alternator-test: reproduce bug in Expected with EQ of set value

Our implementation of the "EQ" operator in Expected (conditional
operation) just compares the JSON represntation of the values.
This is almost always correct, but unfortunately incorrect for
sets - where we can have two equal sets despite having a
different order.

This patch just adds an (xfailing) test for this bug.

The bug itself can be fixed in the future in one of several ways
including changing the implementation of EQ, or changing the
serialization of sets so they'll always be sorted in the same
way.

Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20190909125147.16484-1-nyh@scylladb.com>

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +0,0 @@
-Scylla doesn't use pull-requests, please send a patch to the [mailing list](mailto:scylladb-dev@googlegroups.com) instead.
-See our [contributing guidelines](../CONTRIBUTING.md) and our [Scylla development guidelines](../HACKING.md) for more information.
-
-If you have any questions please don't hesitate to send a mail to the [dev list](mailto:scylladb-dev@googlegroups.com).

.gitmodules

@@ -1,6 +1,6 @@
 [submodule "seastar"]
 	path = seastar
-	url = ../scylla-seastar
+	url = ../seastar
 	ignore = dirty
 [submodule "swagger-ui"]
 	path = swagger-ui
@@ -12,3 +12,6 @@
 [submodule "libdeflate"]
 	path = libdeflate
 	url = ../libdeflate
+[submodule "zstd"]
+	path = zstd
+	url = ../zstd

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Asking questions or requesting help
 
-Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) for general questions and 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.
 
 # Reporting an issue
 

HACKING.md

@@ -22,6 +22,15 @@ Scylla depends on the system package manager for its development dependencies.
 
 Running `./install-dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
 
+On Ubuntu and Debian based Linux distributions, some packages
+required to build Scylla are missing in the official upstream:
+
+- libthrift-dev and libthrift
+- antlr3-c++-dev
+
+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
@@ -55,6 +64,7 @@ To save time -- for instance, to avoid compiling all unit tests -- you can also
 
 ```bash
 $ ninja-build build/release/tests/schema_change_test
+$ ninja-build build/release/service/storage_proxy.o
 ```
 
 You can also specify a single mode. For example
@@ -194,7 +204,7 @@ cqlsh and nodetool. They are available at
 https://github.com/scylladb/scylla-tools-java and can be built with
 
 ```bash
-$ ./install-dependencies.sh
+$ sudo ./install-dependencies.sh
 $ ant jar
 ```
 

