Files
seaweedfs/weed/s3api/bucket_metadata_test.go
T
Yaroslav HalchenkoandClaude Code 2.1.217 / Claude Opus 4.7 490379bff3 Add codespell support with configuration and typo fixes (#10393)
* 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>
2026-07-22 14:38:06 -07:00

228 lines
5.4 KiB
Go

package s3api
import (
"encoding/json"
"fmt"
"reflect"
"sync"
"testing"
"time"
"github.com/aws/aws-sdk-go/service/s3"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/iam_pb"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3err"
)
type BucketMetadataTestCase struct {
filerEntry *filer_pb.Entry
expectBucketMetadata *BucketMetaData
}
var (
//bad entry
badEntry = &filer_pb.Entry{
Name: "badEntry",
}
//good entry
goodEntryAcl, _ = json.Marshal(s3_constants.PublicRead)
goodEntry = &filer_pb.Entry{
Name: "entryWithValidAcp",
Extended: map[string][]byte{
s3_constants.ExtOwnershipKey: []byte(s3_constants.OwnershipBucketOwnerEnforced),
s3_constants.ExtAmzOwnerKey: []byte(AccountAdmin.DisplayName),
s3_constants.ExtAmzAclKey: goodEntryAcl,
},
}
//ownership is ""
ownershipEmptyStr = &filer_pb.Entry{
Name: "ownershipEmptyStr",
Extended: map[string][]byte{
s3_constants.ExtOwnershipKey: []byte(""),
},
}
//ownership valid
ownershipValid = &filer_pb.Entry{
Name: "ownershipValid",
Extended: map[string][]byte{
s3_constants.ExtOwnershipKey: []byte(s3_constants.OwnershipBucketOwnerEnforced),
},
}
//owner is ""
acpEmptyStr = &filer_pb.Entry{
Name: "acpEmptyStr",
Extended: map[string][]byte{
s3_constants.ExtAmzOwnerKey: []byte(""),
},
}
//owner not exists
acpEmptyObject = &filer_pb.Entry{
Name: "acpEmptyObject",
Extended: map[string][]byte{
s3_constants.ExtAmzOwnerKey: []byte("xxxxx"),
},
}
//grants is nil
acpOwnerNilAcp, _ = json.Marshal(make([]*s3.Grant, 0))
acpOwnerNil = &filer_pb.Entry{
Name: "acpOwnerNil",
Extended: map[string][]byte{
s3_constants.ExtAmzAclKey: acpOwnerNilAcp,
},
}
//load filer is
loadFilerBucket = make(map[string]int, 1)
loadFilerBucketLock sync.Mutex
//override `loadBucketMetadataFromFiler` to avoid really load from filer
)
var tcs = []*BucketMetadataTestCase{
{
badEntry, &BucketMetaData{
Name: badEntry.Name,
ObjectOwnership: s3_constants.DefaultOwnershipForExists,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: nil,
},
},
{
goodEntry, &BucketMetaData{
Name: goodEntry.Name,
ObjectOwnership: s3_constants.OwnershipBucketOwnerEnforced,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: s3_constants.PublicRead,
},
},
{
ownershipEmptyStr, &BucketMetaData{
Name: ownershipEmptyStr.Name,
ObjectOwnership: s3_constants.DefaultOwnershipForExists,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: nil,
},
},
{
ownershipValid, &BucketMetaData{
Name: ownershipValid.Name,
ObjectOwnership: s3_constants.OwnershipBucketOwnerEnforced,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: nil,
},
},
{
acpEmptyStr, &BucketMetaData{
Name: acpEmptyStr.Name,
ObjectOwnership: s3_constants.DefaultOwnershipForExists,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: nil,
},
},
{
acpEmptyObject, &BucketMetaData{
Name: acpEmptyObject.Name,
ObjectOwnership: s3_constants.DefaultOwnershipForExists,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: nil,
},
},
{
acpOwnerNil, &BucketMetaData{
Name: acpOwnerNil.Name,
ObjectOwnership: s3_constants.DefaultOwnershipForExists,
Owner: &s3.Owner{
DisplayName: &AccountAdmin.DisplayName,
ID: &AccountAdmin.Id,
},
Acl: make([]*s3.Grant, 0),
},
},
}
func TestBuildBucketMetadata(t *testing.T) {
iam := &IdentityAccessManagement{}
_ = iam.loadS3ApiConfiguration(&iam_pb.S3ApiConfiguration{})
for _, tc := range tcs {
resultBucketMetadata := buildBucketMetadata(iam, tc.filerEntry)
if !reflect.DeepEqual(resultBucketMetadata, tc.expectBucketMetadata) {
t.Fatalf("result is unexpected: \nresult: %v, \nexpect: %v", resultBucketMetadata, tc.expectBucketMetadata)
}
}
}
func TestGetBucketMetadata(t *testing.T) {
loadBucketMetadataFromFiler = func(r *BucketRegistry, bucketName string) (*BucketMetaData, error) {
time.Sleep(time.Second)
loadFilerBucketLock.Lock()
loadFilerBucket[bucketName] = loadFilerBucket[bucketName] + 1
loadFilerBucketLock.Unlock()
return &BucketMetaData{
Name: bucketName,
}, nil
}
br := NewBucketRegistry(nil)
//start 40 goroutine for
var wg sync.WaitGroup
closeCh := make(chan struct{})
for i := 0; i < 40; i++ {
wg.Add(1)
go func() {
defer wg.Done()
outLoop:
for {
for j := 0; j < 5; j++ {
select {
case <-closeCh:
break outLoop
default:
reqBucket := fmt.Sprintf("%c", 67+j)
_, errCode := br.GetBucketMetadata(reqBucket)
if errCode != s3err.ErrNone {
close(closeCh)
t.Error("not expect")
}
}
}
time.Sleep(10 * time.Microsecond)
}
}()
}
time.Sleep(time.Second)
close(closeCh)
wg.Wait()
//Each bucket is loaded from the filer only once
for bucketName, loadCount := range loadFilerBucket {
if loadCount != 1 {
t.Fatalf("lock is uneffict: %s, %d", bucketName, loadCount)
}
}
}