for index in ['hello_g1', 'hello_l1']:
+        expected_items = [i for i in items if i['p'] == p1 and i['x1'] == x1]
+        assert_index_query(test_table_lsi_gsi, index, expected_items,
+            KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                           'x1': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})

alternator-test/test_nested.py

@@ -0,0 +1,60 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Test for operations on items with *nested* attributes.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string
+
+# Test that we can write a top-level attribute that is a nested document, and
+# read it back correctly.
+def test_nested_document_attribute_write(test_table_s):
+    nested_value = {
+        'a': 3,
+        'b': {'c': 'hello', 'd': ['hi', 'there', {'x': 'y'}, '42']},
+    }
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': nested_value})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': nested_value}
+
+# Test that if we have a top-level attribute that is a nested document (i.e.,
+# a dictionary), updating this attribute will replace it entirely by a new
+# nested document - not merge into the old content with the new content.
+def test_nested_document_attribute_overwrite(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5}
+    test_table_s.update_item(Key={'p': p}, AttributeUpdates={'a': {'Value': {'c': 5}, 'Action': 'PUT'}})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'c': 5}, 'd': 5}
+
+# Moreover, we can overwrite an entire nested document by, say, a string,
+# and that's also fine.
+def test_nested_document_attribute_overwrite_2(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5}
+    test_table_s.update_item(Key={'p': p}, AttributeUpdates={'a': {'Value': 'hi', 'Action': 'PUT'}})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hi', 'd': 5}
+
+# Verify that AttributeUpdates cannot be used to update a nested attribute -
+# trying to use a dot in the name of the attribute, will just create one with
+# an actual dot in its name.
+def test_attribute_updates_dot(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, AttributeUpdates={'a.b': {'Value': 3, 'Action': 'PUT'}})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a.b': 3}

alternator-test/test_projection_expression.py

@@ -0,0 +1,201 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the various operations (GetItem, Query, Scan) with a
+# ProjectionExpression parameter.
+#
+# ProjectionExpression is an expension of the legacy AttributesToGet
+# parameter. Both parameters request that only a subset of the attributes
+# be fetched for each item, instead of all of them. But while AttributesToGet
+# was limited to top-level attributes, ProjectionExpression can request also
+# nested attributes.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string, full_scan, full_query, multiset
+
+# Basic test for ProjectionExpression, requesting only top-level attributes.
+# Result should include the selected attributes only - if one wants the key
+# attributes as well, one needs to select them explicitly. When no key
+# attributes are selected, an item may have *none* of the selected
+# attributes, and returned as an empty item.
+def test_projection_expression_toplevel(test_table):
+    p = random_string()
+    c = random_string()
+    item = {'p': p, 'c': c, 'a': 'hello', 'b': 'hi'}
+    test_table.put_item(Item=item)
+    for wanted in [ ['a'],             # only non-key attribute
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # Our item doesn't have this
+                   ]:
+        got_item = test_table.get_item(Key={'p': p, 'c': c}, ProjectionExpression=",".join(wanted), ConsistentRead=True)['Item']
+        expected_item = {k: item[k] for k in wanted if k in item}
+        assert expected_item == got_item
+
+# Various simple tests for ProjectionExpression's syntax, using only top-evel
+# attributes.
+def test_projection_expression_toplevel_syntax(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a')['Item'] == {'a': 'hello'}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#name': 'a'})['Item'] == {'a': 'hello'}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,b')['Item'] == {'a': 'hello', 'b': 'hi'}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression=' a  ,   b  ')['Item'] == {'a': 'hello', 'b': 'hi'}
+    # Missing or unused names in ExpressionAttributeNames are errors:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#wrong': 'a'})['Item'] == {'a': 'hello'}
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#name': 'a', '#unused': 'b'})['Item'] == {'a': 'hello'}
+    # It is not allowed to fetch the same top-level attribute twice (or in
+    # general, list two overlapping attributes). We get an error like
+    # "Invalid ProjectionExpression: Two document paths overlap with each
+    # other; must remove or rewrite one of these paths; path one: [a], path
+    # two: [a]".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,a')['Item']
+    # A comma with nothing after it is a syntax error:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,')['Item']
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression=',a')['Item']
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,,b')['Item']
+    # An empty ProjectionExpression is not allowed. DynamoDB recognizes its
+    # syntax, but then writes: "Invalid ProjectionExpression: The expression
+    # can not be empty".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='')['Item']
+
+# The following two tests are similar to test_projection_expression_toplevel()
+# which tested the GetItem operation - but these test Scan and Query.
+# Both test ProjectionExpression with only top-level attributes.
+def test_projection_expression_scan(filled_test_table):
+    table, items = filled_test_table
+    for wanted in [ ['another'],       # only non-key attributes (one item doesn't have it!)
+                    ['c', 'another'],  # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        got_items = full_scan(table,  ProjectionExpression=",".join(wanted))
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+def test_projection_expression_query(test_table):
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': str(i*10), 'b': str(i*100) } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for wanted in [ ['a'],             # only non-key attributes
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression=",".join(wanted))
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+# The previous tests all fetched only top-level attributes. They could all
+# be written using AttributesToGet instead of ProjectionExpression (and,
+# in fact, we do have similar tests with AttributesToGet in other files),
+# but the previous test checked that the alternative syntax works correctly.
+# The following test checks fetching more elaborate attribute paths from
+# nested documents.
+@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
+def test_projection_expression_path(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={
+        'p': p,
+        'a': {'b': [2, 4, {'x': 'hi', 'y': 'yo'}], 'c': 5},
+        'b': 'hello' 
+        })
+    # Fetching the entire nested document "a" works, of course:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a')['Item'] == {'a': {'b': [2, 4, {'x': 'hi', 'y': 'yo'}], 'c': 5}}
+    # If we fetch a.b, we get only the content of b - but it's still inside
+    # the a dictionary:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b')['Item'] == {'a': {'b': [2, 4, {'x': 'hi', 'y': 'yo'}]}}
+    # Similarly, fetching a.b[0] gives us a one-element array in a dictionary.
+    # Note that [0] is the first element of an array.
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0]')['Item'] == {'a': {'b': [2]}}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[2]')['Item'] == {'a': {'b': [{'x': 'hi', 'y': 'yo'}]}}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[2].y')['Item'] == {'a': {'b': [{'y': 'yo'}]}}
+    # Trying to read any sort of non-existant attribute returns an empty item.
+    # This includes a non-existing top-level attribute, an attempt to read
+    # beyond the end of an array or a non-existant member of a dictionary, as
+    # well as paths which begin with a non-existant prefix.
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='x')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[3]')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.x')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.x.y')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[3].x')['Item'] == {}
+    # We can read multiple paths - the result are merged into one object
+    # structured the same was as in the original item:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.b[1]')['Item'] == {'a': {'b': [2, 4]}}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.c')['Item'] == {'a': {'b': [2], 'c': 5}}
+    # It is not allowed to read the same path multiple times. The error from
+    # DynamoDB looks like: "Invalid ProjectionExpression: Two document paths
+    # overlap with each other; must remove or rewrite one of these paths;
+    # path one: [a, b, [0]], path two: [a, b, [0]]".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.b[0]')['Item']
+    # Two paths are considered to "overlap" if the content of one path
+    # contains the content of the second path. So requesting both "a" and
+    # "a.b[0]" is not allowed.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,a.b[0]')['Item']
+
+@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
+def test_query_projection_expression_path(test_table):
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': {'x': str(i*10), 'y': 'hi'}, 'b': 'hello' } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression="a.x")
+    expected_items = [{'a': {'x': x['a']['x']}} for x in items]
+    assert multiset(expected_items) == multiset(got_items)
+
+@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
+def test_scan_projection_expression_path(test_table):
+    # This test is similar to test_query_projection_expression_path above,
+    # but uses a scan instead of a query. The scan will generate unrelated
+    # partitions created by other tests (hopefully not too many...) that we
+    # need to ignore. We also need to ask for "p" too, so we can filter by it.
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': {'x': str(i*10), 'y': 'hi'}, 'b': 'hello' } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = [ x for x in full_scan(test_table, ProjectionExpression="p, a.x") if x['p'] == p]
+    expected_items = [{'p': p, 'a': {'x': x['a']['x']}} for x in items]
+    assert multiset(expected_items) == multiset(got_items)
+
+# It is not allowed to use both ProjectionExpression and its older cousin,
+# AttributesToGet, together. If trying to do this, DynamoDB produces an error
+# like "Can not use both expression and non-expression parameters in the same
+# request: Non-expression parameters: {AttributesToGet} Expression
+# parameters: {ProjectionExpression}
+def test_projection_expression_and_attributes_to_get(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
+    with pytest.raises(ClientError, match='ValidationException.*both'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a', AttributesToGet=['b'])['Item']
+    with pytest.raises(ClientError, match='ValidationException.*both'):
+        full_scan(test_table_s,  ProjectionExpression='a', AttributesToGet=['a'])
+    with pytest.raises(ClientError, match='ValidationException.*both'):
+        full_query(test_table_s, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression='a', AttributesToGet=['a'])

alternator-test/test_query.py

@@ -0,0 +1,358 @@
+# -*- coding: utf-8 -*-
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the Query operation
+
+import random
+import pytest
+from botocore.exceptions import ClientError
+from decimal import Decimal
+from util import random_string, random_bytes, full_query, multiset
+from boto3.dynamodb.conditions import Key, Attr
+
+# Test that scanning works fine with in-stock paginator
+def test_query_basic_restrictions(dynamodb, filled_test_table):
+    test_table, items = filled_test_table
+    paginator = dynamodb.meta.client.get_paginator('query')
+
+    # EQ
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long']) == multiset(got_items)
+
+    # LT
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['12'], 'ComparisonOperator': 'LT'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] < '12']) == multiset(got_items)
+
+    # LE
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['14'], 'ComparisonOperator': 'LE'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] <= '14']) == multiset(got_items)
+
+    # GT
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['15'], 'ComparisonOperator': 'GT'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] > '15']) == multiset(got_items)
+
+    # GE
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['14'], 'ComparisonOperator': 'GE'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] >= '14']) == multiset(got_items)
+
+    # BETWEEN
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['155', '164'], 'ComparisonOperator': 'BETWEEN'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] >= '155' and item['c'] <= '164']) == multiset(got_items)
+
+    # BEGINS_WITH
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['11'], 'ComparisonOperator': 'BEGINS_WITH'}
+        }):
+        print([item for item in items if item['p'] == 'long' and item['c'].startswith('11')])
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'].startswith('11')]) == multiset(got_items)
+
+# Test that KeyConditionExpression parameter is supported
+@pytest.mark.xfail(reason="KeyConditionExpression not supported yet")
+def test_query_key_condition_expression(dynamodb, filled_test_table):
+    test_table, items = filled_test_table
+    paginator = dynamodb.meta.client.get_paginator('query')
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditionExpression=Key("p").eq("long") & Key("c").lt("12")):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] < '12']) == multiset(got_items)
+
+def test_begins_with(dynamodb, test_table):
+    paginator = dynamodb.meta.client.get_paginator('query')
+    items = [{'p': 'unorthodox_chars', 'c': sort_key, 'str': 'a'} for sort_key in [u'ÿÿÿ', u'cÿbÿ', u'cÿbÿÿabg'] ]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+
+    # TODO(sarna): Once bytes type is supported, /xFF character should be tested
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': [u'ÿÿ'], 'ComparisonOperator': 'BEGINS_WITH'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert sorted([d['c'] for d in got_items]) == sorted([d['c'] for d in items if d['c'].startswith(u'ÿÿ')])
+
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': [u'cÿbÿ'], 'ComparisonOperator': 'BEGINS_WITH'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert sorted([d['c'] for d in got_items]) == sorted([d['c'] for d in items if d['c'].startswith(u'cÿbÿ')])
+
+def test_begins_with_wrong_type(dynamodb, test_table_sn):
+    paginator = dynamodb.meta.client.get_paginator('query')
+    with pytest.raises(ClientError, match='ValidationException'):
+        for page in paginator.paginate(TableName=test_table_sn.name, KeyConditions={
+                'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
+                'c' : {'AttributeValueList': [17], 'ComparisonOperator': 'BEGINS_WITH'}
+                }):
+            pass
+
+# Items returned by Query should be sorted by the sort key. The following
+# tests verify that this is indeed the case, for the three allowed key types:
+# strings, binary, and numbers. These tests test not just the Query operation,
+# but inherently that the sort-key sorting works.
+def test_query_sort_order_string(test_table):
+    # Insert a lot of random items in one new partition:
+    # str(i) has a non-obvious sort order (e.g., "100" comes before "2") so is a nice test.
+    p = random_string()
+    items = [{'p': p, 'c': str(i)} for i in range(128)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    assert len(items) == len(got_items)
+    # Extract just the sort key ("c") from the items
+    sort_keys = [x['c'] for x in items]
+    got_sort_keys = [x['c'] for x in got_items]
+    # Verify that got_sort_keys are already sorted (in string order)
+    assert sorted(got_sort_keys) == got_sort_keys
+    # Verify that got_sort_keys are a sorted version of the expected sort_keys
+    assert sorted(sort_keys) == got_sort_keys
+def test_query_sort_order_bytes(test_table_sb):
+    # Insert a lot of random items in one new partition:
+    # We arbitrarily use random_bytes with a random length.
+    p = random_string()
+    items = [{'p': p, 'c': random_bytes(10)} for i in range(128)]
+    with test_table_sb.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = full_query(test_table_sb, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    assert len(items) == len(got_items)
+    sort_keys = [x['c'] for x in items]
+    got_sort_keys = [x['c'] for x in got_items]
+    # Boto3's "Binary" objects are sorted as if bytes are signed integers.
+    # This isn't the order that DynamoDB itself uses (byte 0 should be first,
+    # not byte -128). Sorting the byte array ".value" works.
+    assert sorted(got_sort_keys, key=lambda x: x.value) == got_sort_keys
+    assert sorted(sort_keys) == got_sort_keys
+def test_query_sort_order_number(test_table_sn):
+    # This is a list of numbers, sorted in correct order, and each suitable
+    # for accurate representation by Alternator's number type.
+    numbers = [
+        Decimal("-2e10"),
+        Decimal("-7.1e2"),
+        Decimal("-4.1"),
+        Decimal("-0.1"),
+        Decimal("-1e-5"),
+        Decimal("0"),
+        Decimal("2e-5"),
+        Decimal("0.15"),
+        Decimal("1"),
+        Decimal("1.00000000000000000000000001"),
+        Decimal("3.14159"),
+        Decimal("3.1415926535897932384626433832795028841"),
+        Decimal("31.4"),
+        Decimal("1.4e10"),
+    ]
+    # Insert these numbers, in random order, into one partition:
+    p = random_string()
+    items = [{'p': p, 'c': num} for num in random.sample(numbers, len(numbers))]
+    with test_table_sn.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # Finally, verify that we get back exactly the same numbers (with identical
+    # precision), and in their original sorted order.
+    got_items = full_query(test_table_sn, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    got_sort_keys = [x['c'] for x in got_items]
+    assert got_sort_keys == numbers
+
+def test_query_filtering_attributes_equality(filled_test_table):
+    test_table, items = filled_test_table
+
+    query_filter = {
+        "attribute" : {
+            "AttributeValueList" : [ "xxxx" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx']) == multiset(got_items)
+
+    query_filter = {
+        "attribute" : {
+            "AttributeValueList" : [ "xxxx" ],
+            "ComparisonOperator": "EQ"
+        },
+        "another" : {
+            "AttributeValueList" : [ "yy" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
+
+# Test that FilterExpression works as expected
+@pytest.mark.xfail(reason="FilterExpression not supported yet")
+def test_query_filter_expression(filled_test_table):
+    test_table, items = filled_test_table
+
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, FilterExpression=Attr("attribute").eq("xxxx"))
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx']) == multiset(got_items)
+
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, FilterExpression=Attr("attribute").eq("xxxx") & Attr("another").eq("yy"))
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
+
+# QueryFilter can only contain non-key attributes in order to be compatible
+def test_query_filtering_key_equality(filled_test_table):
+    test_table, items = filled_test_table
+
+    with pytest.raises(ClientError, match='ValidationException'):
+        query_filter = {
+            "c" : {
+                "AttributeValueList" : [ "5" ],
+                "ComparisonOperator": "EQ"
+            }
+        }
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+        print(got_items)
+
+    with pytest.raises(ClientError, match='ValidationException'):
+        query_filter = {
+            "attribute" : {
+                "AttributeValueList" : [ "x" ],
+                "ComparisonOperator": "EQ"
+            },
+            "p" : {
+                "AttributeValueList" : [ "5" ],
+                "ComparisonOperator": "EQ"
+            }
+        }
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+        print(got_items)
+
+# Test Query with the AttributesToGet parameter. Result should include the
+# selected attributes only - if one wants the key attributes as well, one
+# needs to select them explicitly. When no key attributes are selected,
+# some items may have *none* of the selected attributes. Those items are
+# returned too, as empty items - they are not outright missing.
+def test_query_attributes_to_get(dynamodb, test_table):
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': str(i*10), 'b': str(i*100) } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for wanted in [ ['a'],             # only non-key attributes
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, AttributesToGet=wanted)
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+# Test that in a table with both hash key and sort key, which keys we can
+# Query by: We can Query by the hash key, by a combination of both hash and
+# sort keys, but *cannot* query by just the sort key, and obviously not
+# by any non-key column.
+def test_query_which_key(test_table):
+    p = random_string()
+    c = random_string()
+    p2 = random_string()
+    c2 = random_string()
+    item1 = {'p': p, 'c': c}
+    item2 = {'p': p, 'c': c2}
+    item3 = {'p': p2, 'c': c}
+    for i in [item1, item2, item3]:
+        test_table.put_item(Item=i)
+    # Query by hash key only:
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    expected_items = [item1, item2]
+    assert multiset(expected_items) == multiset(got_items)
+    # Query by hash key *and* sort key (this is basically a GetItem):
+    got_items = full_query(test_table, KeyConditions={
+        'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'},
+        'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+    })
+    expected_items = [item1]
+    assert multiset(expected_items) == multiset(got_items)
+    # Query by sort key alone is not allowed. DynamoDB reports:
+    # "Query condition missed key schema element: p".
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })
+    # Query by a non-key isn't allowed, for the same reason - that the
+    # actual hash key (p) is missing in the query:
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'z': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })
+    # If we try both p and a non-key we get a complaint that the sort
+    # key is missing: "Query condition missed key schema element: c"
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'},
+            'z': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })
+    # If we try p, c and another key, we get an error that
+    # "Conditions can be of length 1 or 2 only".
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'},
+            'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'},
+            'z': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })

alternator-test/test_scan.py

@@ -0,0 +1,191 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the Scan operation
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string, full_scan, multiset
+from boto3.dynamodb.conditions import Attr
+
+# Test that scanning works fine with/without pagination
+def test_scan_basic(filled_test_table):
+    test_table, items = filled_test_table
+    for limit in [None,1,2,4,33,50,100,9007,16*1024*1024]:
+        pos = None
+        got_items = []
+        while True:
+            if limit:
+                response = test_table.scan(Limit=limit, ExclusiveStartKey=pos) if pos else test_table.scan(Limit=limit)
+                assert len(response['Items']) <= limit
+            else:
+                response = test_table.scan(ExclusiveStartKey=pos) if pos else test_table.scan()
+            pos = response.get('LastEvaluatedKey', None)
+            got_items += response['Items']
+            if not pos:
+                break
+
+        assert len(items) == len(got_items)
+        assert multiset(items) == multiset(got_items)
+
+def test_scan_with_paginator(dynamodb, filled_test_table):
+    test_table, items = filled_test_table
+    paginator = dynamodb.meta.client.get_paginator('scan')
+
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name):
+        got_items += page['Items']
+
+    assert len(items) == len(got_items)
+    assert multiset(items) == multiset(got_items)
+
+    for page_size in [1, 17, 1234]:
+        got_items = []
+        for page in paginator.paginate(TableName=test_table.name, PaginationConfig={'PageSize': page_size}):
+            got_items += page['Items']
+
+    assert len(items) == len(got_items)
+    assert multiset(items) == multiset(got_items)
+
+# Although partitions are scanned in seemingly-random order, inside a
+# partition items must be returned by Scan sorted in sort-key order.
+# This test verifies this, for string sort key. We'll need separate
+# tests for the other sort-key types (number and binary)
+def test_scan_sort_order_string(filled_test_table):
+    test_table, items = filled_test_table
+    got_items = full_scan(test_table)
+    assert len(items) == len(got_items)
+    # Extract just the sort key ("c") from the partition "long"
+    items_long = [x['c'] for x in items if x['p'] == 'long']
+    got_items_long = [x['c'] for x in got_items if x['p'] == 'long']
+    # Verify that got_items_long are already sorted (in string order)
+    assert sorted(got_items_long) == got_items_long
+    # Verify that got_items_long are a sorted version of the expected items_long
+    assert sorted(items_long) == got_items_long
+
+# Test Scan with the AttributesToGet parameter. Result should include the
+# selected attributes only - if one wants the key attributes as well, one
+# needs to select them explicitly. When no key attributes are selected,
+# some items may have *none* of the selected attributes. Those items are
+# returned too, as empty items - they are not outright missing.
+def test_scan_attributes_to_get(dynamodb, filled_test_table):
+    table, items = filled_test_table
+    for wanted in [ ['another'],       # only non-key attributes (one item doesn't have it!)
+                    ['c', 'another'],  # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        print(wanted)
+        got_items = full_scan(table, AttributesToGet=wanted)
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+def test_scan_with_attribute_equality_filtering(dynamodb, filled_test_table):
+    table, items = filled_test_table
+    scan_filter = {
+        "attribute" : {
+            "AttributeValueList" : [ "xxxxx" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    got_items = full_scan(table, ScanFilter=scan_filter)
+    expected_items = [item for item in items if "attribute" in item.keys() and item["attribute"] == "xxxxx" ]
+    assert multiset(expected_items) == multiset(got_items)
+
+    scan_filter = {
+        "another" : {
+            "AttributeValueList" : [ "y" ],
+            "ComparisonOperator": "EQ"
+        },
+        "attribute" : {
+            "AttributeValueList" : [ "xxxxx" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    got_items = full_scan(table, ScanFilter=scan_filter)
+    expected_items = [item for item in items if "attribute" in item.keys() and item["attribute"] == "xxxxx" and item["another"] == "y" ]
+    assert multiset(expected_items) == multiset(got_items)
+
+# Test that FilterExpression works as expected
+@pytest.mark.xfail(reason="FilterExpression not supported yet")
+def test_scan_filter_expression(filled_test_table):
+    test_table, items = filled_test_table
+
+    got_items = full_scan(test_table, FilterExpression=Attr("attribute").eq("xxxx"))
+    print(got_items)
+    assert multiset([item for item in items if 'attribute' in item.keys() and item['attribute'] == 'xxxx']) == multiset(got_items)
+
+    got_items = full_scan(test_table, FilterExpression=Attr("attribute").eq("xxxx") & Attr("another").eq("yy"))
+    print(got_items)
+    assert multiset([item for item in items if 'attribute' in item.keys() and 'another' in item.keys() and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
+
+def test_scan_with_key_equality_filtering(dynamodb, filled_test_table):
+    table, items = filled_test_table
+    scan_filter_p = {
+        "p" : {
+            "AttributeValueList" : [ "7" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    scan_filter_c = {
+        "c" : {
+            "AttributeValueList" : [ "9" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    scan_filter_p_and_attribute = {
+        "p" : {
+            "AttributeValueList" : [ "7" ],
+            "ComparisonOperator": "EQ"
+        },
+        "attribute" : {
+            "AttributeValueList" : [ "x"*7 ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    scan_filter_c_and_another = {
+        "c" : {
+            "AttributeValueList" : [ "9" ],
+            "ComparisonOperator": "EQ"
+        },
+        "another" : {
+            "AttributeValueList" : [ "y"*16 ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    # Filtering on the hash key
+    got_items = full_scan(table, ScanFilter=scan_filter_p)
+    expected_items = [item for item in items if "p" in item.keys() and item["p"] == "7" ]
+    assert multiset(expected_items) == multiset(got_items)
+
+    # Filtering on the sort key
+    got_items = full_scan(table, ScanFilter=scan_filter_c)
+    expected_items = [item for item in items if "c" in item.keys() and item["c"] == "9"]
+    assert multiset(expected_items) == multiset(got_items)
+
+    # Filtering on the hash key and an attribute
+    got_items = full_scan(table, ScanFilter=scan_filter_p_and_attribute)
+    expected_items = [item for item in items if "p" in item.keys() and "another" in item.keys() and item["p"] == "7" and item["another"] == "y"*16]
+    assert multiset(expected_items) == multiset(got_items)
+
+    # Filtering on the sort key and an attribute
+    got_items = full_scan(table, ScanFilter=scan_filter_c_and_another)
+    expected_items = [item for item in items if "c" in item.keys() and "another" in item.keys() and item["c"] == "9" and item["another"] == "y"*16]
+    assert multiset(expected_items) == multiset(got_items)