README.md

@@ -2,21 +2,22 @@
 
 ## Quick-start
 
+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 --recursive
-$ sudo ./install-dependencies.sh
-$ ./configure.py --mode=release
-$ ninja-build -j4 # Assuming 4 system threads.
-$ ./build/release/scylla
-$ # Rejoice!
-```
+$ ./tools/toolchain/dbuild ./configure.py
+$ ./tools/toolchain/dbuild ninja build/release/scylla
+$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
+ ```
 
 Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
 
-**Note**: GCC >= 8.1.1 is require to compile Scylla.
-
-**Note**: See [frozen toolchain](tools/toolchain/README.md) for a way to build and run
-   on an older distribution.
+**Note**: GCC >= 8.1.1 is required to compile Scylla.
 
 ## Running Scylla
 
@@ -80,4 +81,5 @@ docker run -p $(hostname -i):9042:9042 -i -t <image name>
 
 ## Contributing to Scylla
 
+[Hacking howto](HACKING.md)
 [Guidelines for contributing](CONTRIBUTING.md)

SCYLLA-VERSION-GEN

@@ -1,7 +1,7 @@
 #!/bin/sh
 
 PRODUCT=scylla
-VERSION=3.1.4
+VERSION=666.development
 
 if test -f version
 then

alternator-test/README.md

@@ -0,0 +1,33 @@
+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
+```
+

alternator-test/conftest.py

@@ -0,0 +1,169 @@
+# 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")
+
+# "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.
+        return boto3.resource('dynamodb', endpoint_url='http://localhost:8000',
+            region_name='us-east-1', aws_access_key_id='whatever', aws_secret_access_key='whatever')
+
+# "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_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 +1,47 @@
+# 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(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.
+        url = "http://" + address
+        if address.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url).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='whatever', aws_secret_access_key='whatever').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

@@ -0,0 +1,369 @@
+# 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 "Expected" parameter used to make certain operations (PutItem,
+# UpdateItem and DeleteItem) conditional on the existing attribute values.
+# "Expected" is the older version of ConditionExpression parameter, which
+# is tested by the separate test_condition_expression.py.
+
+import pytest
+from botocore.exceptions import ClientError
+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
+# DeleteItem operations, and we'll make a small effort verifying that at
+# the end of the file.
+
+# Somewhat pedanticly, DynamoDB forbids using old-style Expected together
+# with new-style UpdateExpression... Expected can only be used with
+# AttributeUpdates (and for UpdateExpression, ConditionExpression should be
+# used).
+def test_update_expression_and_expected(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = :val1',
+        ExpressionAttributeValues={':val1': 1})
+    with pytest.raises(ClientError, match='ValidationException.*UpdateExpression'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = :val1',
+            ExpressionAttributeValues={':val1': 2},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': [1]}}
+        )
+
+# The following string of tests test the various types of Expected conditions
+# on a single attribute. This condition is defined using ComparisonOperator
+# (there are many types of those!) or by Value or Exists, and we need to check
+# all these types of conditions.
+#
+# In each case we have tests for the "true" case of the condition, meaning
+# that the condition evaluates to true and the update is supposed to happen,
+# and the "false" case, where the condition evaluates to false, so the update
+# doesn't happen and we get a ConditionalCheckFailedException instead.
+
+def test_update_expected_1_eq_true(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    # Case where expected and update are on the same attribute:
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 2, 'Action': 'PUT'}},
+        Expected={'a': {'ComparisonOperator': 'EQ',
+                        'AttributeValueList': [1]}}
+    )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 2}
+    # 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': 'EQ',
+                        'AttributeValueList': [2]}}
+    )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 2, 'b': 3}
+    # For EQ, AttributeValueList must have a single element
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': [2, 3]}}
+        )
+
+# 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
+    # set with a different order, we need to build it incrementally.
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': set(['dog', 'chinchilla']), 'Action': 'PUT'}})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    # Sanity check - the attribute contains the set we think it does
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['chinchilla', 'cat', 'dog', 'mouse'])
+    # Now finally check that "Expected"'s equality check knows the equality too.
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+        Expected={'a': {'ComparisonOperator': 'EQ',
+                        'AttributeValueList': [set(['chinchilla', 'cat', 'dog', 'mouse'])]}}
+    )
+    assert 'b' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']
+
+def test_update_expected_1_eq_false(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': [2]}}
+        )
+    # If the compared value has a different type, it results in the
+    # condition failing normally (it's not a validation error).
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': ['dog']}}
+        )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1}
+
+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'}})
+    # 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'] == {'p': p, 'a': 'hello', 'b': 3}
+    # For BEGIN_WITH, AttributeValueList must have a single element
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': ['hell', 'heaven']}}
+        )
+
+def test_update_expected_1_begins_with_false(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'}})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': ['dog']}}
+        )
+    # Although BEGINS_WITH requires String or Binary type, giving it a
+    # number results not with a ValidationException but rather a
+    # failed condition (ConditionalCheckFailedException)
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'ComparisonOperator': 'EQ',
+                            'AttributeValueList': [3]}}
+        )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+
+# FIXME: need to test many more ComparisonOperator options... See full list in
+# description in https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/LegacyConditionalParameters.Expected.html
+
+# Instead of ComparisonOperator and AttributeValueList, one can specify either
+# Value or Exists:
+def test_update_expected_1_value_true(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+        Expected={'a': {'Value': 1}}
+    )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2}
+
+def test_update_expected_1_value_false(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'a': {'Value': 2}}
+        )
+    # If the expected attribute is completely missing, the condition also fails
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'z': {'Value': 1}}
+        )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1}
+
+def test_update_expected_1_exists_true(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    # Surprisingly, the "Exists: True" cannot be used to confirm that the
+    # attribute had *any* old value (use the NOT_NULL comparison operator
+    # for that). It can only be used together with "Value", and in that case
+    # doesn't mean a thing.
+    # Only "Exists: False" has an interesting meaning.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': True}}
+        )
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'c': {'Value': 3, 'Action': 'PUT'}},
+        Expected={'a': {'Exists': True, 'Value': 1}}
+    )
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'d': {'Value': 4, 'Action': 'PUT'}},
+        Expected={'z': {'Exists': False}}
+    )
+    # Exists: False cannot be used together with a Value:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'c': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': False, 'Value': 1}}
+        )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'c': 3, 'd': 4}
+
+def test_update_expected_1_exists_false(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': False}}
+        )
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': True, 'Value': 2}}
+        )
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1}
+
+# Test that it's not allowed to combine ComparisonOperator and Exists or Value
+def test_update_expected_operator_clash(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': False, 'ComparisonOperator': 'EQ', 'AttributeValueList': [3]}})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'b': {'Value': 2, 'Action': 'PUT'}},
+            Expected={'a': {'Value': 3, 'ComparisonOperator': 'EQ', 'AttributeValueList': [3]}})
+
+# All the previous tests involved a single condition on a single attribute.
+# The following tests involving multiple conditions on multiple attributes.
+# ConditionalOperator defaults to AND, and can also be set to OR.
+
+def test_update_expected_multi_true(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
+                          'b': {'Value': 2, 'Action': 'PUT'}})
+    # Test several conditions with default "AND" operator
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'z': {'Value': 3, 'Action': 'PUT'}},
+        Expected={'a': {'Exists': True, 'Value': 1},
+                  'b': {'ComparisonOperator': 'EQ', 'AttributeValueList': [2]},
+                  'c': {'Exists': False}})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2, 'z': 3}
+    # Same with explicit "AND" operator
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
+        Expected={'a': {'Exists': True, 'Value': 1},
+                  'b': {'ComparisonOperator': 'EQ', 'AttributeValueList': [2]},
+                  'c': {'Exists': False}},
+        ConditionalOperator="AND")
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2, 'z': 4}
+    # With "OR" operator, it's enough that just one conditions is true
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'z': {'Value': 5, 'Action': 'PUT'}},
+        Expected={'a': {'Exists': True, 'Value': 74},
+                  'b': {'ComparisonOperator': 'EQ', 'AttributeValueList': [999]},
+                  'c': {'Exists': False}},
+        ConditionalOperator="OR")
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2, 'z': 5}
+
+def test_update_expected_multi_false(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
+                          'b': {'Value': 2, 'Action': 'PUT'},
+                          'c': {'Value': 3, 'Action': 'PUT'}})
+    # Test several conditions, one of them false, with default "AND" operator
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'z': {'Value': 3, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': True, 'Value': 1},
+                      'b': {'ComparisonOperator': 'EQ', 'AttributeValueList': [3]},
+                      'd': {'Exists': False}})
+    # Same with explicit "AND" operator
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': True, 'Value': 1},
+                      'b': {'ComparisonOperator': 'EQ', 'AttributeValueList': [3]},
+                      'd': {'Exists': False}},
+            ConditionalOperator="AND")
+    # With "OR" operator, all the conditions need to be false to fail
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'z': {'Value': 5, 'Action': 'PUT'}},
+            Expected={'a': {'Exists': True, 'Value': 74},
+                      'b': {'ComparisonOperator': 'EQ', 'AttributeValueList': [999]},
+                      'c': {'Exists': False}},
+            ConditionalOperator='OR')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2, 'c': 3}
+
+# Verify the behaviour of an empty Expected parameter:
+def test_update_expected_empty(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    # An empty Expected array results in a successful update:
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'z': {'Value': 3, 'Action': 'PUT'}},
+        Expected={})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'z': 3}
+    # Trying with ConditionalOperator complains that you can't have
+    # ConditionalOperator without Expected (despite Expected existing, though empty).
+    with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
+            Expected={}, ConditionalOperator='OR')
+    with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
+            Expected={}, 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
+# above - we can assume that exactly the same code gets used to test the
+# expected value. So we just need one test for each operation, to verify that
+# this code actually gets called.
+
+def test_delete_item_expected(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
+        test_table_s.delete_item(Key={'p': p}, Expected={'a': {'Value': 2}})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1}
+    test_table_s.delete_item(Key={'p': p}, Expected={'a': {'Value': 1}})
+    assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+
+def test_put_item_expected(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'}})
+    test_table_s.put_item(Item={'p': p, 'a': 2}, Expected={'a': {'Value': 1}})
+    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}})

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_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="SET functions not yet implemented")
+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/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 +1,28 @@
+/*
+ * 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>
+#include "bytes.hh"
+
+std::string base64_encode(bytes_view);
+bytes base64_decode(std::string_view);

alternator/conditions.cc

@@ -0,0 +1,245 @@
+/*
+ * 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/>.
+ */
+
+#include <list>
+#include <map>
+#include <string_view>
+#include "alternator/conditions.hh"
+#include "alternator/error.hh"
+#include "cql3/constants.hh"
+#include <unordered_map>
+#include "rjson.hh"
+
+namespace alternator {
+
+static logging::logger clogger("alternator-conditions");
+
+comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator) {
+    static std::unordered_map<std::string, comparison_operator_type> ops = {
+            {"EQ", comparison_operator_type::EQ},
+            {"LE", comparison_operator_type::LE},
+            {"LT", comparison_operator_type::LT},
+            {"GE", comparison_operator_type::GE},
+            {"GT", comparison_operator_type::GT},
+            {"BETWEEN", comparison_operator_type::BETWEEN},
+            {"BEGINS_WITH", comparison_operator_type::BEGINS_WITH},
+    }; //TODO(sarna): NE, IN, CONTAINS, NULL, NOT_NULL
+    if (!comparison_operator.IsString()) {
+        throw api_error("ValidationException", format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
+    }
+    std::string op = comparison_operator.GetString();
+    auto it = ops.find(op);
+    if (it == ops.end()) {
+        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;
+}
+
+// Check if two JSON-encoded values match with the EQ relation
+static bool check_EQ(const rjson::value& v1, const rjson::value& v2) {
+    return v1 == v2;
+}
+
+// Check if two JSON-encoded values match with the BEGINS_WITH relation
+static bool check_BEGINS_WITH(const rjson::value& v1, const rjson::value& v2) {
+    // BEGINS_WITH only supports comparing two strings or two binaries -
+    // any other combinations of types, or other malformed values, return
+    // false (no match).
+    if (!v1.IsObject() || v1.MemberCount() != 1 || !v2.IsObject() || v2.MemberCount() != 1) {
+        return false;
+    }
+    auto it1 = v1.MemberBegin();
+    auto it2 = v2.MemberBegin();
+    if (it1->name != it2->name) {
+        return false;
+    }
+    if (it1->name != "S" && it1->name != "B") {
+        return false;
+    }
+    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;
+}
+
+// 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
+// succeeded - it does not throw ConditionalCheckFailedException.
+// However, it may throw ValidationException on input validation errors.
+static bool verify_expected_one(const rjson::value& condition, const rjson::value* got) {
+    const rjson::value* comparison_operator = rjson::find(condition, "ComparisonOperator");
+    const rjson::value* attribute_value_list = rjson::find(condition, "AttributeValueList");
+    const rjson::value* value = rjson::find(condition, "Value");
+    const rjson::value* exists = rjson::find(condition, "Exists");
+    // There are three types of conditions that Expected supports:
+    // A value, not-exists, and a comparison of some kind. Each allows
+    // and requires a different combinations of parameters in the request
+    if (value) {
+        if (exists && (!exists->IsBool() || exists->GetBool() != true)) {
+            throw api_error("ValidationException", "Cannot combine Value with Exists!=true");
+        }
+        if (comparison_operator) {
+            throw api_error("ValidationException", "Cannot combine Value with ComparisonOperator");
+        }
+        return got && check_EQ(*got, *value);
+    } else if (exists) {
+        if (comparison_operator) {
+            throw api_error("ValidationException", "Cannot combine Exists with ComparisonOperator");
+        }
+        if (!exists->IsBool() || exists->GetBool() != false) {
+            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("ValidationException", "Missing ComparisonOperator, Value or Exists");
+        }
+        if (!attribute_value_list || !attribute_value_list->IsArray()) {
+            throw api_error("ValidationException", "With ComparisonOperator, AttributeValueList must be given and an array");
+        }
+        comparison_operator_type op = get_comparison_operator(*comparison_operator);
+        switch (op) {
+        case comparison_operator_type::EQ:
+            if (attribute_value_list->Size() != 1) {
+                throw api_error("ValidationException", "EQ operator requires one element in AttributeValueList");
+            }
+            if (got) {
+                const rjson::value& expected = (*attribute_value_list)[0];
+                return check_EQ(*got, expected);
+            }
+            return false;
+        case comparison_operator_type::BEGINS_WITH:
+            if (attribute_value_list->Size() != 1) {
+                throw api_error("ValidationException", "BEGINS_WITH operator requires one element in AttributeValueList");
+            }
+            if (got) {
+                const rjson::value& expected = (*attribute_value_list)[0];
+                return check_BEGINS_WITH(*got, expected);
+            }
+            return false;
+        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));
+        }
+    }
+}
+
+// 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 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.
+void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item) {
+    const rjson::value* expected = rjson::find(req, "Expected");
+    if (!expected) {
+        return;
+    }
+    if (!expected->IsObject()) {
+        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");
+        }
+    }
+
+    for (auto it = expected->MemberBegin(); it != expected->MemberEnd(); ++it) {
+        const rjson::value* got = nullptr;
+        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;
+        } else if (!success && require_all) {
+            // When require_all, one failure is enough!
+            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.
+    if (!require_all) {
+        throw api_error("ConditionalCheckFailedException", "None of ORed Expect conditions were successful.");
+    }
+}
+
+}

alternator/conditions.hh

@@ -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/>.
+ */
+
+/*
+ * This file contains definitions and functions related to placing conditions
+ * on Alternator queries (equivalent of CQL's restrictions).
+ *
+ * With conditions, it's possible to add criteria to selection requests (Scan, Query)
+ * and use them for narrowing down the result set, by means of filtering or indexing.
+ *
+ * Ref: https://docs.aws.amazon.com/amazondynamodb/latest/APIReference/API_Condition.html
+ */
+
+#pragma once
+
+#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, IS_NULL, NOT_NULL, BEGINS_WITH
+};
+
+comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator);
+
+::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter);
+
+void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item);
+
+}

alternator/error.hh

@@ -0,0 +1,50 @@
+/*
+ * 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 <seastar/http/httpd.hh>
+#include "seastarx.hh"
+
+namespace alternator {
+
+// DynamoDB's error messages are described in detail in
+// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
+// 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 = httpd::reply::status_type;
+    status_type _http_code;
+    std::string _type;
+    std::string _msg;
+    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))
+    { }
+    api_error() = default;
+    virtual const char* what() const noexcept override { return _msg.c_str(); }
+};
+
+}
+

alternator/executor.hh

@@ -0,0 +1,71 @@
+/*
+ * 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 <seastar/core/future.hh>
+#include <seastar/http/httpd.hh>
+#include "seastarx.hh"
+#include <seastar/json/json_elements.hh>
+
+#include "service/storage_proxy.hh"
+#include "service/migration_manager.hh"
+#include "service/client_state.hh"
+
+#include "stats.hh"
+
+namespace alternator {
+
+class executor {
+    service::storage_proxy& _proxy;
+    service::migration_manager& _mm;
+
+public:
+    using client_state = service::client_state;
+    stats _stats;
+    static constexpr auto ATTRS_COLUMN_NAME = ":attrs";
+    static constexpr auto KEYSPACE_NAME = "alternator";
+
+    executor(service::storage_proxy& proxy, service::migration_manager& mm) : _proxy(proxy), _mm(mm) {}
+
+    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() { return make_ready_future<>(); }
+
+    future<> maybe_create_keyspace();
+
+    static void maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
+};
+
+}

alternator/expressions.cc

@@ -0,0 +1,98 @@
+/*
+ * 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/>.
+ */
+
+#include "expressions.hh"
+#include "alternator/expressionsLexer.hpp"
+#include "alternator/expressionsParser.hpp"
+
+#include <seastarx.hh>
+
+#include <seastar/core/print.hh>
+#include <seastar/util/log.hh>
+
+#include <functional>
+
+namespace alternator {
+
+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,
+        static_cast<ANTLR_UINT32>(input.size()),
+        nullptr };
+    expressionsLexer lexer(&input_stream);
+    expressionsParser::TokenStreamType tstream(ANTLR_SIZE_HINT, lexer.get_tokSource());
+    expressionsParser parser(&tstream);
+
+    auto result = f(parser);
+    return result;
+}
+
+parsed::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 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()));
+    }
+}
+
+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 {
+        [&] (action::set&)    { seen_set = true; },
+        [&] (action::remove&) { seen_remove = true; },
+        [&] (action::add&)    { seen_add = true; },
+        [&] (action::del&)    { seen_del = true; }
+    }, a._action);
+    _actions.push_back(std::move(a));
+}
+
+void update_expression::append(update_expression other) {
+    if ((seen_set && other.seen_set) ||
+        (seen_remove && other.seen_remove) ||
+        (seen_add && other.seen_add) ||
+        (seen_del && other.seen_del)) {
+        throw expressions_syntax_error("Each of SET, REMOVE, ADD, DELETE may only appear once in UpdateExpression");
+    }
+    std::move(other._actions.begin(), other._actions.end(), std::back_inserter(_actions));
+    seen_set |= other.seen_set;
+    seen_remove |= other.seen_remove;
+    seen_add |= other.seen_add;
+    seen_del |= other.seen_del;
+}
+
+} // namespace parsed
+} // namespace alternator

alternator/expressions.g

@@ -0,0 +1,214 @@
+/*
+ * Copyright 2019 ScyllaDB
+ *
+ * This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
+ * top-level directory for licensing information.
+ */
+
+/*
+ * 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 DynamoDB protocol is based on JSON, and most DynamoDB requests
+ * describe the operation and its parameters via JSON objects such as maps
+ * and lists. Nevertheless, in some types of requests an "expression" is
+ * passed as a single string, and we need to parse this string. These
+ * cases include:
+ *  1. Attribute paths, such as "a[3].b.c", are used in projection
+ *     expressions as well as inside other expressions described below.
+ *  2. Condition expressions, such as "(NOT (a=b OR c=d)) AND e=f",
+ *     used in conditional updates, filters, and other places.
+ *  3. Update expressions, such as "SET #a.b = :x, c = :y DELETE d"
+ *
+ * All these expression syntaxes are very simple: Most of them could be
+ * parsed as regular expressions, and the parenthesized condition expression
+ * could be done with a simple hand-written lexical analyzer and recursive-
+ * descent parser. Nevertheless, we decided to specify these parsers in the
+ * ANTLR3 language already used in the Scylla project, hopefully making these
+ * parsers easier to reason about, and easier to change if needed - and
+ * reducing the amount of boiler-plate code.
+ */
+
+grammar expressions;
+
+options {
+    language = Cpp;
+}
+
+@parser::namespace{alternator}
+@lexer::namespace{alternator}
+
+/* TODO: explain what these traits things are. I haven't seen them explained
+ * in any document... Compilation fails without these fail because a definition
+ * of "expressionsLexerTraits" and "expressionParserTraits" is needed.
+ */
+@lexer::traits {
+    class expressionsLexer;
+    class expressionsParser;
+    typedef antlr3::Traits<expressionsLexer, expressionsParser> expressionsLexerTraits;
+}
+@parser::traits {
+    typedef expressionsLexerTraits expressionsParserTraits;
+}
+
+@lexer::header {
+	#include "alternator/expressions.hh"
+	// ANTLR generates a bunch of unused variables and functions. Yuck...
+    #pragma GCC diagnostic ignored "-Wunused-variable"
+    #pragma GCC diagnostic ignored "-Wunused-function"
+}
+@parser::header {
+	#include "expressionsLexer.hpp"
+}
+
+/* By default, ANTLR3 composes elaborate syntax-error messages, saying which
+ * token was unexpected, where, and so on on, but then dutifully writes these
+ * error messages to the standard error, and returns from the parser as if
+ * everything was fine, with a half-constructed output object! If we define
+ * the "displayRecognitionError" method, it will be called upon to build this
+ * error message, and we can instead throw an exception to stop the parsing
+ * immediately. This is good enough for now, for our simple needs, but if
+ * we ever want to show more information about the syntax error, Cql3.g
+ * contains an elaborate implementation (it would be nice if we could reuse
+ * it, not duplicate it).
+ * Unfortunately, we have to repeat the same definition twice - once for the
+ * parser, and once for the lexer.
+ */
+@parser::context {
+    void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
+        throw expressions_syntax_error("syntax error");
+    }
+}
+@lexer::context {
+    void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
+        throw expressions_syntax_error("syntax error");
+    }
+}
+
+/*
+ * Lexical analysis phase, i.e., splitting the input up to tokens.
+ * Lexical analyzer rules have names starting in capital letters.
+ * "fragment" rules do not generate tokens, and are just aliases used to
+ * make other rules more readable.
+ * Characters *not* listed here, e.g., '=', '(', etc., will be handled
+ * as individual tokens on their own right.
+ * Whitespace spans are skipped, so do not generate tokens.
+ */
+WHITESPACE: (' ' | '\t' | '\n' | '\r')+ { skip(); };
+
+/* shortcuts for case-insensitive keywords */
+fragment A:('a'|'A');
+fragment B:('b'|'B');
+fragment C:('c'|'C');
+fragment D:('d'|'D');
+fragment E:('e'|'E');
+fragment F:('f'|'F');
+fragment G:('g'|'G');
+fragment H:('h'|'H');
+fragment I:('i'|'I');
+fragment J:('j'|'J');
+fragment K:('k'|'K');
+fragment L:('l'|'L');
+fragment M:('m'|'M');
+fragment N:('n'|'N');
+fragment O:('o'|'O');
+fragment P:('p'|'P');
+fragment Q:('q'|'Q');
+fragment R:('r'|'R');
+fragment S:('s'|'S');
+fragment T:('t'|'T');
+fragment U:('u'|'U');
+fragment V:('v'|'V');
+fragment W:('w'|'W');
+fragment X:('x'|'X');
+fragment Y:('y'|'Y');
+fragment Z:('z'|'Z');
+/* These keywords must be appear before the generic NAME token below,
+ * because NAME matches too, and the first to match wins.
+ */
+SET: S E T;
+REMOVE: R E M O V E;
+ADD: A D D;
+DELETE: D E L E T E;
+
+fragment ALPHA: 'A'..'Z' | 'a'..'z';
+fragment DIGIT: '0'..'9';
+fragment ALNUM: ALPHA | DIGIT | '_';
+INTEGER: DIGIT+;
+NAME: ALPHA ALNUM*;
+NAMEREF: '#' ALNUM+;
+VALREF: ':' ALNUM+;
+
+/*
+ * Parsing phase - parsing the string of tokens generated by the lexical
+ * analyzer defined above.
+ */
+
+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 ']'           { $p.add_index(std::stoi($INTEGER.text)); }
+    )*;
+
+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=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)); }
+    )?
+    ;
+
+update_expression_set_action returns [parsed::update_expression::action a]:
+    path '=' rhs=update_expression_set_rhs { $a.assign_set($path.p, $rhs.rhs); };
+
+update_expression_remove_action returns [parsed::update_expression::action a]:
+    path { $a.assign_remove($path.p); };
+
+update_expression_add_action returns [parsed::update_expression::action a]:
+    path VALREF { $a.assign_add($path.p, $VALREF.text); };
+
+update_expression_delete_action returns [parsed::update_expression::action a]:
+    path VALREF { $a.assign_del($path.p, $VALREF.text); };
+
+update_expression_clause returns [parsed::update_expression e]:
+      SET s=update_expression_set_action { $e.add(s); }
+      (',' s=update_expression_set_action { $e.add(s); })*
+    | REMOVE r=update_expression_remove_action { $e.add(r); }
+      (',' r=update_expression_remove_action { $e.add(r); })*
+    | ADD a=update_expression_add_action { $e.add(a); }
+      (',' a=update_expression_add_action { $e.add(a); })*
+    | DELETE d=update_expression_delete_action { $e.add(d); }
+      (',' d=update_expression_delete_action { $e.add(d); })*
+    ;
+
+// Note the "EOF" token at the end of the update expression. We want to the
+//  parser to match the entire string given to it - not just its beginning!
+update_expression returns [parsed::update_expression e]:
+    (update_expression_clause { e.append($update_expression_clause.e); })* EOF;
+
+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;

alternator/expressions.hh

@@ -0,0 +1,41 @@
+/*
+ * 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>
+#include <stdexcept>
+#include <vector>
+
+#include "expressions_types.hh"
+
+namespace alternator {
+
+class expressions_syntax_error : public std::runtime_error {
+public:
+    using runtime_error::runtime_error;
+};
+
+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

@@ -0,0 +1,166 @@
+/*
+ * 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 <vector>
+#include <string>
+#include <variant>
+
+/*
+ * Parsed representation of expressions and their components.
+ *
+ * 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
+ * have only default constructors - but setter functions to set them later.
+ */
+
+namespace alternator {
+namespace parsed {
+
+// "path" is an attribute's path in a document, e.g., a.b[3].c.
+class path {
+    // All paths have a "root", a top-level attribute, and any number of
+    // "dereference operators" - each either an index (e.g., "[2]") or a
+    // dot (e.g., ".xyz").
+    std::string _root;
+    std::vector<std::variant<std::string, unsigned>> _operators;
+public:
+    void set_root(std::string root) {
+        _root = std::move(root);
+    }
