mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-07-25 09:32:45 +00:00
* Add GitHub Actions workflow for codespell on master * Add rudimentary codespell config * Tune codespell config: skip generated code, ignore camelCase, whitelist domain terms Add camelCase/PascalCase regex to ignore common Go/Rust/JS identifiers like allLocations, publishErr, ReadInside, FlushInterval. Also skip templ-generated *_templ.go files, and whitelist a handful of short/domain-specific words (visibles, fo, te, ser, bject, unparseable, keep-alives, tread, anc, ue) that show up as false positives across the tree. Co-Authored-By: Claude Code 2.1.217 / Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Fix ambiguous typos and protect false positives Fixes typos that codespell reports with multiple candidate suggestions (so `codespell -w` cannot auto-apply them), plus one inline pragma and one config entry to protect legitimate identifiers. Manual fixes (single correct answer chosen from context): - pattens -> patterns (5x) in filer/upload/shell flag help strings - finded -> found (2x) in tarantool storage.lua comment - spacify -> specify (2x) in helm chart values.yaml comment - wether -> whether in skiplist.go docstring - simpe -> simple in mq schema test case name False-positive protection: - Add `//codespell:ignore` next to `source GET's` (possessive of HTTP verb) in s3api_object_handlers_copy_stream.go - Whitelist `auther` in .codespellrc — it's a local variable meaning "authenticator" in weed/security/tls.go, not a typo of "author". Co-Authored-By: Claude Code 2.1.217 / Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Extend codespell ignore list: .git-meta path and thirdparty groupId Also skip `.git-meta` (scratch dir for commit messages that may contain typo words verbatim) and whitelist `thirdparty` — it appears as the literal Maven groupId `org.apache.hadoop.thirdparty` in hdfs3 poms and cannot be renamed. Co-Authored-By: Claude Code 2.1.217 / Claude Opus 4.7 (1M context) <noreply@anthropic.com> * [DATALAD RUNCMD] Fix non-ambiguous typos with codespell -w Auto-applied fixes to the 44 remaining single-suggestion typos across docs, comments, log messages, tests, config, and one Java pom. === Do not change lines below === { "chain": [], "cmd": "uvx codespell -w", "exit": 0, "extra_inputs": [], "inputs": [], "outputs": [], "pwd": "." } ^^^ Do not change lines above ^^^ * Revert breaking codespell fixes; whitelist unknwon and atleast Two of the auto-applied `codespell -w` fixes were false positives that would break the build/tests: - go.mod: `github.com/unknwon/goconfig` is a real Go module path — the upstream author's GitHub handle is literally `unknwon`. Renaming to `unknown` would fail dependency resolution. - test/benchmark/fuse_db/bin/{sqlite_verify.py,run_mysql.sh,run_sqlite.sh}: `atleast` is a literal CLI mode value (a string constant compared and passed as a positional argument). Rewriting to `at least` splits it into two arguments and breaks the mode check. Reverted those files and whitelisted both words in .codespellrc so future runs won't re-suggest the same broken fixes. Co-Authored-By: Claude Code 2.1.217 / Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Code 2.1.217 / Claude Opus 4.7 (1M context) <noreply@anthropic.com>
98 lines
4.0 KiB
Lua
98 lines
4.0 KiB
Lua
box.watch('box.status', function()
|
|
if box.info.ro then
|
|
return
|
|
end
|
|
|
|
-- ====================================
|
|
-- key_value space
|
|
-- ====================================
|
|
box.schema.create_space('key_value', {
|
|
format = {
|
|
{ name = 'key', type = 'string' },
|
|
{ name = 'bucket_id', type = 'unsigned' },
|
|
{ name = 'value', type = 'string' }
|
|
},
|
|
if_not_exists = true
|
|
})
|
|
|
|
-- create key_value space indexes
|
|
box.space.key_value:create_index('id', {type = 'tree', parts = { 'key' }, unique = true, if_not_exists = true})
|
|
box.space.key_value:create_index('bucket_id', { type = 'tree', parts = { 'bucket_id' }, unique = false, if_not_exists = true })
|
|
|
|
-- ====================================
|
|
-- filer_metadata space
|
|
-- ====================================
|
|
box.schema.create_space('filer_metadata', {
|
|
format = {
|
|
{ name = 'directory', type = 'string' },
|
|
{ name = 'bucket_id', type = 'unsigned' },
|
|
{ name = 'name', type = 'string' },
|
|
{ name = 'expire_at', type = 'unsigned' },
|
|
{ name = 'data', type = 'string' }
|
|
},
|
|
if_not_exists = true
|
|
})
|
|
|
|
-- create filer_metadata space indexes
|
|
box.space.filer_metadata:create_index('id', {type = 'tree', parts = { 'directory', 'name' }, unique = true, if_not_exists = true})
|
|
box.space.filer_metadata:create_index('bucket_id', { type = 'tree', parts = { 'bucket_id' }, unique = false, if_not_exists = true })
|
|
box.space.filer_metadata:create_index('directory_idx', { type = 'tree', parts = { 'directory' }, unique = false, if_not_exists = true })
|
|
box.space.filer_metadata:create_index('name_idx', { type = 'tree', parts = { 'name' }, unique = false, if_not_exists = true })
|
|
box.space.filer_metadata:create_index('expire_at_idx', { type = 'tree', parts = { 'expire_at' }, unique = false, if_not_exists = true})
|
|
end)
|
|
|
|
-- functions for filer_metadata space
|
|
local filer_metadata = {
|
|
delete_by_directory_idx = function(directory)
|
|
local space = box.space.filer_metadata
|
|
local index = space.index.directory_idx
|
|
-- for each found directory
|
|
for _, tuple in index:pairs({ directory }, { iterator = 'EQ' }) do
|
|
space:delete({ tuple[1], tuple[3] })
|
|
end
|
|
return true
|
|
end,
|
|
find_by_directory_idx_and_name = function(dirPath, startFileName, includeStartFile, limit)
|
|
local space = box.space.filer_metadata
|
|
local directory_idx = space.index.directory_idx
|
|
-- choose filter name function
|
|
local filter_filename_func
|
|
if includeStartFile then
|
|
filter_filename_func = function(value) return value >= startFileName end
|
|
else
|
|
filter_filename_func = function(value) return value > startFileName end
|
|
end
|
|
-- init results
|
|
local results = {}
|
|
-- for each found directory
|
|
for _, tuple in directory_idx:pairs({ dirPath }, { iterator = 'EQ' }) do
|
|
-- filter by name
|
|
if filter_filename_func(tuple[3]) then
|
|
table.insert(results, tuple)
|
|
end
|
|
end
|
|
-- sort
|
|
table.sort(results, function(a, b) return a[3] < b[3] end)
|
|
-- apply limit
|
|
if #results > limit then
|
|
local limitedResults = {}
|
|
for i = 1, limit do
|
|
table.insert(limitedResults, results[i])
|
|
end
|
|
results = limitedResults
|
|
end
|
|
-- return
|
|
return results
|
|
end,
|
|
is_expired = function(args, tuple)
|
|
return (tuple[4] > 0) and (require('fiber').time() > tuple[4])
|
|
end
|
|
}
|
|
|
|
-- register functions for filer_metadata space, set grants
|
|
rawset(_G, 'filer_metadata', filer_metadata)
|
|
for name, _ in pairs(filer_metadata) do
|
|
box.schema.func.create('filer_metadata.' .. name, { setuid = true, if_not_exists = true })
|
|
box.schema.user.grant('storage', 'execute', 'function', 'filer_metadata.' .. name, { if_not_exists = true })
|
|
end
|