alternator-test/test_table.py

@@ -0,0 +1,276 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for basic table operations: CreateTable, DeleteTable, ListTables.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import list_tables, test_table_name, create_test_table, random_string
+
+# Utility function for create a table with a given name and some valid
+# schema.. This function initiates the table's creation, but doesn't
+# wait for the table to actually become ready.
+def create_table(dynamodb, name, BillingMode='PAY_PER_REQUEST', **kwargs):
+    return dynamodb.create_table(
+        TableName=name,
+        BillingMode=BillingMode,
+        KeySchema=[
+            {
+                'AttributeName': 'p',
+                'KeyType': 'HASH'
+            },
+            {
+                'AttributeName': 'c',
+                'KeyType': 'RANGE'
+            }
+        ],
+        AttributeDefinitions=[
+            {
+                'AttributeName': 'p',
+                'AttributeType': 'S'
+            },
+            {
+                'AttributeName': 'c',
+                'AttributeType': 'S'
+            },
+        ],
+        **kwargs
+    )
+
+# Utility function for creating a table with a given name, and then deleting
+# it immediately, waiting for these operations to complete. Since the wait
+# uses DescribeTable, this function requires all of CreateTable, DescribeTable
+# and DeleteTable to work correctly.
+# Note that in DynamoDB, table deletion takes a very long time, so tests
+# successfully using this function are very slow.
+def create_and_delete_table(dynamodb, name, **kwargs):
+    table = create_table(dynamodb, name, **kwargs)
+    table.meta.client.get_waiter('table_exists').wait(TableName=name)
+    table.delete()
+    table.meta.client.get_waiter('table_not_exists').wait(TableName=name)
+
+##############################################################################
+
+# Test creating a table, and then deleting it, waiting for each operation
+# to have completed before proceeding. Since the wait uses DescribeTable,
+# this tests requires all of CreateTable, DescribeTable and DeleteTable to
+# function properly in their basic use cases.
+# Unfortunately, this test is extremely slow with DynamoDB because deleting
+# a table is extremely slow until it really happens.
+def test_create_and_delete_table(dynamodb):
+    create_and_delete_table(dynamodb, 'alternator_test')
+
+# DynamoDB documentation specifies that table names must be 3-255 characters,
+# and match the regex [a-zA-Z0-9._-]+. Names not matching these rules should
+# be rejected, and no table be created.
+def test_create_table_unsupported_names(dynamodb):
+    from botocore.exceptions import ParamValidationError, ClientError
+    # Intererstingly, the boto library tests for names shorter than the
+    # minimum length (3 characters) immediately, and failure results in
+    # ParamValidationError. But the other invalid names are passed to
+    # DynamoDB, which returns an HTTP response code, which results in a
+    # CientError exception.
+    with pytest.raises(ParamValidationError):
+        create_table(dynamodb, 'n')
+    with pytest.raises(ParamValidationError):
+        create_table(dynamodb, 'nn')
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, 'n' * 256)
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, 'nyh@test')
+
+# On the other hand, names following the above rules should be accepted. Even
+# names which the Scylla rules forbid, such as a name starting with .
+def test_create_and_delete_table_non_scylla_name(dynamodb):
+    create_and_delete_table(dynamodb, '.alternator_test')
+
+# names with 255 characters are allowed in Dynamo, but they are not currently
+# supported in Scylla because we create a directory whose name is the table's
+# name followed by 33 bytes (underscore and UUID). So currently, we only
+# correctly support names with length up to 222.
+def test_create_and_delete_table_very_long_name(dynamodb):
+    # In the future, this should work:
+    #create_and_delete_table(dynamodb, 'n' * 255)
+    # But for now, only 222 works:
+    create_and_delete_table(dynamodb, 'n' * 222)
+    # We cannot test the following on DynamoDB because it will succeed
+    # (DynamoDB allows up to 255 bytes)
+    #with pytest.raises(ClientError, match='ValidationException'):
+    #   create_table(dynamodb, 'n' * 223)
+
+# Tests creating a table with an invalid schema should return a
+# ValidationException error.
+def test_create_table_invalid_schema(dynamodb):
+    # The name of the table "created" by this test shouldn't matter, the
+    # creation should not succeed anyway.
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                { 'AttributeName': 'c', 'KeyType': 'HASH' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'p', 'AttributeType': 'S' },
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'p', 'AttributeType': 'S' },
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                { 'AttributeName': 'z', 'KeyType': 'RANGE' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+                { 'AttributeName': 'p', 'AttributeType': 'S' },
+                { 'AttributeName': 'z', 'AttributeType': 'S' }
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'c', 'KeyType': 'HASH' },
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'z', 'AttributeType': 'S' }
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'k', 'KeyType': 'HASH' },
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'k', 'AttributeType': 'Q' }
+            ],
+        )
+
+# Test that trying to create a table that already exists fails in the
+# appropriate way (ResourceInUseException)
+def test_create_table_already_exists(dynamodb, test_table):
+    with pytest.raises(ClientError, match='ResourceInUseException'):
+        create_table(dynamodb, test_table.name)
+
+# Test that BillingMode error path works as expected - only the values
+# PROVISIONED or PAY_PER_REQUEST are allowed. The former requires
+# ProvisionedThroughput to be set, the latter forbids it.
+# If BillingMode is outright missing, it defaults (as original
+# DynamoDB did) to PROVISIONED so ProvisionedThroughput is allowed.
+def test_create_table_billing_mode_errors(dynamodb, test_table):
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(), BillingMode='unknown')
+    # billing mode is case-sensitive
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(), BillingMode='pay_per_request')
+    # PAY_PER_REQUEST cannot come with a ProvisionedThroughput:
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(),
+            BillingMode='PAY_PER_REQUEST', ProvisionedThroughput={'ReadCapacityUnits': 10, 'WriteCapacityUnits': 10})
+    # On the other hand, PROVISIONED requires ProvisionedThroughput:
+    # By the way, ProvisionedThroughput not only needs to appear, it must
+    # have both ReadCapacityUnits and WriteCapacityUnits - but we can't test
+    # this with boto3, because boto3 has its own verification that if
+    # ProvisionedThroughput is given, it must have the correct form.
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(), BillingMode='PROVISIONED')
+    # If BillingMode is completely missing, it defaults to PROVISIONED, so
+    # ProvisionedThroughput is required
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(TableName=test_table_name(),
+            KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+            AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }])
+
+# Our first implementation had a special column name called "attrs" where
+# we stored a map for all non-key columns. If the user tried to name one
+# of the key columns with this same name, the result was a disaster - Scylla
+# goes into a bad state after trying to write data with two updates to same-
+# named columns.
+special_column_name1 = 'attrs'
+special_column_name2 = ':attrs'
+@pytest.fixture(scope="session")
+def test_table_special_column_name(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[
+            { 'AttributeName': special_column_name1, 'KeyType': 'HASH' },
+            { 'AttributeName': special_column_name2, 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+            { 'AttributeName': special_column_name1, 'AttributeType': 'S' },
+            { 'AttributeName': special_column_name2, 'AttributeType': 'S' },
+        ],
+    )
+    yield table
+    table.delete()
+@pytest.mark.xfail(reason="special attrs column not yet hidden correctly")
+def test_create_table_special_column_name(test_table_special_column_name):
+    s = random_string()
+    c = random_string()
+    h = random_string()
+    expected = {special_column_name1: s, special_column_name2: c, 'hello': h}
+    test_table_special_column_name.put_item(Item=expected)
+    got = test_table_special_column_name.get_item(Key={special_column_name1: s, special_column_name2: c}, ConsistentRead=True)['Item']
+    assert got == expected
+
+# Test that all tables we create are listed, and pagination works properly.
+# Note that the DyanamoDB setup we run this against may have hundreds of
+# other tables, for all we know. We just need to check that the tables we
+# created are indeed listed.
+def test_list_tables_paginated(dynamodb, test_table, test_table_s, test_table_b):
+    my_tables_set = {table.name for table in [test_table, test_table_s, test_table_b]}
+    for limit in [1, 2, 3, 4, 50, 100]:
+        print("testing limit={}".format(limit))
+        list_tables_set = set(list_tables(dynamodb, limit))
+        assert my_tables_set.issubset(list_tables_set)
+
+# Test that pagination limit is validated
+def test_list_tables_wrong_limit(dynamodb):
+    # lower limit (min. 1) is imposed by boto3 library checks
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.meta.client.list_tables(Limit=101)