+    void add_index(unsigned i) {
+        _operators.emplace_back(i);
+    }
+    void add_dot(std::string(name)) {
+        _operators.emplace_back(std::move(name));
+    }
+    const std::string& root() const {
+        return _root;
+    }
+    bool has_operators() const {
+        return !_operators.empty();
+    }
+};
+
+// "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.
+struct value {
+    struct function_call {
+        std::string _function_name;
+        std::vector<value> _parameters;
+    };
+    std::variant<std::string, path, function_call> _value;
+    void set_valref(std::string s) {
+        _value = std::move(s);
+    }
+    void set_path(path p) {
+        _value = std::move(p);
+    }
+    void set_func_name(std::string s) {
+        _value = function_call {std::move(s), {}};
+    }
+    void add_func_parameter(value v) {
+        std::get<function_call>(_value)._parameters.emplace_back(std::move(v));
+    }
+};
+
+// The right-hand-side of a SET in an update expression can be either a
+// single value (see above), or value+value, or value-value.
+class set_rhs {
+public:
+    char _op;  // '+', '-', or 'v''
+    value _v1;
+    value _v2;
+    void set_value(value&& v1) {
+        _op = 'v';
+        _v1 = std::move(v1);
+    }
+    void set_plus(value&& v2) {
+        _op = '+';
+        _v2 = std::move(v2);
+    }
+    void set_minus(value&& v2) {
+        _op = '-';
+        _v2 = std::move(v2);
+    }
+};
+
+class update_expression {
+public:
+    struct action {
+        path _path;
+        struct set {
+            set_rhs _rhs;
+        };
+        struct remove {
+        };
+        struct add {
+            std::string _valref;
+        };
+        struct del {
+            std::string _valref;
+        };
+        std::variant<set, remove, add, del> _action;
+
+        void assign_set(path p, set_rhs rhs) {
+            _path = std::move(p);
+            _action = set { std::move(rhs) };
+        }
+        void assign_remove(path p) {
+            _path = std::move(p);
+            _action = remove { };
+        }
+        void assign_add(path p, std::string v) {
+            _path = std::move(p);
+            _action = add { std::move(v) };
+        }
+        void assign_del(path p, std::string v) {
+            _path = std::move(p);
+            _action = del { std::move(v) };
+        }
+    };
+private:
+    std::vector<action> _actions;
+    bool seen_set = false;
+    bool seen_remove = false;
+    bool seen_add = false;
+    bool seen_del = false;
+public:
+    void add(action a);
+    void append(update_expression other);
+    bool empty() const {
+        return _actions.empty();
+    }
+    const std::vector<action>& actions() const {
+        return _actions;
+    }
+};
+
+} // namespace parsed
+} // namespace alternator

alternator/rjson.cc

@@ -0,0 +1,120 @@
+/*
+ * 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/>.
+ */
+
+#include "rjson.hh"
+#include "error.hh"
+#include <seastar/core/print.hh>
+
+namespace rjson {
+
+static allocator the_allocator;
+
+std::string print(const rjson::value& value) {
+    string_buffer buffer;
+    writer writer(buffer);
+    value.Accept(writer);
+    return std::string(buffer.GetString());
+}
+
+rjson::value copy(const rjson::value& value) {
+    return rjson::value(value, the_allocator);
+}
+
+rjson::value parse(const std::string& str) {
+    return parse_raw(str.c_str(), str.size());
+}
+
+rjson::value parse_raw(const char* c_str, size_t size) {
+    rjson::document d;
+    d.Parse(c_str, size);
+    if (d.HasParseError()) {
+        throw rjson::error(format("Parsing JSON failed: {}", GetParseError_En(d.GetParseError())));
+    }
+    rjson::value& v = d;
+    return std::move(v);
+}
+
+rjson::value& get(rjson::value& value, rjson::string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    if (member_it != value.MemberEnd())
+        return member_it->value;
+    else {
+        throw rjson::error(format("JSON parameter {} not found", name));
+    }
+}
+
+const rjson::value& get(const rjson::value& value, rjson::string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    if (member_it != value.MemberEnd())
+        return member_it->value;
+    else {
+        throw rjson::error(format("JSON parameter {} not found", name));
+    }
+}
+
+rjson::value from_string(const std::string& str) {
+    return rjson::value(str.c_str(), str.size(), the_allocator);
+}
+
+rjson::value from_string(const sstring& str) {
+    return rjson::value(str.c_str(), str.size(), the_allocator);
+}
+
+rjson::value from_string(const char* str, size_t size) {
+    return rjson::value(str, size, the_allocator);
+}
+
+const rjson::value* find(const rjson::value& value, string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    return member_it != value.MemberEnd() ? &member_it->value : nullptr;
+}
+
+rjson::value* find(rjson::value& value, string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    return member_it != value.MemberEnd() ? &member_it->value : nullptr;
+}
+
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member) {
+    base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), std::move(member), the_allocator);
+}
+
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member) {
+    base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), rjson::value(member), the_allocator);
+}
+
+void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member) {
+    base.AddMember(name, std::move(member), the_allocator);
+}
+
+void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member) {
+    base.AddMember(name, rjson::value(member), the_allocator);
+}
+
+void push_back(rjson::value& base_array, rjson::value&& item) {
+    base_array.PushBack(std::move(item), the_allocator);
+
+}
+
+} // end namespace rjson
+
+std::ostream& std::operator<<(std::ostream& os, const rjson::value& v) {
+    return os << rjson::print(v);
+}

alternator/rjson.hh

@@ -0,0 +1,159 @@
+/*
+ * 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
+
+/*
+ * rjson is a wrapper over rapidjson library, providing fast JSON parsing and generation.
+ *
+ * rapidjson has strict copy elision policies, which, among other things, involves
+ * using provided char arrays without copying them and allows copying objects only explicitly.
+ * As such, one should be careful when passing strings with limited liveness
+ * (e.g. data underneath local std::strings) to rjson functions, because created JSON objects
+ * may end up relying on dangling char pointers. All rjson functions that create JSONs from strings
+ * by rjson have both APIs for string_ref_type (more optimal, used when the string is known to live
+ * at least as long as the object, e.g. a static char array) and for std::strings. The more optimal
+ * variants should be used *only* if the liveness of the string is guaranteed, otherwise it will
+ * result in undefined behaviour.
+ * Also, bear in mind that methods exposed by rjson::value are generic, but some of them
+ * work fine only for specific types. In case the type does not match, an rjson::error will be thrown.
+ * Examples of such mismatched usages is calling MemberCount() on a JSON value not of object type
+ * or calling Size() on a non-array value.
+ */
+
+#include <string>
+#include <stdexcept>
+
+namespace rjson {
+class error : public std::exception {
+    std::string _msg;
+public:
+    error() = default;
+    error(const std::string& msg) : _msg(msg) {}
+
+    virtual const char* what() const noexcept override { return _msg.c_str(); }
+};
+}
+
+// rapidjson configuration macros
+#define RAPIDJSON_HAS_STDSTRING 1
+// Default rjson policy is to use assert() - which is dangerous for two reasons:
+// 1. assert() can be turned off with -DNDEBUG
+// 2. assert() crashes a program
+// Fortunately, the default policy can be overridden, and so rapidjson errors will
+// throw an rjson::error exception instead.
+#define RAPIDJSON_ASSERT(x) do { if (!(x)) throw rjson::error(std::string("JSON error: condition not met: ") + #x); } while (0)
+
+#include <rapidjson/document.h>
+#include <rapidjson/writer.h>
+#include <rapidjson/stringbuffer.h>
+#include <rapidjson/error/en.h>
+#include <seastar/core/sstring.hh>
+#include "seastarx.hh"
+
+namespace rjson {
+
+using allocator = rapidjson::CrtAllocator;
+using encoding = rapidjson::UTF8<>;
+using document = rapidjson::GenericDocument<encoding, allocator>;
+using value = rapidjson::GenericValue<encoding, allocator>;
+using string_ref_type = value::StringRefType;
+using string_buffer = rapidjson::GenericStringBuffer<encoding>;
+using writer = rapidjson::Writer<string_buffer, encoding>;
+using type = rapidjson::Type;
+
+// Returns an object representing JSON's null
+inline rjson::value null_value() {
+    return rjson::value(rapidjson::kNullType);
+}
+
+// Returns an empty JSON object - {}
+inline rjson::value empty_object() {
+    return rjson::value(rapidjson::kObjectType);
+}
+
+// Returns an empty JSON array - []
+inline rjson::value empty_array() {
+    return rjson::value(rapidjson::kArrayType);
+}
+
+// Returns an empty JSON string - ""
+inline rjson::value empty_string() {
+    return rjson::value(rapidjson::kStringType);
+}
+
+// Convert the JSON value to a string with JSON syntax, the opposite of parse().
+// The representation is dense - without any redundant indentation.
+std::string print(const rjson::value& value);
+
+// Copies given JSON value - involves allocation
+rjson::value copy(const rjson::value& value);
+
+// Parses a JSON value from given string or raw character array.
+// The string/char array liveness does not need to be persisted,
+// as both parse() and parse_raw() will allocate member names and values.
+// Throws rjson::error if parsing failed.
+rjson::value parse(const std::string& str);
+rjson::value parse_raw(const char* c_str, size_t size);
+
+// Creates a JSON value (of JSON string type) out of internal string representations.
+// The string value is copied, so str's liveness does not need to be persisted.
+rjson::value from_string(const std::string& str);
+rjson::value from_string(const sstring& str);
+rjson::value from_string(const char* str, size_t size);
+
+// Returns a pointer to JSON member if it exists, nullptr otherwise
+rjson::value* find(rjson::value& value, rjson::string_ref_type name);
+const rjson::value* find(const rjson::value& value, rjson::string_ref_type name);
+
+// Returns a reference to JSON member if it exists, throws otherwise
+rjson::value& get(rjson::value& value, rjson::string_ref_type name);
+const rjson::value& get(const rjson::value& value, rjson::string_ref_type name);
+
+// Sets a member in given JSON object by moving the member - allocates the name.
+// Throws if base is not a JSON object.
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member);
+
+// Sets a string member in given JSON object by assigning its reference - allocates the name.
+// NOTICE: member string liveness must be ensured to be at least as long as base's.
+// Throws if base is not a JSON object.
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member);
+
+// Sets a member in given JSON object by moving the member.
+// NOTICE: name liveness must be ensured to be at least as long as base's.
+// Throws if base is not a JSON object.
+void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member);
+
+// Sets a string member in given JSON object by assigning its reference.
+// NOTICE: name liveness must be ensured to be at least as long as base's.
+// NOTICE: member liveness must be ensured to be at least as long as base's.
+// Throws if base is not a JSON object.
+void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member);
+
+// Adds a value to a JSON list by moving the item to its end.
+// Throws if base_array is not a JSON array.
+void push_back(rjson::value& base_array, rjson::value&& item);
+
+} // end namespace rjson
+
+namespace std {
+std::ostream& operator<<(std::ostream& os, const rjson::value& v);
+}

alternator/serialization.cc

@@ -0,0 +1,230 @@
+/*
+ * 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/>.
+ */
+
+#include "base64.hh"
+#include "log.hh"
+#include "serialization.hh"
+#include "error.hh"
+#include "rapidjson/writer.h"
+#include "concrete_types.hh"
+
+static logging::logger slogger("alternator-serialization");
+
+namespace alternator {
+
+type_info type_info_from_string(std::string type) {
+    static thread_local const std::unordered_map<std::string, type_info> type_infos = {
+        {"S", {alternator_type::S, utf8_type}},
+        {"B", {alternator_type::B, bytes_type}},
+        {"BOOL", {alternator_type::BOOL, boolean_type}},
+        {"N", {alternator_type::N, decimal_type}}, //FIXME: Replace with custom Alternator type when implemented
+    };
+    auto it = type_infos.find(type);
+    if (it == type_infos.end()) {
+        return {alternator_type::NOT_SUPPORTED_YET, utf8_type};
+    }
+    return it->second;
+}
+
+type_representation represent_type(alternator_type atype) {
+    static thread_local const std::unordered_map<alternator_type, type_representation> type_representations = {
+        {alternator_type::S, {"S", utf8_type}},
+        {alternator_type::B, {"B", bytes_type}},
+        {alternator_type::BOOL, {"BOOL", boolean_type}},
+        {alternator_type::N, {"N", decimal_type}}, //FIXME: Replace with custom Alternator type when implemented
+    };
+    auto it = type_representations.find(atype);
+    if (it == type_representations.end()) {
+        throw std::runtime_error(format("Unknown alternator type {}", int8_t(atype)));
+    }
+    return it->second;
+}
+
+struct from_json_visitor {
+    const rjson::value& v;
+    bytes_ostream& bo;
+
+    void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), from_json_visitor{v, bo}); };
+    void operator()(const string_type_impl& t) {
+        bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
+    }
+    void operator()(const bytes_type_impl& t) const {
+        bo.write(base64_decode(std::string_view(v.GetString(), v.GetStringLength())));
+    }
+    void operator()(const boolean_type_impl& t) const {
+        bo.write(boolean_type->decompose(v.GetBool()));
+    }
+    void operator()(const decimal_type_impl& t) const {
+        bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
+    }
+    // default
+    void operator()(const abstract_type& t) const {
+        bo.write(t.from_json_object(Json::Value(rjson::print(v)), cql_serialization_format::internal()));
+    }
+};
+
+bytes serialize_item(const rjson::value& item) {
+    if (item.IsNull() || item.MemberCount() != 1) {
+        throw api_error("ValidationException", format("An item can contain only one attribute definition: {}", item));
+    }
+    auto it = item.MemberBegin();
+    type_info type_info = type_info_from_string(it->name.GetString()); // JSON keys are guaranteed to be strings
+
+    if (type_info.atype == alternator_type::NOT_SUPPORTED_YET) {
+        slogger.trace("Non-optimal serialization of type {}", it->name.GetString());
+        return bytes{int8_t(type_info.atype)} + to_bytes(rjson::print(item));
+    }
+
+    bytes_ostream bo;
+    bo.write(bytes{int8_t(type_info.atype)});
+    visit(*type_info.dtype, from_json_visitor{it->value, bo});
+
+    return bytes(bo.linearize());
+}
+
+struct to_json_visitor {
+    rjson::value& deserialized;
+    const std::string& type_ident;
+    bytes_view bv;
+
+    void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), to_json_visitor{deserialized, type_ident, bv}); };
+    void operator()(const decimal_type_impl& t) const {
+        auto s = decimal_type->to_json_string(bytes(bv));
+        //FIXME(sarna): unnecessary copy
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(s));
+    }
+    void operator()(const string_type_impl& t) {
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
+    }
+    void operator()(const bytes_type_impl& t) const {
+        std::string b64 = base64_encode(bv);
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(b64));
+    }
+    // default
+    void operator()(const abstract_type& t) const {
+        rjson::set_with_string_name(deserialized, type_ident, rjson::parse(t.to_string(bytes(bv))));
+    }
+};
+
+rjson::value deserialize_item(bytes_view bv) {
+    rjson::value deserialized(rapidjson::kObjectType);
+    if (bv.empty()) {
+        throw api_error("ValidationException", "Serialized value empty");
+    }
+
+    alternator_type atype = alternator_type(bv[0]);
+    bv.remove_prefix(1);
+
+    if (atype == alternator_type::NOT_SUPPORTED_YET) {
+        slogger.trace("Non-optimal deserialization of alternator type {}", int8_t(atype));
+        return rjson::parse_raw(reinterpret_cast<const char *>(bv.data()), bv.size());
+    }
+    type_representation type_representation = represent_type(atype);
+    visit(*type_representation.dtype, to_json_visitor{deserialized, type_representation.ident, bv});
+
+    return deserialized;
+}
+
+std::string type_to_string(data_type type) {
+    static thread_local std::unordered_map<data_type, std::string> types = {
+        {utf8_type, "S"},
+        {bytes_type, "B"},
+        {boolean_type, "BOOL"},
+        {decimal_type, "N"}, // FIXME: use a specialized Alternator number type instead of the general decimal_type
+    };
+    auto it = types.find(type);
+    if (it == types.end()) {
+        throw std::runtime_error(format("Unknown type {}", type->name()));
+    }
+    return it->second;
+}
+
+bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
+    std::string column_name = column.name_as_text();
+    std::string expected_type = type_to_string(column.type);
+
+    const rjson::value& key_typed_value = rjson::get(item, rjson::value::StringRefType(column_name.c_str()));
+    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1) {
+        throw api_error("ValidationException",
+                format("Missing or invalid value object for key column {}: {}", column_name, item));
+    }
+    return get_key_from_typed_value(key_typed_value, column, expected_type);
+}
+
+bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column, const std::string& expected_type) {
+    auto it = key_typed_value.MemberBegin();
+    if (it->name.GetString() != expected_type) {
+        throw api_error("ValidationException",
+                format("Type mismatch: expected type {} for key column {}, got type {}",
+                        expected_type, column.name_as_text(), it->name.GetString()));
+    }
+    if (column.type == bytes_type) {
+        return base64_decode(it->value.GetString());
+    } else {
+        return column.type->from_string(it->value.GetString());
+    }
+
+}
+
+rjson::value json_key_column_value(bytes_view cell, const column_definition& column) {
+    if (column.type == bytes_type) {
+        std::string b64 = base64_encode(cell);
+        return rjson::from_string(b64);
+    } if (column.type == utf8_type) {
+        return rjson::from_string(std::string(reinterpret_cast<const char*>(cell.data()), cell.size()));
+    } else if (column.type == decimal_type) {
+        // FIXME: use specialized Alternator number type, not the more
+        // general "decimal_type". A dedicated type can be more efficient
+        // in storage space and in parsing speed.
+        auto s = decimal_type->to_json_string(bytes(cell));
+        return rjson::from_string(s);
+    } else {
+        // We shouldn't get here, we shouldn't see such key columns.
+        throw std::runtime_error(format("Unexpected key type: {}", column.type->name()));
+    }
+}
+
+
+partition_key pk_from_json(const rjson::value& item, schema_ptr schema) {
+    std::vector<bytes> raw_pk;
+    // FIXME: this is a loop, but we really allow only one partition key column.
+    for (const column_definition& cdef : schema->partition_key_columns()) {
+        bytes raw_value = get_key_column_value(item, cdef);
+        raw_pk.push_back(std::move(raw_value));
+    }
+   return partition_key::from_exploded(raw_pk);
+}
+
+clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
+    if (schema->clustering_key_size() == 0) {
+        return clustering_key::make_empty();
+    }
+    std::vector<bytes> raw_ck;
+    // FIXME: this is a loop, but we really allow only one clustering key column.
+    for (const column_definition& cdef : schema->clustering_key_columns()) {
+        bytes raw_value = get_key_column_value(item,  cdef);
+        raw_ck.push_back(std::move(raw_value));
+    }
+
+    return clustering_key::from_exploded(raw_ck);
+}
+
+}

alternator/serialization.hh

@@ -0,0 +1,61 @@
+/*
+ * 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>
+#include "types.hh"
+#include "schema.hh"
+#include "keys.hh"
+#include "rjson.hh"
+
+namespace alternator {
+
+enum class alternator_type : int8_t {
+    S, B, BOOL, N, NOT_SUPPORTED_YET
+};
+
+struct type_info {
+    alternator_type atype;
+    data_type dtype;
+};
+
+struct type_representation {
+    std::string ident;
+    data_type dtype;
+};
+
+type_info type_info_from_string(std::string type);
+type_representation represent_type(alternator_type atype);
+
+bytes serialize_item(const rjson::value& item);
+rjson::value deserialize_item(bytes_view bv);
+
+std::string type_to_string(data_type type);
+
+bytes get_key_column_value(const rjson::value& item, const column_definition& column);
+bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column, const std::string& expected_type);
+rjson::value json_key_column_value(bytes_view cell, const column_definition& column);
+
+partition_key pk_from_json(const rjson::value& item, schema_ptr schema);
+clustering_key ck_from_json(const rjson::value& item, schema_ptr schema);
+
+}

alternator/server.cc

@@ -0,0 +1,172 @@
+/*
+ * 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/>.
+ */
+
+#include "alternator/server.hh"
+#include "log.hh"
+#include <seastar/http/function_handlers.hh>
+#include <seastar/json/json_elements.hh>
+#include <seastarx.hh>
+#include <boost/algorithm/string/split.hpp>
+#include <boost/algorithm/string/classification.hpp>
+#include "error.hh"
+#include "rjson.hh"
+
+static logging::logger slogger("alternator-server");
+
+using namespace httpd;
+
+namespace alternator {
+
+static constexpr auto TARGET = "X-Amz-Target";
+
+inline std::vector<sstring> split(const sstring& text, const char* separator) {
+    if (text == "") {
+        return std::vector<sstring>();
+    }
+    std::vector<sstring> tokens;
+    return boost::split(tokens, text, boost::is_any_of(separator));
+}
+
+// DynamoDB HTTP error responses are structured as follows
+// https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
+// Our handlers throw an exception to report an error. If the exception
+// is of type alternator::api_error, it unwrapped and properly reported to
+// the user directly. Other exceptions are unexpected, and reported as
+// Internal Server Error.
+class api_handler : public handler_base {
+public:
+    api_handler(const future_json_function& _handle) : _f_handle(
+         [_handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
+         return seastar::futurize_apply(_handle, std::move(req)).then_wrapped([rep = std::move(rep)](future<json::json_return_type> resf) mutable {
+             if (resf.failed()) {
+                 // Exceptions of type api_error are wrapped as JSON and
+                 // returned to the client as expected. Other types of
+                 // exceptions are unexpected, and returned to the user
+                 // as an internal server error:
+                 api_error ret;
+                 try {
+                     resf.get();
+                 } catch (api_error &ae) {
+                     ret = ae;
+                 } catch (rjson::error & re) {
+                     ret = api_error("ValidationException", re.what());
+                 } catch (...) {
+                     ret = api_error(
+                             "Internal Server Error",
+                             format("Internal server error: {}", std::current_exception()),
+                             reply::status_type::internal_server_error);
+                 }
+                 // FIXME: what is this version number?
+                 rep->_content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + ret._type + "\"," +
+                         "\"message\":\"" + ret._msg + "\"}";
+                 rep->_status = ret._http_code;
+                 slogger.trace("api_handler error case: {}", rep->_content);
+                 return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
+             }
+             slogger.trace("api_handler success case");
+             auto res = resf.get0();
+             if (res._body_writer) {
+                 rep->write_body("json", std::move(res._body_writer));
+             } else {
+                 rep->_content += res._res;
+             }
+             return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
+         });
+    }), _type("json") { }
+
+    api_handler(const api_handler&) = default;
+    future<std::unique_ptr<reply>> handle(const sstring& path,
+            std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
+        return _f_handle(std::move(req), std::move(rep)).then(
+                [this](std::unique_ptr<reply> rep) {
+                    rep->done(_type);
+                    return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
+                });
+    }
+
+protected:
+    future_handler_function _f_handle;
+    sstring _type;
+};
+
+void server::set_routes(routes& r) {
+    using alternator_callback = std::function<future<json::json_return_type>(executor&, executor::client_state&, std::unique_ptr<request>)>;
+    std::unordered_map<std::string, alternator_callback> routes{
+        {"CreateTable", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) {
+            return e.maybe_create_keyspace().then([&e, &client_state, req = std::move(req)] { return e.create_table(client_state, req->content); }); }
+        },
+        {"DescribeTable", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.describe_table(client_state, req->content); }},
+        {"DeleteTable", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.delete_table(client_state, req->content); }},
+        {"PutItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.put_item(client_state, req->content); }},
+        {"UpdateItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.update_item(client_state, req->content); }},
+        {"GetItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.get_item(client_state, req->content); }},
+        {"DeleteItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.delete_item(client_state, req->content); }},
+        {"ListTables", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.list_tables(client_state, req->content); }},
+        {"Scan", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.scan(client_state, req->content); }},
+        {"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.describe_endpoints(client_state, req->content, req->get_header("Host")); }},
+        {"BatchWriteItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.batch_write_item(client_state, req->content); }},
+        {"BatchGetItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.batch_get_item(client_state, req->content); }},
+        {"Query", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.query(client_state, req->content); }},
+    };
+
+    api_handler* handler = new api_handler([this, routes = std::move(routes)](std::unique_ptr<request> req) -> future<json::json_return_type> {
+        _executor.local()._stats.total_operations++;
+        sstring target = req->get_header(TARGET);
+        std::vector<sstring> split_target = split(target, ".");
+        //NOTICE(sarna): Target consists of Dynamo API version folllowed by a dot '.' and operation type (e.g. CreateTable)
+        sstring op = split_target.empty() ? sstring() : split_target.back();
+        slogger.trace("Request: {} {}", op, req->content);
+        auto callback_it = routes.find(op);
+        if (callback_it == routes.end()) {
+            _executor.local()._stats.unsupported_operations++;
+            throw api_error("UnknownOperationException",
+                    format("Unsupported operation {}", op));
+        }
+        //FIXME: Client state can provide more context, e.g. client's endpoint address
+        return do_with(executor::client_state::for_internal_calls(), [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (executor::client_state& client_state) mutable {
+            client_state.set_raw_keyspace(executor::KEYSPACE_NAME);
+            executor::maybe_trace_query(client_state, op, req->content);
+            tracing::trace(client_state.get_trace_state(), op);
+            return callback_it->second(_executor.local(), client_state, std::move(req));
+        });
+    });
+
+    r.add(operation_type::POST, url("/"), handler);
+}
+
+future<> server::init(net::inet_address addr, uint16_t port) {
+    return _executor.invoke_on_all([] (executor& e) {
+        return e.start();
+    }).then([this] {
+        return _control.start();
+    }).then([this] {
+        return _control.set_routes(std::bind(&server::set_routes, this, std::placeholders::_1));
+    }).then([this, addr, port] {
+        return _control.listen(socket_address{addr, port});
+    }).then([addr, port] {
+        slogger.info("Alternator HTTP server listening on {} port {}", addr, port);
+    }).handle_exception([addr, port] (std::exception_ptr e) {
+        slogger.warn("Failed to set up Alternator HTTP server on {} port {}: {}", addr, port, e);
+    });
+}
+
+}
+

alternator/server.hh

@@ -0,0 +1,42 @@
+/*
+ * 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 "alternator/executor.hh"
+#include <seastar/core/future.hh>
+#include <seastar/http/httpd.hh>
+
+namespace alternator {
+
+class server {
+    seastar::httpd::http_server_control _control;
+    seastar::sharded<executor>& _executor;
+public:
+    server(seastar::sharded<executor>& executor) : _executor(executor) {}
+
+    seastar::future<> init(net::inet_address addr, uint16_t port);
+private:
+    void set_routes(seastar::httpd::routes& r);
+};
+
+}
+

alternator/stats.cc

@@ -0,0 +1,98 @@
+/*
+ * 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/>.
+ */
+
+#include "stats.hh"
+
+#include <seastar/core/metrics.hh>
+
+namespace alternator {
+
+const char* ALTERNATOR_METRICS = "alternator";
+
+stats::stats() : api_operations{} {
+    // Register the
+    seastar::metrics::label op("op");
+
+    _metrics.add_group("alternator", {
+#define OPERATION(name, CamelCaseName) \
+                seastar::metrics::make_total_operations("operation", api_operations.name, \
+                        seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName)}),
+#define OPERATION_LATENCY(name, CamelCaseName) \
+                seastar::metrics::make_histogram("op_latency", \
+                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return api_operations.name.get_histogram(1,20);}),
+            OPERATION(batch_write_item, "BatchWriteItem")
+            OPERATION(create_backup, "CreateBackup")
+            OPERATION(create_global_table, "CreateGlobalTable")
+            OPERATION(create_table, "CreateTable")
+            OPERATION(delete_backup, "DeleteBackup")
+            OPERATION(delete_item, "DeleteItem")
+            OPERATION(delete_table, "DeleteTable")
+            OPERATION(describe_backup, "DescribeBackup")
+            OPERATION(describe_continuous_backups, "DescribeContinuousBackups")
+            OPERATION(describe_endpoints, "DescribeEndpoints")
+            OPERATION(describe_global_table, "DescribeGlobalTable")
+            OPERATION(describe_global_table_settings, "DescribeGlobalTableSettings")
+            OPERATION(describe_limits, "DescribeLimits")
+            OPERATION(describe_table, "DescribeTable")
+            OPERATION(describe_time_to_live, "DescribeTimeToLive")
+            OPERATION(get_item, "GetItem")
+            OPERATION(list_backups, "ListBackups")
+            OPERATION(list_global_tables, "ListGlobalTables")
+            OPERATION(list_tables, "ListTables")
+            OPERATION(list_tags_of_resource, "ListTagsOfResource")
+            OPERATION(put_item, "PutItem")
+            OPERATION(query, "Query")
+            OPERATION(restore_table_from_backup, "RestoreTableFromBackup")
+            OPERATION(restore_table_to_point_in_time, "RestoreTableToPointInTime")
+            OPERATION(scan, "Scan")