alternator-test/test_update_expression.py

@@ -0,0 +1,854 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the UpdateItem operations with an UpdateExpression parameter
+
+import random
+import string
+import pytest
+from botocore.exceptions import ClientError
+from decimal import Decimal
+from util import random_string
+
+# The simplest test of using UpdateExpression to set a top-level attribute,
+# instead of the older AttributeUpdates parameter.
+# Checks only one "SET" action in an UpdateExpression.
+def test_update_expression_set(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 4}
+
+# An empty UpdateExpression is NOT allowed, and generates a "The expression
+# can not be empty" error. This contrasts with an empty AttributeUpdates which
+# is allowed, and results in the creation of an empty item if it didn't exist
+# yet (see test_empty_update()).
+def test_update_expression_empty(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='')
+
+# A basic test with multiple SET actions in one expression
+def test_update_expression_set_multi(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET x = :val1, y = :val1',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'x': 4, 'y': 4}
+
+# SET can be used to copy an existing attribute to a new one
+def test_update_expression_set_copy(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET b = a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hello'}
+    # Copying an non-existing attribute generates an error
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c = z')
+    # It turns out that attributes to be copied are read before the SET
+    # starts to write, so "SET x = :val1, y = x" does not work...
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET x = :val1, y = x', ExpressionAttributeValues={':val1': 4})
+    # SET z=z does nothing if z exists, or fails if it doesn't
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hello'}
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET z = z')
+    # We can also use name references in either LHS or RHS of SET, e.g.,
+    # SET #one = #two. We need to also take the references used in the RHS
+    # when we want to complain about unused names in ExpressionAttributeNames.
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #one = #two',
+         ExpressionAttributeNames={'#one': 'c', '#two': 'a'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hello', 'c': 'hello'}
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #one = #two',
+             ExpressionAttributeNames={'#one': 'c', '#two': 'a', '#three': 'z'})
+
+# Test for read-before-write action where the value to be read is nested inside a - operator
+def test_update_expression_set_nested_copy(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #n = :two',
+         ExpressionAttributeNames={'#n': 'n'}, ExpressionAttributeValues={':two': 2})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #nn = :seven - #n',
+         ExpressionAttributeNames={'#nn': 'nn', '#n': 'n'}, ExpressionAttributeValues={':seven': 7})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'n': 2, 'nn': 5}
+
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #nnn = :nnn',
+         ExpressionAttributeNames={'#nnn': 'nnn'}, ExpressionAttributeValues={':nnn': [2,4]})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #nnnn = list_append(:val1, #nnn)',
+         ExpressionAttributeNames={'#nnnn': 'nnnn', '#nnn': 'nnn'}, ExpressionAttributeValues={':val1': [1,3]})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'n': 2, 'nn': 5, 'nnn': [2,4], 'nnnn': [1,3,2,4]}
+
+# Test for getting a key value with read-before-write
+def test_update_expression_set_key(test_table_sn):
+    p = random_string()
+    test_table_sn.update_item(Key={'p': p, 'c': 7});
+    test_table_sn.update_item(Key={'p': p, 'c': 7}, UpdateExpression='SET #n = #p',
+         ExpressionAttributeNames={'#n': 'n', '#p': 'p'})
+    test_table_sn.update_item(Key={'p': p, 'c': 7}, UpdateExpression='SET #nn = #c + #c',
+         ExpressionAttributeNames={'#nn': 'nn', '#c': 'c'})
+    assert test_table_sn.get_item(Key={'p': p, 'c': 7}, ConsistentRead=True)['Item'] == {'p': p, 'c': 7, 'n': p, 'nn': 14}
+
+# Simple test for the "REMOVE" action
+def test_update_expression_remove(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hi'}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hi'}
+
+# Demonstrate that although all DynamoDB examples give UpdateExpression
+# action names in uppercase - e.g., "SET", it can actually be any case.
+def test_update_expression_action_case(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET b = :val1', ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 3}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='set b = :val1', ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 4}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='sEt b = :val1', ExpressionAttributeValues={':val1': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 5}
+
+# Demonstrate that whitespace is ignored in UpdateExpression parsing.
+def test_update_expression_action_whitespace(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='set b = :val1', ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 4}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='  set   b=:val1  ', ExpressionAttributeValues={':val1': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 5}
+
+# In UpdateExpression, the attribute name can appear directly in the expression
+# (without a "#placeholder" notation) only if it is a single "token" as
+# determined by DynamoDB's lexical analyzer rules: Such token is composed of
+# alphanumeric characters whose first character must be alphabetic. Other
+# names cause the parser to see multiple tokens, and produce syntax errors.
+def test_update_expression_name_token(test_table_s):
+    p = random_string()
+    # Alphanumeric names starting with an alphabetical character work
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET alnum = :val1', ExpressionAttributeValues={':val1': 1})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['alnum'] == 1
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET Alpha_Numeric_123 = :val1', ExpressionAttributeValues={':val1': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['Alpha_Numeric_123'] == 2
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET A123_ = :val1', ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['A123_'] == 3
+    # But alphanumeric names cannot start with underscore or digits.
+    # DynamoDB's lexical analyzer doesn't recognize them, and produces
+    # a ValidationException looking like:
+    #   Invalid UpdateExpression: Syntax error; token: "_", near: "SET _123"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET _123 = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET _abc = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET 123a = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET 123 = :val1', ExpressionAttributeValues={':val1': 3})
+    # Various other non-alpha-numeric characters, split a token and NOT allowed
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET hi-there = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET hi$there = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET "hithere" = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET !hithere = :val1', ExpressionAttributeValues={':val1': 3})
+
+    # In addition to the literal names, DynamoDB also allows references to any
+    # name, using the "#reference" syntax. It turns out the reference name is
+    # also a token following the rules as above, with one interesting point:
+    # since "#" already started the token, the next character may be any
+    # alphanumeric and doesn't need to be only alphabetical.
+    # Note that the reference target - the actual attribute name - can include
+    # absolutely any characters, and we use silly_name below as an example
+    silly_name = '3can include any character!.#='
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #Alpha_Numeric_123 = :val1', ExpressionAttributeValues={':val1': 4}, ExpressionAttributeNames={'#Alpha_Numeric_123': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 4
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #123a = :val1', ExpressionAttributeValues={':val1': 5}, ExpressionAttributeNames={'#123a': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 5
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #123 = :val1', ExpressionAttributeValues={':val1': 6}, ExpressionAttributeNames={'#123': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 6
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #_ = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#_': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 7
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #hi-there = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#hi-there': silly_name})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #!hi = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#!hi': silly_name})
+    # Just a "#" is not enough as a token. Interestingly, DynamoDB will
+    # find the bad name in ExpressionAttributeNames before it actually tries
+    # to parse UpdateExpression, but we can verify the parse fails too by
+    # using a valid but irrelevant name in ExpressionAttributeNames:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET # = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#': silly_name})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET # = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#a': silly_name})
+
+    # There is also the value references, ":reference", for the right-hand
+    # side of an assignment. These have similar naming rules like "#reference".
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :Alpha_Numeric_123', ExpressionAttributeValues={':Alpha_Numeric_123': 8})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 8
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :123a', ExpressionAttributeValues={':123a': 9})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 9
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :123', ExpressionAttributeValues={':123': 10})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 10
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :_', ExpressionAttributeValues={':_': 11})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 11
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :hi!there', ExpressionAttributeValues={':hi!there': 12})
+    # Just a ":" is not enough as a token.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :', ExpressionAttributeValues={':': 7})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :', ExpressionAttributeValues={':a': 7})
+    # Trying to use a :reference on the left-hand side of an assignment will
+    # not work. In DynamoDB, it's a different type of token (and generates
+    # syntax error).
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET :a = :b', ExpressionAttributeValues={':a': 1, ':b': 2})
+
+# Multiple actions are allowed in one expression, but actions are divided
+# into clauses (SET, REMOVE, DELETE, ADD) and each of those can only appear
+# once.
+def test_update_expression_multi(test_table_s):
+    p = random_string()
+    # We can have two SET actions in one SET clause:
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1, b = :val2', ExpressionAttributeValues={':val1': 1, ':val2': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2}
+    # But not two SET clauses - we get error "The "SET" section can only be used once in an update expression"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1 SET b = :val2', ExpressionAttributeValues={':val1': 1, ':val2': 2})
+    # We can have a REMOVE and a SET clause (note no comma between clauses):
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a SET b = :val2', ExpressionAttributeValues={':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 3}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c = :val2 REMOVE b', ExpressionAttributeValues={':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'c': 3}
+    # The same clause (e.g., SET) cannot be used twice, even if interleaved with something else
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1 REMOVE a SET b = :val2', ExpressionAttributeValues={':val1': 1, ':val2': 2})
+
+# Trying to modify the same item twice in the same update is forbidden.
+# For "SET a=:v REMOVE a" DynamoDB says: "Invalid UpdateExpression: Two
+# document paths overlap with each other; must remove or rewrite one of
+# these paths; path one: [a], path two: [a]". 
+# It is actually good for Scylla that such updates are forbidden, because had
+# we allowed "SET a=:v REMOVE a" the result would be surprising - because data
+# wins over a delete with the same timestamp, so "a" would be set despite the
+# REMOVE command appearing later in the command line.
+def test_update_expression_multi_overlap(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+    # Neither "REMOVE a SET a = :v" nor "SET a = :v REMOVE a" are allowed:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a SET a = :v', ExpressionAttributeValues={':v': 'hi'})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :v REMOVE a', ExpressionAttributeValues={':v': 'yo'})
+    # It's also not allowed to set a twice in the same clause
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :v1, a = :v2', ExpressionAttributeValues={':v1': 'yo', ':v2': 'he'})
+    # Obviously, the paths are compared after the name references are evaluated
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #a1 = :v1, #a2 = :v2', ExpressionAttributeValues={':v1': 'yo', ':v2': 'he'}, ExpressionAttributeNames={'#a1': 'a', '#a2': 'a'})
+
+# The problem isn't just with identical paths - we can't modify two paths that
+# "overlap" in the sense that one is the ancestor of the other.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_multi_overlap_nested(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*overlap'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1, a.b = :val2',
+            ExpressionAttributeValues={':val1': {'b': 7}, ':val2': 'there'})
+    test_table_s.put_item(Item={'p': p, 'a': {'b': {'c': 2}}})
+    with pytest.raises(ClientError, match='ValidationException.*overlap'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.b = :val1, a.b.c = :val2',
+            ExpressionAttributeValues={':val1': 'hi', ':val2': 'there'})
+
+# In the previous test we saw that *modifying* the same item twice in the same
+# update is forbidden; But it is allowed to *read* an item in the same update
+# that also modifies it, and we check this here.
+def test_update_expression_multi_with_copy(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+    # "REMOVE a SET b = a" works: as noted in test_update_expression_set_copy()
+    # the value of 'a' is read before the actual REMOVE operation happens.
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a SET b = a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c = b REMOVE b')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'c': 'hello'}
+
+
+# Test case where a :val1 is referenced, without being defined
+def test_update_expression_set_missing_value(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1',
+            ExpressionAttributeValues={':val2': 4})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1')
+
+# It is forbidden for ExpressionAttributeValues to contain values not used
+# by the expression. DynamoDB produces an error like: "Value provided in
+# ExpressionAttributeValues unused in expressions: keys: {:val1}"
+def test_update_expression_spurious_value(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1',
+            ExpressionAttributeValues={':val1': 3, ':val2': 4})
+
+# Test case where a #name is referenced, without being defined
+def test_update_expression_set_missing_name(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET #name = :val1',
+            ExpressionAttributeValues={':val2': 4},
+            ExpressionAttributeNames={'#wrongname': 'hello'})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET #name = :val1',
+            ExpressionAttributeValues={':val2': 4})
+
+# It is forbidden for ExpressionAttributeNames to contain names not used
+# by the expression. DynamoDB produces an error like: "Value provided in
+# ExpressionAttributeNames unused in expressions: keys: {#b}"
+def test_update_expression_spurious_name(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #a = :val1',
+            ExpressionAttributeNames={'#a': 'hello', '#b': 'hi'},
+            ExpressionAttributeValues={':val1': 3, ':val2': 4})
+
+# Test that the key attributes (hash key or sort key) cannot be modified
+# by an update
+def test_update_expression_cannot_modify_key(test_table):
+    p = random_string()
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='SET p = :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='SET c = :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='REMOVE p')
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='REMOVE c')
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='ADD p :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='ADD c :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='DELETE p :val1', ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='DELETE c :val1', ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    # As sanity check, verify we *can* modify a non-key column
+    test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='SET a = :val1', ExpressionAttributeValues={':val1': 4})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 4}
+    test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='REMOVE a')
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c}
+
+# Test that trying to start an expression with some nonsense like HELLO
+# instead of SET, REMOVE, ADD or DELETE, fails.
+def test_update_expression_non_existant_clause(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='HELLO b = :val1',
+            ExpressionAttributeValues={':val1': 4})
+
+# Test support for "SET a = :val1 + :val2", "SET a = :val1 - :val2"
+# Only exactly these combinations work - e.g., it's a syntax error to
+# try to add three. Trying to add a string fails.
+def test_update_expression_plus_basic(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 + :val2',
+        ExpressionAttributeValues={':val1': 4, ':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 7}
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 - :val2',
+        ExpressionAttributeValues={':val1': 5, ':val2': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 3}
+    # Only the addition of exactly two values is supported!
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1 + :val2 + :val3',
+            ExpressionAttributeValues={':val1': 4, ':val2': 3, ':val3': 2})
+    # Only numeric values can be added - other things like strings or lists
+    # cannot be added, and we get an error like "Incorrect operand type for
+    # operator or function; operator or function: +, operand type: S".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1 + :val2',
+            ExpressionAttributeValues={':val1': 'dog', ':val2': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1 + :val2',
+            ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['1', '2']})
+
+# While most of the Alternator code just saves high-precision numbers
+# unchanged, the "+" and "-" operations need to calculate with them, and
+# we should check the calculation isn't done with some lower-precision
+# representation, e.g., double
+def test_update_expression_plus_precision(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 + :val2',
+        ExpressionAttributeValues={':val1': Decimal("1"), ':val2': Decimal("10000000000000000000000")})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': Decimal("10000000000000000000001")}
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val2 - :val1',
+        ExpressionAttributeValues={':val1': Decimal("1"), ':val2': Decimal("10000000000000000000000")})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': Decimal("9999999999999999999999")}
+
+# Test support for "SET a = b + :val2" et al., i.e., a version of the
+# above test_update_expression_plus_basic with read before write.
+def test_update_expression_plus_rmw(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = a + :val1',
+        ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 5
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = :val1 + a',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 9
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 + a',
+        ExpressionAttributeValues={':val1': 1})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 10
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = b + a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 19
+
+# Test the list_append() function in SET, for the most basic use case of
+# concatenating two value references. Because this is the first test of
+# functions in SET, we also test some generic features of how functions
+# are parsed.
+def test_update_expression_list_append_basic(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(:val1, :val2)',
+        ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': ['hi', 7]})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': [4, 'hello', 'hi', 7]}
+    # Unlike the operation name "SET", function names are case-sensitive!
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = LIST_APPEND(:val1, :val2)',
+            ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': ['hi', 7]})
+    # As usual, spaces are ignored by the parser
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(:val1, :val2)',
+        ExpressionAttributeValues={':val1': ['a'], ':val2': ['b']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['a', 'b']}
+    # The list_append function only allows two parameters. The parser can
+    # correctly parse fewer or more, but then an error is generated: "Invalid
+    # UpdateExpression: Incorrect number of operands for operator or function;
+    # operator or function: list_append, number of operands: 1".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(:val1)',
+            ExpressionAttributeValues={':val1': ['a']})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(:val1, :val2, :val3)',
+            ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': [7], ':val3': ['a']})
+    # If list_append is used on value which isn't a list, we get
+    # error: "Invalid UpdateExpression: Incorrect operand type for operator
+    # or function; operator or function: list_append, operand type: S"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(:val1, :val2)',
+            ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': 'hi'})
+
+# Additional list_append() tests, also using attribute paths as parameters
+# (i.e., read-modify-write).
+def test_update_expression_list_append(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = :val1',
+        ExpressionAttributeValues={':val1': ['hi', 2]})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] ==['hi', 2]
+    # Often, list_append is used to append items to a list attribute
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(a, :val1)',
+        ExpressionAttributeValues={':val1': [4, 'hello']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['hi', 2, 4, 'hello']
+    # But it can also be used to just concatenate in other ways:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(:val1, a)',
+        ExpressionAttributeValues={':val1': ['dog']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['dog', 'hi', 2, 4, 'hello']
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = list_append(a, :val1)',
+        ExpressionAttributeValues={':val1': ['cat']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == ['dog', 'hi', 2, 4, 'hello', 'cat']
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET c = list_append(a, b)')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == ['dog', 'hi', 2, 4, 'hello', 'dog', 'hi', 2, 4, 'hello', 'cat']
+    # As usual, #references are allowed instead of inline names:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET #name1 = list_append(#name2,:val1)',
+        ExpressionAttributeValues={':val1': [8]},
+        ExpressionAttributeNames={'#name1': 'a', '#name2': 'a'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['dog', 'hi', 2, 4, 'hello', 8]
+
+# Test the "if_not_exists" function in SET
+# The test also checks additional features of function-call parsing.
+def test_update_expression_if_not_exists(test_table_s):
+    p = random_string()
+    # Since attribute a doesn't exist, set it:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = if_not_exists(a, :val1)',
+        ExpressionAttributeValues={':val1': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    # Now the attribute does exist, so set does nothing:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = if_not_exists(a, :val1)',
+        ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    # if_not_exists can also be used to check one attribute and set another,
+    # but note that if_not_exists(a, :val) means a's value if it exists,
+    # otherwise :val!
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(c, :val1)',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 4
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(c, :val1)',
+        ExpressionAttributeValues={':val1': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 5
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(a, :val1)',
+        ExpressionAttributeValues={':val1': 6})
+    # note how because 'a' does exist, its value is copied, overwriting b's
+    # value:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 2
+    # The parser expects function parameters to be value references, paths,
+    # or nested call to functions. Other crap will cause syntax errors:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(non@sense, :val1)',
+            ExpressionAttributeValues={':val1': 6})
+    # if_not_exists() requires that the first parameter be a path. However,
+    # the parser doesn't know this, and allows for a function parameter
+    # also a value reference or a function call. If try one of these other
+    # things the parser succeeds, but we get a later error, looking like:
+    # "Invalid UpdateExpression: Operator or function requires a document
+    # path; operator or function: if_not_exists"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(if_not_exists(a, :val2), :val1)',
+            ExpressionAttributeValues={':val1': 6, ':val2': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(:val2, :val1)',
+            ExpressionAttributeValues={':val1': 6, ':val2': 3})
+    # Surprisingly, if the wrong argument is a :val value reference, the
+    # parser first tries to look it up in ExpressionAttributeValues (and
+    # fails if it's missing), before realizing any value reference would be
+    # wrong... So the following fails like the above does - but with a
+    # different error message (which we do not check here): "Invalid
+    # UpdateExpression: An expression attribute value used in expression
+    # is not defined; attribute value: :val2"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(:val2, :val1)',
+            ExpressionAttributeValues={':val1': 6})
+
+# When the expression parser parses a function call f(value, value), each
+# value may itself be a function call - ad infinitum. So expressions like
+# list_append(if_not_exists(a, :val1), :val2) are legal and so is deeper
+# nesting.
+@pytest.mark.xfail(reason="for unknown reason, DynamoDB does not allow nesting list_append")
+def test_update_expression_function_nesting(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(if_not_exists(a, :val1), :val2)',
+            ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['cat', 'dog']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['a', 'b', 'cat', 'dog']
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(if_not_exists(a, :val1), :val2)',
+            ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['1', '2']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['a', 'b', 'cat', 'dog', '1', '2']
+    # I don't understand why the following expression isn't accepted, but it
+    # isn't! It produces a "Invalid UpdateExpression: The function is not
+    # allowed to be used this way in an expression; function: list_append".
+    # I don't know how to explain it. In any case, the *parsing* works -
+    # this is not a syntax error - the failure is in some verification later.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(list_append(:val1, :val2), :val3)',
+                ExpressionAttributeValues={':val1': ['a'], ':val2': ['1'], ':val3': ['hi']})
+    # Ditto, the following passes the parser but fails some later check with
+    # the same error message as above.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(list_append(list_append(:val1, :val2), :val3), :val4)',
+                ExpressionAttributeValues={':val1': ['a'], ':val2': ['1'], ':val3': ['hi'], ':val4': ['yo']})
+
+# Verify how in SET expressions, "+" (or "-") nests with functions.
+# We discover that f(x)+f(y) works but f(x+y) does NOT (results in a syntax
+# error on the "+"). This means that the parser has two separate rules:
+# 1.  set_action: SET path = value + value
+# 2.  value: VALREF | NAME | NAME (value, ...)
+def test_update_expression_function_plus_nesting(test_table_s):
+    p = random_string()
+    # As explained above, this - with "+" outside the expression, works:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(b, :val1)+:val2',
+            ExpressionAttributeValues={':val1': 2, ':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 5
+    # ...but this - with the "+" inside an expression parameter, is a syntax
+    # error:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET c = if_not_exists(c, :val1+:val2)',
+                ExpressionAttributeValues={':val1': 5, ':val2': 4})
+
+# This test tries to use an undefined function "f". This, obviously, fails,
+# but where we to actually print the error we would see "Invalid
+# UpdateExpression: Invalid function name; function: f". Not a syntax error.
+# This means that the parser accepts any alphanumeric name as a function
+# name, and only later use of this function fails because it's not one of
+# the supported file.
+def test_update_expression_unknown_function(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*f'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = f(b,c,d)')
+    with pytest.raises(ClientError, match='ValidationException.*f123_hi'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = f123_hi(b,c,d)')
+    # Just like unreferenced column names parsed by the DynamoDB parser,
+    # function names must also start with an alphabetic character. Trying
+    # to use _f as a function name will result with an actual syntax error,
+    # on the "_" token.
+    with pytest.raises(ClientError, match='ValidationException.*yntax error'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = _f(b,c,d)')
+
+# Test "ADD" operation for numbers
+def test_update_expression_add_numbers(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 3, 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 7
+    # If the value to be added isn't a number, we get an error like "Invalid
+    # UpdateExpression: Incorrect operand type for operator or function;
+    # operator: ADD, operand type: STRING".
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='ADD a :val1',
+            ExpressionAttributeValues={':val1': 'hello'})
+    # Similarly, if the attribute we're adding to isn't a number, we get an
+    # error like "An operand in the update expression has an incorrect data
+    # type"
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='ADD b :val1',
+            ExpressionAttributeValues={':val1': 1})
+
+# Test "ADD" operation for sets
+def test_update_expression_add_sets(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': set(['dog', 'cat', 'mouse']), 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': set(['pig'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog', 'cat', 'mouse', 'pig'])
+
+    # TODO: right now this test won't detect duplicated values in the returned result,
+    # because boto3 parses a set out of the returned JSON anyway. This check should leverage
+    # lower level API (if exists) to ensure that the JSON contains no duplicates
+    # in the set representation. It has been verified manually.
+    test_table_s.put_item(Item={'p': p, 'a': set(['beaver', 'lynx', 'coati']), 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': set(['coati', 'beaver', 'badger'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['beaver', 'badger', 'lynx', 'coati'])
+
+    # The value to be added needs to be a set of the same type - it can't
+    # be a single element or anything else. If the value has the wrong type,
+    # we get an error like "Invalid UpdateExpression: Incorrect operand type
+    # for operator or function; operator: ADD, operand type: STRING".
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='ADD a :val1',
+            ExpressionAttributeValues={':val1': 'hello'})
+
+# Test "DELETE" operation for sets
+def test_update_expression_delete_sets(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': set(['dog', 'cat', 'mouse']), 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='DELETE a :val1',
+        ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog'])
+    # Deleting an element not present in the set is not an error - it just
+    # does nothing
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='DELETE a :val1',
+        ExpressionAttributeValues={':val1': set(['pig'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog'])
+    # The value to be deleted must be a set of the same type - it can't
+    # be a single element or anything else. If the value has the wrong type,
+    # we get an error like "Invalid UpdateExpression: Incorrect operand type
+    # for operator or function; operator: DELETE, operand type: STRING".
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='DELETE a :val1',
+            ExpressionAttributeValues={':val1': 'hello'})
+
+######## Tests for paths and nested attribute updates:
+
+# A dot inside a name in ExpressionAttributeNames is a literal dot, and
+# results in a top-level attribute with an actual dot in its name - not
+# a nested attribute path.
+def test_update_expression_dot_in_name(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #a = :val1',
+        ExpressionAttributeValues={':val1': 3},
+        ExpressionAttributeNames={'#a': 'a.b'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a.b': 3}
+
+# A basic test for direct update of a nested attribute: One of the top-level
+# attributes is itself a document, and we update only one of that document's
+# nested attributes.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_attribute_dot(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c = :val1',
+        ExpressionAttributeValues={':val1': 7})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 7}, 'd': 5}
+    # Of course we can also add new nested attributes, not just modify
+    # existing ones:
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.d = :val1',
+        ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 7, 'd': 3}, 'd': 5}
+
+# Similar test, for a list: one of the top-level attributes is a list, we
+# can update one of its items.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_attribute_index(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': ['one', 'two', 'three']})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[1] = :val1',
+        ExpressionAttributeValues={':val1': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['one', 'hello', 'three']}
+
+# Test that just like happens in top-level attributes, also in nested
+# attributes, setting them replaces the old value - potentially an entire
+# nested document, by the whole value (which may have a different type)
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_different_type(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': {'one': 1, 'two': 2}}})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c = :val1',
+        ExpressionAttributeValues={':val1': 7})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 7}}
+
+# Yet another test of a nested attribute update. This one uses deeper
+# level of nesting (dots and indexes), adds #name references to the mix.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_deep(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': ['hi', {'x': {'y': [3, 5, 7]}}]}})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c[1].#name.y[1] = :val1',
+        ExpressionAttributeValues={':val1': 9}, ExpressionAttributeNames={'#name': 'x'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] ==  {'b': 3, 'c': ['hi', {'x': {'y': [3, 9, 7]}}]}
+    # A deep path can also appear on the right-hand-side of an assignment
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.z = a.c[1].#name.y[1]',
+        ExpressionAttributeNames={'#name': 'x'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a']['z'] ==  9
+
+# A REMOVE operation can be used to remove nested attributes, and also
+# individual list items.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_remove(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': ['hi', {'x': {'y': [3, 5, 7]}, 'q': 2}]}})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a.c[1].x.y[1], a.c[1].q')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] ==  {'b': 3, 'c': ['hi', {'x': {'y': [3, 7]}}]}
+
+# The DynamoDB documentation specifies: "When you use SET to update a list
+# element, the contents of that element are replaced with the new data that
+# you specify. If the element does not already exist, SET will append the
+# new element at the end of the list."
+# So if we take a three-element list a[7], and set a[7], the new element
+# will be put at the end of the list, not position 7 specifically.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_nested_attribute_update_array_out_of_bounds(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': ['one', 'two', 'three']})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[7] = :val1',
+        ExpressionAttributeValues={':val1': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['one', 'two', 'three', 'hello']}
+    # The DynamoDB documentation also says: "If you add multiple elements
+    # in a single SET operation, the elements are sorted in order by element
+    # number.
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[84] = :val1, a[37] = :val2',
+        ExpressionAttributeValues={':val1': 'a1', ':val2': 'a2'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['one', 'two', 'three', 'hello', 'a2', 'a1']}
+
+# Test what happens if we try to write to a.b, which would only make sense if
+# a were a nested document, but a doesn't exist, or exists and is NOT a nested
+# document but rather a scalar or list or something.
+# DynamoDB actually detects this case and prints an error:
+#   ClientError: An error occurred (ValidationException) when calling the
+#   UpdateItem operation: The document path provided in the update expression
+#   is invalid for update
+# Because Scylla doesn't read before write, it cannot detect this as an error,
+# so we'll probably want to allow for that possibility as well.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_nested_attribute_update_bad_path_dot(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': ['hi']})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c = :val1',
+            ExpressionAttributeValues={':val1': 7})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET b.c = :val1',
+            ExpressionAttributeValues={':val1': 7})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c.c = :val1',
+            ExpressionAttributeValues={':val1': 7})
+
+
+# Similarly for other types of bad paths - using [0] on something which
+# isn't an array,
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_nested_attribute_update_bad_path_array(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[0] = :val1',
+            ExpressionAttributeValues={':val1': 7})

alternator-test/util.py

@@ -0,0 +1,121 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Various utility functions which are useful for multiple tests
+
+import string
+import random
+import collections
+import time
+
+def random_string(length=10, chars=string.ascii_uppercase + string.digits):
+    return ''.join(random.choice(chars) for x in range(length))
+
+def random_bytes(length=10):
+    return bytearray(random.getrandbits(8) for _ in range(length))
+
+# Utility functions for scan and query into an array of items:
+# TODO: add to full_scan and full_query by default ConsistentRead=True, as
+# it's not useful for tests without it!
+def full_scan(table, **kwargs):
+    response = table.scan(**kwargs)
+    items = response['Items']
+    while 'LastEvaluatedKey' in response:
+        response = table.scan(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
+        items.extend(response['Items'])
+    return items
+
+# Utility function for fetching the entire results of a query into an array of items
+def full_query(table, **kwargs):
+    response = table.query(**kwargs)
+    items = response['Items']
+    while 'LastEvaluatedKey' in response:
+        response = table.query(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
+        items.extend(response['Items'])
+    return items
+
+# To compare two lists of items (each is a dict) without regard for order,
+# "==" is not good enough because it will fail if the order is different.
+# The following function, multiset() converts the list into a multiset
+# (set with duplicates) where order doesn't matter, so the multisets can
+# be compared.
+
+def freeze(item):
+    if isinstance(item, dict):
+        return frozenset((key, freeze(value)) for key, value in item.items())
+    elif isinstance(item, list):
+        return tuple(freeze(value) for value in item)
+    return item
+
+def multiset(items):
+    return collections.Counter([freeze(item) for item in items])
+
+
+test_table_prefix = 'alternator_test_'
+def test_table_name():
+    current_ms = int(round(time.time() * 1000))
+    # In the off chance that test_table_name() is called twice in the same millisecond...
+    if test_table_name.last_ms >= current_ms:
+        current_ms = test_table_name.last_ms + 1
+    test_table_name.last_ms = current_ms
+    return test_table_prefix + str(current_ms)
+test_table_name.last_ms = 0
+
+def create_test_table(dynamodb, **kwargs):
+    name = test_table_name()
+    print("fixture creating new table {}".format(name))
+    table = dynamodb.create_table(TableName=name,
+        BillingMode='PAY_PER_REQUEST', **kwargs)
+    waiter = table.meta.client.get_waiter('table_exists')
+    # recheck every second instead of the default, lower, frequency. This can
+    # save a few seconds on AWS with its very slow table creation, but can
+    # more on tests on Scylla with its faster table creation turnaround.
+    waiter.config.delay = 1
+    waiter.config.max_attempts = 200
+    waiter.wait(TableName=name)
+    return table
+
+# DynamoDB's ListTables request returns up to a single page of table names
+# (e.g., up to 100) and it is up to the caller to call it again and again
+# to get the next page. This is a utility function which calls it repeatedly
+# as much as necessary to get the entire list.
+# We deliberately return a list and not a set, because we want the caller
+# to be able to recognize bugs in ListTables which causes the same table
+# to be returned twice.
+def list_tables(dynamodb, limit=100):
+    ret = []
+    pos = None
+    while True:
+        if pos:
+            page = dynamodb.meta.client.list_tables(Limit=limit, ExclusiveStartTableName=pos);
+        else:
+            page = dynamodb.meta.client.list_tables(Limit=limit);
+        results = page.get('TableNames', None)
+        assert(results)
+        ret = ret + results
+        newpos = page.get('LastEvaluatedTableName', None)
+        if not newpos:
+            break;
+        # It doesn't make sense for Dynamo to tell us we need more pages, but
+        # not send anything in *this* page!
+        assert len(results) > 0
+        assert newpos != pos
+        # Note that we only checked that we got back tables, not that we got
+        # any new tables not already in ret. So a buggy implementation might
+        # still cause an endless loop getting the same tables again and again.
+        pos = newpos
+    return ret

alternator/CMakeLists.txt

@@ -1,42 +0,0 @@
-include(generate_cql_grammar)
-generate_cql_grammar(
-  GRAMMAR expressions.g
-  SOURCES cql_grammar_srcs)
-
-add_library(alternator STATIC)
-target_sources(alternator
-  PRIVATE
-    controller.cc
-    server.cc
-    executor.cc
-    stats.cc
-    serialization.cc
-    expressions.cc
-    conditions.cc
-    auth.cc
-    streams.cc
-    consumed_capacity.cc
-    ttl.cc
-    parsed_expression_cache.cc
-    http_compression.cc
-    ${cql_grammar_srcs})
-target_include_directories(alternator
-  PUBLIC
-    ${CMAKE_SOURCE_DIR}
-    ${CMAKE_BINARY_DIR}
-  PRIVATE
-    ${RAPIDJSON_INCLUDE_DIRS})
-target_link_libraries(alternator
-  PUBLIC
-    Seastar::seastar
-    xxHash::xxhash
-  PRIVATE
-    cql3
-    idl
-    absl::headers)
-
-if (Scylla_USE_PRECOMPILED_HEADER_USE)
-  target_precompile_headers(alternator REUSE_FROM scylla-precompiled-header)
-endif()
-check_headers(check-headers alternator
-  GLOB_RECURSE ${CMAKE_CURRENT_SOURCE_DIR}/*.hh)

alternator/auth.cc

@@ -1,70 +1,146 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "alternator/error.hh"
-#include "auth/common.hh"
-#include "utils/log.hh"
+#include "log.hh"
 #include <string>
 #include <string_view>
+#include <gnutls/crypto.h>
+#include <seastar/util/defer.hh>
+#include "hashers.hh"
+#include "bytes.hh"
 #include "alternator/auth.hh"
 #include <fmt/format.h>
-#include "db/consistency_level_type.hh"
-#include "db/system_keyspace.hh"
-#include "service/storage_proxy.hh"
-#include "alternator/executor.hh"
-#include "cql3/selection/selection.hh"
-#include "cql3/result_set.hh"
-#include "types/types.hh"
-#include <seastar/core/coroutine.hh>
+#include "auth/common.hh"
+#include "auth/password_authenticator.hh"
+#include "auth/roles-metadata.hh"
+#include "cql3/query_processor.hh"
+#include "cql3/untyped_result_set.hh"
 
 namespace alternator {
 
 static logging::logger alogger("alternator-auth");
 
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username) {
-    schema_ptr schema = proxy.data_dictionary().find_schema(db::system_keyspace::NAME, "roles");
-    partition_key pk = partition_key::from_single_value(*schema, utf8_type->decompose(username));
-    dht::partition_range_vector partition_ranges{dht::partition_range(dht::decorate_key(*schema, pk))};
-    std::vector<query::clustering_range> bounds{query::clustering_range::make_open_ended_both_sides()};
-    const column_definition* salted_hash_col = schema->get_column_definition(bytes("salted_hash"));
-    const column_definition* can_login_col = schema->get_column_definition(bytes("can_login"));
-    if (!salted_hash_col || !can_login_col) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("Credentials cannot be fetched for: {}", username)));
+static hmac_sha256_digest hmac_sha256(std::string_view key, std::string_view msg) {
+    hmac_sha256_digest digest;
+    int ret = gnutls_hmac_fast(GNUTLS_MAC_SHA256, key.data(), key.size(), msg.data(), msg.size(), digest.data());
+    if (ret) {
+        throw std::runtime_error(fmt::format("Computing HMAC failed ({}): {}", ret, gnutls_strerror(ret)));
     }
-    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col, can_login_col});
-    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id, can_login_col->id}, selection->get_query_options());
-    auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice,
-            proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
-    auto cl = db::consistency_level::LOCAL_ONE;
+    return digest;
+}
 