+            OPERATION(tag_resource, "TagResource")
+            OPERATION(transact_get_items, "TransactGetItems")
+            OPERATION(transact_write_items, "TransactWriteItems")
+            OPERATION(untag_resource, "UntagResource")
+            OPERATION(update_continuous_backups, "UpdateContinuousBackups")
+            OPERATION(update_global_table, "UpdateGlobalTable")
+            OPERATION(update_global_table_settings, "UpdateGlobalTableSettings")
+            OPERATION(update_item, "UpdateItem")
+            OPERATION(update_table, "UpdateTable")
+            OPERATION(update_time_to_live, "UpdateTimeToLive")
+            OPERATION_LATENCY(put_item_latency, "PutItem")
+            OPERATION_LATENCY(get_item_latency, "GetItem")
+            OPERATION_LATENCY(delete_item_latency, "DeleteItem")
+            OPERATION_LATENCY(update_item_latency, "UpdateItem")
+    });
+    _metrics.add_group("alternator", {
+            seastar::metrics::make_total_operations("unsupported_operations", unsupported_operations,
+                    seastar::metrics::description("number of unsupported operations via Alternator API")),
+            seastar::metrics::make_total_operations("total_operations", total_operations,
+                    seastar::metrics::description("number of total operations via Alternator API")),
+            seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
+                    seastar::metrics::description("number of performed read-before-write operations")),
+            seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
+                    seastar::metrics::description("number of rows read during filtering operations")),
+            seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,
+                    seastar::metrics::description("number of rows read and matched during filtering operations")),
+            seastar::metrics::make_total_operations("filtered_rows_dropped_total", [this] { return cql_stats.filtered_rows_read_total - cql_stats.filtered_rows_matched_total; },
+                    seastar::metrics::description("number of rows read and dropped during filtering operations")),
+    });
+}
+
+
+}

alternator/stats.hh

@@ -0,0 +1,95 @@
+/*
+ * 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 <cstdint>
+
+#include <seastar/core/metrics_registration.hh>
+#include "seastarx.hh"
+#include "utils/estimated_histogram.hh"
+#include "cql3/stats.hh"
+
+namespace alternator {
+
+// Object holding per-shard statistics related to Alternator.
+// While this object is alive, these metrics are also registered to be
+// visible by the metrics REST API, with the "alternator" prefix.
+class stats {
+public:
+    stats();
+    // Count of DynamoDB API operations by types
+    struct {
+        uint64_t batch_get_item = 0;
+        uint64_t batch_write_item = 0;
+        uint64_t create_backup = 0;
+        uint64_t create_global_table = 0;
+        uint64_t create_table = 0;
+        uint64_t delete_backup = 0;
+        uint64_t delete_item = 0;
+        uint64_t delete_table = 0;
+        uint64_t describe_backup = 0;
+        uint64_t describe_continuous_backups = 0;
+        uint64_t describe_endpoints = 0;
+        uint64_t describe_global_table = 0;
+        uint64_t describe_global_table_settings = 0;
+        uint64_t describe_limits = 0;
+        uint64_t describe_table = 0;
+        uint64_t describe_time_to_live = 0;
+        uint64_t get_item = 0;
+        uint64_t list_backups = 0;
+        uint64_t list_global_tables = 0;
+        uint64_t list_tables = 0;
+        uint64_t list_tags_of_resource = 0;
+        uint64_t put_item = 0;
+        uint64_t query = 0;
+        uint64_t restore_table_from_backup = 0;
+        uint64_t restore_table_to_point_in_time = 0;
+        uint64_t scan = 0;
+        uint64_t tag_resource = 0;
+        uint64_t transact_get_items = 0;
+        uint64_t transact_write_items = 0;
+        uint64_t untag_resource = 0;
+        uint64_t update_continuous_backups = 0;
+        uint64_t update_global_table = 0;
+        uint64_t update_global_table_settings = 0;
+        uint64_t update_item = 0;
+        uint64_t update_table = 0;
+        uint64_t update_time_to_live = 0;
+
+        utils::estimated_histogram put_item_latency;
+        utils::estimated_histogram get_item_latency;
+        utils::estimated_histogram delete_item_latency;
+        utils::estimated_histogram update_item_latency;
+    } api_operations;
+    // Miscellaneous event counters
+    uint64_t total_operations = 0;
+    uint64_t unsupported_operations = 0;
+    uint64_t reads_before_write = 0;
+    // CQL-derived stats
+    cql3::cql_stats cql_stats;
+private:
+    // The metric_groups object holds this stat object's metrics registered
+    // as long as the stats object is alive.
+    seastar::metrics::metric_groups _metrics;
+};
+
+}

api/api-doc/compaction_manager.json

@@ -127,6 +127,24 @@
         }
       ]
     },
+    {
+      "path": "/compaction_manager/metrics/pending_tasks_by_table",
+      "operations": [
+        {
+          "method": "GET",
+          "summary": "Get pending tasks by table name",
+          "type": "array",
+          "items": {
+              "type": "pending_compaction"
+           },
+          "nickname": "get_pending_tasks_by_table",
+          "produces": [
+            "application/json"
+          ],
+          "parameters": []
+        }
+      ]
+    },
     {
       "path": "/compaction_manager/metrics/completed_tasks",
       "operations": [
@@ -244,6 +262,23 @@
             }
          }
       },
+      "pending_compaction": {
+        "id": "pending_compaction",
+        "properties": {
+            "cf": {
+               "type": "string",
+               "description": "The column family name"
+            },
+            "ks": {
+               "type":"string",
+               "description": "The keyspace name"
+            },
+            "task": {
+               "type":"long",
+               "description": "The number of pending tasks"
+            }
+        }
+      },
       "history": {
       "id":"history",
       "description":"Compaction history information",

api/api-doc/storage_proxy.json

@@ -791,6 +791,36 @@
         }
       ]
     },
+    {
+      "path": "/storage_proxy/metrics/cas_read/moving_average_histogram",
+      "operations": [
+        {
+          "method": "GET",
+          "summary": "Get CAS read rate and latency histogram",
+          "$ref": "#/utils/rate_moving_average_and_histogram",
+          "nickname": "get_cas_read_metrics_latency_histogram",
+          "produces": [
+            "application/json"
+          ],
+          "parameters": []
+        }
+      ]
+    },
+    {
+      "path": "/storage_proxy/metrics/view_write/moving_average_histogram",
+      "operations": [
+        {
+          "method": "GET",
+          "summary": "Get view write rate and latency histogram",
+          "$ref": "#/utils/rate_moving_average_and_histogram",
+          "nickname": "get_view_write_metrics_latency_histogram",
+          "produces": [
+            "application/json"
+          ],
+          "parameters": []
+        }
+      ]
+    },
     {
       "path": "/storage_proxy/metrics/range/moving_average_histogram",
       "operations": [
@@ -956,6 +986,21 @@
         }
       ]
     },
+    {
+      "path": "/storage_proxy/metrics/cas_write/moving_average_histogram",
+      "operations": [
+        {
+          "method": "GET",
+          "summary": "Get CAS write rate and latency histogram",
+          "$ref": "#/utils/rate_moving_average_and_histogram",
+          "nickname": "get_cas_write_metrics_latency_histogram",
+          "produces": [
+            "application/json"
+          ],
+          "parameters": []
+        }
+      ]
+    },
     {
          "path":"/storage_proxy/metrics/read/estimated_histogram/",
          "operations":[

api/api-doc/storage_service.json

@@ -2164,7 +2164,42 @@
                ]
             }
          ]
-      }
+      },
+      {
+         "path":"/storage_service/sstable_info",
+         "operations":[
+            {
+               "method":"GET",
+               "summary":"SSTable information",
+               "type":"array",
+               "items":{
+                  "type":"table_sstables"
+               },
+               "nickname":"sstable_info",
+               "produces":[
+                  "application/json"
+               ],
+               "parameters":[
+                  {
+                     "name":"keyspace",
+                     "description":"The keyspace",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  },
+                  {
+                     "name":"cf",
+                     "description":"column family name",
+                     "required":false,
+                     "allowMultiple":false,
+                     "type":"string",
+                     "paramType":"query"
+                  }
+               ]
+            }
+         ]
+      }      
    ],
    "models":{
       "mapper":{
@@ -2324,6 +2359,92 @@
                "description":"The endpoint details"
             }
          }
+      },
+      "named_maps":{
+        "id":"named_maps",
+        "properties":{
+            "group":{
+                "type":"string"
+            },
+            "attributes":{
+                "type":"array",
+                "items":{
+                    "type":"mapper"
+                }
+            }
+        }
+      },
+      "sstable":{
+        "id":"sstable",
+        "properties":{
+            "size":{
+               "type":"long",
+               "description":"Total size in bytes of sstable"
+            },
+            "data_size":{
+                "type":"long",
+                "description":"The size in bytes on disk of data"
+            },
+            "index_size":{
+               "type":"long",
+               "description":"The size in bytes on disk of index"
+            },
+            "filter_size":{
+               "type":"long",
+               "description":"The size in bytes on disk of filter"
+            },
+            "timestamp":{
+                "type":"datetime",
+                "description":"File creation time"
+            },
+            "generation":{
+                "type":"long",
+                "description":"SSTable generation"
+            },
+            "level":{
+               "type":"long",
+               "description":"SSTable level"
+            },
+            "version":{
+               "type":"string",
+               "enum":[
+                  "ka", "la", "mc"
+               ],
+               "description":"SSTable version"
+            },
+            "properties":{
+                "type":"array",
+                "description":"SSTable attributes",
+                "items":{
+                    "type":"mapper"
+                }
+            },
+            "extended_properties":{
+                "type":"array",
+                "description":"SSTable extended attributes",
+                "items":{
+                    "type":"named_maps"
+                }
+            }
+        }
+      },
+      "table_sstables":{
+        "id":"table_sstables",
+        "description":"Per-table SSTable info and attributes",
+        "properties":{
+            "keyspace":{
+                "type":"string"
+            },
+            "table":{
+                "type":"string"
+            },
+            "sstables":{
+                "type":"array",
+                "items":{
+                    "$ref":"sstable"
+                }
+            }
+        }
       }
    }
 }

api/column_family.hh

@@ -39,14 +39,14 @@ template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
         Mapper mapper, Reducer reducer) {
     auto uuid = get_uuid(name, ctx.db.local());
-    using mapper_type = std::function<std::any (database&)>;
-    using reducer_type = std::function<std::any (std::any, std::any)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(database&)>;
+    using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
     return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
-        return I(mapper(db.find_column_family(uuid)));
-    }), std::any(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::any a, std::any b) mutable {
-        return I(reducer(std::any_cast<I>(std::move(a)), std::any_cast<I>(std::move(b))));
-    })).then([] (std::any r) {
-        return std::any_cast<I>(std::move(r));
+        return std::make_unique<std::any>(I(mapper(db.find_column_family(uuid))));
+    }), std::make_unique<std::any>(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
+        return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
+    })).then([] (std::unique_ptr<std::any> r) {
+        return std::any_cast<I>(std::move(*r));
     });
 }
 
@@ -70,14 +70,14 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
 
 struct map_reduce_column_families_locally {
     std::any init;
-    std::function<std::any (column_family&)> mapper;
-    std::function<std::any (std::any, std::any)> reducer;
-    future<std::any> operator()(database& db) const {
-        auto res = seastar::make_lw_shared<std::any>(init);
+    std::function<std::unique_ptr<std::any>(column_family&)> mapper;
+    std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)> reducer;
+    future<std::unique_ptr<std::any>> operator()(database& db) const {
+        auto res = seastar::make_lw_shared<std::unique_ptr<std::any>>(std::make_unique<std::any>(init));
         return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
-            *res = reducer(*res.get(), mapper(*i.second.get()));
+            *res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
         }).then([res] {
-            return *res;
+            return std::move(*res);
         });
     }
 };
@@ -85,16 +85,17 @@ struct map_reduce_column_families_locally {
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, I init,
         Mapper mapper, Reducer reducer) {
-    using mapper_type = std::function<std::any (column_family&)>;
-    using reducer_type = std::function<std::any (std::any, std::any)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(column_family&)>;
+    using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
     auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
-        return I(mapper(cf));
+        return std::make_unique<std::any>(I(mapper(cf)));
     });
-    auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::any a, std::any b) mutable {
-        return I(reducer(std::any_cast<I>(std::move(a)), std::any_cast<I>(std::move(b))));
+    auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
+        return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
     });
-    return ctx.db.map_reduce0(map_reduce_column_families_locally{init, std::move(wrapped_mapper), wrapped_reducer}, std::any(init), wrapped_reducer).then([] (std::any res) {
-        return std::any_cast<I>(std::move(res));
+    return ctx.db.map_reduce0(map_reduce_column_families_locally{init,
+            std::move(wrapped_mapper), wrapped_reducer}, std::make_unique<std::any>(init), wrapped_reducer).then([] (std::unique_ptr<std::any> res) {
+        return std::any_cast<I>(std::move(*res));
     });
 }
 

api/compaction_manager.cc

@@ -24,6 +24,7 @@
 #include "api/api-doc/compaction_manager.json.hh"
 #include "db/system_keyspace.hh"
 #include "column_family.hh"
+#include <utility>
 
 namespace api {
 
@@ -38,6 +39,16 @@ static future<json::json_return_type> get_cm_stats(http_context& ctx,
         return make_ready_future<json::json_return_type>(res);
     });
 }
+static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash> sum_pending_tasks(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>&& a,
+        const std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& b) {
+    for (auto&& i : b) {
+        if (i.second) {
+            a[i.first] += i.second;
+        }
+    }
+    return std::move(a);
+}
+
 
 void set_compaction_manager(http_context& ctx, routes& r) {
     cm::get_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -61,6 +72,31 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         });
     });
 
+    cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return ctx.db.map_reduce0([&ctx](database& db) {
+            std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash> tasks;
+            return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+                table& cf = *i.second.get();
+                tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf);
+                return make_ready_future<>();
+            }).then([&tasks] {
+                return tasks;
+            });
+        }, std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), sum_pending_tasks).then(
+                [](const std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& task_map) {
+            std::vector<cm::pending_compaction> res;
+            res.reserve(task_map.size());
+            for (auto i : task_map) {
+                cm::pending_compaction task;
+                task.ks = i.first.first;
+                task.cf = i.first.second;
+                task.task = i.second;
+                res.emplace_back(std::move(task));
+            }
+            return make_ready_future<json::json_return_type>(res);
+        });
+    });
+
     cm::force_user_defined_compaction.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         // FIXME

api/config.cc

@@ -44,14 +44,14 @@ json::json_return_type get_json_return_type(const db::seed_provider_type& val) {
     return json::json_return_type(val.class_name);
 }
 
-std::string format_type(const std::string& type) {
+std::string_view format_type(std::string_view type) {
     if (type == "int") {
         return "integer";
     }
     return type;
 }
 
-future<> get_config_swagger_entry(const std::string& name, const std::string& description, const std::string& type, bool& first, output_stream<char>& os) {
+future<> get_config_swagger_entry(std::string_view name, const std::string& description, std::string_view type, bool& first, output_stream<char>& os) {
     std::stringstream ss;
     if (first) {
         first=false;
@@ -88,23 +88,29 @@ future<> get_config_swagger_entry(const std::string& name, const std::string& de
 }
 
 namespace cs = httpd::config_json;
-#define _get_config_value(name, type, deflt, status, desc, ...) if (id == #name) {return get_json_return_type(ctx.db.local().get_config().name());}
-
-
-#define _get_config_description(name, type, deflt, status, desc, ...) f = f.then([&os, &first] {return get_config_swagger_entry(#name, desc, #type, first, os);});
 
 void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
-    rb->register_function(r, [] (output_stream<char>& os) {
-        return do_with(true, [&os] (bool& first) {
+    rb->register_function(r, [&ctx] (output_stream<char>& os) {
+        return do_with(true, [&os, &ctx] (bool& first) {
             auto f = make_ready_future();
-            _make_config_values(_get_config_description)
+            for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
+                auto&& cfg = cfg_ref.get();
+                f = f.then([&os, &first, &cfg] {
+                    return get_config_swagger_entry(cfg.name(), std::string(cfg.desc()), cfg.type_name(), first, os);
+                });
+            }
             return f;
         });
     });
 
     cs::find_config_id.set(r, [&ctx] (const_req r) {
         auto id = r.param["id"];
-        _make_config_values(_get_config_value)
+        for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
+            auto&& cfg = cfg_ref.get();
+            if (id == cfg.name()) {
+                return cfg.value_as_json();
+            }
+        }
         throw bad_param_exception(sstring("No such config entry: ") + id);
     });
 }

api/messaging_service.cc

@@ -76,7 +76,7 @@ future_json_function get_server_getter(std::function<uint64_t(const rpc::stats&)
         auto get_shard_map = [f](messaging_service& ms) {
             std::unordered_map<gms::inet_address, unsigned long> map;
             ms.foreach_server_connection_stats([&map, f] (const rpc::client_info& info, const rpc::stats& stats) mutable {
-                map[gms::inet_address(net::ipv4_address(info.addr))] = f(stats);
+                map[gms::inet_address(info.addr.addr())] = f(stats);
             });
             return map;
         };

api/storage_proxy.cc

@@ -47,6 +47,10 @@ static future<json::json_return_type>  sum_timed_rate_as_obj(distributed<proxy>&
     });
 }
 
+httpd::utils_json::rate_moving_average_and_histogram get_empty_moving_average() {
+    return timer_to_json(utils::rate_moving_average_and_histogram());
+}
+
 static future<json::json_return_type>  sum_timed_rate_as_long(distributed<proxy>& d, utils::timed_rate_moving_average proxy::stats::*f) {
     return sum_timed_rate(d, f).then([](const utils::rate_moving_average& val) {
         return make_ready_future<json::json_return_type>(val.count);
@@ -377,6 +381,29 @@ void set_storage_proxy(http_context& ctx, routes& r) {
     sp::get_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
         return sum_timer_stats(ctx.sp, &proxy::stats::write);
     });
+    sp::get_cas_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // cas is not supported yet, so just return empty moving average
+
+        return make_ready_future<json::json_return_type>(get_empty_moving_average());
+    });
+
+    sp::get_cas_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // cas is not supported yet, so just return empty moving average
+
+        return make_ready_future<json::json_return_type>(get_empty_moving_average());
+    });
+
+    sp::get_view_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        //TBD
+        // FIXME
+        // No View metrics are available, so just return empty moving average
+
+        return make_ready_future<json::json_return_type>(get_empty_moving_average());
+    });
 
     sp::get_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
         return sum_timer_stats(ctx.sp, &proxy::stats::read);

api/storage_service.cc

@@ -22,13 +22,15 @@
 #include "storage_service.hh"
 #include "api/api-doc/storage_service.json.hh"
 #include "db/config.hh"
+#include <optional>
+#include <time.h>
 #include <boost/range/adaptor/map.hpp>
 #include <boost/range/adaptor/filtered.hpp>
-#include <service/storage_service.hh>
-#include <db/commitlog/commitlog.hh>
-#include <gms/gossiper.hh>
-#include <db/system_keyspace.hh>
-#include <seastar/http/exception.hh>
+#include "service/storage_service.hh"
+#include "db/commitlog/commitlog.hh"
+#include "gms/gossiper.hh"
+#include "db/system_keyspace.hh"
+#include "seastar/http/exception.hh"
 #include "repair/repair.hh"
 #include "locator/snitch_base.hh"
 #include "column_family.hh"
@@ -37,6 +39,7 @@
 #include "sstables/compaction_manager.hh"
 #include "sstables/sstables.hh"
 #include "database.hh"
+#include "db/extensions.hh"
 
 sstables::sstable::version_types get_highest_supported_format();
 
@@ -52,7 +55,6 @@ static sstring validate_keyspace(http_context& ctx, const parameters& param) {
     throw bad_param_exception("Keyspace " + param["keyspace"] + " Does not exist");
 }
 
-
 static std::vector<ss::token_range> describe_ring(const sstring& keyspace) {
     std::vector<ss::token_range> res;
     for (auto d : service::get_local_storage_service().describe_ring(keyspace)) {
@@ -900,6 +902,133 @@ void set_storage_service(http_context& ctx, routes& r) {
             return make_ready_future<json::json_return_type>(map_to_key_value(std::move(status), res));
         });
     });
+
+    ss::sstable_info.set(r, [&ctx] (std::unique_ptr<request> req) {
+        auto ks = api::req_param<sstring>(*req, "keyspace", {}).value;
+        auto cf = api::req_param<sstring>(*req, "cf", {}).value;
+
+        // The size of this vector is bound by ks::cf. I.e. it is as most Nks + Ncf long
+        // which is not small, but not huge either. 
+        using table_sstables_list = std::vector<ss::table_sstables>;
+
+        return do_with(table_sstables_list{}, [ks, cf, &ctx](table_sstables_list& dst) {
+            return service::get_local_storage_service().db().map_reduce([&dst](table_sstables_list&& res) {
+                for (auto&& t : res) {
+                    auto i = std::find_if(dst.begin(), dst.end(), [&t](const ss::table_sstables& t2) {
+                        return t.keyspace() == t2.keyspace() && t.table() == t2.table();
+                    });
+                    if (i == dst.end()) {
+                        dst.emplace_back(std::move(t));
+                        continue;
+                    }
+                    auto& ssd = i->sstables; 
+                    for (auto&& sd : t.sstables._elements) {
+                        auto j = std::find_if(ssd._elements.begin(), ssd._elements.end(), [&sd](const ss::sstable& s) {
+                            return s.generation() == sd.generation();
+                        });
+                        if (j == ssd._elements.end()) {
+                            i->sstables.push(std::move(sd));
+                        }
+                    }
+                }
+            }, [ks, cf](const database& db) {
+                // see above
+                table_sstables_list res;
+
+                auto& ext = db.get_config().extensions();
+
+                for (auto& t : db.get_column_families() | boost::adaptors::map_values) {
+                    auto& schema = t->schema();
+                    if ((ks.empty() || ks == schema->ks_name()) && (cf.empty() || cf == schema->cf_name())) {
+                        // at most Nsstables long
+                        ss::table_sstables tst;
+                        tst.keyspace = schema->ks_name();
+                        tst.table = schema->cf_name();
+
+                        for (auto sstable : *t->get_sstables_including_compacted_undeleted()) {
+                            auto ts = db_clock::to_time_t(sstable->data_file_write_time());
+                            ::tm t;
+                            ::gmtime_r(&ts, &t);
+
+                            ss::sstable info;
+
+                            info.timestamp = t;
+                            info.generation = sstable->generation();
+                            info.level = sstable->get_sstable_level();
+                            info.size = sstable->bytes_on_disk();
+                            info.data_size = sstable->ondisk_data_size();
+                            info.index_size = sstable->index_size();
+                            info.filter_size = sstable->filter_size();
+                            info.version = sstable->get_version();
+
+                            if (sstable->has_component(sstables::component_type::CompressionInfo)) {
+                                auto& c = sstable->get_compression();
+                                auto cp = sstables::get_sstable_compressor(c);
+
+                                ss::named_maps nm;
+                                nm.group = "compression_parameters";
+                                for (auto& p : cp->options()) {
+                                    ss::mapper e;
+                                    e.key = p.first;
+                                    e.value = p.second;
+                                    nm.attributes.push(std::move(e));
+                                }
+                                if (!cp->options().count(compression_parameters::SSTABLE_COMPRESSION)) {
+                                    ss::mapper e;
+                                    e.key = compression_parameters::SSTABLE_COMPRESSION;
+                                    e.value = cp->name();
+                                    nm.attributes.push(std::move(e));
+                                }
+                                info.extended_properties.push(std::move(nm));
+                            }
+
+                            sstables::file_io_extension::attr_value_map map;
+
+                            for (auto* ep : ext.sstable_file_io_extensions()) {
+                                map.merge(ep->get_attributes(*sstable));
+                            }
+
+                            for (auto& p : map) {
+                                struct {
+                                    const sstring& key; 
+                                    ss::sstable& info;
+                                    void operator()(const std::map<sstring, sstring>& map) const {
+                                        ss::named_maps nm;
+                                        nm.group = key;
+                                        for (auto& p : map) {
+                                            ss::mapper e;
+                                            e.key = p.first;
+                                            e.value = p.second;
+                                            nm.attributes.push(std::move(e));
+                                        }
+                                        info.extended_properties.push(std::move(nm));
+                                    }
+                                    void operator()(const sstring& value) const {
+                                        ss::mapper e;
+                                        e.key = key;
+                                        e.value = value;
+                                        info.properties.push(std::move(e));                                        
+                                    }
+                                } v{p.first, info};
+
+                                std::visit(v, p.second);
+                            }
+
+                            tst.sstables.push(std::move(info));
+                        }
+                        res.emplace_back(std::move(tst));
+                    }
+                }
+                std::sort(res.begin(), res.end(), [](const ss::table_sstables& t1, const ss::table_sstables& t2) {
+                    return t1.keyspace() < t2.keyspace() || (t1.keyspace() == t2.keyspace() && t1.table() < t2.table());
+                });
+                return res;
+            }).then([&dst] {
+                return make_ready_future<json::json_return_type>(stream_object(dst));
+            });
+        });
+    });
+
 }
 
 }

cache_flat_mutation_reader.hh

@@ -61,7 +61,6 @@ class cache_flat_mutation_reader final : public flat_mutation_reader::impl {
         // - _last_row points at a direct predecessor of the next row which is going to be read.
         //   Used for populating continuity.
         // - _population_range_starts_before_all_rows is set accordingly
-        // - _underlying is engaged and fast-forwarded
         reading_from_underlying,
 
         end_of_stream
@@ -100,13 +99,7 @@ class cache_flat_mutation_reader final : public flat_mutation_reader::impl {
     // forward progress is not guaranteed in case iterators are getting constantly invalidated.
     bool _lower_bound_changed = false;
 
-    // Points to the underlying reader conforming to _schema,
-    // either to *_underlying_holder or _read_context->underlying().underlying().
-    flat_mutation_reader* _underlying = nullptr;
-    std::optional<flat_mutation_reader> _underlying_holder;
-
     future<> do_fill_buffer(db::timeout_clock::time_point);
-    future<> ensure_underlying(db::timeout_clock::time_point);
     void copy_from_cache_to_buffer();
     future<> process_static_row(db::timeout_clock::time_point);
     void move_to_end();
@@ -193,22 +186,23 @@ future<> cache_flat_mutation_reader::process_static_row(db::timeout_clock::time_
         return make_ready_future<>();
     } else {
         _read_context->cache().on_row_miss();
-        return ensure_underlying(timeout).then([this, timeout] {
-            return (*_underlying)(timeout).then([this] (mutation_fragment_opt&& sr) {
-                if (sr) {
-                    assert(sr->is_static_row());
-                    maybe_add_to_cache(sr->as_static_row());
-                    push_mutation_fragment(std::move(*sr));
-                }
-                maybe_set_static_row_continuous();
-            });
+        return _read_context->get_next_fragment(timeout).then([this] (mutation_fragment_opt&& sr) {
+            if (sr) {
+                assert(sr->is_static_row());
+                maybe_add_to_cache(sr->as_static_row());