-    service::client_state client_state{service::client_state::internal_tag()};
-    service::storage_proxy::coordinator_query_result qr = co_await proxy.query(schema, std::move(command), std::move(partition_ranges), cl,
-            service::storage_proxy::coordinator_query_options(executor::default_timeout(), empty_service_permit(), client_state));
+static hmac_sha256_digest get_signature_key(std::string_view key, std::string_view date_stamp, std::string_view region_name, std::string_view service_name) {
+    auto date = hmac_sha256("AWS4" + std::string(key), date_stamp);
+    auto region = hmac_sha256(std::string_view(date.data(), date.size()), region_name);
+    auto service = hmac_sha256(std::string_view(region.data(), region.size()), service_name);
+    auto signing = hmac_sha256(std::string_view(service.data(), service.size()), "aws4_request");
+    return signing;
+}
 
-    cql3::selection::result_set_builder builder(*selection, gc_clock::now());
-    query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
+static std::string apply_sha256(std::string_view msg) {
+    sha256_hasher hasher;
+    hasher.update(msg.data(), msg.size());
+    return to_hex(hasher.finalize());
+}
 
-    auto result_set = builder.build();
-    if (result_set->empty()) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("User not found: {}", username)));
+static std::string format_time_point(db_clock::time_point tp) {
+    time_t time_point_repr = db_clock::to_time_t(tp);
+    std::string time_point_str;
+    time_point_str.resize(17);
+    // strftime prints the terminating null character as well
+    std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", std::gmtime(&time_point_repr));
+    time_point_str.resize(16);
+    return time_point_str;
+}
+
+void check_expiry(std::string_view signature_date) {
+    //FIXME: The default 15min can be changed with X-Amz-Expires header - we should honor it
+    std::string expiration_str = format_time_point(db_clock::now() - 15min);
+    std::string validity_str = format_time_point(db_clock::now() + 15min);
+    if (signature_date < expiration_str) {
+        throw api_error("InvalidSignatureException",
+                fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
+                signature_date, expiration_str));
     }
-    const auto& result = result_set->rows().front();
-    bool can_login = result[1] && value_cast<bool>(boolean_type->deserialize(*result[1]));
-    if (!can_login) {
-        // This is a valid role name, but has "login=False" so should not be
-        // usable for authentication (see #19735).
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("Role {} has login=false so cannot be used for login", username)));
+    if (signature_date > validity_str) {
+        throw api_error("InvalidSignatureException",
+                fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
+                signature_date, validity_str));
     }
-    const managed_bytes_opt& salted_hash = result.front();
-    if (!salted_hash) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(fmt::format("No password found for user: {}", username)));
+}
+
+std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
+        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
+        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string) {
+    auto amz_date_it = signed_headers_map.find("x-amz-date");
+    if (amz_date_it == signed_headers_map.end()) {
+        throw api_error("InvalidSignatureException", "X-Amz-Date header is mandatory for signature verification");
     }
-    co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
+    std::string_view amz_date = amz_date_it->second;
+    check_expiry(amz_date);
+    std::string_view datestamp = amz_date.substr(0, 8);
+    if (datestamp != orig_datestamp) {
+        throw api_error("InvalidSignatureException",
+                format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
+                        orig_datestamp, datestamp));
+    }
+    std::string_view canonical_uri = "/";
+
+    std::stringstream canonical_headers;
+    for (const auto& header : signed_headers_map) {
+        canonical_headers << fmt::format("{}:{}", header.first, header.second) << '\n';
+    }
+
+    std::string payload_hash = apply_sha256(body_content);
+    std::string canonical_request = fmt::format("{}\n{}\n{}\n{}\n{}\n{}", method, canonical_uri, query_string, canonical_headers.str(), signed_headers_str, payload_hash);
+
+    std::string_view algorithm = "AWS4-HMAC-SHA256";
+    std::string credential_scope = fmt::format("{}/{}/{}/aws4_request", datestamp, region, service);
+    std::string string_to_sign = fmt::format("{}\n{}\n{}\n{}", algorithm, amz_date, credential_scope,  apply_sha256(canonical_request));
+
+    hmac_sha256_digest signing_key = get_signature_key(secret_access_key, datestamp, region, service);
+    hmac_sha256_digest signature = hmac_sha256(std::string_view(signing_key.data(), signing_key.size()), string_to_sign);
+
+    return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
+}
+
+future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username) {
+    static const sstring query = format("SELECT salted_hash FROM {} WHERE {} = ?",
+            auth::meta::roles_table::qualified_name(), auth::meta::roles_table::role_col_name);
+
+    auto cl = auth::password_authenticator::consistency_for_user(username);
+    auto timeout = auth::internal_distributed_timeout_config();
+    return qp.process(query, cl, timeout, {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
+        auto res = f.get0();
+        auto salted_hash = std::optional<sstring>();
+        if (res->empty()) {
+            throw api_error("UnrecognizedClientException", fmt::format("User not found: {}", username));
+        }
+        salted_hash = res->one().get_opt<sstring>("salted_hash");
+        if (!salted_hash) {
+            throw api_error("UnrecognizedClientException", fmt::format("No password found for user: {}", username));
+        }
+        return make_ready_future<std::string>(*salted_hash);
+    });
 }
 
 }

alternator/auth.hh

@@ -1,25 +1,46 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include <string>
+#include <string_view>
+#include <array>
+#include "gc_clock.hh"
 #include "utils/loading_cache.hh"
-#include "auth/service.hh"
 
-namespace service {
-class storage_proxy;
+namespace cql3 {
+class query_processor;
 }
 
 namespace alternator {
 
-using key_cache = utils::loading_cache<std::string, std::string, 1>;
+using hmac_sha256_digest = std::array<char, 32>;
 
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username);
+using key_cache = utils::loading_cache<std::string, std::string>;
+
+std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
+        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
+        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string);
+
+future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username);
 
 }

alternator/base64.cc

@@ -0,0 +1,111 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+// The DynamoAPI dictates that "binary" (a.k.a. "bytes" or "blob") values
+// be encoded in the JSON API as base64-encoded strings. This is code to
+// convert byte arrays to base64-encoded strings, and back.
+
+#include "base64.hh"
+
+#include <ctype.h>
+
+
+// Arrays for quickly converting to and from an integer between 0 and 63,
+// and the character used in base64 encoding to represent it.
+static class base64_chars {
+public:
+    static constexpr const char* to =
+            "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+    int8_t from[255];
+    base64_chars() {
+        static_assert(strlen(to) == 64);
+        for (int i = 0; i < 255; i++) {
+            from[i] = 255; // signal invalid character
+        }
+        for (int i = 0; i < 64; i++) {
+            from[(unsigned) to[i]] = i;
+        }
+    }
+} base64_chars;
+
+std::string base64_encode(bytes_view in) {
+    std::string ret;
+    ret.reserve(((4 * in.size() / 3) + 3) & ~3);
+    int i = 0;
+    unsigned char chunk3[3]; // chunk of input
+    for (auto byte : in) {
+        chunk3[i++] = byte;
+        if (i == 3) {
+            ret += base64_chars.to[ (chunk3[0] & 0xfc) >> 2 ];
+            ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
+            ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
+            ret += base64_chars.to[ chunk3[2] & 0x3f ];
+            i = 0;
+        }
+    }
+    if (i) {
+        // i can be 1 or 2.
+        for(int j = i; j < 3; j++)
+            chunk3[j] = '\0';
+        ret += base64_chars.to[ ( chunk3[0] & 0xfc) >> 2 ];
+        ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
+        if (i == 2) {
+            ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
+        } else {
+            ret += '=';
+        }
+        ret += '=';
+    }
+    return ret;
+}
+
+bytes base64_decode(std::string_view in) {
+    int i = 0;
+    int8_t chunk4[4]; // chunk of input, each byte converted to 0..63;
+    std::string ret;
+    ret.reserve(in.size() * 3 / 4);
+    for (unsigned char c : in) {
+        uint8_t dc = base64_chars.from[c];
+        if (dc == 255) {
+            // Any unexpected character, include the "=" character usually
+            // used for padding, signals the end of the decode.
+            break;
+        }
+        chunk4[i++] = dc;
+        if (i == 4) {
+            ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
+            ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
+            ret += ((chunk4[2] & 0x3) << 6) + chunk4[3];
+            i = 0;
+        }
+    }
+    if (i) {
+        // i can be 2 or 3, meaning 1 or 2 more output characters
+        if (i>=2)
+            ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
+        if (i==3)
+            ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
+    }
+    // FIXME: This copy is sad. The problem is we need back "bytes"
+    // but "bytes" doesn't have efficient append and std::string.
+    // To fix this we need to use bytes' "uninitialized" feature.
+    return bytes(ret.begin(), ret.end());
+}

alternator/base64.hh

@@ -0,0 +1,34 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include <string_view>
+#include "bytes.hh"
+#include "rjson.hh"
+
+std::string base64_encode(bytes_view);
+
+bytes base64_decode(std::string_view);
+
+inline bytes base64_decode(const rjson::value& v) {
+  return base64_decode(std::string_view(v.GetString(), v.GetStringLength()));
+}

alternator/conditions.cc

@@ -1,23 +1,34 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <list>
+#include <map>
 #include <string_view>
 #include "alternator/conditions.hh"
 #include "alternator/error.hh"
+#include "cql3/constants.hh"
 #include <unordered_map>
-#include "utils/rjson.hh"
+#include "rjson.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
-#include <stdexcept>
-#include "utils/overloaded_functor.hh"
-
-#include "expressions.hh"
+#include "base64.hh"
 
 namespace alternator {
 
@@ -36,20 +47,61 @@ comparison_operator_type get_comparison_operator(const rjson::value& comparison_
             {"NOT_NULL", comparison_operator_type::NOT_NULL},
             {"BETWEEN", comparison_operator_type::BETWEEN},
             {"BEGINS_WITH", comparison_operator_type::BEGINS_WITH},
-            {"CONTAINS", comparison_operator_type::CONTAINS},
-            {"NOT_CONTAINS", comparison_operator_type::NOT_CONTAINS},
-    };
+    }; //TODO: CONTAINS
     if (!comparison_operator.IsString()) {
-        throw api_error::validation(fmt::format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
+        throw api_error("ValidationException", format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
     }
-    std::string op = rjson::to_string(comparison_operator);
+    std::string op = comparison_operator.GetString();
     auto it = ops.find(op);
     if (it == ops.end()) {
-        throw api_error::validation(fmt::format("Unsupported comparison operator {}", op));
+        throw api_error("ValidationException", format("Unsupported comparison operator {}", op));
     }
     return it->second;
 }
 
+static ::shared_ptr<cql3::restrictions::single_column_restriction::contains> make_map_element_restriction(const column_definition& cdef, std::string_view key, const rjson::value& value) {
+    bytes raw_key = utf8_type->from_string(sstring_view(key.data(), key.size()));
+    auto key_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_key)));
+    bytes raw_value = serialize_item(value);
+    auto entry_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_value)));
+    return make_shared<cql3::restrictions::single_column_restriction::contains>(cdef, std::move(key_value), std::move(entry_value));
+}
+
+static ::shared_ptr<cql3::restrictions::single_column_restriction::EQ> make_key_eq_restriction(const column_definition& cdef, const rjson::value& value) {
+    bytes raw_value = get_key_from_typed_value(value, cdef, type_to_string(cdef.type));
+    auto restriction_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_value)));
+    return make_shared<cql3::restrictions::single_column_restriction::EQ>(cdef, std::move(restriction_value));
+}
+
+::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter) {
+    clogger.trace("Getting filtering restrictions for: {}", rjson::print(query_filter));
+    auto filtering_restrictions = ::make_shared<cql3::restrictions::statement_restrictions>(schema, true);
+    for (auto it = query_filter.MemberBegin(); it != query_filter.MemberEnd(); ++it) {
+        std::string_view column_name(it->name.GetString(), it->name.GetStringLength());
+        const rjson::value& condition = it->value;
+
+        const rjson::value& comp_definition = rjson::get(condition, "ComparisonOperator");
+        const rjson::value& attr_list = rjson::get(condition, "AttributeValueList");
+        comparison_operator_type op = get_comparison_operator(comp_definition);
+
+        if (op != comparison_operator_type::EQ) {
+            throw api_error("ValidationException", "Filtering is currently implemented for EQ operator only");
+        }
+        if (attr_list.Size() != 1) {
+            throw api_error("ValidationException", format("EQ restriction needs exactly 1 attribute value: {}", rjson::print(attr_list)));
+        }
+        if (const column_definition* cdef = schema->get_column_definition(to_bytes(column_name.data()))) {
+            // Primary key restriction
+            filtering_restrictions->add_restriction(make_key_eq_restriction(*cdef, attr_list[0]), false, true);
+        } else {
+            // Regular column restriction
+            filtering_restrictions->add_restriction(make_map_element_restriction(attrs_col, column_name, attr_list[0]), false, true);
+        }
+
+    }
+    return filtering_restrictions;
+}
+
 namespace {
 
 struct size_check {
@@ -81,221 +133,61 @@ struct nonempty : public size_check {
 
 // Check that array has the expected number of elements
 static void verify_operand_count(const rjson::value* array, const size_check& expected, const rjson::value& op) {
-    if (!array && expected(0)) {
-        // If expected() allows an empty AttributeValueList, it is also fine
-        // that it is missing.
-        return;
-    }
     if (!array || !array->IsArray()) {
-        throw api_error::validation("With ComparisonOperator, AttributeValueList must be given and an array");
+        throw api_error("ValidationException", "With ComparisonOperator, AttributeValueList must be given and an array");
     }
     if (!expected(array->Size())) {
-        throw api_error::validation(
+        throw api_error("ValidationException",
                         format("{} operator requires AttributeValueList {}, instead found list size {}",
                                op, expected.what(), array->Size()));
     }
 }
 
-struct rjson_engaged_ptr_comp {
-    bool operator()(const rjson::value* p1, const rjson::value* p2) const {
-        return rjson::single_value_comp()(*p1, *p2);
-    }
-};
-
-// It's not enough to compare underlying JSON objects when comparing sets,
-// as internally they're stored in an array, and the order of elements is
-// not important in set equality. See issue #5021
-static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2) {
-    if (!set1.IsArray() || !set2.IsArray() || set1.Size() != set2.Size()) {
-        return false;
-    }
-    std::set<const rjson::value*, rjson_engaged_ptr_comp> set1_raw;
-    for (auto it = set1.Begin(); it != set1.End(); ++it) {
-        set1_raw.insert(&*it);
-    }
-    for (const auto& a : set2.GetArray()) {
-        if (!set1_raw.contains(&a)) {
-            return false;
-        }
-    }
-    return true;
-}
-// Moreover, the JSON being compared can be a nested document with outer
-// layers of lists and maps and some inner set - and we need to get to that
-// inner set to compare it correctly with check_EQ_for_sets() (issue #8514).
-static bool check_EQ(const rjson::value* v1, const rjson::value& v2);
-static bool check_EQ_for_lists(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsArray() || !list2.IsArray() || list1.Size() != list2.Size()) {
-        return false;
-    }
-    auto it1 = list1.Begin();
-    auto it2 = list2.Begin();
-    while (it1 != list1.End()) {
-        // Note: Alternator limits an item's depth (rjson::parse() limits
-        // it to around 37 levels), so this recursion is safe.
-        if (!check_EQ(&*it1, *it2)) {
-            return false;
-        }
-        ++it1;
-        ++it2;
-    }
-    return true;
-}
-static bool check_EQ_for_maps(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsObject() || !list2.IsObject() || list1.MemberCount() != list2.MemberCount()) {
-        return false;
-    }
-    for (auto it1 = list1.MemberBegin(); it1 != list1.MemberEnd(); ++it1) {
-        auto it2 = list2.FindMember(it1->name);
-        if (it2 == list2.MemberEnd() || !check_EQ(&it1->value, it2->value)) {
-            return false;
-        }
-    }
-    return true;
-}
-
 // Check if two JSON-encoded values match with the EQ relation
 static bool check_EQ(const rjson::value* v1, const rjson::value& v2) {
-    if (v1 && v1->IsObject() && v1->MemberCount() == 1 && v2.IsObject() && v2.MemberCount() == 1) {
-        auto it1 = v1->MemberBegin();
-        auto it2 = v2.MemberBegin();
-        if (it1->name != it2->name) {
-            return false;
-        }
-        if (it1->name == "SS" || it1->name == "NS" || it1->name == "BS") {
-            return check_EQ_for_sets(it1->value, it2->value);
-        } else if(it1->name == "L") {
-            return check_EQ_for_lists(it1->value, it2->value);
-        } else if(it1->name == "M") {
-            return check_EQ_for_maps(it1->value, it2->value);
-        } else {
-            // Other, non-nested types (number, string, etc.) can be compared
-            // literally, comparing their JSON representation.
-            return it1->value == it2->value;
-        }
-    } else {
-        // If v1 and/or v2 are missing (IsNull()) the result should be false.
-        // In the unlikely case that the object is malformed (issue #8070),
-        // let's also return false.
-        return false;
-    }
+    return v1 && *v1 == v2;
 }
 
 // Check if two JSON-encoded values match with the NE relation
 static bool check_NE(const rjson::value* v1, const rjson::value& v2) {
-    return !check_EQ(v1, v2);
+    return !v1 || *v1 != v2; // null is unequal to anything.
 }
 
 // Check if two JSON-encoded values match with the BEGINS_WITH relation
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
-                       bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
-        if (v1_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v1->MemberBegin()->name != "S" && v1->MemberBegin()->name != "B") {
-        if (v1_from_query) {
-            throw api_error::validation(format("begins_with supports only string or binary type, got: {}", *v1));
-        } else {
-            bad = true;
-        }
-    }
+static bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2) {
+    // BEGINS_WITH requires that its single operand (v2) be a string or
+    // binary - otherwise it's a validation error. However, problems with
+    // the stored attribute (v1) will just return false (no match).
     if (!v2.IsObject() || v2.MemberCount() != 1) {
-        if (v2_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
-        if (v2_from_query) {
-            throw api_error::validation(format("begins_with() supports only string or binary type, got: {}", v2));
-        } else {
-            bad = true;
-        }
+        throw api_error("ValidationException", format("BEGINS_WITH operator encountered malformed AttributeValue: {}", v2));
     }
-    if (bad) {
+    auto it2 = v2.MemberBegin();
+    if (it2->name != "S" && it2->name != "B") {
+        throw api_error("ValidationException", format("BEGINS_WITH operator requires String or Binary in AttributeValue, got {}", it2->name));
+    }
+
+
+    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
         return false;
     }
     auto it1 = v1->MemberBegin();
-    auto it2 = v2.MemberBegin();
     if (it1->name != it2->name) {
         return false;
     }
-    if (it2->name == "S") {
-        return rjson::to_string_view(it1->value).starts_with(rjson::to_string_view(it2->value));
-    } else /* it2->name == "B" */ {
-        try {
-            return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
-        } catch(std::invalid_argument&) {
-            // determine if any of the malformed values is from query and raise an exception if so
-            unwrap_bytes(it1->value, v1_from_query);
-            unwrap_bytes(it2->value, v2_from_query);
-            return false;
-        }
-    }
-}
-
-static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
-    return (type2 == "S" && type1 == "SS") || (type2 == "N" && type1 == "NS") || (type2 == "B" && type1 == "BS");
-}
-
-// Check if two JSON-encoded values match with the CONTAINS relation
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query) {
-    if (!v1) {
-        return false;
-    }
-    const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
-    if (kv1.name == "S" && kv2.name == "S") {
-        return rjson::to_string_view(kv1.value).find(rjson::to_string_view(kv2.value)) != std::string_view::npos;
-    } else if (kv1.name == "B" && kv2.name == "B") {
-        auto d_kv1 = unwrap_bytes(kv1.value, v1_from_query);
-        auto d_kv2 = unwrap_bytes(kv2.value, v2_from_query);
-        if (!d_kv1 || !d_kv2) {
-            return false;
-        }
-        return d_kv1->find(*d_kv2) != bytes::npos;
-    } else if (is_set_of(kv1.name, kv2.name)) {
-        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
-            if (*i == kv2.value) {
-                return true;
-            }
-        }
-    } else if (kv1.name == "L") {
-        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
-            if (!i->IsObject() || i->MemberCount() != 1) {
-                clogger.error("check_CONTAINS received a list whose element is malformed");
-                return false;
-            }
-            const auto& el = *i->MemberBegin();
-            if (el.name == kv2.name && el.value == kv2.value) {
-                return true;
-            }
-        }
-    }
-    return false;
-}
-
-// Check if two JSON-encoded values match with the NOT_CONTAINS relation
-static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query) {
-    if (!v1) {
-        return false;
-    }
-    return !check_CONTAINS(v1, v2, v1_from_query, v2_from_query);
+    std::string_view val1(it1->value.GetString(), it1->value.GetStringLength());
+    std::string_view val2(it2->value.GetString(), it2->value.GetStringLength());
+    return val1.substr(0, val2.size()) == val2;
 }
 
 // Check if a JSON-encoded value equals any element of an array, which must have at least one element.
 static bool check_IN(const rjson::value* val, const rjson::value& array) {
     if (!array[0].IsObject() || array[0].MemberCount() != 1) {
-        throw api_error::validation(
+        throw api_error("ValidationException",
                         format("IN operator encountered malformed AttributeValue: {}", array[0]));
     }
     const auto& type = array[0].MemberBegin()->name;
     if (type != "S" && type != "N" && type != "B") {
-        throw api_error::validation(
+        throw api_error("ValidationException",
                         "IN operator requires AttributeValueList elements to be of type String, Number, or Binary ");
     }
     if (!val) {
@@ -304,7 +196,7 @@ static bool check_IN(const rjson::value* val, const rjson::value& array) {
     bool have_match = false;
     for (const auto& elem : array.GetArray()) {
         if (!elem.IsObject() || elem.MemberCount() != 1 || elem.MemberBegin()->name != type) {
-            throw api_error::validation(
+            throw api_error("ValidationException",
                             "IN operator requires all AttributeValueList elements to have the same type ");
         }
         if (!have_match && *val == elem) {
@@ -315,19 +207,6 @@ static bool check_IN(const rjson::value* val, const rjson::value& array) {
     return have_match;
 }
 
-// Another variant of check_IN, this one for ConditionExpression. It needs to
-// check whether the first element in the given vector is equal to any of the
-// others.
-static bool check_IN(const std::vector<rjson::value>& array) {
-    const rjson::value* first = &array[0];
-    for (unsigned i = 1; i < array.size(); i++) {
-        if (check_EQ(first, array[i])) {
-            return true;
-        }
-    }
-    return false;
-}
-
 static bool check_NULL(const rjson::value* val) {
     return val == nullptr;
 }
@@ -336,163 +215,52 @@ static bool check_NOT_NULL(const rjson::value* val) {
     return val != nullptr;
 }
 
-// Only types S, N or B (string, number or bytes) may be compared by the
-// various comparison operators - lt, le, gt, ge, and between.
-// Note that in particular, if the value is missing (v->IsNull()), this
-// check returns false.
-static bool check_comparable_type(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return false;
-    }
-    const rjson::value& type = v.MemberBegin()->name;
-    return type == "S" || type == "N" || type == "B";
-}
-
 // Check if two JSON-encoded values match with cmp.
 template <typename Comparator>
-bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp,
-                   bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !check_comparable_type(*v1)) {
-        if (v1_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
+bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp) {
+    if (!v2.IsObject() || v2.MemberCount() != 1) {
+        throw api_error("ValidationException",
+                        format("{} requires a single AttributeValue of type String, Number, or Binary",
+                               cmp.diagnostic()));
     }
-    if (!check_comparable_type(v2)) {
-        if (v2_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
+    const auto& kv2 = *v2.MemberBegin();
+    if (kv2.name != "S" && kv2.name != "N" && kv2.name != "B") {
+        throw api_error("ValidationException",
+                        format("{} requires a single AttributeValue of type String, Number, or Binary",
+                               cmp.diagnostic()));
     }
-    if (bad) {
+    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
         return false;
     }
     const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
     if (kv1.name != kv2.name) {
         return false;
     }
     if (kv1.name == "N") {
-        return cmp(unwrap_number(*v1, cmp.diagnostic), unwrap_number(v2, cmp.diagnostic));
+        return cmp(unwrap_number(*v1, cmp.diagnostic()), unwrap_number(v2, cmp.diagnostic()));
     }
     if (kv1.name == "S") {
-        return cmp(rjson::to_string_view(kv1.value),
-                   rjson::to_string_view(kv2.value));
+        return cmp(std::string_view(kv1.value.GetString(), kv1.value.GetStringLength()),
+                   std::string_view(kv2.value.GetString(), kv2.value.GetStringLength()));
     }
     if (kv1.name == "B") {
-        auto d_kv1 = unwrap_bytes(kv1.value, v1_from_query);
-        auto d_kv2 = unwrap_bytes(kv2.value, v2_from_query);
-        if(!d_kv1 || !d_kv2) {
-            return false;
-        }
-        return cmp(*d_kv1, *d_kv2);
+        return cmp(base64_decode(kv1.value), base64_decode(kv2.value));
     }
-    // cannot reach here, as check_comparable_type() verifies the type is one
-    // of the above options.
+    clogger.error("check_compare panic: LHS type equals RHS type, but one is in {N,S,B} while the other isn't");
     return false;
 }
 
 struct cmp_lt {
     template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs < rhs; }
-    // We cannot use the normal comparison operators like "<" on the bytes
-    // type, because they treat individual bytes as signed but we need to
-    // compare them as *unsigned*. So we need a specialization for bytes.
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) < 0; }
-    static constexpr const char* diagnostic = "LT operator";
-};
-
-struct cmp_le {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs <= rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) <= 0; }
-    static constexpr const char* diagnostic = "LE operator";
-};
-
-struct cmp_ge {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs >= rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) >= 0; }
-    static constexpr const char* diagnostic = "GE operator";
+    const char* diagnostic() const { return "LT operator"; }
 };
 
 struct cmp_gt {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs > rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) > 0; }
-    static constexpr const char* diagnostic = "GT operator";
+    // bytes only has <
+    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return rhs < lhs; }
+    const char* diagnostic() const { return "GT operator"; }
 };
 
-// True if v is between lb and ub, inclusive.  Throws or returns false
-// (depending on bounds_from_query parameter) if lb > ub.
-template <typename T>
-static bool check_BETWEEN(const T& v, const T& lb, const T& ub, bool bounds_from_query) {
-    if (cmp_lt()(ub, lb)) {
-        if (bounds_from_query) {
-            throw api_error::validation(
-                fmt::format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
-        } else {
-            return false;
-        }
-    }
-    return cmp_ge()(v, lb) && cmp_le()(v, ub);
-}
-
-static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const rjson::value& ub,
-                          bool v_from_query, bool lb_from_query, bool ub_from_query) {
-    if ((v && v_from_query && !check_comparable_type(*v)) ||
-        (lb_from_query && !check_comparable_type(lb)) ||
-        (ub_from_query && !check_comparable_type(ub))) {
-        throw api_error::validation("between allow only the types String, Number, or Binary");
-
-    }
-    if (!v || !v->IsObject() || v->MemberCount() != 1 ||
-        !lb.IsObject() || lb.MemberCount() != 1 ||
-        !ub.IsObject() || ub.MemberCount() != 1) {
-        return false;
-    }
-
-    const auto& kv_v = *v->MemberBegin();
-    const auto& kv_lb = *lb.MemberBegin();
-    const auto& kv_ub = *ub.MemberBegin();
-    bool bounds_from_query = lb_from_query && ub_from_query;
-    if (kv_lb.name != kv_ub.name) {
-        if (bounds_from_query) {
-           throw api_error::validation(
-                format("BETWEEN operator requires the same type for lower and upper bound; instead got {} and {}",
-                       kv_lb.name, kv_ub.name));
-        } else {
-            return false;
-        }
-    }
-    if (kv_v.name != kv_lb.name) { // Cannot compare different types, so v is NOT between lb and ub.
-        return false;
-    }
-    if (kv_v.name == "N") {
-        const char* diag = "BETWEEN operator";
-        return check_BETWEEN(unwrap_number(*v, diag), unwrap_number(lb, diag), unwrap_number(ub, diag), bounds_from_query);
-    }
-    if (kv_v.name == "S") {
-        return check_BETWEEN(rjson::to_string_view(kv_v.value),
-                             rjson::to_string_view(kv_lb.value),
-                             rjson::to_string_view(kv_ub.value),
-                             bounds_from_query);
-    }
-    if (kv_v.name == "B") {
-        auto d_kv_v = unwrap_bytes(kv_v.value, v_from_query);
-        auto d_kv_lb = unwrap_bytes(kv_lb.value, lb_from_query);
-        auto d_kv_ub = unwrap_bytes(kv_ub.value, ub_from_query);
-        if(!d_kv_v || !d_kv_lb || !d_kv_ub) {
-            return false;
-        }
-        return check_BETWEEN(*d_kv_v, *d_kv_lb, *d_kv_ub, bounds_from_query);
-    }
-    if (v_from_query) {
-        throw api_error::validation(
-            format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
-               kv_lb.name));
-    } else {
-        return false;
-    }
-}
-
 // Verify one Expect condition on one attribute (whose content is "got")
 // for the verify_expected() below.
 // This function returns true or false depending on whether the condition
@@ -508,24 +276,24 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
     // and requires a different combinations of parameters in the request
     if (value) {
         if (exists && (!exists->IsBool() || exists->GetBool() != true)) {
-            throw api_error::validation("Cannot combine Value with Exists!=true");
+            throw api_error("ValidationException", "Cannot combine Value with Exists!=true");
         }
         if (comparison_operator) {
-            throw api_error::validation("Cannot combine Value with ComparisonOperator");
+            throw api_error("ValidationException", "Cannot combine Value with ComparisonOperator");
         }
         return check_EQ(got, *value);
     } else if (exists) {
         if (comparison_operator) {
-            throw api_error::validation("Cannot combine Exists with ComparisonOperator");
+            throw api_error("ValidationException", "Cannot combine Exists with ComparisonOperator");
         }
         if (!exists->IsBool() || exists->GetBool() != false) {
-            throw api_error::validation("Exists!=false requires Value");
+            throw api_error("ValidationException", "Exists!=false requires Value");
         }
         // Remember Exists=false, so we're checking that the attribute does *not* exist:
         return !got;
     } else {
         if (!comparison_operator) {
-            throw api_error::validation("Missing ComparisonOperator, Value or Exists");
+            throw api_error("ValidationException", "Missing ComparisonOperator, Value or Exists");
         }
         comparison_operator_type op = get_comparison_operator(*comparison_operator);
         switch (op) {
@@ -537,19 +305,13 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
             return check_NE(got, (*attribute_value_list)[0]);
         case comparison_operator_type::LT:
             verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_lt{}, false, true);
-        case comparison_operator_type::LE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_le{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_lt{});
         case comparison_operator_type::GT:
             verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_gt{}, false, true);
-        case comparison_operator_type::GE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_ge{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_gt{});
         case comparison_operator_type::BEGINS_WITH:
             verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_BEGINS_WITH(got, (*attribute_value_list)[0], false, true);
+            return check_BEGINS_WITH(got, (*attribute_value_list)[0]);
         case comparison_operator_type::IN:
             verify_operand_count(attribute_value_list, nonempty(), *comparison_operator);
             return check_IN(got, *attribute_value_list);
@@ -559,198 +321,67 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
         case comparison_operator_type::NOT_NULL:
             verify_operand_count(attribute_value_list, empty(), *comparison_operator);
             return check_NOT_NULL(got);
-        case comparison_operator_type::BETWEEN:
-            verify_operand_count(attribute_value_list, exact_size(2), *comparison_operator);
-            return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1],
-                                 false, true, true);
-        case comparison_operator_type::CONTAINS:
-            {
-                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-                // Expected's "CONTAINS" has this artificial limitation.
-                // ConditionExpression's "contains()" does not...
-                const rjson::value& arg = (*attribute_value_list)[0];
-                const auto& argtype = (*arg.MemberBegin()).name;
-                if (argtype != "S" && argtype != "N" && argtype != "B") {
-                    throw api_error::validation(
-                            format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
-                                    "got {} instead", argtype));
-                }
-                return check_CONTAINS(got, arg, false, true);
-            }
-        case comparison_operator_type::NOT_CONTAINS:
-            {
-                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-                // Expected's "NOT_CONTAINS" has this artificial limitation.
-                // ConditionExpression's "contains()" does not...
-                const rjson::value& arg = (*attribute_value_list)[0];
-                const auto& argtype = (*arg.MemberBegin()).name;
-                if (argtype != "S" && argtype != "N" && argtype != "B") {
-                    throw api_error::validation(
-                            format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
-                                    "got {} instead", argtype));
-                }
-                return check_NOT_CONTAINS(got, arg, false, true);
-            }
+        default:
+            // FIXME: implement all the missing types, so there will be no default here.
+            throw api_error("ValidationException", format("ComparisonOperator {} is not yet supported", *comparison_operator));
         }
-        throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));
     }
 }
 
-conditional_operator_type get_conditional_operator(const rjson::value& req) {
-    const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
-    if (!conditional_operator) {
-        return conditional_operator_type::MISSING;
-    }
-    if (!conditional_operator->IsString()) {
-        throw api_error::validation("'ConditionalOperator' parameter, if given, must be a string");
-    }
-    auto s = rjson::to_string_view(*conditional_operator);
-    if (s == "AND") {
-        return conditional_operator_type::AND;
-    } else if (s == "OR") {
-        return conditional_operator_type::OR;
-    } else {
-        throw api_error::validation(
-                fmt::format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
-    }
-}
-
-// Check if the existing values of the item (previous_item) match the
+// Verify that the existing values of the item (previous_item) match the
 // conditions given by the Expected and ConditionalOperator parameters
 // (if they exist) in the request (an UpdateItem, PutItem or DeleteItem).
-// This function can throw a ValidationException API error if there
+// This function will throw a ConditionalCheckFailedException API error
+// if the values do not match the condition, or ValidationException if there
 // are errors in the format of the condition itself.
-bool verify_expected(const rjson::value& req, const rjson::value* previous_item) {
+void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item) {
     const rjson::value* expected = rjson::find(req, "Expected");
-    auto conditional_operator = get_conditional_operator(req);
-    if (conditional_operator != conditional_operator_type::MISSING &&
-        (!expected || (expected->IsObject() && expected->GetObject().ObjectEmpty()))) {
-            throw api_error::validation("'ConditionalOperator' parameter cannot be specified for missing or empty Expression");
-    }
     if (!expected) {
-        return true;
+        return;
     }
     if (!expected->IsObject()) {
-        throw api_error::validation("'Expected' parameter, if given, must be an object");
+        throw api_error("ValidationException", "'Expected' parameter, if given, must be an object");
+    }
+    // ConditionalOperator can be "AND" for requiring all conditions, or
+    // "OR" for requiring one condition, and defaults to "AND" if missing.
+    const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
+    bool require_all = true;
+    if (conditional_operator) {
+        if (!conditional_operator->IsString()) {
+            throw api_error("ValidationException", "'ConditionalOperator' parameter, if given, must be a string");
+        }
+        std::string_view s(conditional_operator->GetString(), conditional_operator->GetStringLength());
+        if (s == "AND") {
+            // require_all is already true
+        } else if (s == "OR") {
+            require_all = false;
+        } else {
+            throw api_error("ValidationException", "'ConditionalOperator' parameter must be AND, OR or missing");
+        }
+        if (expected->GetObject().ObjectEmpty()) {
+            throw api_error("ValidationException", "'ConditionalOperator' parameter cannot be specified for empty Expression");
+        }
     }
-    bool require_all = conditional_operator != conditional_operator_type::OR;
-    return verify_condition(*expected, require_all, previous_item);
-}
 
-bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item) {
-    for (auto it = condition.MemberBegin(); it != condition.MemberEnd(); ++it) {
+    for (auto it = expected->MemberBegin(); it != expected->MemberEnd(); ++it) {
         const rjson::value* got = nullptr;
-        if (previous_item) {
-            got = rjson::find(*previous_item, rjson::to_string_view(it->name));
+        if (previous_item && previous_item->IsObject() && previous_item->HasMember("Item")) {
+            got = rjson::find((*previous_item)["Item"], rjson::string_ref_type(it->name.GetString()));
         }
         bool success = verify_expected_one(it->value, got);
         if (success && !require_all) {
             // When !require_all, one success is enough!
-            return true;
+            return;
         } else if (!success && require_all) {
             // When require_all, one failure is enough!
-            return false;
+            throw api_error("ConditionalCheckFailedException", "Failed condition.");
         }
     }
     // If we got here and require_all, none of the checks failed, so succeed.
     // If we got here and !require_all, all of the checks failed, so fail.
-    return require_all;
-}
-
-static bool calculate_primitive_condition(const parsed::primitive_condition& cond,
-        const rjson::value* previous_item) {
-    std::vector<rjson::value> calculated_values;
-    calculated_values.reserve(cond._values.size());
-    for (const parsed::value& v : cond._values) {
-        calculated_values.push_back(calculate_value(v,
-                cond._op == parsed::primitive_condition::type::VALUE ?
-                        calculate_value_caller::ConditionExpressionAlone :
-                        calculate_value_caller::ConditionExpression,
-                previous_item));
-    }
-    switch (cond._op) {
-    case parsed::primitive_condition::type::BETWEEN:
-        if (calculated_values.size() != 3) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error(format("Wrong number of values {} in BETWEEN primitive_condition", cond._values.size()));
-        }
-        return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2],
-                             cond._values[0].is_constant(), cond._values[1].is_constant(), cond._values[2].is_constant());
-    case parsed::primitive_condition::type::IN:
-        return check_IN(calculated_values);
-    case parsed::primitive_condition::type::VALUE:
-        if (calculated_values.size() != 1) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error(format("Unexpected values in primitive_condition", cond._values.size()));
-        }
-        // Unwrap the boolean wrapped as the value (if it is a boolean)
-        if (calculated_values[0].IsObject() && calculated_values[0].MemberCount() == 1) {
-            auto it = calculated_values[0].MemberBegin();
-            if (it->name == "BOOL" && it->value.IsBool()) {
-                return it->value.GetBool();
-            }
-        }
-        throw api_error::validation(
-                format("ConditionExpression: condition results in a non-boolean value: {}",
-                        calculated_values[0]));
-    default:
-        // All the rest of the operators have exactly two parameters (and unless
-        // we have a bug in the parser, that's what we have in the parsed object:
-        if (calculated_values.size() != 2) {
-            throw std::logic_error(format("Wrong number of values {} in primitive_condition object", cond._values.size()));
-        }
-    }
-    switch (cond._op) {
-    case parsed::primitive_condition::type::EQ:
-        return check_EQ(&calculated_values[0], calculated_values[1]);
-    case parsed::primitive_condition::type::NE:
-        return check_NE(&calculated_values[0], calculated_values[1]);
-    case parsed::primitive_condition::type::GT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::GE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::LT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::LE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_le{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    default:
-        // Shouldn't happen unless we have a bug in the parser
-        throw std::logic_error(format("Unknown type {} in primitive_condition object", (int)(cond._op)));
+    if (!require_all) {
+        throw api_error("ConditionalCheckFailedException", "None of ORed Expect conditions were successful.");
     }
 }
 
-// Check if the existing values of the item (previous_item) match the
-// conditions given by the given parsed ConditionExpression.
-bool verify_condition_expression(
-        const parsed::condition_expression& condition_expression,
-        const rjson::value* previous_item) {
-    if (condition_expression.empty()) {
-        return true;
-    }
-    bool ret = std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) -> bool {
-            return calculate_primitive_condition(cond, previous_item);
-        },
-        [&] (const parsed::condition_expression::condition_list& list) -> bool {
-            auto verify_condition = [&] (const parsed::condition_expression& e) {
-                return verify_condition_expression(e, previous_item);
-            };
-            switch (list.op) {
-            case '&':
-                return std::ranges::all_of(list.conditions, verify_condition);
-            case '|':
-                return std::ranges::any_of(list.conditions, verify_condition);
-            default:
-                // Shouldn't happen unless we have a bug in the parser
-                throw std::logic_error("bad operator in condition_list");
-            }
-        }
-    }, condition_expression._expression);
-    return condition_expression._negated ? !ret : ret;
-}
-
 }

alternator/conditions.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -18,29 +31,19 @@
 
 #pragma once
 
-#include "expressions_types.hh"
+#include "cql3/restrictions/statement_restrictions.hh"
+#include "serialization.hh"
 
 namespace alternator {
 
 enum class comparison_operator_type {
-    EQ, NE, LE, LT, GE, GT, IN, BETWEEN, CONTAINS, NOT_CONTAINS, IS_NULL, NOT_NULL, BEGINS_WITH
+    EQ, NE, LE, LT, GE, GT, IN, BETWEEN, CONTAINS, IS_NULL, NOT_NULL, BEGINS_WITH
 };
 
 comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator);
 
-enum class conditional_operator_type {
-    AND, OR, MISSING
-};
-conditional_operator_type get_conditional_operator(const rjson::value& req);
+::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter);
 
-bool verify_expected(const rjson::value& req, const rjson::value* previous_item);
-bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);
-
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
-
-bool verify_condition_expression(
-        const parsed::condition_expression& condition_expression,
-        const rjson::value* previous_item);
+void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item);
 
 }

alternator/consumed_capacity.cc

@@ -1,96 +0,0 @@
-/*
- * Copyright 2024-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include "consumed_capacity.hh"
-#include "error.hh"
-#include "utils/rjson.hh"
-#include <fmt/format.h>
-
-namespace alternator {
-
-/*
- * \brief DynamoDB counts read capacity in half-integers - a short
- * eventually-consistent read is counted as 0.5 unit.
- * Because we want our counter to be an integer, it counts half units.
- * Both read and write counters count in these half-units, and should be
- * multiply by 0.5 (HALF_UNIT_MULTIPLIER) to get the DynamoDB-compatible RCU or WCU numbers.
- */
-static constexpr double HALF_UNIT_MULTIPLIER = 0.5;
-
-static constexpr uint64_t KB = 1024ULL;
-static constexpr uint64_t RCU_BLOCK_SIZE_LENGTH = 4*KB;
-static constexpr uint64_t WCU_BLOCK_SIZE_LENGTH = 1*KB;
-
-bool consumed_capacity_counter::should_add_capacity(const rjson::value& request) {
-    const rjson::value* return_consumed = rjson::find(request, "ReturnConsumedCapacity");
-    if (!return_consumed) {
-        return false;
-    }
-    if (!return_consumed->IsString()) {
-        throw api_error::validation("Non-string ReturnConsumedCapacity field in request");
-    }
-    std::string_view consumed = rjson::to_string_view(*return_consumed);
-    if (consumed == "INDEXES") {
-        throw api_error::validation("INDEXES consumed capacity is not supported");
-    }
-    if (consumed != "TOTAL") {
-        throw api_error::validation(fmt::format("Unknown consumed capacity {}", consumed));
-    }
-    return true;
-}
-
-void consumed_capacity_counter::add_consumed_capacity_to_response_if_needed(rjson::value& response) const noexcept {
-    if (_should_add_to_response) {
-        auto consumption = rjson::empty_object();
-        rjson::add(consumption, "CapacityUnits", get_consumed_capacity_units());
-        rjson::add(response, "ConsumedCapacity", std::move(consumption));
-    }
-}
-
-static uint64_t calculate_half_units(uint64_t unit_block_size, uint64_t total_bytes, bool is_quorum) {
-    uint64_t half_units = (total_bytes + unit_block_size -1) / unit_block_size; //divide by unit_block_size and round up
-
-    if (is_quorum) {
-        half_units *= 2;
-    }
-    return half_units;
-}
-
-rcu_consumed_capacity_counter::rcu_consumed_capacity_counter(const rjson::value& request, bool is_quorum) :
-        consumed_capacity_counter(should_add_capacity(request)),_is_quorum(is_quorum) {
-}
-uint64_t rcu_consumed_capacity_counter::get_half_units(uint64_t total_bytes, bool is_quorum) noexcept {
-    return calculate_half_units(RCU_BLOCK_SIZE_LENGTH, total_bytes, is_quorum);
-}
-
-uint64_t rcu_consumed_capacity_counter::get_half_units() const noexcept {
-    return get_half_units(_total_bytes, _is_quorum);
-}
-
-uint64_t wcu_consumed_capacity_counter::get_half_units() const noexcept {
-    return calculate_half_units(WCU_BLOCK_SIZE_LENGTH, _total_bytes, true);
-}
-
-uint64_t wcu_consumed_capacity_counter::get_units(uint64_t total_bytes) noexcept {
-    return calculate_half_units(WCU_BLOCK_SIZE_LENGTH, total_bytes, true) * HALF_UNIT_MULTIPLIER;
-}
-
-wcu_consumed_capacity_counter::wcu_consumed_capacity_counter(const rjson::value& request) :
-        consumed_capacity_counter(should_add_capacity(request)) {
-}
-
-consumed_capacity_counter& consumed_capacity_counter::operator +=(uint64_t units) {
-    _total_bytes += units;
-    return *this;
-}
-
-double consumed_capacity_counter::get_consumed_capacity_units() const noexcept {
-    return get_half_units() * HALF_UNIT_MULTIPLIER;
-}
-
-}