+                push_mutation_fragment(std::move(*sr));
+            }
+            maybe_set_static_row_continuous();
         });
     }
 }
 
 inline
 void cache_flat_mutation_reader::touch_partition() {
-    _snp->touch();
+    if (_snp->at_latest_version()) {
+        rows_entry& last_dummy = *_snp->version()->partition().clustered_rows().rbegin();
+        _snp->tracker()->touch(last_dummy);
+    }
 }
 
 inline
@@ -238,36 +232,14 @@ future<> cache_flat_mutation_reader::fill_buffer(db::timeout_clock::time_point t
     });
 }
 
-inline
-future<> cache_flat_mutation_reader::ensure_underlying(db::timeout_clock::time_point timeout) {
-    if (_underlying) {
-        return make_ready_future<>();
-    }
-    return _read_context->ensure_underlying(timeout).then([this, timeout] {
-        flat_mutation_reader& ctx_underlying = _read_context->underlying().underlying();
-        if (ctx_underlying.schema() != _schema) {
-            _underlying_holder = make_delegating_reader(ctx_underlying);
-            _underlying_holder->upgrade_schema(_schema);
-            _underlying = &*_underlying_holder;
-        } else {
-            _underlying = &ctx_underlying;
-        }
-    });
-}
-
 inline
 future<> cache_flat_mutation_reader::do_fill_buffer(db::timeout_clock::time_point timeout) {
     if (_state == state::move_to_underlying) {
-        if (!_underlying) {
-            return ensure_underlying(timeout).then([this, timeout] {
-                return do_fill_buffer(timeout);
-            });
-        }
         _state = state::reading_from_underlying;
         _population_range_starts_before_all_rows = _lower_bound.is_before_all_clustered_rows(*_schema);
         auto end = _next_row_in_range ? position_in_partition(_next_row.position())
                                       : position_in_partition(_upper_bound);
-        return _underlying->fast_forward_to(position_range{_lower_bound, std::move(end)}, timeout).then([this, timeout] {
+        return _read_context->fast_forward_to(position_range{_lower_bound, std::move(end)}, timeout).then([this, timeout] {
             return read_from_underlying(timeout);
         });
     }
@@ -308,7 +280,7 @@ future<> cache_flat_mutation_reader::do_fill_buffer(db::timeout_clock::time_poin
 
 inline
 future<> cache_flat_mutation_reader::read_from_underlying(db::timeout_clock::time_point timeout) {
-    return consume_mutation_fragments_until(*_underlying,
+    return consume_mutation_fragments_until(_read_context->underlying().underlying(),
         [this] { return _state != state::reading_from_underlying || is_buffer_full(); },
         [this] (mutation_fragment mf) {
             _read_context->cache().on_row_miss();

coding-style.md

@@ -1,3 +1,8 @@
 # Scylla Coding Style
 
 Please see the [Seastar style document](https://github.com/scylladb/seastar/blob/master/coding-style.md).
+
+Scylla code is written with "using namespace seastar", and should not
+explicitly add the "seastar::" prefix to Seastar symbols.
+There is usually no need to add "using namespace seastar" to Source files,
+because most Scylla header files #include "seastarx.hh", which does this.

column_computation.hh

@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 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 General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include "bytes.hh"
+
+class schema;
+class partition_key;
+class clustering_row;
+
+class column_computation;
+using column_computation_ptr = std::unique_ptr<column_computation>;
+
+/*
+ * Column computation represents a computation performed in order to obtain a value for a computed column.
+ * Computed columns description is also available at docs/system_schema_keyspace.md. They hold values
+ * not provided directly by the user, but rather computed: from other column values and possibly other sources.
+ * This class is able to serialize/deserialize column computations and perform the computation itself,
+ * based on given schema, partition key and clustering row. Responsibility for providing enough data
+ * in the clustering row in order for computation to succeed belongs to the caller. In particular,
+ * generating a value might involve performing a read-before-write if the computation is performed
+ * on more values than are present in the update request.
+ */
+class column_computation {
+public:
+    virtual ~column_computation() = default;
+
+    static column_computation_ptr deserialize(bytes_view raw);
+    static column_computation_ptr deserialize(const Json::Value& json);
+
+    virtual column_computation_ptr clone() const = 0;
+
+    virtual bytes serialize() const = 0;
+    virtual bytes_opt compute_value(const schema& schema, const partition_key& key, const clustering_row& row) const = 0;
+};
+
+class token_column_computation : public column_computation {
+public:
+    virtual column_computation_ptr clone() const override {
+        return std::make_unique<token_column_computation>(*this);
+    }
+    virtual bytes serialize() const override;
+    virtual bytes_opt compute_value(const schema& schema, const partition_key& key, const clustering_row& row) const override;
+};

compaction_garbage_collector.hh

@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 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 General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include "schema.hh"
+#include "types/collection.hh"
+
+class atomic_cell;
+class row_marker;
+
+class compaction_garbage_collector {
+public:
+    virtual ~compaction_garbage_collector() = default;
+    virtual void collect(column_id id, atomic_cell) = 0;
+    virtual void collect(column_id id, collection_type_impl::mutation) = 0;
+    virtual void collect(row_marker) = 0;
+};

compaction_strategy.hh

@@ -21,14 +21,19 @@
 
 #pragma once
 
+#include <seastar/core/future.hh>
+#include <seastar/util/noncopyable_function.hh>
+
+#include "schema_fwd.hh"
 #include "sstables/shared_sstable.hh"
 #include "exceptions/exceptions.hh"
 #include "sstables/compaction_backlog_manager.hh"
 
 class table;
 using column_family = table;
-class schema;
-using schema_ptr = lw_shared_ptr<const schema>;
+
+class flat_mutation_reader;
+struct mutation_source_metadata;
 
 namespace sstables {
 
@@ -47,6 +52,8 @@ class sstable_set;
 struct compaction_descriptor;
 struct resharding_descriptor;
 
+using reader_consumer = noncopyable_function<future<> (flat_mutation_reader)>;
+
 class compaction_strategy {
     ::shared_ptr<compaction_strategy_impl> _compaction_strategy_impl;
 public:
@@ -75,8 +82,8 @@ public:
     // Return if optimization to rule out sstables based on clustering key filter should be applied.
     bool use_clustering_key_filter() const;
 
-    // Return true if compaction strategy ignores sstables coming from partial runs.
-    bool ignore_partial_runs() const;
+    // Return true if compaction strategy doesn't care if a sstable belonging to partial sstable run is compacted.
+    bool can_compact_partial_runs() const;
 
     // An estimation of number of compaction for strategy to be satisfied.
     int64_t estimated_pending_compactions(column_family& cf) const;
@@ -129,6 +136,10 @@ public:
     sstable_set make_sstable_set(schema_ptr schema) const;
 
     compaction_backlog_tracker& get_backlog_tracker();
+
+    uint64_t adjust_partition_estimate(const mutation_source_metadata& ms_meta, uint64_t partition_estimate);
+
+    reader_consumer make_interposer_consumer(const mutation_source_metadata& ms_meta, reader_consumer end_consumer);
 };
 
 // Creates a compaction_strategy object from one of the strategies available.

compatible_ring_position.hh

@@ -0,0 +1,165 @@
+/*
+ * Copyright (C) 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 General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+#pragma once
+
+#include "query-request.hh"
+#include <optional>
+#include <variant>
+
+// Wraps ring_position_view so it is compatible with old-style C++: default
+// constructor, stateless comparators, yada yada.
+class compatible_ring_position_view {
+    const ::schema* _schema = nullptr;
+    // Optional to supply a default constructor, no more.
+    std::optional<dht::ring_position_view> _rpv;
+public:
+    constexpr compatible_ring_position_view() = default;
+    compatible_ring_position_view(const schema& s, dht::ring_position_view rpv)
+        : _schema(&s), _rpv(rpv) {
+    }
+    const dht::ring_position_view& position() const {
+        return *_rpv;
+    }
+    const ::schema& schema() const {
+        return *_schema;
+    }
+    friend int tri_compare(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return dht::ring_position_tri_compare(*x._schema, *x._rpv, *y._rpv);
+    }
+    friend bool operator<(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return tri_compare(x, y) < 0;
+    }
+    friend bool operator<=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return tri_compare(x, y) <= 0;
+    }
+    friend bool operator>(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return tri_compare(x, y) > 0;
+    }
+    friend bool operator>=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return tri_compare(x, y) >= 0;
+    }
+    friend bool operator==(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return tri_compare(x, y) == 0;
+    }
+    friend bool operator!=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
+        return tri_compare(x, y) != 0;
+    }
+};
+
+// Wraps ring_position so it is compatible with old-style C++: default
+// constructor, stateless comparators, yada yada.
+class compatible_ring_position {
+    schema_ptr _schema;
+    // Optional to supply a default constructor, no more.
+    std::optional<dht::ring_position> _rp;
+public:
+    constexpr compatible_ring_position() = default;
+    compatible_ring_position(schema_ptr s, dht::ring_position rp)
+        : _schema(std::move(s)), _rp(std::move(rp)) {
+    }
+    dht::ring_position_view position() const {
+        return *_rp;
+    }
+    const ::schema& schema() const {
+        return *_schema;
+    }
+    friend int tri_compare(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return dht::ring_position_tri_compare(*x._schema, *x._rp, *y._rp);
+    }
+    friend bool operator<(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return tri_compare(x, y) < 0;
+    }
+    friend bool operator<=(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return tri_compare(x, y) <= 0;
+    }
+    friend bool operator>(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return tri_compare(x, y) > 0;
+    }
+    friend bool operator>=(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return tri_compare(x, y) >= 0;
+    }
+    friend bool operator==(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return tri_compare(x, y) == 0;
+    }
+    friend bool operator!=(const compatible_ring_position& x, const compatible_ring_position& y) {
+        return tri_compare(x, y) != 0;
+    }
+};
+
+// Wraps ring_position or ring_position_view so either is compatible with old-style C++: default
+// constructor, stateless comparators, yada yada.
+// The motivations for supporting both types are to make containers self-sufficient by not relying
+// on callers to keep ring position alive, allow lookup on containers that don't support different
+// key types, and also avoiding unnecessary copies.
+class compatible_ring_position_or_view {
+    // Optional to supply a default constructor, no more.
+    std::optional<std::variant<compatible_ring_position, compatible_ring_position_view>> _crp_or_view;
+public:
+    constexpr compatible_ring_position_or_view() = default;
+    explicit compatible_ring_position_or_view(schema_ptr s, dht::ring_position rp)
+        : _crp_or_view(compatible_ring_position(std::move(s), std::move(rp))) {
+    }
+    explicit compatible_ring_position_or_view(const schema& s, dht::ring_position_view rpv)
+        : _crp_or_view(compatible_ring_position_view(s, rpv)) {
+    }
+    dht::ring_position_view position() const {
+        struct rpv_accessor {
+            dht::ring_position_view operator()(const compatible_ring_position& crp) {
+                return crp.position();
+            }
+            dht::ring_position_view operator()(const compatible_ring_position_view& crpv) {
+                return crpv.position();
+            }
+        };
+        return std::visit(rpv_accessor{}, *_crp_or_view);
+    }
+    friend int tri_compare(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        struct schema_accessor {
+            const ::schema& operator()(const compatible_ring_position& crp) {
+                return crp.schema();
+            }
+            const ::schema& operator()(const compatible_ring_position_view& crpv) {
+                return crpv.schema();
+            }
+        };
+        return dht::ring_position_tri_compare(std::visit(schema_accessor{}, *x._crp_or_view), x.position(), y.position());
+    }
+    friend bool operator<(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        return tri_compare(x, y) < 0;
+    }
+    friend bool operator<=(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        return tri_compare(x, y) <= 0;
+    }
+    friend bool operator>(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        return tri_compare(x, y) > 0;
+    }
+    friend bool operator>=(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        return tri_compare(x, y) >= 0;
+    }
+    friend bool operator==(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        return tri_compare(x, y) == 0;
+    }
+    friend bool operator!=(const compatible_ring_position_or_view& x, const compatible_ring_position_or_view& y) {
+        return tri_compare(x, y) != 0;
+    }
+};

compatible_ring_position_view.hh

@@ -1,64 +0,0 @@
-/*
- * Copyright (C) 2016 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 General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#pragma once
-
-#include "query-request.hh"
-#include <optional>
-
-// Wraps ring_position_view so it is compatible with old-style C++: default
-// constructor, stateless comparators, yada yada.
-class compatible_ring_position_view {
-    const schema* _schema = nullptr;
-    // Optional to supply a default constructor, no more.
-    std::optional<dht::ring_position_view> _rpv;
-public:
-    constexpr compatible_ring_position_view() = default;
-    compatible_ring_position_view(const schema& s, dht::ring_position_view rpv)
-        : _schema(&s), _rpv(rpv) {
-    }
-    const dht::ring_position_view& position() const {
-        return *_rpv;
-    }
-    friend int tri_compare(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return dht::ring_position_tri_compare(*x._schema, *x._rpv, *y._rpv);
-    }
-    friend bool operator<(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return tri_compare(x, y) < 0;
-    }
-    friend bool operator<=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return tri_compare(x, y) <= 0;
-    }
-    friend bool operator>(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return tri_compare(x, y) > 0;
-    }
-    friend bool operator>=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return tri_compare(x, y) >= 0;
-    }
-    friend bool operator==(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return tri_compare(x, y) == 0;
-    }
-    friend bool operator!=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
-        return tri_compare(x, y) != 0;
-    }
-};
-

concrete_types.hh

@@ -0,0 +1,241 @@
+/*
+ * Copyright (C) 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 General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include <seastar/net/inet_address.hh>
+
+#include "types.hh"
+#include "types/list.hh"
+#include "types/map.hh"
+#include "types/set.hh"
+#include "types/tuple.hh"
+#include "types/user.hh"
+#include "utils/big_decimal.hh"
+
+struct empty_type_impl final : public abstract_type {
+    empty_type_impl();
+};
+
+struct counter_type_impl final : public abstract_type {
+    counter_type_impl();
+};
+
+template <typename T>
+struct simple_type_impl : public concrete_type<T> {
+    simple_type_impl(abstract_type::kind k, sstring name, std::optional<uint32_t> value_length_if_fixed);
+};
+
+template<typename T>
+struct integer_type_impl : public simple_type_impl<T> {
+    integer_type_impl(abstract_type::kind k, sstring name, std::optional<uint32_t> value_length_if_fixed);
+};
+
+struct byte_type_impl final : public integer_type_impl<int8_t> {
+    byte_type_impl();
+};
+
+struct short_type_impl final : public integer_type_impl<int16_t> {
+    short_type_impl();
+};
+
+struct int32_type_impl final : public integer_type_impl<int32_t> {
+    int32_type_impl();
+};
+
+struct long_type_impl final : public integer_type_impl<int64_t> {
+    long_type_impl();
+};
+
+struct boolean_type_impl final : public simple_type_impl<bool> {
+    boolean_type_impl();
+};
+
+template <typename T>
+struct floating_type_impl : public simple_type_impl<T> {
+    floating_type_impl(abstract_type::kind k, sstring name, std::optional<uint32_t> value_length_if_fixed);
+};
+
+struct double_type_impl final : public floating_type_impl<double> {
+    double_type_impl();
+};
+
+struct float_type_impl final : public floating_type_impl<float> {
+    float_type_impl();
+};
+
+struct decimal_type_impl final : public concrete_type<big_decimal> {
+    decimal_type_impl();
+};
+
+struct duration_type_impl final : public concrete_type<cql_duration> {
+    duration_type_impl();
+};
+
+struct timestamp_type_impl final : public simple_type_impl<db_clock::time_point> {
+    timestamp_type_impl();
+};
+
+struct simple_date_type_impl final : public simple_type_impl<uint32_t> {
+    simple_date_type_impl();
+};
+
+struct time_type_impl final : public simple_type_impl<int64_t> {
+    time_type_impl();
+};
+
+struct string_type_impl : public concrete_type<sstring> {
+    string_type_impl(kind k, sstring name);
+};
+
+struct ascii_type_impl final : public string_type_impl {
+    ascii_type_impl();
+};
+
+struct utf8_type_impl final : public string_type_impl {
+    utf8_type_impl();
+};
+
+struct bytes_type_impl final : public concrete_type<bytes> {
+    bytes_type_impl();
+};
+
+// This is the old version of timestamp_type_impl, but has been replaced as it
+// wasn't comparing pre-epoch timestamps correctly. This is kept for backward
+// compatibility but shouldn't be used in new code.
+struct date_type_impl final : public concrete_type<db_clock::time_point> {
+    date_type_impl();
+};
+
+struct timeuuid_type_impl final : public concrete_type<utils::UUID> {
+    timeuuid_type_impl();
+};
+
+struct varint_type_impl final : public concrete_type<boost::multiprecision::cpp_int> {
+    varint_type_impl();
+};
+
+struct inet_addr_type_impl final : public concrete_type<seastar::net::inet_address> {
+    inet_addr_type_impl();
+};
+
+struct uuid_type_impl final : public concrete_type<utils::UUID> {
+    uuid_type_impl();
+};
+
+template <typename Func> using visit_ret_type = std::invoke_result_t<Func, const ascii_type_impl&>;
+
+GCC6_CONCEPT(
+template <typename Func> concept bool CanHandleAllTypes = requires(Func f) {
+    { f(*static_cast<const ascii_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const boolean_type_impl*>(nullptr)) }     -> visit_ret_type<Func>;
+    { f(*static_cast<const byte_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const bytes_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const counter_type_impl*>(nullptr)) }     -> visit_ret_type<Func>;
+    { f(*static_cast<const date_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const decimal_type_impl*>(nullptr)) }     -> visit_ret_type<Func>;
+    { f(*static_cast<const double_type_impl*>(nullptr)) }      -> visit_ret_type<Func>;
+    { f(*static_cast<const duration_type_impl*>(nullptr)) }    -> visit_ret_type<Func>;
+    { f(*static_cast<const empty_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const float_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const inet_addr_type_impl*>(nullptr)) }   -> visit_ret_type<Func>;
+    { f(*static_cast<const int32_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const list_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const long_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const map_type_impl*>(nullptr)) }         -> visit_ret_type<Func>;
+    { f(*static_cast<const reversed_type_impl*>(nullptr)) }    -> visit_ret_type<Func>;
+    { f(*static_cast<const set_type_impl*>(nullptr)) }         -> visit_ret_type<Func>;
+    { f(*static_cast<const short_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const simple_date_type_impl*>(nullptr)) } -> visit_ret_type<Func>;
+    { f(*static_cast<const time_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const timestamp_type_impl*>(nullptr)) }   -> visit_ret_type<Func>;
+    { f(*static_cast<const timeuuid_type_impl*>(nullptr)) }    -> visit_ret_type<Func>;
+    { f(*static_cast<const tuple_type_impl*>(nullptr)) }       -> visit_ret_type<Func>;
+    { f(*static_cast<const user_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const utf8_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const uuid_type_impl*>(nullptr)) }        -> visit_ret_type<Func>;
+    { f(*static_cast<const varint_type_impl*>(nullptr)) }      -> visit_ret_type<Func>;
+};
+)
+
+template<typename Func>
+GCC6_CONCEPT(requires CanHandleAllTypes<Func>)
+static inline visit_ret_type<Func> visit(const abstract_type& t, Func&& f) {
+    switch (t.get_kind()) {
+    case abstract_type::kind::ascii:
+        return f(*static_cast<const ascii_type_impl*>(&t));
+    case abstract_type::kind::boolean:
+        return f(*static_cast<const boolean_type_impl*>(&t));
+    case abstract_type::kind::byte:
+        return f(*static_cast<const byte_type_impl*>(&t));
+    case abstract_type::kind::bytes:
+        return f(*static_cast<const bytes_type_impl*>(&t));
+    case abstract_type::kind::counter:
+        return f(*static_cast<const counter_type_impl*>(&t));
+    case abstract_type::kind::date:
+        return f(*static_cast<const date_type_impl*>(&t));
+    case abstract_type::kind::decimal:
+        return f(*static_cast<const decimal_type_impl*>(&t));
+    case abstract_type::kind::double_kind:
+        return f(*static_cast<const double_type_impl*>(&t));
+    case abstract_type::kind::duration:
+        return f(*static_cast<const duration_type_impl*>(&t));
+    case abstract_type::kind::empty:
+        return f(*static_cast<const empty_type_impl*>(&t));
+    case abstract_type::kind::float_kind:
+        return f(*static_cast<const float_type_impl*>(&t));
+    case abstract_type::kind::inet:
+        return f(*static_cast<const inet_addr_type_impl*>(&t));
+    case abstract_type::kind::int32:
+        return f(*static_cast<const int32_type_impl*>(&t));
+    case abstract_type::kind::list:
+        return f(*static_cast<const list_type_impl*>(&t));
+    case abstract_type::kind::long_kind:
+        return f(*static_cast<const long_type_impl*>(&t));
+    case abstract_type::kind::map:
+        return f(*static_cast<const map_type_impl*>(&t));
+    case abstract_type::kind::reversed:
+        return f(*static_cast<const reversed_type_impl*>(&t));
+    case abstract_type::kind::set:
+        return f(*static_cast<const set_type_impl*>(&t));
+    case abstract_type::kind::short_kind:
+        return f(*static_cast<const short_type_impl*>(&t));
+    case abstract_type::kind::simple_date:
+        return f(*static_cast<const simple_date_type_impl*>(&t));
+    case abstract_type::kind::time:
+        return f(*static_cast<const time_type_impl*>(&t));
+    case abstract_type::kind::timestamp:
+        return f(*static_cast<const timestamp_type_impl*>(&t));
+    case abstract_type::kind::timeuuid:
+        return f(*static_cast<const timeuuid_type_impl*>(&t));
+    case abstract_type::kind::tuple:
+        return f(*static_cast<const tuple_type_impl*>(&t));
+    case abstract_type::kind::user:
+        return f(*static_cast<const user_type_impl*>(&t));
+    case abstract_type::kind::utf8:
+        return f(*static_cast<const utf8_type_impl*>(&t));
+    case abstract_type::kind::uuid:
+        return f(*static_cast<const uuid_type_impl*>(&t));
+    case abstract_type::kind::varint:
+        return f(*static_cast<const varint_type_impl*>(&t));
+    }
+    __builtin_unreachable();
+}

conf/scylla.yaml

@@ -613,10 +613,16 @@ commitlog_total_space_in_mb: -1
 # compaction_throughput_mb_per_sec: 16
 
 # Log a warning when writing partitions larger than this value
-# compaction_large_partition_warning_threshold_mb: 100
+# compaction_large_partition_warning_threshold_mb: 1000
 
 # Log a warning when writing rows larger than this value
-# compaction_large_row_warning_threshold_mb: 50
+# compaction_large_row_warning_threshold_mb: 10
+
+# Log a warning when writing cells larger than this value
+# compaction_large_cell_warning_threshold_mb: 1
+
+# Log a warning when row number is larger than this value
+# compaction_rows_count_warning_threshold: 100000
 
 # When compacting, the replacement sstable(s) can be opened before they
 # are completely written, and used in place of the prior sstables for

configure.py

@@ -240,8 +240,7 @@ def find_headers(repodir, excluded_dirs):
 modes = {
     'debug': {
         'cxxflags': '-DDEBUG -DDEBUG_LSA_SANITIZER',
-        # Disable vptr because of https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88684
-        'cxx_ld_flags': '-O0 -fsanitize=address -fsanitize=leak -fsanitize=undefined -fno-sanitize=vptr',
+        'cxx_ld_flags': '',
     },
     'release': {
         'cxxflags': '',
@@ -251,6 +250,10 @@ modes = {
         'cxxflags': '',
         'cxx_ld_flags': '-O1',
     },
+    'sanitize': {
+        'cxxflags': '-DDEBUG -DDEBUG_LSA_SANITIZER',
+        'cxx_ld_flags': '-Os',
+    }
 }
 
 scylla_tests = [
@@ -363,7 +366,7 @@ scylla_tests = [
     'tests/imr_test',
     'tests/partition_data_test',
     'tests/reusable_buffer_test',
-    'tests/multishard_writer_test',
+    'tests/mutation_writer_test',
     'tests/observable_test',
     'tests/transport_test',
     'tests/fragmented_temporary_buffer_test',
@@ -375,6 +378,7 @@ scylla_tests = [
     'tests/small_vector_test',
     'tests/data_listeners_test',
     'tests/truncation_migration_test',
+    'tests/like_matcher_test',
 ]
 
 perf_tests = [
@@ -480,6 +484,7 @@ scylla_core = (['database.cc',
                 'utils/large_bitset.cc',
                 'utils/buffer_input_stream.cc',
                 'utils/limiting_data_source.cc',
+                'utils/updateable_value.cc',
                 'mutation_partition.cc',
                 'mutation_partition_view.cc',
                 'mutation_partition_serializer.cc',
@@ -490,6 +495,7 @@ scylla_core = (['database.cc',
                 'keys.cc',
                 'counters.cc',
                 'compress.cc',
+                'zstd.cc',
                 'sstables/mp_row_consumer.cc',
                 'sstables/sstables.cc',
                 'sstables/sstables_manager.cc',
@@ -719,12 +725,14 @@ scylla_core = (['database.cc',
                 'utils/arch/powerpc/crc32-vpmsum/crc32_wrapper.cc',
                 'querier.cc',
                 'data/cell.cc',
-                'multishard_writer.cc',
+                'mutation_writer/multishard_writer.cc',
                 'multishard_mutation_query.cc',
                 'reader_concurrency_semaphore.cc',
                 'distributed_loader.cc',
                 'utils/utf8.cc',
                 'utils/ascii.cc',
+                'utils/like_matcher.cc',
+                'mutation_writer/timestamp_based_splitting_writer.cc',
                 ] + [Antlr3Grammar('cql3/Cql.g')] + [Thrift('interface/cassandra.thrift', 'Cassandra')]
                )
 
@@ -764,6 +772,18 @@ api = ['api/api.cc',
        'api/api-doc/config.json',
        ]
 
+alternator = [
+       'alternator/server.cc',
+       'alternator/executor.cc',
+       'alternator/stats.cc',
+       'alternator/base64.cc',
+       'alternator/serialization.cc',
+       'alternator/expressions.cc',
+       Antlr3Grammar('alternator/expressions.g'),
+       'alternator/conditions.cc',
+       'alternator/rjson.cc',
+]
+
 idls = ['idl/gossip_digest.idl.hh',
         'idl/uuid.idl.hh',
         'idl/range.idl.hh',
@@ -802,10 +822,12 @@ scylla_tests_dependencies = scylla_core + idls + scylla_tests_generic_dependenci
     'tests/result_set_assertions.cc',
     'tests/mutation_source_test.cc',
     'tests/data_model.cc',
+    'tests/exception_utils.cc',
+    'tests/random_schema.cc',
 ]
 
 deps = {
-    'scylla': idls + ['main.cc', 'release.cc'] + scylla_core + api,
+    'scylla': idls + ['main.cc', 'release.cc'] + scylla_core + api + alternator,
 }
 
 pure_boost_tests = set([
@@ -834,14 +856,12 @@ pure_boost_tests = set([
     'tests/enum_set_test',
     'tests/cql_auth_syntax_test',
     'tests/meta_test',
-    'tests/imr_test',
-    'tests/partition_data_test',
-    'tests/reusable_buffer_test',
     'tests/observable_test',
     'tests/json_test',
     'tests/auth_passwords_test',
     'tests/top_k_test',
     'tests/small_vector_test',
+    'tests/like_matcher_test',
 ])
 
 tests_not_using_seastar_test_framework = set([
@@ -853,8 +873,6 @@ tests_not_using_seastar_test_framework = set([
     'tests/perf/perf_hash',
     'tests/perf/perf_cql_parser',
     'tests/message',
-    'tests/perf/perf_simple_query',
-    'tests/perf/perf_fast_forward',
     'tests/perf/perf_cache_eviction',
     'tests/row_cache_stress_test',
     'tests/memory_footprint',
@@ -902,6 +920,8 @@ deps['tests/small_vector_test'] = ['tests/small_vector_test.cc']
 deps['tests/multishard_mutation_query_test'] += ['tests/test_table.cc']
 deps['tests/vint_serialization_test'] = ['tests/vint_serialization_test.cc', 'vint-serialization.cc', 'bytes.cc']
 
+deps['tests/duration_test'] += ['tests/exception_utils.cc']
+
 deps['utils/gz/gen_crc_combine_table'] = ['utils/gz/gen_crc_combine_table.cc']
 
 warnings = [
@@ -1036,6 +1056,7 @@ total_memory = os.sysconf('SC_PAGE_SIZE') * os.sysconf('SC_PHYS_PAGES')
 link_pool_depth = max(int(total_memory / 7e9), 1)
 
 selected_modes = args.selected_modes or modes.keys()
+default_modes = args.selected_modes or ['debug', 'release', 'dev']
 build_modes =  {m: modes[m] for m in selected_modes}
 build_artifacts = all_artifacts if not args.artifacts else args.artifacts
 
@@ -1068,8 +1089,8 @@ modes['debug']['cxxflags'] += ' -gz'
 flag_dest = 'cxx_ld_flags' if args.compress_exec_debuginfo else 'cxxflags'
 modes['release'][flag_dest] += ' -gz'
 
-modes['debug']['cxxflags'] += ' ' + dbgflag
-modes['release']['cxxflags'] += ' ' + dbgflag
+for m in ['debug', 'release', 'sanitize']:
+    modes[m]['cxxflags'] += ' ' + dbgflag
 
 seastar_cflags = args.user_cflags
 seastar_cflags += ' -Wno-error'
@@ -1080,6 +1101,7 @@ seastar_flags += ['--compiler', args.cxx, '--c-compiler', args.cc, '--cflags=%s'
                   '--c++-dialect=gnu++17', '--use-std-optional-variant-stringview=1', '--optflags=%s' % (modes['release']['cxx_ld_flags']), ]
 
 libdeflate_cflags = seastar_cflags
+zstd_cflags = seastar_cflags + ' -Wno-implicit-fallthrough'
 
 status = subprocess.call([args.python, './configure.py'] + seastar_flags, cwd='seastar')
 
@@ -1109,11 +1131,32 @@ for mode in build_modes:
     modes[mode]['seastar_cflags'] = seastar_cflags
     modes[mode]['seastar_libs'] = seastar_libs
 
+MODE_TO_CMAKE_BUILD_TYPE = {'release' : 'RelWithDebInfo', 'debug' : 'Debug', 'dev' : 'Dev', 'sanitize' : 'Sanitize' }
+
+# We need to use experimental features of the zstd library (to use our own allocators for the (de)compression context),
+# which are available only when the library is linked statically.
+def configure_zstd(build_dir, mode):
+    zstd_build_dir = os.path.join(build_dir, mode, 'zstd')
+
+    zstd_cmake_args = [
+        '-DCMAKE_BUILD_TYPE={}'.format(MODE_TO_CMAKE_BUILD_TYPE[mode]),
+        '-DCMAKE_C_COMPILER={}'.format(args.cc),
+        '-DCMAKE_CXX_COMPILER={}'.format(args.cxx),
+        '-DCMAKE_C_FLAGS={}'.format(zstd_cflags),
+        '-DZSTD_BUILD_PROGRAMS=OFF'
+    ]
+
+    zstd_cmd = ['cmake', '-G', 'Ninja', os.path.relpath('zstd/build/cmake', zstd_build_dir)] + zstd_cmake_args
+
+    print(zstd_cmd)
+    os.makedirs(zstd_build_dir, exist_ok=True)
+    subprocess.check_call(zstd_cmd, shell=False, cwd=zstd_build_dir)
+
 args.user_cflags += " " + pkg_config('jsoncpp', '--cflags')
 args.user_cflags += ' -march=' + args.target