alternator/consumed_capacity.hh

@@ -1,66 +0,0 @@
-/*
- * Copyright 2024-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include "utils/rjson.hh"
-
-namespace alternator {
-
-/**
- * \brief consumed_capacity_counter is a base class that holds the bookkeeping
- *  to calculate RCU and WCU
- *
- * DynamoDB counts read capacity in half-integers - a short
- * eventually-consistent read is counted as 0.5 unit.
- * Because we want our counter to be an integer, we counts half units in
- * our internal calculations.
- *
- * We use consumed_capacity_counter for calculation of a specific action
- *
- * It is also used to update the response if needed.
- */
-class consumed_capacity_counter {
-public:
-    consumed_capacity_counter() = default;
-    consumed_capacity_counter(bool should_add_to_response) : _should_add_to_response(should_add_to_response){}
-    bool operator()() const noexcept {
-        return _should_add_to_response;
-    }
-
-    consumed_capacity_counter& operator +=(uint64_t bytes);
-    double get_consumed_capacity_units() const noexcept;
-    void add_consumed_capacity_to_response_if_needed(rjson::value& response) const noexcept;
-    virtual ~consumed_capacity_counter() = default;
-    /**
-     * \brief get_half_units calculate the half units from the total bytes based on the type of the request
-     */
-    virtual uint64_t get_half_units() const noexcept = 0;
-    uint64_t _total_bytes = 0;
-    static bool should_add_capacity(const rjson::value& request);
-protected:
-    bool _should_add_to_response = false;
-};
-
-class rcu_consumed_capacity_counter : public consumed_capacity_counter {
-    bool _is_quorum = false;
-public:
-    rcu_consumed_capacity_counter(const rjson::value& request, bool is_quorum);
-    rcu_consumed_capacity_counter(): consumed_capacity_counter(false), _is_quorum(false){}
-    virtual uint64_t get_half_units() const noexcept;
-    static uint64_t get_half_units(uint64_t total_bytes, bool is_quorum) noexcept;
-};
-
-class wcu_consumed_capacity_counter : public consumed_capacity_counter {
-    virtual uint64_t get_half_units() const noexcept;
-public:
-    wcu_consumed_capacity_counter(const rjson::value& request);
-    static uint64_t get_units(uint64_t total_bytes) noexcept;
-};
-
-}

alternator/controller.cc

@@ -1,199 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#include <seastar/core/with_scheduling_group.hh>
-#include <seastar/net/dns.hh>
-
-#include "controller.hh"
-#include "server.hh"
-#include "executor.hh"
-#include "rmw_operation.hh"
-#include "db/config.hh"
-#include "cdc/generation_service.hh"
-#include "service/memory_limiter.hh"
-#include "auth/service.hh"
-#include "service/qos/service_level_controller.hh"
-
-using namespace seastar;
-
-namespace alternator {
-
-static logging::logger logger("alternator_controller");
-
-controller::controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::storage_service>& ss,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config,
-        seastar::scheduling_group sg)
-    : protocol_server(sg)
-    , _gossiper(gossiper)
-    , _proxy(proxy)
-    , _ss(ss)
-    , _mm(mm)
-    , _sys_dist_ks(sys_dist_ks)
-    , _cdc_gen_svc(cdc_gen_svc)
-    , _memory_limiter(memory_limiter)
-    , _auth_service(auth_service)
-    , _sl_controller(sl_controller)
-    , _config(config)
-{
-}
-
-sstring controller::name() const {
-    return "alternator";
-}
-
-sstring controller::protocol() const {
-    return "dynamodb";
-}
-
-sstring controller::protocol_version() const {
-    return version;
-}
-
-std::vector<socket_address> controller::listen_addresses() const {
-    return _listen_addresses;
-}
-
-future<> controller::start_server() {
-    seastar::thread_attributes attr;
-    attr.sched_group = _sched_group;
-    return seastar::async(std::move(attr), [this] {
-        _listen_addresses.clear();
-
-        auto preferred = _config.listen_interface_prefer_ipv6() ? std::make_optional(net::inet_address::family::INET6) : std::nullopt;
-        auto family = _config.enable_ipv6_dns_lookup() || preferred ? std::nullopt : std::make_optional(net::inet_address::family::INET);
-
-        // Create an smp_service_group to be used for limiting the
-        // concurrency when forwarding Alternator request between
-        // shards - if necessary for LWT.
-        smp_service_group_config c;
-        c.max_nonlocal_requests = 5000;
-        _ssg = create_smp_service_group(c).get();
-
-        rmw_operation::set_default_write_isolation(_config.alternator_write_isolation());
-
-        net::inet_address addr = utils::resolve(_config.alternator_address, family).get();
-
-        auto get_cdc_metadata = [] (cdc::generation_service& svc) { return std::ref(svc.get_cdc_metadata()); };
-        auto get_timeout_in_ms = [] (const db::config& cfg) -> utils::updateable_value<uint32_t> {
-            return cfg.alternator_timeout_in_ms;
-        };
-        _executor.start(std::ref(_gossiper), std::ref(_proxy), std::ref(_ss), std::ref(_mm), std::ref(_sys_dist_ks),
-                        sharded_parameter(get_cdc_metadata, std::ref(_cdc_gen_svc)), _ssg.value(),
-                        sharded_parameter(get_timeout_in_ms, std::ref(_config))).get();
-        _server.start(std::ref(_executor), std::ref(_proxy), std::ref(_gossiper), std::ref(_auth_service), std::ref(_sl_controller)).get();
-        // Note: from this point on, if start_server() throws for any reason,
-        // it must first call stop_server() to stop the executor and server
-        // services we just started - or Scylla will cause an assertion
-        // failure when the controller object is destroyed in the exception
-        // unwinding.
-        std::optional<uint16_t> alternator_port;
-        if (_config.alternator_port()) {
-            alternator_port = _config.alternator_port();
-            _listen_addresses.push_back({addr, *alternator_port});
-        }
-        std::optional<uint16_t> alternator_port_proxy_protocol;
-        if (_config.alternator_port_proxy_protocol()) {
-            alternator_port_proxy_protocol = _config.alternator_port_proxy_protocol();
-            _listen_addresses.push_back({addr, *alternator_port_proxy_protocol});
-        }
-        std::optional<uint16_t> alternator_https_port;
-        std::optional<uint16_t> alternator_https_port_proxy_protocol;
-        std::optional<tls::credentials_builder> creds;
-        if (_config.alternator_https_port() || _config.alternator_https_port_proxy_protocol()) {
-            if (_config.alternator_https_port()) {
-                alternator_https_port = _config.alternator_https_port();
-                _listen_addresses.push_back({addr, *alternator_https_port});
-            }
-            if (_config.alternator_https_port_proxy_protocol()) {
-                alternator_https_port_proxy_protocol = _config.alternator_https_port_proxy_protocol();
-                _listen_addresses.push_back({addr, *alternator_https_port_proxy_protocol});
-            }
-            creds.emplace();
-            auto opts = _config.alternator_encryption_options();
-            if (opts.empty()) {
-                // Earlier versions mistakenly configured Alternator's
-                // HTTPS parameters via the "server_encryption_option"
-                // configuration parameter. We *temporarily* continue
-                // to allow this, for backward compatibility.
-                opts = _config.server_encryption_options();
-                if (!opts.empty()) {
-                logger.warn("Setting server_encryption_options to configure "
-                        "Alternator's HTTPS encryption is deprecated. Please "
-                        "switch to setting alternator_encryption_options instead.");
-                }
-            }
-            opts.erase("require_client_auth");
-            opts.erase("truststore");
-            try {
-                utils::configure_tls_creds_builder(creds.value(), std::move(opts)).get();
-            } catch(...) {
-                logger.error("Failed to set up Alternator TLS credentials: {}", std::current_exception());
-                stop_server().get();
-                std::throw_with_nested(std::runtime_error("Failed to set up Alternator TLS credentials"));
-            }
-        }
-        _server.invoke_on_all(
-                [this, addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol, creds = std::move(creds)] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol, creds,
-                    _config.alternator_enforce_authorization,
-                    _config.alternator_warn_authorization,
-                    _config.alternator_max_users_query_size_in_trace_output,
-                    &_memory_limiter.local().get_semaphore(),
-                    _config.max_concurrent_requests_per_shard);
-        }).handle_exception([this, addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol] (std::exception_ptr ep) {
-            logger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}, proxy-protocol port {}, TLS proxy-protocol port {}: {}",
-                    addr,
-                    alternator_port ? std::to_string(*alternator_port) : "OFF",
-                    alternator_https_port ? std::to_string(*alternator_https_port) : "OFF",
-                    alternator_port_proxy_protocol ? std::to_string(*alternator_port_proxy_protocol) : "OFF",
-                    alternator_https_port_proxy_protocol ? std::to_string(*alternator_https_port_proxy_protocol) : "OFF",
-                    ep);
-            return stop_server().then([ep = std::move(ep)] { return make_exception_future<>(ep); });
-        }).then([addr, alternator_port, alternator_https_port, alternator_port_proxy_protocol, alternator_https_port_proxy_protocol] {
-            logger.info("Alternator server listening on {}, HTTP port {}, HTTPS port {}, proxy-protocol port {}, TLS proxy-protocol port {}",
-                    addr,
-                    alternator_port ? std::to_string(*alternator_port) : "OFF",
-                    alternator_https_port ? std::to_string(*alternator_https_port) : "OFF",
-                    alternator_port_proxy_protocol ? std::to_string(*alternator_port_proxy_protocol) : "OFF",
-                    alternator_https_port_proxy_protocol ? std::to_string(*alternator_https_port_proxy_protocol) : "OFF");
-        }).get();
-    });
-}
-
-future<> controller::stop_server() {
-    return seastar::async([this] {
-        if (!_ssg) {
-            return;
-        }
-        _server.stop().get();
-        _executor.stop().get();
-        _listen_addresses.clear();
-        destroy_smp_service_group(_ssg.value()).get();
-    });
-}
-
-future<> controller::request_stop_server() {
-    return with_scheduling_group(_sched_group, [this] {
-        return stop_server();
-    });
-}
-
-future<utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>>> controller::get_client_data() {
-    return _server.local().get_client_data();
-}
-
-}

alternator/controller.hh

@@ -1,102 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
- */
-
-#pragma once
-
-#include <seastar/core/sharded.hh>
-#include <seastar/core/smp.hh>
-
-#include "transport/protocol_server.hh"
-
-namespace service {
-class storage_proxy;
-class storage_service;
-class migration_manager;
-class memory_limiter;
-}
-
-namespace db {
-class system_distributed_keyspace;
-class config;
-}
-
-namespace cdc {
-class generation_service;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
-
-namespace auth {
-class service;
-}
-
-namespace qos {
-class service_level_controller;
-}
-
-namespace alternator {
-
-// This is the official DynamoDB API version.
-// It represents the last major reorganization of that API, and all the features
-// that were added since did NOT increment this version string.
-constexpr const char* version = "2012-08-10";
-
-using namespace seastar;
-
-class executor;
-class server;
-
-class controller : public protocol_server {
-    sharded<gms::gossiper>& _gossiper;
-    sharded<service::storage_proxy>& _proxy;
-    sharded<service::storage_service>& _ss;
-    sharded<service::migration_manager>& _mm;
-    sharded<db::system_distributed_keyspace>& _sys_dist_ks;
-    sharded<cdc::generation_service>& _cdc_gen_svc;
-    sharded<service::memory_limiter>& _memory_limiter;
-    sharded<auth::service>& _auth_service;
-    sharded<qos::service_level_controller>& _sl_controller;
-    const db::config& _config;
-
-    std::vector<socket_address> _listen_addresses;
-    sharded<executor> _executor;
-    sharded<server> _server;
-    std::optional<smp_service_group> _ssg;
-
-public:
-    controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::storage_service>& ss,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config,
-        seastar::scheduling_group sg);
-
-    virtual sstring name() const override;
-    virtual sstring protocol() const override;
-    virtual sstring protocol_version() const override;
-    virtual std::vector<socket_address> listen_addresses() const override;
-    virtual future<> start_server() override;
-    virtual future<> stop_server() override;
-    virtual future<> request_stop_server() override;
-    // This virtual function is called (on each shard separately) when the
-    // virtual table "system.clients" is read. It is expected to generate a
-    // list of clients connected to this server (on this shard).
-    virtual future<utils::chunked_vector<foreign_ptr<std::unique_ptr<client_data>>>> get_client_data() override;
-};
-
-}

alternator/error.hh

@@ -1,110 +1,49 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include <seastar/http/httpd.hh>
 #include "seastarx.hh"
-#include "utils/rjson.hh"
 
 namespace alternator {
 
-// api_error contains a DynamoDB error message to be returned to the user.
-// It can be returned by value (see executor::request_return_type) or thrown.
-// The DynamoDB's error messages are described in detail in
+// DynamoDB's error messages are described in detail in
 // https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
-// An error message has an HTTP code (almost always 400), a type, e.g.,
-// "ResourceNotFoundException", and a human readable message.
-// Eventually alternator::api_handler will convert a returned or thrown
-// api_error into a JSON object, and that is returned to the user.
-class api_error final : public std::exception {
+// Ah An error message has a "type", e.g., "ResourceNotFoundException", a coarser
+// HTTP code (almost always, 400), and a human readable message. Eventually these
+// will be wrapped into a JSON object returned to the client.
+class api_error : public std::exception {
 public:
-    using status_type = http::reply::status_type;
+    using status_type = httpd::reply::status_type;
     status_type _http_code;
     std::string _type;
     std::string _msg;
-    // Additional data attached to the error, null value if not set. It's wrapped in copyable_value
-    // class because copy constructor is required for exception classes otherwise it won't compile
-    // (despite that its use may be optimized away).
-    rjson::copyable_value _extra_fields; 
-    api_error(std::string type, std::string msg, status_type http_code = status_type::bad_request,
-    rjson::value extra_fields = rjson::null_value())
+    api_error(std::string type, std::string msg, status_type http_code = status_type::bad_request)
         : _http_code(std::move(http_code))
         , _type(std::move(type))
         , _msg(std::move(msg))
-        , _extra_fields(std::move(extra_fields))
     { }
-
-    // Factory functions for some common types of DynamoDB API errors
-    static api_error validation(std::string msg) {
-        return api_error("ValidationException", std::move(msg));
-    }
-    static api_error resource_not_found(std::string msg) {
-        return api_error("ResourceNotFoundException", std::move(msg));
-    }
-    static api_error resource_in_use(std::string msg) {
-        return api_error("ResourceInUseException", std::move(msg));
-    }
-    static api_error invalid_signature(std::string msg) {
-        return api_error("InvalidSignatureException", std::move(msg));
-    }
-    static api_error missing_authentication_token(std::string msg) {
-        return api_error("MissingAuthenticationTokenException", std::move(msg));
-    }
-    static api_error unrecognized_client(std::string msg) {
-        return api_error("UnrecognizedClientException", std::move(msg));
-    }
-    static api_error unknown_operation(std::string msg) {
-        return api_error("UnknownOperationException", std::move(msg));
-    }
-    static api_error access_denied(std::string msg) {
-        return api_error("AccessDeniedException", std::move(msg));
-    }
-    static api_error conditional_check_failed(std::string msg, rjson::value&& item) {
-        if (!item.IsNull()) {
-            auto tmp = rjson::empty_object();
-            rjson::add(tmp, "Item", std::move(item));
-            item = std::move(tmp);
-        }
-        return api_error("ConditionalCheckFailedException", std::move(msg), status_type::bad_request, std::move(item));
-    }
-    static api_error expired_iterator(std::string msg) {
-        return api_error("ExpiredIteratorException", std::move(msg));
-    }
-    static api_error trimmed_data_access_exception(std::string msg) {
-        return api_error("TrimmedDataAccessException", std::move(msg));
-    }
-    static api_error request_limit_exceeded(std::string msg) {
-        return api_error("RequestLimitExceeded", std::move(msg));
-    }
-    static api_error serialization(std::string msg) {
-        return api_error("SerializationException", std::move(msg));
-    }
-    static api_error table_not_found(std::string msg) {
-        return api_error("TableNotFoundException", std::move(msg));
-    }
-    static api_error limit_exceeded(std::string msg) {
-        return api_error("LimitExceededException", std::move(msg));
-    }
-    static api_error internal(std::string msg) {
-        return api_error("InternalServerError", std::move(msg), http::reply::status_type::internal_server_error);
-    }
-    static api_error payload_too_large(std::string msg) {
-        return api_error("PayloadTooLarge", std::move(msg), status_type::payload_too_large);
-    }
-
-    // Provide the "std::exception" interface, to make it easier to print this
-    // exception in log messages. Note that this function is *not* used to
-    // format the error to send it back to the client - server.cc has
-    // generate_error_reply() to format an api_error as the DynamoDB protocol
-    // requires.
-    virtual const char* what() const noexcept override;
-    mutable std::string _what_string;
+    api_error() = default;
+    virtual const char* what() const noexcept override { return _msg.c_str(); }
 };
 
 }

alternator/executor.hh

@@ -1,304 +1,71 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include <seastar/core/future.hh>
+#include <seastar/http/httpd.hh>
 #include "seastarx.hh"
-#include <seastar/core/sharded.hh>
-#include <seastar/util/noncopyable_function.hh>
+#include <seastar/json/json_elements.hh>
 
+#include "service/storage_proxy.hh"
 #include "service/migration_manager.hh"
 #include "service/client_state.hh"
-#include "service_permit.hh"
-#include "db/timeout_clock.hh"
-#include "db/config.hh"
 
-#include "alternator/error.hh"
 #include "stats.hh"
-#include "utils/rjson.hh"
-#include "utils/updateable_value.hh"
-#include "utils/simple_value_with_expiry.hh"
-
-#include "tracing/trace_state.hh"
-
-namespace db {
-    class system_distributed_keyspace;
-}
-
-namespace query {
-class partition_slice;
-class result;
-}
-
-namespace cql3::selection {
-    class selection;
-}
-
-namespace service {
-    class storage_proxy;
-    class cas_shard;
-    class storage_service;
-}
-
-namespace cdc {
-    class metadata;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
-
-class schema_builder;
 
 namespace alternator {
 
-enum class table_status;
-class rmw_operation;
-class put_or_delete_item;
-
-schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
-bool is_alternator_keyspace(const sstring& ks_name);
-// Wraps the db::get_tags_of_table and throws if the table is missing the tags extension.
-const std::map<sstring, sstring>& get_tags_of_table_or_throw(schema_ptr schema);
-
-// An attribute_path_map object is used to hold data for various attributes
-// paths (parsed::path) in a hierarchy of attribute paths. Each attribute path
-// has a root attribute, and then modified by member and index operators -
-// for example in "a.b[2].c" we have "a" as the root, then ".b" member, then
-// "[2]" index, and finally ".c" member.
-// Data can be added to an attribute_path_map using the add() function, but
-// requires that attributes with data not be *overlapping* or *conflicting*:
-//
-// 1. Two attribute paths which are identical or an ancestor of one another
-//    are considered *overlapping* and not allowed. If a.b.c has data,
-//    we can't add more data in a.b.c or any of its descendants like a.b.c.d.
-//
-// 2. Two attribute paths which need the same parent to have both a member and
-//    an index are considered *conflicting* and not allowed. E.g., if a.b has
-//    data, you can't add a[1]. The meaning of adding both would be that the
-//    attribute a is both a map and an array, which isn't sensible.
-//
-// These two requirements are common to the two places where Alternator uses
-// this abstraction to describe how a hierarchical item is to be transformed:
-//
-// 1. In ProjectExpression: for filtering from a full top-level attribute
-//    only the parts for which user asked in ProjectionExpression.
-//
-// 2. In UpdateExpression: for taking the previous value of a top-level
-//    attribute, and modifying it based on the instructions in the user
-//    wrote in UpdateExpression.
-
-template<typename T>
-class attribute_path_map_node {
-public:
-    using data_t = T;
-    // We need the extra unique_ptr<> here because libstdc++ unordered_map
-    // doesn't work with incomplete types :-(
-    using members_t =  std::unordered_map<std::string, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The indexes list is sorted because DynamoDB requires handling writes
-    // beyond the end of a list in index order.
-    using indexes_t = std::map<unsigned, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The prohibition on "overlap" and "conflict" explained above means
-    // That only one of data, members or indexes is non-empty.
-    std::optional<std::variant<data_t, members_t, indexes_t>> _content;
-
-    bool is_empty() const { return !_content; }
-    bool has_value() const { return _content && std::holds_alternative<data_t>(*_content); }
-    bool has_members() const { return _content && std::holds_alternative<members_t>(*_content); }
-    bool has_indexes() const { return _content && std::holds_alternative<indexes_t>(*_content); }
-    // get_members() assumes that has_members() is true
-    members_t& get_members() { return std::get<members_t>(*_content); }
-    const members_t& get_members() const { return std::get<members_t>(*_content); }
-    indexes_t& get_indexes() { return std::get<indexes_t>(*_content); }
-    const indexes_t& get_indexes() const { return std::get<indexes_t>(*_content); }
-    T& get_value() { return std::get<T>(*_content); }
-    const T& get_value() const { return std::get<T>(*_content); }
-};
-
-template<typename T>
-using attribute_path_map = std::unordered_map<std::string, attribute_path_map_node<T>>;
-
-using attrs_to_get_node = attribute_path_map_node<std::monostate>;
-// attrs_to_get lists which top-level attribute are needed, and possibly also
-// which part of the top-level attribute is really needed (when nested
-// attribute paths appeared in the query).
-// Most code actually uses optional<attrs_to_get>. There, a disengaged
-// optional means we should get all attributes, not specific ones.
-using attrs_to_get = attribute_path_map<std::monostate>;
-
-namespace parsed {
-class expression_cache;
-}
-
-class executor : public peering_sharded_service<executor> {
-    gms::gossiper& _gossiper;
-    service::storage_service& _ss;
+class executor {
     service::storage_proxy& _proxy;
     service::migration_manager& _mm;
-    db::system_distributed_keyspace& _sdks;
-    cdc::metadata& _cdc_metadata;
-    utils::updateable_value<bool> _enforce_authorization;
-    utils::updateable_value<bool> _warn_authorization;
-    // An smp_service_group to be used for limiting the concurrency when
-    // forwarding Alternator request between shards - if necessary for LWT.
-    smp_service_group _ssg;
 
-    std::unique_ptr<parsed::expression_cache> _parsed_expression_cache;
-
-    struct describe_table_info_manager;
-    std::unique_ptr<describe_table_info_manager> _describe_table_info_manager;
-
-    future<> cache_newly_calculated_size_on_all_shards(schema_ptr schema, std::uint64_t size_in_bytes, std::chrono::nanoseconds ttl);
-    future<> fill_table_size(rjson::value &table_description, schema_ptr schema, bool deleting);
 public:
     using client_state = service::client_state;
-    // request_return_type is the return type of the executor methods, which
-    // can be one of:
-    // 1. A string, which is the response body for the request.
-    // 2. A body_writer, an asynchronous function (returning future<>) that
-    //    takes an output_stream and writes the response body into it.
-    // 3. An api_error, which is an error response that should be returned to
-    //    the client.
-    // The body_writer is used for streaming responses, where the response body
-    // is written in chunks to the output_stream. This allows for efficient
-    // handling of large responses without needing to allocate a large buffer
-    // in memory.
-    using body_writer = noncopyable_function<future<>(output_stream<char>&&)>;
-    using request_return_type = std::variant<std::string, body_writer, api_error>;
     stats _stats;
-    // The metric_groups object holds this stat object's metrics registered
-    // as long as the stats object is alive.
-    seastar::metrics::metric_groups _metrics;
     static constexpr auto ATTRS_COLUMN_NAME = ":attrs";
-    static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
-    static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.alternator.";
+    static constexpr auto KEYSPACE_NAME = "alternator";
 
-    executor(gms::gossiper& gossiper,
-             service::storage_proxy& proxy,
-             service::storage_service& ss,
-             service::migration_manager& mm,
-             db::system_distributed_keyspace& sdks,
-             cdc::metadata& cdc_metadata,
-             smp_service_group ssg,
-             utils::updateable_value<uint32_t> default_timeout_in_ms);
-    ~executor();
+    executor(service::storage_proxy& proxy, service::migration_manager& mm) : _proxy(proxy), _mm(mm) {}
 