 libs = ' '.join([maybe_static(args.staticyamlcpp, '-lyaml-cpp'), '-latomic', '-llz4', '-lz', '-lsnappy', pkg_config('jsoncpp', '--libs'),
                  ' -lstdc++fs', ' -lcrypt', ' -lcryptopp', ' -lpthread',
-                 maybe_static(args.staticboost, '-lboost_date_time'), ])
+                 maybe_static(args.staticboost, '-lboost_date_time -lboost_regex -licuuc'), ])
 
 xxhash_dir = 'xxHash'
 
@@ -1123,6 +1166,17 @@ if not os.path.exists(xxhash_dir) or not os.listdir(xxhash_dir):
 if not args.staticboost:
     args.user_cflags += ' -DBOOST_TEST_DYN_LINK'
 
+# thrift version detection, see #4538
+proc_res = subprocess.run(["thrift", "-version"], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+proc_res_output = proc_res.stdout.decode("utf-8")
+if proc_res.returncode != 0 and not re.search(r'^Thrift version', proc_res_output):
+    raise Exception("Thrift compiler must be missing: {}".format(proc_res_output))
+
+thrift_version = proc_res_output.split(" ")[-1]
+thrift_boost_versions = ["0.{}.".format(n) for n in range(1, 11)]
+if any(filter(thrift_version.startswith, thrift_boost_versions)):
+    args.user_cflags += ' -DTHRIFT_USES_BOOST'
+
 for pkg in pkgs:
     args.user_cflags += ' ' + pkg_config(pkg, '--cflags')
     libs += ' ' + pkg_config(pkg, '--libs')
@@ -1148,7 +1202,16 @@ if args.antlr3_exec:
 else:
     antlr3_exec = "antlr3"
 
-with open(buildfile, 'w') as f:
+for mode in build_modes:
+    configure_zstd(outdir, mode)
+
+# configure.py may run automatically from an already-existing build.ninja.
+# If the user interrupts configure.py in the middle, we need build.ninja
+# to remain in a valid state.  So we write our output to a temporary
+# file, and only when done we rename it atomically to build.ninja.
+buildfile_tmp = buildfile + ".tmp"
+
+with open(buildfile_tmp, 'w') as f:
     f.write(textwrap.dedent('''\
         configure_args = {configure_args}
         builddir = {outdir}
@@ -1158,7 +1221,7 @@ with open(buildfile, 'w') as f:
         libs = {libs}
         pool link_pool
             depth = {link_pool_depth}
-        pool seastar_pool
+        pool submodule_pool
             depth = 1
         rule gen
             command = echo -e $text > $out
@@ -1258,7 +1321,8 @@ with open(buildfile, 'w') as f:
                 f.write('build $builddir/{}/{}: ar.{} {}\n'.format(mode, binary, mode, str.join(' ', objs)))
             else:
                 objs.extend(['$builddir/' + mode + '/' + artifact for artifact in [
-                    'libdeflate/libdeflate.a'
+                    'libdeflate/libdeflate.a',
+                    'zstd/lib/libzstd.a',
                 ]])
                 objs.append('$builddir/' + mode + '/gen/utils/gz/crc_combine_table.o')
                 if binary.startswith('tests/'):
@@ -1305,6 +1369,7 @@ with open(buildfile, 'w') as f:
                                             '$builddir/' + mode + '/utils/gz/gen_crc_combine_table'))
         f.write('build {}: link.{} {}\n'.format('$builddir/' + mode + '/utils/gz/gen_crc_combine_table', mode,
                                                 '$builddir/' + mode + '/utils/gz/gen_crc_combine_table.o'))
+        f.write('   libs = $seastar_libs_{}\n'.format(mode))
         f.write(
             'build {mode}-objects: phony {objs}\n'.format(
                 mode=mode,
@@ -1353,19 +1418,30 @@ with open(buildfile, 'w') as f:
             f.write('build $builddir/{mode}/{hh}.o: checkhh.{mode} {hh} || {gen_headers_dep}\n'.format(
                     mode=mode, hh=hh, gen_headers_dep=gen_headers_dep))
 
-        f.write('build seastar/build/{mode}/libseastar.a seastar/build/{mode}/apps/iotune/iotune: ninja | always\n'
+        f.write('build seastar/build/{mode}/libseastar.a: ninja | always\n'
                 .format(**locals()))
-        f.write('  pool = seastar_pool\n')
+        f.write('  pool = submodule_pool\n')
         f.write('  subdir = seastar/build/{mode}\n'.format(**locals()))
-        f.write('  target = seastar seastar_testing app_iotune\n'.format(**locals()))
+        f.write('  target = seastar seastar_testing\n'.format(**locals()))
+        f.write('build seastar/build/{mode}/apps/iotune/iotune: ninja\n'
+                .format(**locals()))
+        f.write('  pool = submodule_pool\n')
+        f.write('  subdir = seastar/build/{mode}\n'.format(**locals()))
+        f.write('  target = iotune\n'.format(**locals()))
         f.write(textwrap.dedent('''\
             build build/{mode}/iotune: copy seastar/build/{mode}/apps/iotune/iotune
             ''').format(**locals()))
         f.write('build build/{mode}/scylla-package.tar.gz: package build/{mode}/scylla build/{mode}/iotune build/SCYLLA-RELEASE-FILE build/SCYLLA-VERSION-FILE | always\n'.format(**locals()))
-        f.write('    mode = {mode}\n'.format(**locals()))
+        f.write('  pool = submodule_pool\n')
+        f.write('  mode = {mode}\n'.format(**locals()))
         f.write('rule libdeflate.{mode}\n'.format(**locals()))
-        f.write('    command = make -C libdeflate BUILD_DIR=../build/{mode}/libdeflate/ CFLAGS="{libdeflate_cflags}" CC={args.cc} ../build/{mode}/libdeflate//libdeflate.a\n'.format(**locals()))
+        f.write('  command = make -C libdeflate BUILD_DIR=../build/{mode}/libdeflate/ CFLAGS="{libdeflate_cflags}" CC={args.cc} ../build/{mode}/libdeflate//libdeflate.a\n'.format(**locals()))
         f.write('build build/{mode}/libdeflate/libdeflate.a: libdeflate.{mode}\n'.format(**locals()))
+        f.write('  pool = submodule_pool\n')
+        f.write('build build/{mode}/zstd/lib/libzstd.a: ninja\n'.format(**locals()))
+        f.write('  pool = submodule_pool\n')
+        f.write('  subdir = build/{mode}/zstd\n'.format(**locals()))
+        f.write('  target = libzstd.a\n'.format(**locals()))
 
     mode = 'dev' if 'dev' in modes else modes[0]
     f.write('build checkheaders: phony || {}\n'.format(' '.join(['$builddir/{}/{}.o'.format(mode, hh) for hh in headers])))
@@ -1384,10 +1460,12 @@ with open(buildfile, 'w') as f:
             description = CLEAN
         build clean: clean
         default {modes_list}
-        ''').format(modes_list=' '.join(build_modes), **globals()))
+        ''').format(modes_list=' '.join(default_modes), **globals()))
     f.write(textwrap.dedent('''\
         build always: phony
         rule scylla_version_gen
             command = ./SCYLLA-VERSION-GEN
         build build/SCYLLA-RELEASE-FILE build/SCYLLA-VERSION-FILE: scylla_version_gen
         ''').format(modes_list=' '.join(build_modes), **globals()))
+
+os.rename(buildfile_tmp, buildfile)

counters.hh

@@ -309,7 +309,8 @@ class basic_counter_cell_view {
 protected:
     using linearized_value_view = std::conditional_t<is_mutable == mutable_view::no,
                                                      bytes_view, bytes_mutable_view>;
-    using pointer_type = typename linearized_value_view::pointer;
+    using pointer_type = std::conditional_t<is_mutable == mutable_view::no,
+                                            bytes_view::const_pointer, bytes_mutable_view::pointer>;
     basic_atomic_cell_view<is_mutable> _cell;
     linearized_value_view _value;
 private:

cql3/Cql.g

@@ -125,6 +125,7 @@ struct uninitialized {
     uninitialized& operator=(uninitialized&&) = default;
     operator const T&() const & { return check(), *_val; }
     operator T&&() && { return check(), std::move(*_val); }
+    operator std::optional<T>&&() && { return check(), std::move(_val); }
     void check() const { if (!_val) { throw std::runtime_error("not intitialized"); } }
 };
 
@@ -394,6 +395,7 @@ selectStatement returns [shared_ptr<raw::select_statement> expr]
                )
       K_FROM cf=columnFamilyName
       ( K_WHERE wclause=whereClause )?
+      ( K_GROUP K_BY gbcolumns=listOfIdentifiers)?
       ( K_ORDER K_BY orderByClause[orderings] ( ',' orderByClause[orderings] )* )?
       ( K_PER K_PARTITION K_LIMIT rows=intValue { per_partition_limit = rows; } )?
       ( K_LIMIT rows=intValue { limit = rows; } )?
@@ -402,7 +404,8 @@ selectStatement returns [shared_ptr<raw::select_statement> expr]
       {
           auto params = ::make_shared<raw::select_statement::parameters>(std::move(orderings), is_distinct, allow_filtering, is_json, bypass_cache);
           $expr = ::make_shared<raw::select_statement>(std::move(cf), std::move(params),
-            std::move(sclause), std::move(wclause), std::move(limit), std::move(per_partition_limit));
+            std::move(sclause), std::move(wclause), std::move(limit), std::move(per_partition_limit),
+            std::move(gbcolumns));
       }
     ;
 
@@ -1125,10 +1128,10 @@ createUserStatement returns [::shared_ptr<create_role_statement> stmt]
 
         bool ifNotExists = false;
     }
-    : K_CREATE K_USER (K_IF K_NOT K_EXISTS { ifNotExists = true; })? username
+    : K_CREATE K_USER (K_IF K_NOT K_EXISTS { ifNotExists = true; })? u=username
       ( K_WITH K_PASSWORD v=STRING_LITERAL { opts.password = $v.text; })?
       ( K_SUPERUSER { opts.is_superuser = true; } | K_NOSUPERUSER { opts.is_superuser = false; } )?
-      { $stmt = ::make_shared<create_role_statement>(cql3::role_name($username.text, cql3::preserve_role_case::yes), std::move(opts), ifNotExists); }
+      { $stmt = ::make_shared<create_role_statement>(cql3::role_name(u, cql3::preserve_role_case::yes), std::move(opts), ifNotExists); }
     ;
 
 /**
@@ -1138,10 +1141,10 @@ alterUserStatement returns [::shared_ptr<alter_role_statement> stmt]
     @init {
         cql3::role_options opts;
     }
-    : K_ALTER K_USER username
+    : K_ALTER K_USER u=username
       ( K_WITH K_PASSWORD v=STRING_LITERAL { opts.password = $v.text; })?
       ( K_SUPERUSER { opts.is_superuser = true; } | K_NOSUPERUSER { opts.is_superuser = false; } )?
-      { $stmt = ::make_shared<alter_role_statement>(cql3::role_name($username.text, cql3::preserve_role_case::yes), std::move(opts)); }
+      { $stmt = ::make_shared<alter_role_statement>(cql3::role_name(u, cql3::preserve_role_case::yes), std::move(opts)); }
     ;
 
 /**
@@ -1149,8 +1152,8 @@ alterUserStatement returns [::shared_ptr<alter_role_statement> stmt]
  */
 dropUserStatement returns [::shared_ptr<drop_role_statement> stmt]
     @init { bool ifExists = false; }
-    : K_DROP K_USER (K_IF K_EXISTS { ifExists = true; })? username
-      { $stmt = ::make_shared<drop_role_statement>(cql3::role_name($username.text, cql3::preserve_role_case::yes), ifExists); }
+    : K_DROP K_USER (K_IF K_EXISTS { ifExists = true; })? u=username
+      { $stmt = ::make_shared<drop_role_statement>(cql3::role_name(u, cql3::preserve_role_case::yes), ifExists); }
     ;
 
 /**
@@ -1488,6 +1491,7 @@ relationType returns [const cql3::operator_type* op = nullptr]
     | '>'  { $op = &cql3::operator_type::GT; }
     | '>=' { $op = &cql3::operator_type::GTE; }
     | '!=' { $op = &cql3::operator_type::NEQ; }
+    | K_LIKE { $op = &cql3::operator_type::LIKE; }
     ;
 
 relation[std::vector<cql3::relation_ptr>& clauses]
@@ -1537,6 +1541,10 @@ tupleOfIdentifiers returns [std::vector<::shared_ptr<cql3::column_identifier::ra
     : '(' n1=cident { $ids.push_back(n1); } (',' ni=cident { $ids.push_back(ni); })* ')'
     ;
 
+listOfIdentifiers returns [std::vector<::shared_ptr<cql3::column_identifier::raw>> ids]
+    : n1=cident { $ids.push_back(n1); } (',' ni=cident { $ids.push_back(ni); })*
+    ;
+
 singleColumnInValues returns [std::vector<::shared_ptr<cql3::term::raw>> terms]
     : '(' ( t1 = term { $terms.push_back(t1); } (',' ti=term { $terms.push_back(ti); })* )? ')'
     ;
@@ -1657,9 +1665,10 @@ tuple_type [bool internal] returns [shared_ptr<cql3::cql3_type::raw> t]
       '>' { $t = cql3::cql3_type::raw::tuple(std::move(types)); }
     ;
 
-username
-    : IDENT
-    | STRING_LITERAL
+username returns [sstring str]
+    : t=IDENT { $str = $t.text; }
+    | t=STRING_LITERAL { $str = $t.text; }
+    | s=unreserved_keyword { $str = s; }
     | QUOTED_NAME { add_recognition_error("Quoted strings are not supported for user names"); }
     ;
 
@@ -1728,8 +1737,10 @@ basic_unreserved_keyword returns [sstring str]
         | K_JSON
         | K_CACHE
         | K_BYPASS
+        | K_LIKE
         | K_PER
         | K_PARTITION
+        | K_GROUP
         ) { $str = $k.text; }
     ;
 
@@ -1881,6 +1892,10 @@ K_PARTITION:   P A R T I T I O N;
 K_SCYLLA_TIMEUUID_LIST_INDEX: S C Y L L A '_' T I M E U U I D '_' L I S T '_' I N D E X;
 K_SCYLLA_COUNTER_SHARD_LIST: S C Y L L A '_' C O U N T E R '_' S H A R D '_' L I S T; 
 
+K_GROUP:       G R O U P;
+
+K_LIKE:        L I K E;
+
 // Case-insensitive alpha characters
 fragment A: ('a'|'A');
 fragment B: ('b'|'B');

cql3/abstract_marker.cc

@@ -72,11 +72,11 @@ abstract_marker::raw::raw(int32_t bind_index)
     if (receiver_type == nullptr) {
         return ::make_shared<constants::marker>(_bind_index, receiver);
     }
-    if (&receiver_type->_kind == &collection_type_impl::kind::list) {
+    if (receiver_type->get_kind() == abstract_type::kind::list) {
         return ::make_shared<lists::marker>(_bind_index, receiver);
-    } else if (&receiver_type->_kind == &collection_type_impl::kind::set) {
+    } else if (receiver_type->get_kind() == abstract_type::kind::set) {
         return ::make_shared<sets::marker>(_bind_index, receiver);
-    } else if (&receiver_type->_kind == &collection_type_impl::kind::map) {
+    } else if (receiver_type->get_kind() == abstract_type::kind::map) {
         return ::make_shared<maps::marker>(_bind_index, receiver);
     }
     assert(0);

cql3/column_condition.cc

@@ -124,13 +124,13 @@ column_condition::raw::prepare(database& db, const sstring& keyspace, const colu
 
     shared_ptr<column_specification> element_spec, value_spec;
     auto ctype = static_cast<const collection_type_impl*>(receiver.type.get());
-    if (&ctype->_kind == &collection_type_impl::kind::list) {
+    if (ctype->get_kind() == abstract_type::kind::list) {
         element_spec = lists::index_spec_of(receiver.column_specification);
         value_spec = lists::value_spec_of(receiver.column_specification);
-    } else if (&ctype->_kind == &collection_type_impl::kind::map) {
+    } else if (ctype->get_kind() == abstract_type::kind::map) {
         element_spec = maps::key_spec_of(*receiver.column_specification);
         value_spec = maps::value_spec_of(*receiver.column_specification);
-    } else if (&ctype->_kind == &collection_type_impl::kind::set) {
+    } else if (ctype->get_kind() == abstract_type::kind::set) {
         throw exceptions::invalid_request_exception(format("Invalid element access syntax for set column {}", receiver.name()));
     } else {
         abort();

cql3/cql3_type.cc

@@ -79,16 +79,16 @@ public:
     }
 
     virtual bool is_duration() const override {
-        return _type.get_type()->equals(duration_type);
+        return _type.get_type() == duration_type;
     }
 };
 
 class cql3_type::raw_collection : public raw {
-    const collection_type_impl::kind* _kind;
+    const abstract_type::kind _kind;
     shared_ptr<raw> _keys;
     shared_ptr<raw> _values;
 public:
-    raw_collection(const collection_type_impl::kind* kind, shared_ptr<raw> keys, shared_ptr<raw> values)
+    raw_collection(const abstract_type::kind kind, shared_ptr<raw> keys, shared_ptr<raw> values)
             : _kind(kind), _keys(std::move(keys)), _values(std::move(values)) {
     }
 
@@ -126,14 +126,14 @@ public:
             }
         }
 
-        if (_kind == &collection_type_impl::kind::list) {
+        if (_kind == abstract_type::kind::list) {
             return cql3_type(list_type_impl::get_instance(_values->prepare_internal(keyspace, user_types).get_type(), !_frozen));
-        } else if (_kind == &collection_type_impl::kind::set) {
+        } else if (_kind == abstract_type::kind::set) {
             if (_values->is_duration()) {
                 throw exceptions::invalid_request_exception(format("Durations are not allowed inside sets: {}", *this));
             }
             return cql3_type(set_type_impl::get_instance(_values->prepare_internal(keyspace, user_types).get_type(), !_frozen));
-        } else if (_kind == &collection_type_impl::kind::map) {
+        } else if (_kind == abstract_type::kind::map) {
             assert(_keys); // "Got null keys type for a collection";
             if (_keys->is_duration()) {
                 throw exceptions::invalid_request_exception(format("Durations are not allowed as map keys: {}", *this));
@@ -154,11 +154,11 @@ public:
     virtual sstring to_string() const override {
         sstring start = _frozen ? "frozen<" : "";
         sstring end = _frozen ? ">" : "";
-        if (_kind == &collection_type_impl::kind::list) {
+        if (_kind == abstract_type::kind::list) {
             return format("{}list<{}>{}", start, _values, end);
-        } else if (_kind == &collection_type_impl::kind::set) {
+        } else if (_kind == abstract_type::kind::set) {
             return format("{}set<{}>{}", start, _values, end);
-        } else if (_kind == &collection_type_impl::kind::map) {
+        } else if (_kind == abstract_type::kind::map) {
             return format("{}map<{}, {}>{}", start, _keys, _values, end);
         }
         abort();
@@ -297,17 +297,17 @@ cql3_type::raw::user_type(ut_name name) {
 
 shared_ptr<cql3_type::raw>
 cql3_type::raw::map(shared_ptr<raw> t1, shared_ptr<raw> t2) {
-    return make_shared(raw_collection(&collection_type_impl::kind::map, std::move(t1), std::move(t2)));
+    return make_shared(raw_collection(abstract_type::kind::map, std::move(t1), std::move(t2)));
 }
 
 shared_ptr<cql3_type::raw>
 cql3_type::raw::list(shared_ptr<raw> t) {
-    return make_shared(raw_collection(&collection_type_impl::kind::list, {}, std::move(t)));
+    return make_shared(raw_collection(abstract_type::kind::list, {}, std::move(t)));
 }
 
 shared_ptr<cql3_type::raw>
 cql3_type::raw::set(shared_ptr<raw> t) {
-    return make_shared(raw_collection(&collection_type_impl::kind::set, {}, std::move(t)));
+    return make_shared(raw_collection(abstract_type::kind::set, {}, std::move(t)));
 }
 
 shared_ptr<cql3_type::raw>

cql3/functions/functions.cc

@@ -131,6 +131,10 @@ functions::init() {
     declare(aggregate_fcts::make_max_function<bytes>());
     declare(aggregate_fcts::make_min_function<bytes>());
 
+    declare(aggregate_fcts::make_count_function<bool>());
+    declare(aggregate_fcts::make_max_function<bool>());
+    declare(aggregate_fcts::make_min_function<bool>());
+
     // FIXME: more count/min/max
 
     declare(make_varchar_as_blob_fct());
@@ -194,7 +198,7 @@ make_from_json_function(database& db, const sstring& keyspace, data_type t) {
         if (!json_value.isNull()) {
             parsed_json_value.emplace(t->from_json_object(json_value, sf));
         }
-        return std::move(parsed_json_value);
+        return parsed_json_value;
     });
 }
 
@@ -468,11 +472,11 @@ function_call::make_terminal(shared_ptr<function> fun, cql3::raw_value result, c
     if (result) {
         res = fragmented_temporary_buffer::view(bytes_view(*result));
     }
-    if (&ctype->_kind == &collection_type_impl::kind::list) {
+    if (ctype->get_kind() == abstract_type::kind::list) {
         return make_shared(lists::value::from_serialized(std::move(res), static_pointer_cast<const list_type_impl>(ctype), sf));
-    } else if (&ctype->_kind == &collection_type_impl::kind::set) {
+    } else if (ctype->get_kind() == abstract_type::kind::set) {
         return make_shared(sets::value::from_serialized(std::move(res), static_pointer_cast<const set_type_impl>(ctype), sf));
-    } else if (&ctype->_kind == &collection_type_impl::kind::map) {
+    } else if (ctype->get_kind() == abstract_type::kind::map) {
         return make_shared(maps::value::from_serialized(std::move(res), static_pointer_cast<const map_type_impl>(ctype), sf));
     }
     abort();
@@ -551,7 +555,7 @@ function_call::raw::test_assignment(database& db, const sstring& keyspace, share
     // later with a more helpful error message that if we were to return false here.
     try {
         auto&& fun = functions::get(db, keyspace, _name, _terms, receiver->ks_name, receiver->cf_name, receiver);
-        if (fun && receiver->type->equals(fun->return_type())) {
+        if (fun && receiver->type == fun->return_type()) {
             return assignment_testable::test_result::EXACT_MATCH;
         } else if (!fun || receiver->type->is_value_compatible_with(*fun->return_type())) {
             return assignment_testable::test_result::WEAKLY_ASSIGNABLE;

cql3/functions/time_uuid_fcts.hh

@@ -61,16 +61,6 @@ make_now_fct() {
     });
 }
 
-static int64_t get_valid_timestamp(const data_value& ts_obj) {
-    auto ts = value_cast<db_clock::time_point>(ts_obj);
-    int64_t ms = ts.time_since_epoch().count();
-    auto nanos_since = utils::UUID_gen::make_nanos_since(ms);
-    if (!utils::UUID_gen::is_valid_nanos_since(nanos_since)) {
-        throw exceptions::server_exception(format("{}: timestamp is out of range. Must be in milliseconds since epoch", ms));
-    }
-    return ms;
-}
-
 inline
 shared_ptr<function>
 make_min_timeuuid_fct() {
@@ -84,7 +74,8 @@ make_min_timeuuid_fct() {
         if (ts_obj.is_null()) {
             return {};
         }
-        auto uuid = utils::UUID_gen::min_time_UUID(get_valid_timestamp(ts_obj));
+        auto ts = value_cast<db_clock::time_point>(ts_obj);
+        auto uuid = utils::UUID_gen::min_time_UUID(ts.time_since_epoch().count());
         return {timeuuid_type->decompose(uuid)};
     });
 }
@@ -94,6 +85,7 @@ shared_ptr<function>
 make_max_timeuuid_fct() {
     return make_native_scalar_function<true>("maxtimeuuid", timeuuid_type, { timestamp_type },
             [] (cql_serialization_format sf, const std::vector<bytes_opt>& values) -> bytes_opt {
+        // FIXME: should values be a vector<optional<bytes>>?
         auto& bb = values[0];
         if (!bb) {
             return {};
@@ -102,22 +94,12 @@ make_max_timeuuid_fct() {
         if (ts_obj.is_null()) {
             return {};
         }
-        auto uuid = utils::UUID_gen::max_time_UUID(get_valid_timestamp(ts_obj));
+        auto ts = value_cast<db_clock::time_point>(ts_obj);
+        auto uuid = utils::UUID_gen::max_time_UUID(ts.time_since_epoch().count());
         return {timeuuid_type->decompose(uuid)};
     });
 }
 
-inline utils::UUID get_valid_timeuuid(bytes raw) {
-    if (!utils::UUID_gen::is_valid_UUID(raw)) {
-        throw exceptions::server_exception(format("invalid timeuuid: size={}", raw.size()));
-    }
-    auto uuid = utils::UUID_gen::get_UUID(raw);
-    if (!uuid.is_timestamp()) {
-        throw exceptions::server_exception(format("{}: Not a timeuuid: version={}", uuid, uuid.version()));
-    }
-    return uuid;
-}
-
 inline
 shared_ptr<function>
 make_date_of_fct() {
@@ -128,7 +110,7 @@ make_date_of_fct() {
         if (!bb) {
             return {};
         }
-        auto ts = db_clock::time_point(db_clock::duration(UUID_gen::unix_timestamp(get_valid_timeuuid(*bb))));
+        auto ts = db_clock::time_point(db_clock::duration(UUID_gen::unix_timestamp(UUID_gen::get_UUID(*bb))));
         return {timestamp_type->decompose(ts)};
     });
 }
@@ -143,7 +125,7 @@ make_unix_timestamp_of_fct() {
         if (!bb) {
             return {};
         }
-        return {long_type->decompose(UUID_gen::unix_timestamp(get_valid_timeuuid(*bb)))};
+        return {long_type->decompose(UUID_gen::unix_timestamp(UUID_gen::get_UUID(*bb)))};
     });
 }
 
@@ -194,7 +176,7 @@ make_timeuuidtodate_fct() {
         if (!bb) {
             return {};
         }
-        auto ts = db_clock::time_point(db_clock::duration(UUID_gen::unix_timestamp(get_valid_timeuuid(*bb))));
+        auto ts = db_clock::time_point(db_clock::duration(UUID_gen::unix_timestamp(UUID_gen::get_UUID(*bb))));
         auto to_simple_date = get_castas_fctn(simple_date_type, timestamp_type);
         return {simple_date_type->decompose(to_simple_date(ts))};
     });
@@ -229,7 +211,7 @@ make_timeuuidtotimestamp_fct() {
         if (!bb) {
             return {};
         }
-        auto ts = db_clock::time_point(db_clock::duration(UUID_gen::unix_timestamp(get_valid_timeuuid(*bb))));
+        auto ts = db_clock::time_point(db_clock::duration(UUID_gen::unix_timestamp(UUID_gen::get_UUID(*bb))));
         return {timestamp_type->decompose(ts)};
     });
 }
@@ -263,14 +245,10 @@ make_timeuuidtounixtimestamp_fct() {
         if (!bb) {
             return {};
         }
-        return {long_type->decompose(UUID_gen::unix_timestamp(get_valid_timeuuid(*bb)))};
+        return {long_type->decompose(UUID_gen::unix_timestamp(UUID_gen::get_UUID(*bb)))};
     });
 }
 
-inline bytes time_point_to_long(const data_value& v) {
-    return data_value(get_valid_timestamp(v)).serialize();
-}
-
 inline
 shared_ptr<function>
 make_timestamptounixtimestamp_fct() {
@@ -285,7 +263,7 @@ make_timestamptounixtimestamp_fct() {
         if (ts_obj.is_null()) {
             return {};
         }
-        return time_point_to_long(ts_obj);
+        return {long_type->decompose(ts_obj)};
     });
 }
 
@@ -304,7 +282,7 @@ make_datetounixtimestamp_fct() {
             return {};
         }
         auto from_simple_date = get_castas_fctn(timestamp_type, simple_date_type);
-        return time_point_to_long(from_simple_date(simple_date_obj));
+        return {long_type->decompose(from_simple_date(simple_date_obj))};
     });
 }
 

cql3/multi_column_relation.hh

@@ -188,6 +188,11 @@ protected:
         throw exceptions::invalid_request_exception(format("{} cannot be used for Multi-column relations", get_operator()));
     }
 
+    virtual ::shared_ptr<restrictions::restriction> new_LIKE_restriction(
+            database& db, schema_ptr schema, ::shared_ptr<variable_specifications> bound_names) override {
+        throw exceptions::invalid_request_exception("LIKE cannot be used for Multi-column relations");
+    }
+
     virtual ::shared_ptr<relation> maybe_rename_identifier(const column_identifier::raw& from, column_identifier::raw to) override {
         auto new_entities = boost::copy_range<decltype(_entities)>(_entities | boost::adaptors::transformed([&] (auto&& entity) {
             return *entity == from ? ::make_shared<column_identifier::raw>(to) : entity;

cql3/operation.cc

@@ -65,7 +65,7 @@ operation::set_element::prepare(database& db, const sstring& keyspace, const col
         throw invalid_request_exception(format("Invalid operation ({}) for frozen collection column {}", to_string(receiver), receiver.name()));
     }
 
-    if (&rtype->_kind == &collection_type_impl::kind::list) {
+    if (rtype->get_kind() == abstract_type::kind::list) {
         auto&& lval = _value->prepare(db, keyspace, lists::value_spec_of(receiver.column_specification));
         if (_by_uuid) {
             auto&& idx = _selector->prepare(db, keyspace, lists::uuid_index_spec_of(receiver.column_specification));
@@ -74,9 +74,9 @@ operation::set_element::prepare(database& db, const sstring& keyspace, const col
             auto&& idx = _selector->prepare(db, keyspace, lists::index_spec_of(receiver.column_specification));
             return make_shared<lists::setter_by_index>(receiver, idx, lval);
         }
-    } else if (&rtype->_kind == &collection_type_impl::kind::set) {
+    } else if (rtype->get_kind() == abstract_type::kind::set) {
         throw invalid_request_exception(format("Invalid operation ({}) for set column {}", to_string(receiver), receiver.name()));
-    } else if (&rtype->_kind == &collection_type_impl::kind::map) {
+    } else if (rtype->get_kind() == abstract_type::kind::map) {
         auto key = _selector->prepare(db, keyspace, maps::key_spec_of(*receiver.column_specification));
         auto mval = _value->prepare(db, keyspace, maps::value_spec_of(*receiver.column_specification));
         return make_shared<maps::setter_by_key>(receiver, key, mval);
@@ -110,11 +110,11 @@ operation::addition::prepare(database& db, const sstring& keyspace, const column
         throw exceptions::invalid_request_exception(format("Invalid operation ({}) for frozen collection column {}", to_string(receiver), receiver.name()));
     }
 
-    if (&ctype->_kind == &collection_type_impl::kind::list) {
+    if (ctype->get_kind() == abstract_type::kind::list) {
         return make_shared<lists::appender>(receiver, v);
-    } else if (&ctype->_kind == &collection_type_impl::kind::set) {
+    } else if (ctype->get_kind() == abstract_type::kind::set) {
         return make_shared<sets::adder>(receiver, v);
-    } else if (&ctype->_kind == &collection_type_impl::kind::map) {
+    } else if (ctype->get_kind() == abstract_type::kind::map) {
         return make_shared<maps::putter>(receiver, v);
     } else {
         abort();
@@ -146,11 +146,11 @@ operation::subtraction::prepare(database& db, const sstring& keyspace, const col
                 format("Invalid operation ({}) for frozen collection column {}", to_string(receiver), receiver.name()));
     }
 
-    if (&ctype->_kind == &collection_type_impl::kind::list) {
+    if (ctype->get_kind() == abstract_type::kind::list) {
         return make_shared<lists::discarder>(receiver, _value->prepare(db, keyspace, receiver.column_specification));
-    } else if (&ctype->_kind == &collection_type_impl::kind::set) {
+    } else if (ctype->get_kind() == abstract_type::kind::set) {
         return make_shared<sets::discarder>(receiver, _value->prepare(db, keyspace, receiver.column_specification));
-    } else if (&ctype->_kind == &collection_type_impl::kind::map) {
+    } else if (ctype->get_kind() == abstract_type::kind::map) {
         auto&& mtype = dynamic_pointer_cast<const map_type_impl>(ctype);
         // The value for a map subtraction is actually a set
         auto&& vr = make_shared<column_specification>(
@@ -204,12 +204,12 @@ operation::set_value::prepare(database& db, const sstring& keyspace, const colum
         return ::make_shared<constants::setter>(receiver, v);
     }
 
-    auto& k = static_pointer_cast<const collection_type_impl>(receiver.type)->_kind;
-    if (&k == &collection_type_impl::kind::list) {
+    auto k = static_pointer_cast<const collection_type_impl>(receiver.type)->get_kind();
+    if (k == abstract_type::kind::list) {
         return make_shared<lists::setter>(receiver, v);
-    } else if (&k == &collection_type_impl::kind::set) {
+    } else if (k == abstract_type::kind::set) {
         return make_shared<sets::setter>(receiver, v);
-    } else if (&k == &collection_type_impl::kind::map) {
+    } else if (k == abstract_type::kind::map) {
         return make_shared<maps::setter>(receiver, v);
     } else {
         abort();
@@ -308,13 +308,13 @@ operation::element_deletion::prepare(database& db, const sstring& keyspace, cons
         throw exceptions::invalid_request_exception(format("Invalid deletion operation for frozen collection column {}", receiver.name()));
     }
     auto ctype = static_pointer_cast<const collection_type_impl>(receiver.type);
-    if (&ctype->_kind == &collection_type_impl::kind::list) {
+    if (ctype->get_kind() == abstract_type::kind::list) {
         auto&& idx = _element->prepare(db, keyspace, lists::index_spec_of(receiver.column_specification));
         return make_shared<lists::discarder_by_index>(receiver, std::move(idx));
-    } else if (&ctype->_kind == &collection_type_impl::kind::set) {
+    } else if (ctype->get_kind() == abstract_type::kind::set) {
         auto&& elt = _element->prepare(db, keyspace, sets::value_spec_of(receiver.column_specification));
         return make_shared<sets::element_discarder>(receiver, std::move(elt));
-    } else if (&ctype->_kind == &collection_type_impl::kind::map) {
+    } else if (ctype->get_kind() == abstract_type::kind::map) {
         auto&& key = _element->prepare(db, keyspace, maps::key_spec_of(*receiver.column_specification));
         return make_shared<maps::discarder_by_key>(receiver, std::move(key));
     }

cql3/operator.cc

@@ -53,5 +53,6 @@ const operator_type operator_type::CONTAINS(5, operator_type::CONTAINS, "CONTAIN
 const operator_type operator_type::CONTAINS_KEY(6, operator_type::CONTAINS_KEY, "CONTAINS_KEY");
 const operator_type operator_type::NEQ(8, operator_type::NEQ, "!=");
 const operator_type operator_type::IS_NOT(9, operator_type::IS_NOT, "IS NOT");
+const operator_type operator_type::LIKE(10, operator_type::LIKE, "LIKE");
 
 }

cql3/operator.hh

@@ -60,6 +60,7 @@ public:
     static const operator_type CONTAINS_KEY;
     static const operator_type NEQ;
     static const operator_type IS_NOT;
+    static const operator_type LIKE;
 private:
     int32_t _b;
     const operator_type& _reverse;

cql3/query_processor.cc

@@ -69,7 +69,7 @@ const std::chrono::minutes prepared_statements_cache::entry_expiry = std::chrono
 class query_processor::internal_state {
     service::query_state _qs;
 public:
-    internal_state() : _qs(service::client_state{service::client_state::internal_tag()}) {
+    internal_state() : _qs(service::client_state{service::client_state::internal_tag()}, empty_service_permit()) {
     }
     operator service::query_state&() {
         return _qs;

cql3/relation.hh

@@ -160,6 +160,8 @@ public:
             // This case is not supposed to happen: statement_restrictions
             // constructor does not call this function for views' IS_NOT.
             throw exceptions::invalid_request_exception(format("Unsupported \"IS NOT\" relation: {}", to_string()));
+        } else if (_relation_type == operator_type::LIKE) {
+            return new_LIKE_restriction(db, schema, bound_names);
         } else {
             throw exceptions::invalid_request_exception(format("Unsupported \"!=\" relation: {}", to_string()));
         }
@@ -220,6 +222,12 @@ public:
     virtual ::shared_ptr<restrictions::restriction> new_contains_restriction(database& db, schema_ptr schema,
         ::shared_ptr<variable_specifications> bound_names, bool isKey) = 0;
 
+    /**
+     * Creates a new LIKE restriction instance.
+     */
+    virtual ::shared_ptr<restrictions::restriction> new_LIKE_restriction(database& db, schema_ptr schema,
+        ::shared_ptr<variable_specifications> bound_names) = 0;
+
     /**
      * Renames an identifier in this Relation, if applicable.
      * @param from the old identifier

cql3/restrictions/abstract_restriction.hh

@@ -1,160 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one
- * or more contributor license agreements.  See the NOTICE file
- * distributed with this work for additional information
- * regarding copyright ownership.  The ASF licenses this file
- * to you under the Apache License, Version 2.0 (the
- * "License"); you may not use this file except in compliance
- * with the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-/*
- * Copyright (C) 2015 ScyllaDB
- *
- * Modified by 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 General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <vector>
-
-#include <seastar/core/shared_ptr.hh>
-#include <seastar/core/sstring.hh>
-#include "cql3/restrictions/restriction.hh"
-#include "cql3/term.hh"
-#include "types.hh"
-
-namespace cql3 {
-
-namespace restrictions {
-
-/**
- * Base class for <code>Restriction</code>s
- */
-class abstract_restriction : public restriction {
-public:
-    virtual bool is_on_token() const override {
-        return false;
-    }
-
-    virtual bool is_multi_column() const override {
-        return false;
-    }
-
-    virtual bool is_slice() const override {
-        return false;
-    }
-
-    virtual bool is_EQ() const override {
-        return false;
-    }
-
-    virtual bool is_IN() const override {
-        return false;
-    }
-
-    virtual bool is_contains() const override {
-        return false;
-    }
-
-    virtual bool has_bound(statements::bound b) const override {
-        return true;
-    }
-
-    virtual std::vector<bytes_opt> bounds(statements::bound b, const query_options& options) const override {
-        return values(options);
-    }
-
-    virtual bool is_inclusive(statements::bound b) const override {
-        return true;
-    }
-
-    /**
-     * Whether the specified row satisfied this restriction.
-     * Assumes the row is live, but not all cells. If a cell
-     * isn't live and there's a restriction on its column,
-     * then the function returns false.
-     *
-     * @param schema the schema the row belongs to
-     * @param key the partition key
-     * @param ckey the clustering key
-     * @param cells the remaining row columns
-     * @return the restriction resulting of the merge
-     * @throws InvalidRequestException if the restrictions cannot be merged
-     */
-    virtual bool is_satisfied_by(const schema& schema,
-                                 const partition_key& key,
-                                 const clustering_key_prefix& ckey,
-                                 const row& cells,
-                                 const query_options& options,
-                                 gc_clock::time_point now) const = 0;
-
-protected:
-#if 0
-    protected static ByteBuffer validateIndexedValue(ColumnSpecification columnSpec,
-                                                     ByteBuffer value)
-                                                     throws InvalidRequestException
-    {
-        checkNotNull(value, "Unsupported null value for indexed column %s", columnSpec.name);
-        checkFalse(value.remaining() > 0xFFFF, "Index expression values may not be larger than 64K");
-        return value;
-    }
-#endif
-    /**
-     * Checks if the specified term is using the specified function.
-     *
-     * @param term the term to check
-     * @param ks_name the function keyspace name
-     * @param function_name the function name
-     * @return <code>true</code> if the specified term is using the specified function, <code>false</code> otherwise.
-     */
-    static bool term_uses_function(::shared_ptr<term> term, const sstring& ks_name, const sstring& function_name) {
-        return bool(term) && term->uses_function(ks_name, function_name);
-    }
-
-    /**
-     * Checks if one of the specified term is using the specified function.
-     *
-     * @param terms the terms to check
-     * @param ks_name the function keyspace name
-     * @param function_name the function name
-     * @return <code>true</code> if one of the specified term is using the specified function, <code>false</code> otherwise.
-     */
-    static bool term_uses_function(const std::vector<::shared_ptr<term>>& terms, const sstring& ks_name, const sstring& function_name) {
-        for (auto&& value : terms) {
-            if (term_uses_function(value, ks_name, function_name)) {
-                return true;
-            }
-        }
-        return false;
-    }
-};
-
-}
-
-}

cql3/restrictions/multi_column_restriction.hh

@@ -61,17 +61,14 @@ protected:
     schema_ptr _schema;
     std::vector<const column_definition*> _column_defs;
 public:
-    multi_column_restriction(schema_ptr schema, std::vector<const column_definition*>&& defs)
-        : _schema(schema)
+    multi_column_restriction(op op, schema_ptr schema, std::vector<const column_definition*>&& defs)
+        : clustering_key_restrictions(op, target::MULTIPLE_COLUMNS)
+        , _schema(schema)
         , _column_defs(std::move(defs))
     {
         update_asc_desc_existence();
     }
 
-    virtual bool is_multi_column() const override {
-        return true;
-    }
-
     virtual std::vector<const column_definition*> get_column_defs() const override {
         return _column_defs;
     }
@@ -211,12 +208,12 @@ private:
     ::shared_ptr<term> _value;
 public:
     EQ(schema_ptr schema, std::vector<const column_definition*> defs, ::shared_ptr<term> value)
-        : multi_column_restriction(schema, std::move(defs))
+        : multi_column_restriction(op::EQ, schema, std::move(defs))
         , _value(std::move(value))
     { }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return abstract_restriction::term_uses_function(_value, ks_name, function_name);
+        return restriction::term_uses_function(_value, ks_name, function_name);
     }
 
     virtual bool is_supported_by(const secondary_index::index& index) const override {
@@ -285,7 +282,9 @@ public:
 
 class multi_column_restriction::IN : public multi_column_restriction {
 public:
-    using multi_column_restriction::multi_column_restriction;
+    IN(schema_ptr schema, std::vector<const column_definition*> defs)
+        :  multi_column_restriction(op::IN, schema, std::move(defs))
+    { }
 
     virtual bool is_supported_by(const secondary_index::index& index) const override {
         for (auto* cdef : _column_defs) {
@@ -296,10 +295,6 @@ public:
         return false;
     }
 
-    virtual bool is_IN() const override {
-        return true;
-    }
-
     virtual std::vector<clustering_key_prefix> values_as_keys(const query_options& options) const override {
         auto split_in_values = split_values(options);
         std::vector<clustering_key_prefix> keys;
@@ -382,7 +377,7 @@ public:
     { }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override  {
-        return abstract_restriction::term_uses_function(_values, ks_name, function_name);
+        return restriction::term_uses_function(_values, ks_name, function_name);
     }
 
     virtual sstring to_string() const override  {
@@ -436,7 +431,7 @@ private:
     term_slice _slice;
 
     slice(schema_ptr schema, std::vector<const column_definition*> defs, term_slice slice)
-        : multi_column_restriction(schema, std::move(defs))
+        : multi_column_restriction(op::SLICE, schema, std::move(defs))
         , _slice(slice)
     { }
 public:
@@ -453,10 +448,6 @@ public:
         return false;
     }
 
-    virtual bool is_slice() const override {
-        return true;
-    }
-
     virtual std::vector<clustering_key_prefix> values_as_keys(const query_options&) const override {
         throw exceptions::unsupported_operation_exception();
     }
@@ -503,8 +494,8 @@ public:
     }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return (_slice.has_bound(statements::bound::START) && abstract_restriction::term_uses_function(_slice.bound(statements::bound::START), ks_name, function_name))
-                || (_slice.has_bound(statements::bound::END) && abstract_restriction::term_uses_function(_slice.bound(statements::bound::END), ks_name, function_name));
+        return (_slice.has_bound(statements::bound::START) && restriction::term_uses_function(_slice.bound(statements::bound::START), ks_name, function_name))
+                || (_slice.has_bound(statements::bound::END) && restriction::term_uses_function(_slice.bound(statements::bound::END), ks_name, function_name));
     }
 
     virtual bool is_inclusive(statements::bound b) const override {

cql3/restrictions/primary_key_restrictions.hh

@@ -48,7 +48,7 @@
 #include "cql3/statements/bound.hh"
 #include "cql3/restrictions/restrictions.hh"
 #include "cql3/restrictions/restriction.hh"
-#include "cql3/restrictions/abstract_restriction.hh"
+#include "cql3/restrictions/restriction.hh"
 #include "types.hh"
 #include "query-request.hh"
 #include <seastar/core/shared_ptr.hh>
@@ -63,10 +63,13 @@ namespace restrictions {
  * implementations of methods).
  */
 
-class partition_key_restrictions: public abstract_restriction, public restrictions, public enable_shared_from_this<partition_key_restrictions> {
+class partition_key_restrictions: public restriction, public restrictions, public enable_shared_from_this<partition_key_restrictions> {
 public:
     using bounds_range_type = dht::partition_range;
 
+    partition_key_restrictions() = default;
+    partition_key_restrictions(op op, target target) : restriction(op, target) {}
+
     virtual ::shared_ptr<partition_key_restrictions> merge_to(schema_ptr, ::shared_ptr<restriction> restriction) {
         merge_with(restriction);
         return this->shared_from_this();
@@ -91,7 +94,8 @@ public:
     }
 
     virtual bool needs_filtering(const schema& schema) const {
-        return !empty() && !is_on_token() && (has_unrestricted_components(schema) || is_contains() || is_slice());
+        return !empty() && !is_on_token() &&
+                (has_unrestricted_components(schema) || is_contains() || is_slice() || is_LIKE());
     }
 
     // NOTICE(sarna): This function is useless for partition key restrictions,
@@ -113,10 +117,13 @@ public:
     }
 };
 
-class clustering_key_restrictions : public abstract_restriction, public restrictions, public enable_shared_from_this<clustering_key_restrictions> {
+class clustering_key_restrictions : public restriction, public restrictions, public enable_shared_from_this<clustering_key_restrictions> {
 public:
     using bounds_range_type = query::clustering_range;
 
+    clustering_key_restrictions() = default;
+    clustering_key_restrictions(op op, target target) : restriction(op, target) {}
+
     virtual ::shared_ptr<clustering_key_restrictions> merge_to(schema_ptr, ::shared_ptr<restriction> restriction) {
         merge_with(restriction);
         return this->shared_from_this();

cql3/restrictions/restriction.hh

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2015 ScyllaDB
+ * Copyright (C) 2019 ScyllaDB
  *
  * Modified by ScyllaDB
  */
@@ -43,9 +43,12 @@
 
 #include <vector>
 
-#include "index/secondary_index_manager.hh"
+#include <seastar/core/shared_ptr.hh>
+#include <seastar/core/sstring.hh>
 #include "cql3/query_options.hh"
+#include "cql3/term.hh"
 #include "cql3/statements/bound.hh"
+#include "index/secondary_index_manager.hh"
 #include "types.hh"
 
 namespace cql3 {
@@ -56,51 +59,80 @@ struct allow_local_index_tag {};
 using allow_local_index = bool_class<allow_local_index_tag>;
 
 /**
- * A restriction/clause on a column.
- * The goal of this class being to group all conditions for a column in a SELECT.
+ * Base class for <code>Restriction</code>s
  */
 class restriction {
+public:
+    enum class op {
+        EQ, SLICE, IN, CONTAINS, LIKE
+    };
+    enum class target {
+        SINGLE_COLUMN, MULTIPLE_COLUMNS, TOKEN
+    };
+protected:
+    using op_enum = super_enum<restriction::op, restriction::op::EQ, restriction::op::SLICE, restriction::op::IN, restriction::op::CONTAINS, restriction::op::LIKE>;
+    enum_set<op_enum> _ops;
+    target _target = target::SINGLE_COLUMN;
 public:
     virtual ~restriction() {}
-    virtual bool is_on_token() const = 0;
-    virtual bool is_slice() const = 0;
-    virtual bool is_EQ() const = 0;
-    virtual bool is_IN() const = 0;
-    virtual bool is_contains() const = 0;
-    virtual bool is_multi_column() const = 0;
 
-    virtual std::vector<bytes_opt> values(const query_options& options) const = 0;
-
-    virtual bytes_opt value(const query_options& options) const {
-        auto vec = values(options);
-        assert(vec.size() == 1);
-        return std::move(vec[0]);
+    restriction() = default;
+    explicit restriction(op op) : _target(target::SINGLE_COLUMN) {
+        _ops.set(op);
     }
 
-    /**
-     * Returns <code>true</code> if one of the restrictions use the specified function.
-     *
-     * @param ks_name the keyspace name
-     * @param function_name the function name
-     * @return <code>true</code> if one of the restrictions use the specified function, <code>false</code> otherwise.
-     */
-    virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const = 0;
+    restriction(op op, target target) : _target(target) {
+        _ops.set(op);
+    }
+
+    bool is_on_token() const {
+        return _target == target::TOKEN;
+    }
+
+    bool is_multi_column() const {
+        return _target == target::MULTIPLE_COLUMNS;
+    }
+
+    bool is_slice() const {
+        return _ops.contains(op::SLICE);
+    }
+
+    bool is_EQ() const {
+        return _ops.contains(op::EQ);
+    }
+
+    bool is_IN() const {
+        return _ops.contains(op::IN);
+    }
+
+    bool is_contains() const {
+        return _ops.contains(op::CONTAINS);
+    }
+
+    bool is_LIKE() const {
+        return _ops.contains(op::LIKE);
+    }
+
+    const enum_set<op_enum>& get_ops() const {
+        return _ops;
+    }
 
     /**
      * Checks if the specified bound is set or not.
      * @param b the bound type
      * @return <code>true</code> if the specified bound is set, <code>false</code> otherwise
      */
-    virtual bool has_bound(statements::bound b) const = 0;
+    virtual bool has_bound(statements::bound b) const {
+        return true;
+    }
 
-    virtual std::vector<bytes_opt> bounds(statements::bound b, const query_options& options) const = 0;
+    virtual std::vector<bytes_opt> bounds(statements::bound b, const query_options& options) const {
+        return values(options);
+    }
 
-    /**
-     * Checks if the specified bound is inclusive or not.
-     * @param b the bound type
-     * @return <code>true</code> if the specified bound is inclusive, <code>false</code> otherwise
-     */
-    virtual bool is_inclusive(statements::bound b) const = 0;
+    virtual bool is_inclusive(statements::bound b) const {
+        return true;
+    }
 
     /**
      * Merges this restriction with the specified one.
@@ -119,21 +151,74 @@ public:
      */
     virtual bool has_supporting_index(const secondary_index::secondary_index_manager& index_manager, allow_local_index allow_local) const = 0;
 
-#if 0
-    /**
-     * Adds to the specified list the <code>IndexExpression</code>s corresponding to this <code>Restriction</code>.
-     *
-     * @param expressions the list to add the <code>IndexExpression</code>s to
-     * @param options the query options
-     * @throws InvalidRequestException if this <code>Restriction</code> cannot be converted into 
-     * <code>IndexExpression</code>s
-     */
-    public void addIndexExpressionTo(List<IndexExpression> expressions,
-                                     QueryOptions options)
-                                     throws InvalidRequestException;
-#endif
-
     virtual sstring to_string() const = 0;
+
+    /**
+     * Returns <code>true</code> if one of the restrictions use the specified function.
+     *
+     * @param ks_name the keyspace name
+     * @param function_name the function name
+     * @return <code>true</code> if one of the restrictions use the specified function, <code>false</code> otherwise.
+     */
+    virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const = 0;
+
+    virtual std::vector<bytes_opt> values(const query_options& options) const = 0;
+
+    virtual bytes_opt value(const query_options& options) const {
+        auto vec = values(options);
+        assert(vec.size() == 1);
+        return std::move(vec[0]);
+    }
+
+    /**
+     * Whether the specified row satisfied this restriction.
+     * Assumes the row is live, but not all cells. If a cell
+     * isn't live and there's a restriction on its column,
+     * then the function returns false.
+     *
+     * @param schema the schema the row belongs to
+     * @param key the partition key
+     * @param ckey the clustering key
+     * @param cells the remaining row columns
+     * @return the restriction resulting of the merge
+     * @throws InvalidRequestException if the restrictions cannot be merged
+     */
+    virtual bool is_satisfied_by(const schema& schema,
+                                 const partition_key& key,
+                                 const clustering_key_prefix& ckey,
+                                 const row& cells,
+                                 const query_options& options,
+                                 gc_clock::time_point now) const = 0;
+
+protected:
+    /**
+     * Checks if the specified term is using the specified function.
+     *
+     * @param term the term to check
+     * @param ks_name the function keyspace name
+     * @param function_name the function name
+     * @return <code>true</code> if the specified term is using the specified function, <code>false</code> otherwise.
+     */
+    static bool term_uses_function(::shared_ptr<term> term, const sstring& ks_name, const sstring& function_name) {
+        return bool(term) && term->uses_function(ks_name, function_name);
+    }
+
+    /**
+     * Checks if one of the specified term is using the specified function.
+     *
+     * @param terms the terms to check
+     * @param ks_name the function keyspace name
+     * @param function_name the function name
+     * @return <code>true</code> if one of the specified term is using the specified function, <code>false</code> otherwise.
+     */
+    static bool term_uses_function(const std::vector<::shared_ptr<term>>& terms, const sstring& ks_name, const sstring& function_name) {
+        for (auto&& value : terms) {
+            if (term_uses_function(value, ks_name, function_name)) {
+                return true;
+            }
+        }
+        return false;
+    }
 };
 
 }

cql3/restrictions/restrictions.hh

@@ -58,6 +58,9 @@ namespace restrictions {
  * Sets of restrictions
  */
 class restrictions {
+protected:
+    using op_enum = super_enum<restriction::op, restriction::op::EQ, restriction::op::SLICE, restriction::op::IN, restriction::op::CONTAINS, restriction::op::LIKE>;
+    enum_set<op_enum> _ops;
 public:
     virtual ~restrictions() {}
 

cql3/restrictions/single_column_primary_key_restrictions.hh

@@ -69,17 +69,11 @@ private:
     schema_ptr _schema;
     bool _allow_filtering;
     ::shared_ptr<single_column_restrictions> _restrictions;
-    bool _slice;
-    bool _contains;
-    bool _in;
 public:
     single_column_primary_key_restrictions(schema_ptr schema, bool allow_filtering)
         : _schema(schema)
         , _allow_filtering(allow_filtering)
         , _restrictions(::make_shared<single_column_restrictions>(schema))
-        , _slice(false)
-        , _contains(false)
-        , _in(false)
     { }
 
     // Convert another primary key restrictions type into this type, possibly using different schema
@@ -88,9 +82,6 @@ public:
         : _schema(schema)
         , _allow_filtering(other._allow_filtering)
         , _restrictions(::make_shared<single_column_restrictions>(schema))
-        , _slice(other._slice)
-        , _contains(other._contains)
-        , _in(other._in)
     {
         for (const auto& entry : other._restrictions->restrictions()) {
             const column_definition* other_cdef = entry.first;
@@ -103,26 +94,6 @@ public:
         }
     }
 
-    virtual bool is_on_token() const override {
-        return false;
-    }
-
-    virtual bool is_multi_column() const override {
-        return false;
-    }
-
-    virtual bool is_slice() const override {
-        return _slice;
-    }
-
-    virtual bool is_contains() const override {
-        return _contains;
-    }
-
-    virtual bool is_IN() const override {
-        return _in;
-    }
-
     virtual bool is_all_eq() const override {
         return _restrictions->is_all_eq();
     }
@@ -144,7 +115,7 @@ public:
             auto last_column = *_restrictions->last_column();
             auto new_column = restriction->get_column_def();
 
-            if (_slice && _schema->position(new_column) > _schema->position(last_column)) {
+            if (this->is_slice() && _schema->position(new_column) > _schema->position(last_column)) {
                 throw exceptions::invalid_request_exception(format("Clustering column \"{}\" cannot be restricted (preceding column \"{}\" is restricted by a non-EQ relation)",
                     new_column.name_as_text(), last_column.name_as_text()));
             }
@@ -156,10 +127,7 @@ public:
                 }
             }
         }
-
-        _slice |= restriction->is_slice();
-        _in |= restriction->is_IN();
-        _contains |= restriction->is_contains();
+        restriction::_ops.add(restriction->get_ops());
         _restrictions->add_restriction(restriction);
     }
 
@@ -264,7 +232,7 @@ private:
             const column_definition* def = e.first;
             auto&& r = e.second;
 
-            if (vec_of_values.size() != _schema->position(*def) || r->is_contains()) {
+            if (vec_of_values.size() != _schema->position(*def) || r->is_contains() || r->is_LIKE()) {
                 // The prefixes built so far are the longest we can build,
                 // the rest of the constraints will have to be applied using filtering.
                 break;
@@ -288,7 +256,7 @@ private:
                     if (def->type->is_reversed()) {
                         ranges.back().reverse();
                     }
-                    return std::move(ranges);
+                    return ranges;
                 }
 
                 ranges.reserve(cartesian_product_size(vec_of_values));
@@ -317,7 +285,7 @@ private:
                     }
                 }
 
-                return std::move(ranges);
+                return ranges;
             }
 
             auto values = r->values(options);
@@ -337,7 +305,7 @@ private:
             ranges.emplace_back(range_type::make_singular(ValueType::from_optional_exploded(*_schema, std::move(prefix))));
         }
 
-        return std::move(ranges);
+        return ranges;
     }
 
 public:

cql3/restrictions/single_column_restriction.hh

@@ -41,7 +41,7 @@
 
 #pragma once
 
-#include "cql3/restrictions/abstract_restriction.hh"
+#include "cql3/restrictions/restriction.hh"
 #include "cql3/restrictions/term_slice.hh"
 #include "cql3/term.hh"
 #include "cql3/abstract_marker.hh"
@@ -56,15 +56,16 @@ namespace cql3 {
 
 namespace restrictions {
 
-class single_column_restriction : public abstract_restriction {
+class single_column_restriction : public restriction {
 protected:
     /**
      * The definition of the column to which apply the restriction.
      */
     const column_definition& _column_def;
 public:
-    single_column_restriction(const column_definition& column_def)
-        : _column_def(column_def)
+    single_column_restriction(op op, const column_definition& column_def)
+        : restriction(op)
+        , _column_def(column_def)
     { }
 
     const column_definition& get_column_def() const {
@@ -96,7 +97,7 @@ public:
     }
 
     virtual bool is_supported_by(const secondary_index::index& index) const = 0;
-    using abstract_restriction::is_satisfied_by;
+    using restriction::is_satisfied_by;
     virtual bool is_satisfied_by(bytes_view data, const query_options& options) const = 0;
     virtual ::shared_ptr<single_column_restriction> apply_to(const column_definition& cdef) = 0;
 #if 0
@@ -114,7 +115,7 @@ public:
     class IN;
     class IN_with_values;
     class IN_with_marker;
-
+    class LIKE;
     class slice;
     class contains;
 
@@ -131,22 +132,18 @@ private:
     ::shared_ptr<term> _value;
 public:
     EQ(const column_definition& column_def, ::shared_ptr<term> value)
-        : single_column_restriction(column_def)
+        : single_column_restriction(op::EQ, column_def)
         , _value(std::move(value))
     { }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return abstract_restriction::term_uses_function(_value, ks_name, function_name);
+        return restriction::term_uses_function(_value, ks_name, function_name);
     }
 
     virtual bool is_supported_by(const secondary_index::index& index) const override {
         return index.supports_expression(_column_def, cql3::operator_type::EQ);
     }
 
-    virtual bool is_EQ() const override {
-        return true;
-    }
-
     virtual std::vector<bytes_opt> values(const query_options& options) const override {
         std::vector<bytes_opt> v;
         v.push_back(to_bytes_opt(_value->bind_and_get(options)));
@@ -188,13 +185,9 @@ public:
 class single_column_restriction::IN : public single_column_restriction {
 public:
     IN(const column_definition& column_def)
-        : single_column_restriction(column_def)
+        : single_column_restriction(op::IN, column_def)
     { }
 
-    virtual bool is_IN() const override {
-        return true;
-    }
-
     virtual bool is_supported_by(const secondary_index::index& index) const override {
         return index.supports_expression(_column_def, cql3::operator_type::IN);
     }
@@ -241,7 +234,7 @@ public:
     { }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return abstract_restriction::term_uses_function(_values, ks_name, function_name);
+        return restriction::term_uses_function(_values, ks_name, function_name);
     }
 
     virtual std::vector<bytes_opt> values_raw(const query_options& options) const override {
@@ -295,28 +288,24 @@ private:
     term_slice _slice;
 public:
     slice(const column_definition& column_def, statements::bound bound, bool inclusive, ::shared_ptr<term> term)
-        : single_column_restriction(column_def)
+        : single_column_restriction(op::SLICE, column_def)
         , _slice(term_slice::new_instance(bound, inclusive, std::move(term)))
     { }
 
     slice(const column_definition& column_def, term_slice slice)
-        : single_column_restriction(column_def)
+        : single_column_restriction(op::SLICE, column_def)
         , _slice(slice)
     { }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return (_slice.has_bound(statements::bound::START) && abstract_restriction::term_uses_function(_slice.bound(statements::bound::START), ks_name, function_name))
-                || (_slice.has_bound(statements::bound::END) && abstract_restriction::term_uses_function(_slice.bound(statements::bound::END), ks_name, function_name));
+        return (_slice.has_bound(statements::bound::START) && restriction::term_uses_function(_slice.bound(statements::bound::START), ks_name, function_name))
+                || (_slice.has_bound(statements::bound::END) && restriction::term_uses_function(_slice.bound(statements::bound::END), ks_name, function_name));
     }
 
     virtual bool is_supported_by(const secondary_index::index& index) const override {
         return _slice.is_supported_by(_column_def, index);
     }
 
-    virtual bool is_slice() const override {
-        return true;
-    }
-
     virtual std::vector<bytes_opt> values(const query_options& options) const override {
         throw exceptions::unsupported_operation_exception();
     }
@@ -392,6 +381,51 @@ public:
     }
 };
 
+class single_column_restriction::LIKE final : public single_column_restriction {
+private:
+    ::shared_ptr<term> _value;
+public:
+    LIKE(const column_definition& column_def, ::shared_ptr<term> value)
+        : single_column_restriction(op::LIKE, column_def)
+        , _value(value)
+    { }
+
+    virtual std::vector<bytes_opt> values(const query_options& options) const override {
+        std::vector<bytes_opt> v;
+        v.push_back(to_bytes_opt(_value->bind_and_get(options)));
+        return v;
+    }
+
+    virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
+        return false;
+    }
+
+    virtual bool is_supported_by(const secondary_index::index& index) const {
+        return index.supports_expression(_column_def, cql3::operator_type::LIKE);
+    }
+
+    virtual sstring to_string() const override {
+        return format("LIKE({})", _value->to_string());
+    }
+
+    virtual void merge_with(::shared_ptr<restriction> other) {
+        throw exceptions::invalid_request_exception(
+            format("{} cannot be restricted by more than one relation if it includes a LIKE",
+                   _column_def.name_as_text()));
+    }
+
+    virtual bool is_satisfied_by(const schema& schema,
+                                 const partition_key& key,
+                                 const clustering_key_prefix& ckey,
+                                 const row& cells,
+                                 const query_options& options,
+                                 gc_clock::time_point now) const override;
+    virtual bool is_satisfied_by(bytes_view data, const query_options& options) const override;
+    virtual ::shared_ptr<single_column_restriction> apply_to(const column_definition& cdef) override {
+        return ::make_shared<LIKE>(cdef, _value);
+    }
+};
+
 // This holds CONTAINS, CONTAINS_KEY, and map[key] = value restrictions because we might want to have any combination of them.
 class single_column_restriction::contains final : public single_column_restriction {
 private:
@@ -401,7 +435,7 @@ private:
     std::vector<::shared_ptr<term>> _entry_values;
 public:
     contains(const column_definition& column_def, ::shared_ptr<term> t, bool is_key)
-            : single_column_restriction(column_def) {
+            : single_column_restriction(op::CONTAINS, column_def) {
         if (is_key) {
             _keys.emplace_back(std::move(t));
         } else {
@@ -410,7 +444,8 @@ public:
     }
 
     contains(const column_definition& column_def, ::shared_ptr<term> map_key, ::shared_ptr<term> map_value)
-            : single_column_restriction(column_def) {
+            : single_column_restriction(op::CONTAINS, column_def)
+        {
         _entry_keys.emplace_back(std::move(map_key));