-    future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> delete_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> put_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> delete_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_tables(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> scan(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_endpoints(client_state& client_state, service_permit permit, rjson::value request, std::string host_header);
-    future<request_return_type> batch_write_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> batch_get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> query(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> tag_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> untag_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_tags_of_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_streams(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_stream(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_shard_iterator(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_records(client_state& client_state, tracing::trace_state_ptr, service_permit permit, rjson::value request);
-    future<request_return_type> describe_continuous_backups(client_state& client_state, service_permit permit, rjson::value request);
+    future<json::json_return_type> create_table(client_state& client_state, std::string content);
+    future<json::json_return_type> describe_table(client_state& client_state, std::string content);
+    future<json::json_return_type> delete_table(client_state& client_state, std::string content);
+    future<json::json_return_type> put_item(client_state& client_state, std::string content);
+    future<json::json_return_type> get_item(client_state& client_state, std::string content);
+    future<json::json_return_type> delete_item(client_state& client_state, std::string content);
+    future<json::json_return_type> update_item(client_state& client_state, std::string content);
+    future<json::json_return_type> list_tables(client_state& client_state, std::string content);
+    future<json::json_return_type> scan(client_state& client_state, std::string content);
+    future<json::json_return_type> describe_endpoints(client_state& client_state, std::string content, std::string host_header);
+    future<json::json_return_type> batch_write_item(client_state& client_state, std::string content);
+    future<json::json_return_type> batch_get_item(client_state& client_state, std::string content);
+    future<json::json_return_type> query(client_state& client_state, std::string content);
 
     future<> start();
-    future<> stop();
+    future<> stop() { return make_ready_future<>(); }
 
-    static sstring table_name(const schema&);
-    static db::timeout_clock::time_point default_timeout();
-private:
-    static thread_local utils::updateable_value<uint32_t> s_default_timeout_in_ms;
-public:
-    static schema_ptr find_table(service::storage_proxy&, std::string_view table_name);
-    static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);
+    future<> maybe_create_keyspace();
 
-private:
-    friend class rmw_operation;
-
-    static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr, const std::map<sstring, sstring> *tags = nullptr);
-    future<rjson::value> fill_table_description(schema_ptr schema, table_status tbl_status, service::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit);
-    future<executor::request_return_type> create_table_on_shard0(service::client_state&& client_state, tracing::trace_state_ptr trace_state, rjson::value request, bool enforce_authorization, bool warn_authorization, const db::tablets_mode_t::mode tablets_mode);
-
-    future<> do_batch_write(
-        std::vector<std::pair<schema_ptr, put_or_delete_item>> mutation_builders,
-        service::client_state& client_state,
-        tracing::trace_state_ptr trace_state,
-        service_permit permit);
-
-    future<> cas_write(schema_ptr schema, service::cas_shard cas_shard, const dht::decorated_key& dk,
-        const std::vector<put_or_delete_item>& mutation_builders, service::client_state& client_state,
-        tracing::trace_state_ptr trace_state, service_permit permit);
-
-public:
-    static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&, const std::map<sstring, sstring> *tags = nullptr);
-
-    static std::optional<rjson::value> describe_single_item(schema_ptr,
-        const query::partition_slice&,
-        const cql3::selection::selection&,
-        const query::result&,
-        const std::optional<attrs_to_get>&,
-        uint64_t* = nullptr);
-
-    // Converts a multi-row selection result to JSON compatible with DynamoDB.
-    // For each row, this method calls item_callback, which takes the size of
-    // the item as the parameter.
-    static future<std::vector<rjson::value>> describe_multi_item(schema_ptr schema,
-        const query::partition_slice&& slice,
-        shared_ptr<cql3::selection::selection> selection,
-        foreign_ptr<lw_shared_ptr<query::result>> query_result,
-        shared_ptr<const std::optional<attrs_to_get>> attrs_to_get,
-        noncopyable_function<void(uint64_t)> item_callback = {});
-
-    static void describe_single_item(const cql3::selection::selection&,
-        const std::vector<managed_bytes_opt>&,
-        const std::optional<attrs_to_get>&,
-        rjson::value&,
-        uint64_t* item_length_in_bytes = nullptr,
-        bool = false);
-
-    static bool add_stream_options(const rjson::value& stream_spec, schema_builder&, service::storage_proxy& sp);
-    static void supplement_table_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
-    static void supplement_table_stream_info(rjson::value& descr, const schema& schema, const service::storage_proxy& sp);
+    static void maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
 };
 
-// is_big() checks approximately if the given JSON value is "bigger" than
-// the given big_size number of bytes. The goal is to *quickly* detect
-// oversized JSON that, for example, is too large to be serialized to a
-// contiguous string - we don't need an accurate size for that. Moreover,
-// as soon as we detect that the JSON is indeed "big", we can return true
-// and don't need to continue calculating its exact size.
-// For simplicity, we use a recursive implementation. This is fine because
-// Alternator limits the depth of JSONs it reads from inputs, and doesn't
-// add more than a couple of levels in its own output construction.
-bool is_big(const rjson::value& val, int big_size = 100'000);
-
-// Check CQL's Role-Based Access Control (RBAC) permission (MODIFY,
-// SELECT, DROP, etc.) on the given table. When permission is denied an
-// appropriate user-readable api_error::access_denied is thrown.
-future<> verify_permission(bool enforce_authorization, bool warn_authorization, const service::client_state&, const schema_ptr&, auth::permission, alternator::stats& stats);
-
-/**
- * Make return type for serializing the object "streamed",
- * i.e. direct to HTTP output stream. Note: only useful for
- * (very) large objects as there are overhead issues with this
- * as well, but for massive lists of return objects this can
- * help avoid large allocations/many re-allocs
- */
-executor::body_writer make_streamed(rjson::value&&);
-
 }

alternator/expressions.cc

@@ -1,32 +1,39 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "expressions.hh"
-#include "serialization.hh"
-#include "utils/base64.hh"
-#include "conditions.hh"
 #include "alternator/expressionsLexer.hpp"
 #include "alternator/expressionsParser.hpp"
-#include "utils/overloaded_functor.hh"
-#include "error.hh"
 
-#include "seastarx.hh"
+#include <seastarx.hh>
 
-#include <seastar/core/format.hh>
+#include <seastar/core/print.hh>
 #include <seastar/util/log.hh>
 
 #include <functional>
-#include <unordered_map>
 
 namespace alternator {
 
-template <typename Func, typename Result = std::invoke_result_t<Func, expressionsParser&>>
-static Result do_with_parser(std::string_view input, Func&& f) {
+template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
+Result do_with_parser(std::string input, Func&& f) {
     expressionsLexer::InputStreamType input_stream{
         reinterpret_cast<const ANTLR_UINT8*>(input.data()),
         ANTLR_ENC_UTF8,
@@ -40,47 +47,31 @@ static Result do_with_parser(std::string_view input, Func&& f) {
     return result;
 }
 
-template <typename Func, typename Result = std::invoke_result_t<Func, expressionsParser&>>
-static Result parse(const char* input_name, std::string_view input, Func&& f) {
-    if (input.length() > 4096) {
-        throw expressions_syntax_error(format("{} expression size {} exceeds allowed maximum 4096.",
-            input_name, input.length()));
-    }
-    try {
-        return do_with_parser(input, f);
-    } catch (expressions_syntax_error& e) {
-        // If already an expressions_syntax_error, don't print the type's
-        // name (it's just ugly), just the message.
-        // TODO: displayRecognitionError could set a position inside the
-        // expressions_syntax_error in throws, and we could use it here to
-        // mark the broken position in 'input'.
-        throw expressions_syntax_error(fmt::format("Failed parsing {} '{}': {}",
-            input_name, input, e.what()));
-    } catch (...) {
-        throw expressions_syntax_error(fmt::format("Failed parsing {} '{}': {}",
-            input_name, input, std::current_exception()));
-    }
-}
-
 parsed::update_expression
-parse_update_expression(std::string_view query) {
-    return parse("UpdateExpression", query,  std::mem_fn(&expressionsParser::update_expression));
+parse_update_expression(std::string query) {
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::update_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing UpdateExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 std::vector<parsed::path>
-parse_projection_expression(std::string_view query) {
-    return parse ("ProjectionExpression", query,  std::mem_fn(&expressionsParser::projection_expression));
+parse_projection_expression(std::string query) {
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::projection_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing ProjectionExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
-parsed::condition_expression
-parse_condition_expression(std::string_view query, const char* caller) {
-    return parse(caller, query,  std::mem_fn(&expressionsParser::condition_expression));
-}
+template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
+template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
 
 namespace parsed {
 
 void update_expression::add(update_expression::action a) {
-    std::visit(overloaded_functor {
+    std::visit(overloaded {
         [&] (action::set&)    { seen_set = true; },
         [&] (action::remove&) { seen_remove = true; },
         [&] (action::add&)    { seen_add = true; },
@@ -103,677 +94,5 @@ void update_expression::append(update_expression other) {
     seen_del |= other.seen_del;
 }
 
-void condition_expression::append(condition_expression&& a, char op) {
-    std::visit(overloaded_functor {
-        [&] (condition_list& x) {
-            // If 'a' has a single condition, we could, instead of inserting
-            // it insert its single condition (possibly negated if a._negated)
-            // But considering it we don't evaluate these expressions many
-            // times, this optimization is not worth extra code complexity.
-            if (!x.conditions.empty() && x.op != op) {
-                // Shouldn't happen unless we have a bug in the parser
-                throw std::logic_error("condition_expression::append called with mixed operators");
-            }
-            x.conditions.push_back(std::move(a));
-            x.op = op;
-        },
-        [&] (primitive_condition& x) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error("condition_expression::append called on primitive_condition");
-        }
-    }, _expression);
-}
-
-void path::check_depth_limit() {
-    if (1 + _operators.size() > depth_limit) {
-        throw expressions_syntax_error(format("Document path exceeded {} nesting levels", depth_limit));
-    }
-}
-
 } // namespace parsed
-
-// The following resolve_*() functions resolve references in parsed
-// expressions of different types. Resolving a parsed expression means
-// replacing:
-//  1. In parsed::path objects, replace references like "#name" with the
-//     attribute name from ExpressionAttributeNames,
-//  2. In parsed::constant objects, replace references like ":value" with
-//     the value from ExpressionAttributeValues.
-// These function also track which name and value references were used, to
-// allow complaining if some remain unused.
-// Note that the resolve_*() functions modify the expressions in-place,
-// so if we ever intend to cache parsed expression, we need to pass a copy
-// into this function.
-//
-// Doing the "resolving" stage before the evaluation stage has two benefits.
-// First, it allows us to be compatible with DynamoDB in catching unused
-// names and values (see issue #6572). Second, in the FilterExpression case,
-// we need to resolve the expression just once but then use it many times
-// (once for each item to be filtered).
-
-static std::optional<std::string> resolve_path_component(const std::string& column_name,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    if (column_name.size() > 0 && column_name.front() == '#') {
-        if (!expression_attribute_names) {
-            throw api_error::validation(
-                    fmt::format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
-        }
-        const rjson::value* value = rjson::find(*expression_attribute_names, column_name);
-        if (!value || !value->IsString()) {
-            throw api_error::validation(
-                    fmt::format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
-        }
-        used_attribute_names.emplace(column_name);
-        auto result = std::string(rjson::to_string_view(*value));
-        validate_attr_name_length("", result.size(), false, "ExpressionAttributeNames contains invalid value: ");
-        return result;
-    }
-    return std::nullopt;
-}
-
-static void resolve_path(parsed::path& p,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    std::optional<std::string> r = resolve_path_component(p.root(), expression_attribute_names, used_attribute_names);
-    if (r) {
-        p.set_root(std::move(*r));
-    }
-    for (auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (std::string& s) {
-                r = resolve_path_component(s, expression_attribute_names, used_attribute_names);
-                if (r) {
-                    s = std::move(*r);
-                }
-            },
-            [&] (unsigned index) {
-                // nothing to resolve
-            }
-        }, op);
-    }
-}
-
-static void resolve_constant(parsed::constant& c,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (const std::string& valref) {
-            if (!expression_attribute_values) {
-                throw api_error::validation(
-                        fmt::format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
-            }
-            const rjson::value* value = rjson::find(*expression_attribute_values, valref);
-            if (!value) {
-                throw api_error::validation(
-                        fmt::format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
-            }
-            if (value->IsNull()) {
-                throw api_error::validation(
-                        fmt::format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
-            }
-            validate_value(*value, "ExpressionAttributeValues");
-            used_attribute_values.emplace(valref);
-            c.set(*value);
-        },
-        [&] (const parsed::constant::literal& lit) {
-            // Nothing to do, already resolved
-        }
-    }, c._value);
-
-}
-
-void resolve_value(parsed::value& rhs,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (parsed::constant& c) {
-            resolve_constant(c, expression_attribute_values, used_attribute_values);
-        },
-        [&] (parsed::value::function_call& f) {
-            for (parsed::value& value : f._parameters) {
-                resolve_value(value, expression_attribute_names, expression_attribute_values,
-                        used_attribute_names, used_attribute_values);
-            }
-        },
-        [&] (parsed::path& p) {
-            resolve_path(p, expression_attribute_names, used_attribute_names);
-        }
-    }, rhs._value);
-}
-
-void resolve_set_rhs(parsed::set_rhs& rhs,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    resolve_value(rhs._v1, expression_attribute_names, expression_attribute_values,
-            used_attribute_names, used_attribute_values);
-    if (rhs._op != 'v') {
-        resolve_value(rhs._v2, expression_attribute_names, expression_attribute_values,
-                used_attribute_names, used_attribute_values);
-    }
-}
-
-void resolve_update_expression(parsed::update_expression& ue,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    for (parsed::update_expression::action& action : ue.actions()) {
-        resolve_path(action._path, expression_attribute_names, used_attribute_names);
-        std::visit(overloaded_functor {
-            [&] (parsed::update_expression::action::set& a) {
-                resolve_set_rhs(a._rhs, expression_attribute_names, expression_attribute_values,
-                        used_attribute_names, used_attribute_values);
-            },
-            [&] (parsed::update_expression::action::remove& a) {
-                // nothing to do
-            },
-            [&] (parsed::update_expression::action::add& a) {
-                resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
-            },
-            [&] (parsed::update_expression::action::del& a) {
-                resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
-            }
-        }, action._action);
-    }
-}
-
-static void resolve_primitive_condition(parsed::primitive_condition& pc,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    for (parsed::value& value : pc._values) {
-        resolve_value(value,
-                expression_attribute_names, expression_attribute_values,
-                used_attribute_names, used_attribute_values);
-    }
-}
-
-void resolve_condition_expression(parsed::condition_expression& ce,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (parsed::primitive_condition& cond) {
-            resolve_primitive_condition(cond,
-                    expression_attribute_names, expression_attribute_values,
-                    used_attribute_names, used_attribute_values);
-        },
-        [&] (parsed::condition_expression::condition_list& list) {
-            for (parsed::condition_expression& cond : list.conditions) {
-                resolve_condition_expression(cond,
-                        expression_attribute_names, expression_attribute_values,
-                            used_attribute_names, used_attribute_values);
-
-            }
-        }
-    }, ce._expression);
-}
-
-void resolve_projection_expression(std::vector<parsed::path>& pe,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    for (parsed::path& p : pe) {
-        resolve_path(p, expression_attribute_names, used_attribute_names);
-    }
-}
-
-// condition_expression_on() checks whether a condition_expression places any
-// condition on the given attribute. It can be useful, for example, for
-// checking whether the condition tries to restrict a key column.
-
-static bool value_on(const parsed::value& v, std::string_view attribute) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) {
-            return false;
-        },
-        [&] (const parsed::value::function_call& f) {
-            for (const parsed::value& value : f._parameters) {
-                if (value_on(value, attribute)) {
-                    return true;
-                }
-            }
-            return false;
-        },
-        [&] (const parsed::path& p) {
-            return p.root() == attribute;
-        }
-    }, v._value);
-}
-
-static bool primitive_condition_on(const parsed::primitive_condition& pc, std::string_view attribute) {
-    for (const parsed::value& value : pc._values) {
-        if (value_on(value, attribute)) {
-            return true;
-        }
-    }
-    return false;
-}
-
-bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) {
-            return primitive_condition_on(cond, attribute);
-        },
-        [&] (const parsed::condition_expression::condition_list& list) {
-            for (const parsed::condition_expression& cond : list.conditions) {
-                if (condition_expression_on(cond, attribute)) {
-                    return true;
-                }
-            }
-            return false;
-        }
-    }, ce._expression);
-}
-
-// for_condition_expression_on() runs a given function over all the attributes
-// mentioned in the expression. If the same attribute is mentioned more than
-// once, the function will be called more than once for the same attribute.
-
-static void for_value_on(const parsed::value& v, const noncopyable_function<void(std::string_view)>& func) {
-    std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) { },
-        [&] (const parsed::value::function_call& f) {
-            for (const parsed::value& value : f._parameters) {
-                for_value_on(value, func);
-            }
-        },
-        [&] (const parsed::path& p) {
-            func(p.root());
-        }
-    }, v._value);
-}
-
-void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func) {
-    std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) {
-            for (const parsed::value& value : cond._values) {
-                for_value_on(value, func);
-            }
-        },
-        [&] (const parsed::condition_expression::condition_list& list) {
-            for (const parsed::condition_expression& cond : list.conditions) {
-                for_condition_expression_on(cond, func);
-            }
-        }
-    }, ce._expression);
-}
-
-// The following calculate_value() functions calculate, or evaluate, a parsed
-// expression. The parsed expression is assumed to have been "resolved", with
-// the matching resolve_* function.
-
-// calculate_size() is ConditionExpression's size() function, i.e., it takes
-// a JSON-encoded value and returns its "size" as defined differently for the
-// different types - also as a JSON-encoded number.
-// If the value's type (e.g. number) has no size defined, there are two cases:
-// 1. If from_data (the value came directly from an attribute of the data),
-//    It returns a JSON-encoded "null" value. Comparisons against this
-//    non-numeric value will later fail, so eventually the application will
-//    get a ConditionalCheckFailedException.
-// 2. Otherwise (the value came from a constant in the query or some other
-//    calculation), throw a ValidationException.
-static rjson::value calculate_size(const rjson::value& v, bool from_data) {
-    // NOTE: If v is improperly formatted for our JSON value encoding, it
-    // must come from the request itself, not from the database, so it makes
-    // sense to throw a ValidationException if we see such a problem.
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(format("invalid object: {}", v));
-    }
-    auto it = v.MemberBegin();
-    int ret;
-    if (it->name == "S") {
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("invalid string: {}", v));
-        }
-        ret = it->value.GetStringLength();
-    } else if (it->name == "NS" || it->name == "SS" || it->name == "BS" || it->name == "L") {
-        if (!it->value.IsArray()) {
-            throw api_error::validation(format("invalid set: {}", v));
-        }
-        ret = it->value.Size();
-    } else if (it->name == "M") {
-        if (!it->value.IsObject()) {
-            throw api_error::validation(format("invalid map: {}", v));
-        }
-        ret = it->value.MemberCount();
-    } else if (it->name == "B") {
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("invalid byte string: {}", v));
-        }
-        ret = base64_decoded_len(rjson::to_string_view(it->value));
-    } else if (from_data) {
-        rjson::value json_ret = rjson::empty_object();
-        rjson::add(json_ret, "null", rjson::value(true));
-        return json_ret;
-    } else {
-        throw api_error::validation(format("Unsupported operand type {} for function size()", it->name));
-    }
-    rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "N", rjson::from_string(std::to_string(ret)));
-    return json_ret;
-}
-
-static const rjson::value& calculate_value(const parsed::constant& c) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant::literal& v) -> const rjson::value& {
-            return *v;
-        },
-        [&] (const std::string& valref) -> const rjson::value& {
-            // Shouldn't happen, we should have called resolve_value() earlier
-            // and replaced the value reference by the literal constant.
-            throw std::logic_error("calculate_value() called before resolve_value()");
-        }
-    }, c._value);
-}
-
-static rjson::value to_bool_json(bool b) {
-    rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "BOOL", rjson::value(b));
-    return json_ret;
-}
-
-static bool known_type(std::string_view type) {
-    static thread_local const std::unordered_set<std::string_view> types = {
-            "N", "S", "B", "NS", "SS", "BS", "L", "M", "NULL", "BOOL"
-    };
-    return types.contains(type);
-}
-
-using function_handler_type = rjson::value(calculate_value_caller, const rjson::value*, const parsed::value::function_call&);
-static const
-std::unordered_map<std::string_view, function_handler_type*> function_handlers {
-    {"list_append", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::UpdateExpression) {
-                throw api_error::validation(
-                        format("{}: list_append() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: list_append() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            rjson::value ret = list_concatenate(v1, v2);
-            if (ret.IsNull()) {
-                throw api_error::validation("UpdateExpression: list_append() given a non-list");
-            }
-            return ret;
-        }
-    },
-    {"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::UpdateExpression) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() must include path as its first argument", caller));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return v1.IsNull() ? std::move(v2) : std::move(v1);
-        }
-    },
-    {"size", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpression) {
-                throw api_error::validation(
-                        format("{}: size() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: size() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return calculate_size(v, f._parameters[0].is_path());
-        }
-    },
-    {"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: attribute_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: attribute_exists()'s parameter must be a path", caller));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return to_bool_json(!v.IsNull());
-        }
-    },
-    {"attribute_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists()'s parameter must be a path", caller));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return to_bool_json(v.IsNull());
-        }
-    },
-    {"attribute_type", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_type() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: attribute_type() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            // There is no real reason for the following check (not
-            // allowing the type to come from a document attribute), but
-            // DynamoDB does this check, so we do too...
-            if (!f._parameters[1].is_constant()) {
-                throw api_error::validation(
-                        format("{}: attribute_types()'s first parameter must be an expression attribute", caller));
-            }
-            rjson::value v0 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v1 = calculate_value(f._parameters[1], caller, previous_item);
-            if (v1.IsObject() && v1.MemberCount() == 1 && v1.MemberBegin()->name == "S") {
-                // If the type parameter is not one of the legal types
-                // we should generate an error, not a failed condition:
-                if (!known_type(rjson::to_string_view(v1.MemberBegin()->value))) {
-                    throw api_error::validation(
-                            format("{}: attribute_types()'s second parameter, {}, is not a known type",
-                                    caller, v1.MemberBegin()->value));
-                }
-                if (v0.IsObject() && v0.MemberCount() == 1) {
-                    return to_bool_json(v1.MemberBegin()->value == v0.MemberBegin()->name);
-                } else {
-                    return to_bool_json(false);
-                }
-            } else {
-                throw api_error::validation(
-                        format("{}: attribute_type() second parameter must refer to a string, got {}", caller, v1));
-            }
-        }
-    },
-    {"begins_with", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: begins_with() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: begins_with() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_BEGINS_WITH(v1.IsNull() ? nullptr : &v1,  v2,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
-        }
-    },
-    {"contains", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: contains() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: contains() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1,  v2,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
-        }
-    },
-};
-
-// Given a parsed::path and an item read from the table, extract the value
-// of a certain attribute path, such as "a" or "a.b.c[3]". Returns a null
-// value if the item or the requested attribute does not exist.
-// Note that the item is assumed to be encoded in JSON using DynamoDB
-// conventions - each level of a nested document is a map with one key -
-// a type (e.g., "M" for map) - and its value is the representation of
-// that value.
-static rjson::value extract_path(const rjson::value* item,
-        const parsed::path& p, calculate_value_caller caller) {
-    if (!item) {
-        return rjson::null_value();
-    }
-    const rjson::value* v = rjson::find(*item, p.root());
-    if (!v) {
-        return rjson::null_value();
-    }
-    for (const auto& op : p.operators()) {
-        if (!v->IsObject() || v->MemberCount() != 1) {
-            // This shouldn't happen. We shouldn't have stored malformed
-            // objects. But today Alternator does not validate the structure
-            // of nested documents before storing them, so this can happen on
-            // read.
-            throw api_error::validation(format("{}: malformed item read: {}", caller, *item));
-        }
-        const char* type = v->MemberBegin()->name.GetString();
-        v = &(v->MemberBegin()->value);
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                if (type[0] == 'M' && v->IsObject()) {
-                    v = rjson::find(*v, member);
-                } else {
-                    v = nullptr;
-                }
-            },
-            [&] (unsigned index) {
-                if (type[0] == 'L' && v->IsArray() && index < v->Size()) {
-                    v = &(v->GetArray()[index]);
-                } else {
-                    v = nullptr;
-                }
-            }
-        }, op);
-        if (!v) {
-            return rjson::null_value();
-        }
-    }
-    return rjson::copy(*v);
-}
-
-// Given a parsed::value, which can refer either to a constant value from
-// ExpressionAttributeValues, to the value of some attribute, or to a function
-// of other values, this function calculates the resulting value.
-// "caller" determines which expression - ConditionExpression or
-// UpdateExpression - is asking for this value. We need to know this because
-// DynamoDB allows a different choice of functions for different expressions.
-rjson::value calculate_value(const parsed::value& v,
-        calculate_value_caller caller,
-        const rjson::value* previous_item) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) -> rjson::value {
-            return rjson::copy(calculate_value(c));
-        },
-        [&] (const parsed::value::function_call& f) -> rjson::value {
-            auto function_it = function_handlers.find(std::string_view(f._function_name));
-            if (function_it == function_handlers.end()) {
-                throw api_error::validation(
-                        fmt::format("{}: unknown function '{}' called.", caller, f._function_name));
-            }
-            return function_it->second(caller, previous_item, f);
-        },
-        [&] (const parsed::path& p) -> rjson::value {
-            return extract_path(previous_item, p, caller);
-        }
-    }, v._value);
-}
-
-// Same as calculate_value() above, except takes a set_rhs, which may be
-// either a single value, or v1+v2 or v1-v2.
-rjson::value calculate_value(const parsed::set_rhs& rhs,
-        const rjson::value* previous_item) {
-    switch (rhs._op) {
-    case 'v':
-        return calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-    case '+': {
-        rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-        rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
-        return number_add(v1, v2);
-    }
-    case '-': {
-        rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-        rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
-        return number_subtract(v1, v2);
-    }
-    }
-    // Can't happen
-    return rjson::null_value();
-}
-
-void validate_attr_name_length(std::string_view supplementary_context, size_t attr_name_length, bool is_key, std::string_view error_msg_prefix) {
-    constexpr const size_t DYNAMODB_KEY_ATTR_NAME_SIZE_MAX = 255;
-    constexpr const size_t DYNAMODB_NONKEY_ATTR_NAME_SIZE_MAX = 65535;
-
-    const size_t max_length = is_key ? DYNAMODB_KEY_ATTR_NAME_SIZE_MAX : DYNAMODB_NONKEY_ATTR_NAME_SIZE_MAX;
-    if (attr_name_length > max_length) {
-        std::string error_msg;
-        if (!error_msg_prefix.empty()) {
-            error_msg += error_msg_prefix;
-        }
-        if (!supplementary_context.empty()) {
-            error_msg += "in ";
-            error_msg += supplementary_context;
-            error_msg += " - ";
-        }
-        error_msg += fmt::format("Attribute name is too large, must be less than {} bytes", std::to_string(max_length + 1));
-        throw api_error::validation(error_msg);
-    }
-}
-
 } // namespace alternator
-
-auto fmt::formatter<alternator::parsed::path>::format(const alternator::parsed::path& p, fmt::format_context& ctx) const
-        -> decltype(ctx.out()) {
-    auto out = ctx.out();
-    out = fmt::format_to(out, "{}", p.root());
-    for (const auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                out = fmt::format_to(out, ".{}", member);
-            },
-            [&] (unsigned index) {
-                out = fmt::format_to(out, "[{}]", index);
-            }
-        }, op);
-    }
-    return out;
-}