         _entry_values.emplace_back(std::move(map_value));
     }
@@ -419,10 +454,6 @@ public:
         return bind_and_get(_values, options);
     }
 
-    virtual bool is_contains() const override {
-        return true;
-    }
-
     virtual void merge_with(::shared_ptr<restriction> other_restriction) override {
         if (!other_restriction->is_contains()) {
             throw exceptions::invalid_request_exception(format("Collection column {} can only be restricted by CONTAINS, CONTAINS KEY, or map-entry equality",
@@ -481,10 +512,10 @@ public:
     }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return abstract_restriction::term_uses_function(_values, ks_name, function_name)
-            || abstract_restriction::term_uses_function(_keys, ks_name, function_name)
-            || abstract_restriction::term_uses_function(_entry_keys, ks_name, function_name)
-            || abstract_restriction::term_uses_function(_entry_values, ks_name, function_name);
+        return restriction::term_uses_function(_values, ks_name, function_name)
+            || restriction::term_uses_function(_keys, ks_name, function_name)
+            || restriction::term_uses_function(_entry_keys, ks_name, function_name)
+            || restriction::term_uses_function(_entry_values, ks_name, function_name);
     }
 
     virtual sstring to_string() const override {

cql3/restrictions/statement_restrictions.cc

@@ -35,6 +35,7 @@
 #include "types/map.hh"
 #include "types/list.hh"
 #include "types/set.hh"
+#include "utils/like_matcher.hh"
 
 namespace cql3 {
 namespace restrictions {
@@ -380,45 +381,28 @@ std::vector<const column_definition*> statement_restrictions::get_column_defs_fo
     if (need_filtering()) {
         auto& sim = db.find_column_family(_schema).get_index_manager();
         auto [opt_idx, _] = find_idx(sim);
-        auto column_uses_indexing = [&opt_idx] (const column_definition* cdef, ::shared_ptr<single_column_restriction> restr) {
-            return opt_idx && restr && restr->is_supported_by(*opt_idx);
+        auto column_uses_indexing = [&opt_idx] (const column_definition* cdef) {
+            return opt_idx && opt_idx->depends_on(*cdef);
         };
-        auto single_pk_restrs = dynamic_pointer_cast<single_column_partition_key_restrictions>(_partition_key_restrictions);
         if (_partition_key_restrictions->needs_filtering(*_schema)) {
             for (auto&& cdef : _partition_key_restrictions->get_column_defs()) {
-                ::shared_ptr<single_column_restriction> restr;
-                if (single_pk_restrs) {
-                    auto it = single_pk_restrs->restrictions().find(cdef);
-                    if (it != single_pk_restrs->restrictions().end()) {
-                        restr = dynamic_pointer_cast<single_column_restriction>(it->second);
-                    }
-                }
-                if (!column_uses_indexing(cdef, restr)) {
+                if (!column_uses_indexing(cdef)) {
                     column_defs_for_filtering.emplace_back(cdef);
                 }
             }
         }
-        auto single_ck_restrs = dynamic_pointer_cast<single_column_clustering_key_restrictions>(_clustering_columns_restrictions);
         const bool pk_has_unrestricted_components = _partition_key_restrictions->has_unrestricted_components(*_schema);
         if (pk_has_unrestricted_components || _clustering_columns_restrictions->needs_filtering(*_schema)) {
             column_id first_filtering_id = pk_has_unrestricted_components ? 0 : _schema->clustering_key_columns().begin()->id +
                     _clustering_columns_restrictions->num_prefix_columns_that_need_not_be_filtered();
             for (auto&& cdef : _clustering_columns_restrictions->get_column_defs()) {
-                ::shared_ptr<single_column_restriction> restr;
-                if (single_pk_restrs) {
-                    auto it = single_ck_restrs->restrictions().find(cdef);
-                    if (it != single_ck_restrs->restrictions().end()) {
-                        restr = dynamic_pointer_cast<single_column_restriction>(it->second);
-                    }
-                }
-                if (cdef->id >= first_filtering_id && !column_uses_indexing(cdef, restr)) {
+                if (cdef->id >= first_filtering_id && !column_uses_indexing(cdef)) {
                     column_defs_for_filtering.emplace_back(cdef);
                 }
             }
         }
         for (auto&& cdef : _nonprimary_key_restrictions->get_column_defs()) {
-            auto restr = dynamic_pointer_cast<single_column_restriction>(_nonprimary_key_restrictions->get_restriction(*cdef));
-            if (!column_uses_indexing(cdef, restr)) {
+            if (!column_uses_indexing(cdef)) {
                 column_defs_for_filtering.emplace_back(cdef);
             }
         }
@@ -932,5 +916,30 @@ bool token_restriction::slice::is_satisfied_by(const schema& schema,
     return satisfied;
 }
 
+bool single_column_restriction::LIKE::is_satisfied_by(const schema& schema,
+        const partition_key& key,
+        const clustering_key_prefix& ckey,
+        const row& cells,
+        const query_options& options,
+        gc_clock::time_point now) const {
+    if (!_column_def.type->is_string()) {
+        throw exceptions::invalid_request_exception("LIKE is allowed only on string types");
+    }
+    auto cell_value = get_value(schema, key, ckey, cells, now);
+    return !cell_value ? false :
+            cell_value->with_linearized([&] (bytes_view data) {
+                 auto pattern = to_bytes_opt(_value->bind_and_get(options));
+                 return pattern ? like_matcher(*pattern)(data) : false;
+            });
+}
+
+bool single_column_restriction::LIKE::is_satisfied_by(bytes_view data, const query_options& options) const {
+    if (!_column_def.type->is_string()) {
+        throw exceptions::invalid_request_exception("LIKE is allowed only on string types");
+    }
+    auto pattern = to_bytes_opt(_value->bind_and_get(options));
+    return pattern ? like_matcher(*pattern)(data) : false;
+}
+
 }
 }

cql3/restrictions/statement_restrictions.hh

@@ -119,7 +119,7 @@ public:
         bool select_a_collection,
         bool for_view = false,
         bool allow_filtering = false);
-private:
+
     void add_restriction(::shared_ptr<restriction> restriction, bool for_view, bool allow_filtering);
     void add_single_column_restriction(::shared_ptr<single_column_restriction> restriction, bool for_view, bool allow_filtering);
 public:

cql3/restrictions/term_slice.hh

@@ -41,7 +41,7 @@
 
 #pragma once
 
-#include "cql3/restrictions/abstract_restriction.hh"
+#include "cql3/restrictions/restriction.hh"
 #include "cql3/term.hh"
 #include <seastar/core/shared_ptr.hh>
 #include "to_string.hh"

cql3/restrictions/token_restriction.hh

@@ -62,13 +62,10 @@ private:
      */
     std::vector<const column_definition *> _column_definitions;
 public:
-    token_restriction(std::vector<const column_definition *> c)
-            : _column_definitions(std::move(c)) {
+    token_restriction(op op, std::vector<const column_definition *> c)
+            : partition_key_restrictions(op, target::TOKEN), _column_definitions(std::move(c)) {
     }
 
-    bool is_on_token() const override {
-        return true;
-    }
     std::vector<const column_definition*> get_column_defs() const override {
         return _column_definitions;
     }
@@ -148,16 +145,12 @@ private:
     ::shared_ptr<term> _value;
 public:
     EQ(std::vector<const column_definition*> column_defs, ::shared_ptr<term> value)
-        : token_restriction(column_defs)
+        : token_restriction(op::EQ, column_defs)
         , _value(std::move(value))
     {}
 
-    bool is_EQ() const {
-        return true;
-    }
-
     bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
-        return abstract_restriction::term_uses_function(_value, ks_name, function_name);
+        return restriction::term_uses_function(_value, ks_name, function_name);
     }
 
     void merge_with(::shared_ptr<restriction>) override {
@@ -187,14 +180,9 @@ private:
     term_slice _slice;
 public:
     slice(std::vector<const column_definition*> column_defs, statements::bound bound, bool inclusive, ::shared_ptr<term> term)
-        : token_restriction(column_defs)
+        : token_restriction(op::SLICE, column_defs)
         , _slice(term_slice::new_instance(bound, inclusive, std::move(term)))
     {}
-
-    bool is_slice() const override {
-        return true;
-    }
-
     bool has_bound(statements::bound b) const override {
         return _slice.has_bound(b);
     }
@@ -210,11 +198,11 @@ public:
     bool uses_function(const sstring& ks_name,
             const sstring& function_name) const override {
         return (_slice.has_bound(statements::bound::START)
-                && abstract_restriction::term_uses_function(
+                && restriction::term_uses_function(
                         _slice.bound(statements::bound::START), ks_name,
                         function_name))
                 || (_slice.has_bound(statements::bound::END)
-                        && abstract_restriction::term_uses_function(
+                        && restriction::term_uses_function(
                                 _slice.bound(statements::bound::END),
                                 ks_name, function_name));
     }

cql3/selection/abstract_function_selector.hh

@@ -92,14 +92,6 @@ public:
             : abstract_function_selector(fun, std::move(arg_selectors))
             , _tfun(dynamic_pointer_cast<T>(fun)) {
     }
-
-    const functions::function_name& name() const {
-        return _tfun->name();
-    }
-
-    virtual sstring assignment_testable_source_context() const override {
-        return format("{}", this->name());
-    }
 };
 
 }

cql3/selection/aggregate_function_selector.hh

@@ -79,6 +79,11 @@ public:
                     dynamic_pointer_cast<functions::aggregate_function>(func), std::move(arg_selectors))
             , _aggregate(fun()->new_aggregate()) {
     }
+
+    virtual sstring assignment_testable_source_context() const override {
+        // FIXME:
+        return "FIXME";
+    }
 };
 
 }

cql3/selection/scalar_function_selector.hh

@@ -82,6 +82,12 @@ public:
             : abstract_function_selector_for<functions::scalar_function>(
                 dynamic_pointer_cast<functions::scalar_function>(std::move(fun)), std::move(arg_selectors)) {
     }
+
+    virtual sstring assignment_testable_source_context() const override {
+        // FIXME:
+        return "FIXME";
+    }
+
 };
 
 }

cql3/selection/selection.cc

@@ -39,8 +39,9 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <boost/range/adaptor/transformed.hpp>
-#include <boost/range/adaptor/filtered.hpp>
+#include <boost/range/adaptors.hpp>
+#include <boost/range/algorithm/equal.hpp>
+#include <boost/range/algorithm/transform.hpp>
 
 #include "cql3/selection/selection.hh"
 #include "cql3/selection/selector_factories.hh"
@@ -114,9 +115,11 @@ protected:
     class simple_selectors : public selectors {
     private:
         std::vector<bytes_opt> _current;
+        bool _first = true; ///< Whether the next row we receive is the first in its group.
     public:
         virtual void reset() override {
             _current.clear();
+            _first = true;
         }
 
         virtual std::vector<bytes_opt> get_output_row(cql_serialization_format sf) override {
@@ -124,7 +127,13 @@ protected:
         }
 
         virtual void add_input_row(cql_serialization_format sf, result_set_builder& rs) override {
-            _current = std::move(*rs.current);
+            // GROUP BY calls add_input_row() repeatedly without reset() in between, and it expects
+            // the output to be the first value encountered:
+            // https://cassandra.apache.org/doc/latest/cql/dml.html#grouping-results
+            if (_first) {
+                _current = std::move(*rs.current);
+                _first = false;
+            }
         }
 
         virtual bool is_aggregate() {
@@ -147,11 +156,7 @@ public:
             factories->contains_write_time_selector_factory(),
             factories->contains_ttl_selector_factory())
         , _factories(std::move(factories))
-    {
-        if (_factories->does_aggregation() && !_factories->contains_only_aggregate_functions()) {
-            throw exceptions::invalid_request_exception("the select clause must either contains only aggregates or none");
-        }
-    }
+    { }
 
     virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const override {
         return _factories->uses_function(ks_name, function_name);
@@ -164,7 +169,7 @@ public:
     }
 
     virtual bool is_aggregate() const override {
-        return _factories->contains_only_aggregate_functions();
+        return _factories->does_aggregation();
     }
 protected:
     class selectors_with_processing : public selectors {
@@ -184,7 +189,7 @@ protected:
         }
 
         virtual bool is_aggregate() override {
-            return _factories->contains_only_aggregate_functions();
+            return _factories->does_aggregation();
         }
 
         virtual std::vector<bytes_opt> get_output_row(cql_serialization_format sf) override {
@@ -263,9 +268,13 @@ selection::collect_metadata(schema_ptr schema, const std::vector<::shared_ptr<ra
     return r;
 }
 
-result_set_builder::result_set_builder(const selection& s, gc_clock::time_point now, cql_serialization_format sf)
+result_set_builder::result_set_builder(const selection& s, gc_clock::time_point now, cql_serialization_format sf,
+                                       std::vector<size_t> group_by_cell_indices)
     : _result_set(std::make_unique<result_set>(::make_shared<metadata>(*(s.get_result_metadata()))))
     , _selectors(s.new_selectors())
+    , _group_by_cell_indices(std::move(group_by_cell_indices))
+    , _last_group(_group_by_cell_indices.size())
+    , _group_began(false)
     , _now(now)
     , _cql_serialization_format(sf)
 {
@@ -311,29 +320,56 @@ void result_set_builder::add_collection(const column_definition& def, bytes_view
     // timestamps, ttls meaningless for collections
 }
 
-void result_set_builder::new_row() {
-    if (current) {
-        _selectors->add_input_row(_cql_serialization_format, *this);
-        if (!_selectors->is_aggregate()) {
-            _result_set->add_row(_selectors->get_output_row(_cql_serialization_format));
-            _selectors->reset();
-        }
+void result_set_builder::update_last_group() {
+    _group_began = true;
+    boost::transform(_group_by_cell_indices, _last_group.begin(), [this](size_t i) { return (*current)[i]; });
+}
+
+bool result_set_builder::last_group_ended() const {
+    if (!_group_began) {
+        return false;
+    }
+    if (_last_group.empty()) {
+        return !_selectors->is_aggregate();
+    }
+    using boost::adaptors::reversed;
+    using boost::adaptors::transformed;
+    return !boost::equal(
+            _last_group | reversed,
+            _group_by_cell_indices | reversed | transformed([this](size_t i) { return (*current)[i]; }));
+}
+
+void result_set_builder::flush_selectors() {
+    _result_set->add_row(_selectors->get_output_row(_cql_serialization_format));
+    _selectors->reset();
+}
+
+void result_set_builder::process_current_row(bool more_rows_coming) {
+    if (!current) {
+        return;
+    }
+    if (last_group_ended()) {
+        flush_selectors();
+    }
+    update_last_group();
+    _selectors->add_input_row(_cql_serialization_format, *this);
+    if (more_rows_coming) {
         current->clear();
     } else {
-        // FIXME: we use optional<> here because we don't have an end_row() signal
-        //        instead, !current means that new_row has never been called, so this
-        //        call to new_row() does not end a previous row.
-        current.emplace();
+        flush_selectors();
     }
 }
 
+void result_set_builder::new_row() {
+    process_current_row(/*more_rows_coming=*/true);
+    // FIXME: we use optional<> here because we don't have an end_row() signal
+    //        instead, !current means that new_row has never been called, so this
+    //        call to new_row() does not end a previous row.
+    current.emplace();
+}
+
 std::unique_ptr<result_set> result_set_builder::build() {
-    if (current) {
-        _selectors->add_input_row(_cql_serialization_format, *this);
-        _result_set->add_row(_selectors->get_output_row(_cql_serialization_format));
-        _selectors->reset();
-        current = std::nullopt;
-    }
+    process_current_row(/*more_rows_coming=*/false);
     if (_result_set->empty() && _selectors->is_aggregate()) {
         _result_set->add_row(_selectors->get_output_row(_cql_serialization_format));
     }

cql3/selection/selection.hh

@@ -244,6 +244,9 @@ class result_set_builder {
 private:
     std::unique_ptr<result_set> _result_set;
     std::unique_ptr<selectors> _selectors;
+    const std::vector<size_t> _group_by_cell_indices; ///< Indices in \c current of cells holding GROUP BY values.
+    std::vector<bytes_opt> _last_group; ///< Previous row's group: all of GROUP BY column values.
+    bool _group_began; ///< Whether a group began being formed.
 public:
     std::optional<std::vector<bytes_opt>> current;
 private:
@@ -306,7 +309,8 @@ public:
         bool do_filter(const selection& selection, const std::vector<bytes>& pk, const std::vector<bytes>& ck, const query::result_row_view& static_row, const query::result_row_view& row) const;
     };
 
-    result_set_builder(const selection& s, gc_clock::time_point now, cql_serialization_format sf);
+    result_set_builder(const selection& s, gc_clock::time_point now, cql_serialization_format sf,
+                       std::vector<size_t> group_by_cell_indices = {});
     void add_empty();
     void add(bytes_opt value);
     void add(const column_definition& def, const query::result_atomic_cell_view& c);
@@ -423,6 +427,20 @@ public:
 
 private:
     bytes_opt get_value(data_type t, query::result_atomic_cell_view c);
+
+    /// True iff the \c current row ends a previously started group, either according to
+    /// _group_by_cell_indices or aggregation.
+    bool last_group_ended() const;
+
+    /// If there is a valid row in this->current, process it; if \p more_rows_coming, get ready to
+    /// receive another.
+    void process_current_row(bool more_rows_coming);
+
+    /// Gets output row from _selectors and resets them.
+    void flush_selectors();
+
+    /// Updates _last_group from the \c current row.
+    void update_last_group();
 };
 
 }

cql3/selection/simple_selector.hh

@@ -77,6 +77,7 @@ private:
     const uint32_t _idx;
     data_type _type;
     bytes_opt _current;
+    bool _first; ///< Whether the next row we receive is the first in its group.
 public:
     static ::shared_ptr<factory> new_factory(const sstring& column_name, uint32_t idx, data_type type) {
         return ::make_shared<simple_selector_factory>(column_name, idx, type);
@@ -86,11 +87,18 @@ public:
         : _column_name(std::move(column_name))
         , _idx(idx)
         , _type(type)
+        , _first(true)
     { }
 
     virtual void add_input(cql_serialization_format sf, result_set_builder& rs) override {
-        // TODO: can we steal it?
-        _current = (*rs.current)[_idx];
+        // GROUP BY calls add_input() repeatedly without reset() in between, and it expects the
+        // output to be the first value encountered:
+        // https://cassandra.apache.org/doc/latest/cql/dml.html#grouping-results
+        if (_first) {
+            // TODO: can we steal it?
+            _current = (*rs.current)[_idx];
+            _first = false;
+        }
     }
 
     virtual bytes_opt get_output(cql_serialization_format sf) override {
@@ -99,6 +107,7 @@ public:
 
     virtual void reset() override {
         _current = {};
+        _first = true;
     }
 
     virtual data_type get_type() override {

cql3/single_column_relation.cc

@@ -95,6 +95,18 @@ single_column_relation::new_IN_restriction(database& db, schema_ptr schema, ::sh
     return ::make_shared<single_column_restriction::IN_with_values>(column_def, std::move(terms));
 }
 
+::shared_ptr<restrictions::restriction>
+single_column_relation::new_LIKE_restriction(
+        database& db, schema_ptr schema, ::shared_ptr<variable_specifications> bound_names) {
+    const column_definition& column_def = to_column_definition(schema, _entity);
+    if (!column_def.type->is_string()) {
+        throw exceptions::invalid_request_exception(
+                format("LIKE is allowed only on string types, which {} is not", column_def.name_as_text()));
+    }
+    auto term = to_term(to_receivers(schema, column_def), _value, db, schema->ks_name(), bound_names);
+    return ::make_shared<single_column_restriction::LIKE>(column_def, std::move(term));
+}
+
 std::vector<::shared_ptr<column_specification>>
 single_column_relation::to_receivers(schema_ptr schema, const column_definition& column_def)
 {

cql3/single_column_relation.hh

@@ -183,6 +183,9 @@ protected:
         return ::make_shared<restrictions::single_column_restriction::contains>(column_def, std::move(term), is_key);
     }
 
+    virtual ::shared_ptr<restrictions::restriction> new_LIKE_restriction(
+            database& db, schema_ptr schema, ::shared_ptr<variable_specifications> bound_names) override;
+
     virtual ::shared_ptr<relation> maybe_rename_identifier(const column_identifier::raw& from, column_identifier::raw to) override {
         return *_entity == from
             ? ::make_shared(single_column_relation(

cql3/statements/alter_table_statement.cc

@@ -221,7 +221,7 @@ void alter_table_statement::add_column(schema_ptr schema, const table& cf, schem
             schema_builder builder(view);
             if (view->view_info()->include_all_columns()) {
                 builder.with_column(column_name->name(), type);
-            } else if (!view->view_info()->base_non_pk_column_in_view_pk()) {
+            } else if (view->view_info()->base_non_pk_columns_in_view_pk().empty()) {
                 db::view::create_virtual_column(builder, column_name->name(), type);
             }
             view_updates.push_back(view_ptr(builder.build()));

cql3/statements/batch_statement.cc

@@ -192,20 +192,21 @@ const std::vector<batch_statement::single_statement>& batch_statement::get_state
     return _statements;
 }
 
-future<std::vector<mutation>> batch_statement::get_mutations(service::storage_proxy& storage, const query_options& options, db::timeout_clock::time_point timeout, bool local, api::timestamp_type now, tracing::trace_state_ptr trace_state) {
+future<std::vector<mutation>> batch_statement::get_mutations(service::storage_proxy& storage, const query_options& options, db::timeout_clock::time_point timeout, bool local, api::timestamp_type now, tracing::trace_state_ptr trace_state,
+                                                             service_permit permit) {
     // Do not process in parallel because operations like list append/prepend depend on execution order.
     using mutation_set_type = std::unordered_set<mutation, mutation_hash_by_key, mutation_equals_by_key>;
-    return do_with(mutation_set_type(), [this, &storage, &options, timeout, now, local, trace_state] (auto& result) {
+    return do_with(mutation_set_type(), [this, &storage, &options, timeout, now, local, trace_state, permit = std::move(permit)] (auto& result) mutable {
         result.reserve(_statements.size());
         _stats.statements_in_batches += _statements.size();
         return do_for_each(boost::make_counting_iterator<size_t>(0),
                            boost::make_counting_iterator<size_t>(_statements.size()),
-                           [this, &storage, &options, now, local, &result, timeout, trace_state] (size_t i) {
+                           [this, &storage, &options, now, local, &result, timeout, trace_state, permit = std::move(permit)] (size_t i) {
             auto&& statement = _statements[i].statement;
             statement->inc_cql_stats();
             auto&& statement_options = options.for_statement(i);
             auto timestamp = _attrs->get_timestamp(now, statement_options);
-            return statement->get_mutations(storage, statement_options, timeout, local, timestamp, trace_state).then([&result] (auto&& more) {
+            return statement->get_mutations(storage, statement_options, timeout, local, timestamp, trace_state, permit).then([&result] (auto&& more) {
                 for (auto&& m : more) {
                     // We want unordered_set::try_emplace(), but we don't have it
                     auto pos = result.find(m);
@@ -295,8 +296,9 @@ future<shared_ptr<cql_transport::messages::result_message>> batch_statement::do_
     }
 
     auto timeout = db::timeout_clock::now() + options.get_timeout_config().*get_timeout_config_selector();
-    return get_mutations(storage, options, timeout, local, now, query_state.get_trace_state()).then([this, &storage, &options, timeout, tr_state = query_state.get_trace_state()] (std::vector<mutation> ms) mutable {
-        return execute_without_conditions(storage, std::move(ms), options.get_consistency(), timeout, std::move(tr_state));
+    return get_mutations(storage, options, timeout, local, now, query_state.get_trace_state(), query_state.get_permit()).then([this, &storage, &options, timeout, tr_state = query_state.get_trace_state(),
+                                                                                                                               permit = query_state.get_permit()] (std::vector<mutation> ms) mutable {
+        return execute_without_conditions(storage, std::move(ms), options.get_consistency(), timeout, std::move(tr_state), std::move(permit));
     }).then([] {
         return make_ready_future<shared_ptr<cql_transport::messages::result_message>>(
                 make_shared<cql_transport::messages::result_message::void_message>());
@@ -308,7 +310,8 @@ future<> batch_statement::execute_without_conditions(
         std::vector<mutation> mutations,
         db::consistency_level cl,
         db::timeout_clock::time_point timeout,
-        tracing::trace_state_ptr tr_state)
+        tracing::trace_state_ptr tr_state,
+        service_permit permit)
 {
     // FIXME: do we need to do this?
 #if 0
@@ -335,7 +338,7 @@ future<> batch_statement::execute_without_conditions(
             mutate_atomic = false;
         }
     }
-    return storage.mutate_with_triggers(std::move(mutations), cl, timeout, mutate_atomic, std::move(tr_state));
+    return storage.mutate_with_triggers(std::move(mutations), cl, timeout, mutate_atomic, std::move(tr_state), std::move(permit));
 }
 
 future<shared_ptr<cql_transport::messages::result_message>> batch_statement::execute_with_conditions(

cql3/statements/batch_statement.hh

@@ -125,7 +125,8 @@ public:
 
     const std::vector<single_statement>& get_statements();
 private:
-    future<std::vector<mutation>> get_mutations(service::storage_proxy& storage, const query_options& options, db::timeout_clock::time_point timeout, bool local, api::timestamp_type now, tracing::trace_state_ptr trace_state);
+    future<std::vector<mutation>> get_mutations(service::storage_proxy& storage, const query_options& options, db::timeout_clock::time_point timeout, bool local, api::timestamp_type now, tracing::trace_state_ptr trace_state,
+                                                service_permit permit);
 
 public:
     /**
@@ -148,7 +149,8 @@ private:
             std::vector<mutation> mutations,
             db::consistency_level cl,
             db::timeout_clock::time_point timeout,
-            tracing::trace_state_ptr tr_state);
+            tracing::trace_state_ptr tr_state,
+            service_permit permit);
 
     future<shared_ptr<cql_transport::messages::result_message>> execute_with_conditions(
             service::storage_proxy& storage,

cql3/statements/create_keyspace_statement.cc

@@ -43,6 +43,8 @@
 #include "prepared_statement.hh"
 #include "database.hh"
 #include "service/migration_manager.hh"
+#include "service/storage_service.hh"
+#include "transport/messages/result_message.hh"
 
 #include <regex>
 
@@ -52,6 +54,8 @@ namespace cql3 {
 
 namespace statements {
 
+logging::logger create_keyspace_statement::_logger("create_keyspace");
+
 create_keyspace_statement::create_keyspace_statement(const sstring& name, shared_ptr<ks_prop_defs> attrs, bool if_not_exists)
     : _name{name}
     , _attrs{attrs}
@@ -139,6 +143,24 @@ future<> cql3::statements::create_keyspace_statement::grant_permissions_to_creat
     });
 }
 
+future<::shared_ptr<messages::result_message>>
+create_keyspace_statement::execute(service::storage_proxy& proxy, service::query_state& state, const query_options& options) {
+    return schema_altering_statement::execute(proxy, state, options).then([this] (::shared_ptr<messages::result_message> msg) {
+        bool multidc = service::get_local_storage_service().get_token_metadata().
+                                get_topology().get_datacenter_endpoints().size() > 1;
+        bool simple = _attrs->get_replication_strategy_class() == "SimpleStrategy";
+
+        if (multidc && simple) {
+            static const auto warning = "Using SimpleStrategy in a multi-datacenter environment is not recommended.";
+
+            msg->add_warning(warning);
+            _logger.warn(warning);
+        }
+
+        return msg;
+    });
+}
+
 }
 
 }

cql3/statements/create_keyspace_statement.hh

@@ -44,6 +44,7 @@
 #include "cql3/statements/schema_altering_statement.hh"
 #include "cql3/statements/ks_prop_defs.hh"
 #include "transport/event.hh"
+#include "log.hh"
 
 #include <seastar/core/shared_ptr.hh>
 
@@ -54,6 +55,8 @@ namespace statements {
 /** A <code>CREATE KEYSPACE</code> statement parsed from a CQL query. */
 class create_keyspace_statement : public schema_altering_statement {
 private:
+    static logging::logger _logger;
+
     sstring _name;
     shared_ptr<ks_prop_defs> _attrs;
     bool _if_not_exists;
@@ -86,6 +89,9 @@ public:
     virtual std::unique_ptr<prepared> prepare(database& db, cql_stats& stats) override;
 
     virtual future<> grant_permissions_to_creator(const service::client_state&) override;
+
+    virtual future<::shared_ptr<messages::result_message>>
+    execute(service::storage_proxy& proxy, service::query_state& state, const query_options& options) override;
 };
 
 }

cql3/statements/create_view_statement.cc

@@ -223,7 +223,7 @@ future<shared_ptr<cql_transport::event::schema_change>> create_view_statement::a
     }
 
     auto parameters = ::make_shared<raw::select_statement::parameters>(raw::select_statement::parameters::orderings_type(), false, true);
-    raw::select_statement raw_select(_base_name, std::move(parameters), _select_clause, _where_clause, nullptr, nullptr);
+    raw::select_statement raw_select(_base_name, std::move(parameters), _select_clause, _where_clause, nullptr, nullptr, {});
     raw_select.prepare_keyspace(keyspace());
     raw_select.set_bound_variables({});
 

cql3/statements/delete_statement.cc

@@ -41,6 +41,7 @@
 
 #include "delete_statement.hh"
 #include "raw/delete_statement.hh"
+#include "database.hh"
 
 namespace cql3 {
 
@@ -102,9 +103,11 @@ delete_statement::prepare_internal(database& db, schema_ptr schema, shared_ptr<v
     }
 
     stmt->process_where_clause(db, _where_clause, std::move(bound_names));
-    if (!stmt->restrictions()->get_clustering_columns_restrictions()->has_bound(bound::START)
-            || !stmt->restrictions()->get_clustering_columns_restrictions()->has_bound(bound::END)) {
-        throw exceptions::invalid_request_exception("A range deletion operation needs to specify both bounds");
+    if (!db.supports_infinite_bound_range_deletions()) {
+        if (!stmt->restrictions()->get_clustering_columns_restrictions()->has_bound(bound::START)
+                || !stmt->restrictions()->get_clustering_columns_restrictions()->has_bound(bound::END)) {
+            throw exceptions::invalid_request_exception("A range deletion operation needs to specify both bounds for clusters without sstable mc format support");
+        }
     }
     if (!schema->is_compound() && stmt->restrictions()->get_clustering_columns_restrictions()->is_slice()) {
         throw exceptions::invalid_request_exception("Range deletions on \"compact storage\" schemas are not supported");