alternator/expressions.g

@@ -1,9 +1,25 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
+ *
+ * This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
+ * top-level directory for licensing information.
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -74,34 +90,7 @@ options {
  */
 @parser::context {
     void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
-        const char* err;
-        switch (ex->getType()) {
-        case antlr3::ExceptionType::FAILED_PREDICATE_EXCEPTION:
-            err = "expression nested too deeply";
-            break;
-        default:
-            err = "syntax error";
-            break;
-        }
-        // Alternator expressions are always single line so ex->get_line()
-        // is always 1, no sense to print it.
-        // TODO: return the position as part of the exception, so the
-        // caller in expressions.cc that knows the expression string can
-        // mark the error position in the final error message.
-        throw expressions_syntax_error(format("{} at char {}", err,
-            ex->get_charPositionInLine()));
-    }
-
-    // ANTLR3 tries to recover missing tokens - it tries to finish parsing
-    // and create valid objects, as if the missing token was there.
-    // But it has a bug and leaks these tokens.
-    // We override offending method and handle abandoned pointers.
-    std::vector<std::unique_ptr<TokenType>> _missing_tokens;
-    TokenType* getMissingSymbol(IntStreamType* istream, ExceptionBaseType* e,
-                                ANTLR_UINT32 expectedTokenType, BitsetListType* follow) {
-        auto token = BaseType::getMissingSymbol(istream, e, expectedTokenType, follow);
-        _missing_tokens.emplace_back(token);
-        return token;
+        throw expressions_syntax_error("syntax error");
     }
 }
 @lexer::context {
@@ -110,23 +99,6 @@ options {
     }
 }
 
-/* Unfortunately, ANTLR uses recursion - not the heap - to parse recursive
- * expressions. To make things even worse, ANTLR has no way to limit the
- * depth of this recursion (unlike Yacc which has YYMAXDEPTH). So deeply-
- * nested expression like "(((((((((((((..." can easily crash Scylla on a
- * stack overflow (see issue #14477).
- *
- * We are lucky that in the grammar for DynamoDB expressions (below),
- * only a few specific rules can recurse, so it was fairly easy to add a
- * "depth" counter to a few specific rules, and then use a predicate
- * "{depth<MAX_DEPTH}?" to avoid parsing if the depth exceeds this limit,
- * and throw a FAILED_PREDICATE_EXCEPTION in that case, which we will
- * report to the user as a "expression nested too deeply" error.
- */
-@parser::members {
-    static constexpr int MAX_DEPTH = 400;
-}
-
 /*
  * Lexical analysis phase, i.e., splitting the input up to tokens.
  * Lexical analyzer rules have names starting in capital letters.
@@ -173,12 +145,6 @@ REMOVE: R E M O V E;
 ADD: A D D;
 DELETE: D E L E T E;
 
-AND: A N D;
-OR: O R;
-NOT: N O T;
-BETWEEN: B E T W E E N;
-IN: I N;
-
 fragment ALPHA: 'A'..'Z' | 'a'..'z';
 fragment DIGIT: '0'..'9';
 fragment ALNUM: ALPHA | DIGIT | '_';
@@ -196,29 +162,22 @@ path_component: NAME | NAMEREF;
 path returns [parsed::path p]:
     root=path_component           { $p.set_root($root.text); }
     (   '.' name=path_component   { $p.add_dot($name.text); }
-      | '[' INTEGER ']'           {
-                try {
-                    $p.add_index(std::stoi($INTEGER.text));
-                } catch(std::out_of_range&) {
-                    throw expressions_syntax_error("list index out of integer range");
-                }
-            }
+      | '[' INTEGER ']'           { $p.add_index(std::stoi($INTEGER.text)); }
     )*;
 
-/* See comment above why the "depth" counter was needed here */
-value[int depth] returns [parsed::value v]:
-      VALREF       { $v.set_valref($VALREF.text); }
-    | path         { $v.set_path($path.p); }
-    | {depth<MAX_DEPTH}? NAME { $v.set_func_name($NAME.text); }
-     '(' x=value[depth+1]    { $v.add_func_parameter($x.v); }
-     (',' x=value[depth+1]   { $v.add_func_parameter($x.v); })*
+update_expression_set_value returns [parsed::value v]:
+      VALREF                             { $v.set_valref($VALREF.text); }
+    | path                               { $v.set_path($path.p); }
+    | NAME                               { $v.set_func_name($NAME.text); }
+     '(' x=update_expression_set_value   { $v.add_func_parameter($x.v); }
+     (',' x=update_expression_set_value  { $v.add_func_parameter($x.v); })*
      ')'
     ;
 
 update_expression_set_rhs returns [parsed::set_rhs rhs]:
-    v=value[0]  { $rhs.set_value(std::move($v.v)); }
-    (   '+' v=value[0]  { $rhs.set_plus(std::move($v.v)); }
-      | '-' v=value[0]  { $rhs.set_minus(std::move($v.v)); }
+    v=update_expression_set_value  { $rhs.set_value(std::move($v.v)); }
+    (   '+' v=update_expression_set_value  { $rhs.set_plus(std::move($v.v)); }
+      | '-' v=update_expression_set_value  { $rhs.set_minus(std::move($v.v)); }
     )?
     ;
 
@@ -248,61 +207,8 @@ update_expression_clause returns [parsed::update_expression e]:
 // Note the "EOF" token at the end of the update expression. We want to the
 //  parser to match the entire string given to it - not just its beginning!
 update_expression returns [parsed::update_expression e]:
-    (update_expression_clause { e.append($update_expression_clause.e); })+ EOF;
+    (update_expression_clause { e.append($update_expression_clause.e); })* EOF;
 
 projection_expression returns [std::vector<parsed::path> v]:
     p=path      { $v.push_back(std::move($p.p)); }
     (',' p=path { $v.push_back(std::move($p.p)); } )* EOF;
-
-
-primitive_condition returns [parsed::primitive_condition c]:
-      v=value[0]      { $c.add_value(std::move($v.v));
-                        $c.set_operator(parsed::primitive_condition::type::VALUE); }
-      (  (  '='       { $c.set_operator(parsed::primitive_condition::type::EQ); }
-          | '<' '>'   { $c.set_operator(parsed::primitive_condition::type::NE); }
-          | '<'       { $c.set_operator(parsed::primitive_condition::type::LT); }
-          | '<' '='   { $c.set_operator(parsed::primitive_condition::type::LE); }
-          | '>'       { $c.set_operator(parsed::primitive_condition::type::GT); }
-          | '>' '='   { $c.set_operator(parsed::primitive_condition::type::GE); }
-         )
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-       | BETWEEN      { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-         AND
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-       | IN '('       { $c.set_operator(parsed::primitive_condition::type::IN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-         (',' v=value[0] { $c.add_value(std::move($v.v)); })*
-         ')'
-      )?
-      {
-          // Post-parse check to reject non-function single values
-          if ($c._op == parsed::primitive_condition::type::VALUE &&
-              !$c._values.front().is_func()) {
-              throw expressions_syntax_error("Single value must be a function");
-          }
-      }
-    ;
-
-// The following rules for parsing boolean expressions are verbose and
-// somewhat strange because of Antlr 3's limitations on recursive rules,
-// common rule prefixes, and (lack of) support for operator precedence.
-// These rules could have been written more clearly using a more powerful
-// parser generator - such as Yacc.
-// See comment above why the "depth" counter was needed here.
-boolean_expression[int depth] returns [parsed::condition_expression e]:
-	  b=boolean_expression_1[depth]       { $e.append(std::move($b.e), '|'); }
-	  (OR b=boolean_expression_1[depth]   { $e.append(std::move($b.e), '|'); } )*
-	;
-boolean_expression_1[int depth] returns [parsed::condition_expression e]:
-	  b=boolean_expression_2[depth]       { $e.append(std::move($b.e), '&'); }
-	  (AND b=boolean_expression_2[depth]  { $e.append(std::move($b.e), '&'); } )*
-	;
-boolean_expression_2[int depth] returns [parsed::condition_expression e]:
-	  p=primitive_condition        { $e.set_primitive(std::move($p.c)); }
-	| {depth<MAX_DEPTH}? NOT b=boolean_expression_2[depth+1]   { $e = std::move($b.e); $e.apply_not(); }
-	| {depth<MAX_DEPTH}? '(' b=boolean_expression[depth+1] ')' { $e = std::move($b.e); }
-    ;
-
-condition_expression returns [parsed::condition_expression e]:
-    boolean_expression[0] { e=std::move($boolean_expression.e); } EOF;

alternator/expressions.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -11,15 +24,8 @@
 #include <string>
 #include <stdexcept>
 #include <vector>
-#include <unordered_set>
-#include <string_view>
-
-#include <seastar/util/noncopyable_function.hh>
 
 #include "expressions_types.hh"
-#include "utils/rjson.hh"
-#include "utils/updateable_value.hh"
-#include "stats.hh"
 
 namespace alternator {
 
@@ -28,92 +34,8 @@ public:
     using runtime_error::runtime_error;
 };
 
-namespace parsed {
-class expression_cache_impl;
-class expression_cache {
-    std::unique_ptr<expression_cache_impl> _impl;
-public:
-    struct config {
-        utils::updateable_value<uint32_t> max_cache_entries;
-    };
-    expression_cache(config cfg, stats& stats);
-    ~expression_cache();
-    // stop background tasks, if any
-    future<> stop();
-
-    update_expression parse_update_expression(std::string_view query);
-    std::vector<path> parse_projection_expression(std::string_view query);
-    condition_expression parse_condition_expression(std::string_view query, const char* caller);
-};
-} // namespace parsed
-
-// Preferably use parsed::expression_cache instance instead of this free functions.
-parsed::update_expression parse_update_expression(std::string_view query);
-std::vector<parsed::path> parse_projection_expression(std::string_view query);
-parsed::condition_expression parse_condition_expression(std::string_view query, const char* caller);
-
-void resolve_update_expression(parsed::update_expression& ue,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values);
-void resolve_projection_expression(std::vector<parsed::path>& pe,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names);
-void resolve_condition_expression(parsed::condition_expression& ce,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values);
-
-void validate_value(const rjson::value& v, const char* caller);
-
-bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute);
-
-// for_condition_expression_on() runs the given function on the attributes
-// that the expression uses. It may run for the same attribute more than once
-// if the same attribute is used more than once in the expression.
-void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func);
-
-// calculate_value() behaves slightly different (especially, different
-// functions supported) when used in different types of expressions, as
-// enumerated in this enum:
-enum class calculate_value_caller {
-    UpdateExpression, ConditionExpression, ConditionExpressionAlone
-};
-
-}
-
-template <> struct fmt::formatter<alternator::calculate_value_caller> {
-    constexpr auto parse(format_parse_context& ctx) { return ctx.begin(); }
-    auto format(alternator::calculate_value_caller caller, fmt::format_context& ctx) const {
-        std::string_view name = "unknown type of expression";
-        switch (caller) {
-            using enum alternator::calculate_value_caller;
-            case UpdateExpression:
-                name = "UpdateExpression";
-                break;
-            case ConditionExpression:
-                name = "ConditionExpression";
-                break;
-            case ConditionExpressionAlone:
-                name = "ConditionExpression";
-                break;
-        }
-        return fmt::format_to(ctx.out(), "{}", name);
-    }
-};
-
-namespace alternator {
-
-rjson::value calculate_value(const parsed::value& v,
-        calculate_value_caller caller,
-        const rjson::value* previous_item);
-
-rjson::value calculate_value(const parsed::set_rhs& rhs,
-        const rjson::value* previous_item);
-
-void validate_attr_name_length(std::string_view supplementary_context, size_t attr_name_length, bool is_key, std::string_view error_msg_prefix = {});
+parsed::update_expression parse_update_expression(std::string query);
+std::vector<parsed::path> parse_projection_expression(std::string query);
 
 
 } /* namespace alternator */

alternator/expressions_types.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,14 +25,10 @@
 #include <string>
 #include <variant>
 
-#include <seastar/core/shared_ptr.hh>
-
-#include "utils/rjson.hh"
-
 /*
  * Parsed representation of expressions and their components.
  *
- * Types in alternator::parsed namespace are used for holding the parse
+ * Types in alternator::parse namespace are used for holding the parse
  * tree - objects generated by the Antlr rules after parsing an expression.
  * Because of the way Antlr works, all these objects are default-constructed
  * first, and then assigned when the rule is completed, so all these types
@@ -36,23 +45,15 @@ class path {
     // dot (e.g., ".xyz").
     std::string _root;
     std::vector<std::variant<std::string, unsigned>> _operators;
-    // It is useful to limit the depth of a user-specified path, because is
-    // allows us to use recursive algorithms without worrying about recursion
-    // depth. DynamoDB officially limits the length of paths to 32 components
-    // (including the root) so let's use the same limit.
-    static constexpr unsigned depth_limit = 32;
-    void check_depth_limit();
 public:
     void set_root(std::string root) {
         _root = std::move(root);
     }
     void add_index(unsigned i) {
         _operators.emplace_back(i);
-        check_depth_limit();
     }
-    void add_dot(std::string name) {
+    void add_dot(std::string(name)) {
         _operators.emplace_back(std::move(name));
-        check_depth_limit();
     }
     const std::string& root() const {
         return _root;
@@ -60,35 +61,12 @@ public:
     bool has_operators() const {
         return !_operators.empty();
     }
-    const std::vector<std::variant<std::string, unsigned>>& operators() const {
-        return _operators;
-    }
-    std::vector<std::variant<std::string, unsigned>>& operators() {
-        return _operators;
-    }
 };
 
-// When an expression is first parsed, all constants are references, like
-// ":val1", into ExpressionAttributeValues. This uses std::string() variant.
-// The resolve_value() function replaces these constants by the JSON item
-// extracted from the ExpressionAttributeValues.
-struct constant {
-    // We use lw_shared_ptr<rjson::value> just to make rjson::value copyable,
-    // to make this entire object copyable as ANTLR needs.
-    using literal = lw_shared_ptr<rjson::value>;
-    std::variant<std::string, literal> _value;
-    void set(const rjson::value& v) {
-        _value = make_lw_shared<rjson::value>(rjson::copy(v));
-    }
-    void set(std::string& s) {
-        _value = s;
-    }
-};
-
-// "value" is a value used in the right hand side of an assignment
-// expression, "SET a = ...". It can be a constant (a reference to a value
-// included in the request, e.g., ":val"), a path to an attribute from the
-// existing item (e.g., "a.b[3].c"), or a function of other such values.
+// "value" is is a value used in the right hand side of an assignment
+// expression, "SET a = ...". It can be a reference to a value included in
+// the request (":val"), a path to an attribute from the existing item
+// (e.g., "a.b[3].c"), or a function of other such values.
 // Note that the real right-hand-side of an assignment is actually a bit
 // more general - it allows either a value, or a value+value or value-value -
 // see class set_rhs below.
@@ -97,12 +75,9 @@ struct value {
         std::string _function_name;
         std::vector<value> _parameters;
     };
-    std::variant<constant, path, function_call> _value;
-    void set_constant(constant c) {
-        _value = std::move(c);
-    }
+    std::variant<std::string, path, function_call> _value;
     void set_valref(std::string s) {
-        _value = constant { std::move(s) };
+        _value = std::move(s);
     }
     void set_path(path p) {
         _value = std::move(p);
@@ -113,15 +88,6 @@ struct value {
     void add_func_parameter(value v) {
         std::get<function_call>(_value)._parameters.emplace_back(std::move(v));
     }
-    bool is_constant() const {
-        return std::holds_alternative<constant>(_value);
-    }
-    bool is_path() const {
-        return std::holds_alternative<path>(_value);
-    }
-    bool is_func() const {
-        return std::holds_alternative<function_call>(_value);
-    }
 };
 
 // The right-hand-side of a SET in an update expression can be either a
@@ -155,10 +121,10 @@ public:
         struct remove {
         };
         struct add {
-            constant _valref;
+            std::string _valref;
         };
         struct del {
-            constant _valref;
+            std::string _valref;
         };
         std::variant<set, remove, add, del> _action;
 
@@ -172,11 +138,11 @@ public:
         }
         void assign_add(path p, std::string v) {
             _path = std::move(p);
-            _action = add { constant { std::move(v) } };
+            _action = add { std::move(v) };
         }
         void assign_del(path p, std::string v) {
             _path = std::move(p);
-            _action = del { constant { std::move(v) } };
+            _action = del { std::move(v) };
         }
     };
 private:
@@ -194,65 +160,7 @@ public:
     const std::vector<action>& actions() const {
         return _actions;
     }
-    std::vector<action>& actions() {
-        return _actions;
-    }
-};
-
-// A primitive_condition is a condition expression involving one condition,
-// while the full condition_expression below adds boolean logic over these
-// primitive conditions.
-// The supported primitive conditions are:
-// 1. Binary operators - v1 OP v2, where OP is =, <>, <, <=, >, or >= and
-//    v1 and v2 are values - from the item (an attribute path), the query
-//    (a ":val" reference), or a function of the above (only the size()
-//    function is supported).
-// 2. Ternary operator - v1 BETWEEN v2 and v3 (means v1 >= v2 AND v1 <= v3).
-// 3. N-ary operator - v1 IN ( v2, v3, ... )
-// 4. A single function call (attribute_exists etc.).
-class primitive_condition {
-public:
-    enum class type {
-        UNDEFINED, VALUE, EQ, NE, LT, LE, GT, GE, BETWEEN, IN
-    };
-    type _op = type::UNDEFINED;
-    std::vector<value> _values;
-    void set_operator(type op) {
-        _op = op;
-    }
-    void add_value(value&& v) {
-        _values.push_back(std::move(v));
-    }
-    bool empty() const {
-        return _op == type::UNDEFINED;
-    }
-};
-
-class condition_expression {
-public:
-    bool _negated = false; // If true, the entire condition is negated
-    struct condition_list {
-        char op = '|'; // '&' or '|'
-        std::vector<condition_expression> conditions;
-    };
-    std::variant<primitive_condition, condition_list> _expression = condition_list();
-
-    void set_primitive(primitive_condition&& p) {
-        _expression = std::move(p);
-    }
-    void append(condition_expression&& c, char op);
-    void apply_not() {
-        _negated = !_negated;
-    }
-    bool empty() const {
-        return std::holds_alternative<condition_list>(_expression) &&
-               std::get<condition_list>(_expression).conditions.empty();
-    }
 };
 
 } // namespace parsed
 } // namespace alternator
-
-template <> struct fmt::formatter<alternator::parsed::path> : fmt::formatter<string_view> {
-    auto format(const alternator::parsed::path&, fmt::format_context& ctx) const -> decltype(ctx.out());
-};