fix(storage): fix Azure Blob dump failing with file does not exist (#38814)

## Issue

Gitea fails to dump LFS (and other object-storage) files when Azure Blob
Storage is configured as the storage backend. The dump reports:

Failed to dump LFS objects: /file/path: copying contents: file does not
exist

This happens with any non-empty base path (the default for LFS storage),
which is why the user could only work around it by using `--skip-*`
flags.

The root cause is in `AzureBlobStorage.IterateObjects()`: Azure's list
API already returns each blob's name including the configured base path,
but the code was building the read client by running that name through
the base-path-prepending helper a second time. This doubled the base
path (e.g. `gitea-lfs/gitea-lfs/aa/bb/hash`), pointing at a blob that
doesn't exist. `Stat()` still succeeded because it doesn't touch the
network, so the failure only surfaced when the dumper actually tried to
read the object's contents.

## Solution

Add `getBlobClientByFullName()`, which builds a blob client from a name
that is already fully qualified, without re-applying
`buildAzureBlobPath()`. `IterateObjects()` now uses it for names
obtained from Azure's list API. `getBlobClient()` (used by `Open`,
`Stat`, `Delete`, `ServeDirectURL`, which take relative paths) is
unchanged in behavior.

Also add `TestAzureBlobStorageDumpArchive`, a regression test that
drives the real dump path (`IterateObjects` → `Stat` →
`dump.Dumper.AddFileByReader` → `mholt/archives` zip writer) against a
**non-empty** `BasePath`, and verifies the produced archive contains the
object with the correct content. The existing Azure tests use an empty
`BasePath` and never read object content via `IterateObjects`, which is
why they didn't catch this.

Fixes #35476

---------

Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This commit is contained in:
Mitrahsoft
2026-08-07 16:35:30 +00:00
committed by GitHub
co-authored by wxiaoguang
parent 4c382cea59
commit 7733f1953f
7 changed files with 198 additions and 226 deletions
+21 -58
View File
@@ -10,82 +10,45 @@ import (
"gitea.dev/modules/setting"
"gitea.dev/modules/test"
"gitea.dev/modules/util"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestAzureBlobStorage(t *testing.T) {
func prepareAzureStorageConfig(t *testing.T, basePath ...string) *setting.Storage {
endpoint := test.ExternalServiceHTTP(t, "TEST_AZURESTORAGE_ENDPOINT", "http://devstoreaccount1.azurite.local:10000")
storageType := setting.AzureBlobStorageType
config := &setting.Storage{
return &setting.Storage{
AzureBlobConfig: setting.AzureBlobStorageConfig{
// https://learn.microsoft.com/azure/storage/common/storage-use-azurite?tabs=visual-studio-code#ip-style-url
Endpoint: endpoint,
// https://learn.microsoft.com/azure/storage/common/storage-use-azurite?tabs=visual-studio-code#well-known-storage-account-and-key
AccountName: "devstoreaccount1",
AccountKey: "Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==",
Container: "test",
Container: "test-container",
BasePath: util.OptionalArg(basePath),
},
}
table := []struct {
name string
test func(t *testing.T, typStr Type, cfg *setting.Storage)
}{
{
name: "iterator",
test: testStorageIterator,
},
{
name: "testBlobStorageURLContentTypeAndDisposition",
test: testBlobStorageURLContentTypeAndDisposition,
},
}
for _, entry := range table {
t.Run(entry.name, func(t *testing.T) {
entry.test(t, storageType, config)
})
}
}
func TestAzureBlobStoragePath(t *testing.T) {
m := &AzureBlobStorage{cfg: &setting.AzureBlobStorageConfig{BasePath: ""}}
assert.Empty(t, m.buildAzureBlobPath("/"))
assert.Empty(t, m.buildAzureBlobPath("."))
assert.Equal(t, "a", m.buildAzureBlobPath("/a"))
assert.Equal(t, "a/b", m.buildAzureBlobPath("/a/b/"))
m = &AzureBlobStorage{cfg: &setting.AzureBlobStorageConfig{BasePath: "/"}}
assert.Empty(t, m.buildAzureBlobPath("/"))
assert.Empty(t, m.buildAzureBlobPath("."))
assert.Equal(t, "a", m.buildAzureBlobPath("/a"))
assert.Equal(t, "a/b", m.buildAzureBlobPath("/a/b/"))
m = &AzureBlobStorage{cfg: &setting.AzureBlobStorageConfig{BasePath: "/base"}}
assert.Equal(t, "base", m.buildAzureBlobPath("/"))
assert.Equal(t, "base", m.buildAzureBlobPath("."))
assert.Equal(t, "base/a", m.buildAzureBlobPath("/a"))
assert.Equal(t, "base/a/b", m.buildAzureBlobPath("/a/b/"))
m = &AzureBlobStorage{cfg: &setting.AzureBlobStorageConfig{BasePath: "/base/"}}
assert.Equal(t, "base", m.buildAzureBlobPath("/"))
assert.Equal(t, "base", m.buildAzureBlobPath("."))
assert.Equal(t, "base/a", m.buildAzureBlobPath("/a"))
assert.Equal(t, "base/a/b", m.buildAzureBlobPath("/a/b/"))
func TestAzureBlobStorage(t *testing.T) {
t.Run("NoBasePath", func(t *testing.T) {
config := prepareAzureStorageConfig(t)
objStore, err := NewStorage(setting.AzureBlobStorageType, config)
require.NoError(t, err)
testStorageGeneral(t, objStore)
})
t.Run("WithBasePath", func(t *testing.T) {
config := prepareAzureStorageConfig(t, "test-base-path")
objStore, err := NewStorage(setting.AzureBlobStorageType, config)
require.NoError(t, err)
testStorageGeneral(t, objStore)
})
}
func Test_azureBlobObject(t *testing.T) {
endpoint := test.ExternalServiceHTTP(t, "TEST_AZURESTORAGE_ENDPOINT", "http://devstoreaccount1.azurite.local:10000")
s, err := NewStorage(setting.AzureBlobStorageType, &setting.Storage{
AzureBlobConfig: setting.AzureBlobStorageConfig{
// https://learn.microsoft.com/azure/storage/common/storage-use-azurite?tabs=visual-studio-code#ip-style-url
Endpoint: endpoint,
// https://learn.microsoft.com/azure/storage/common/storage-use-azurite?tabs=visual-studio-code#well-known-storage-account-and-key
AccountName: "devstoreaccount1",
AccountKey: "Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==",
Container: "test",
},
})
assert.NoError(t, err)
s, err := NewStorage(setting.AzureBlobStorageType, prepareAzureStorageConfig(t))
require.NoError(t, err)
data := "Q2xTckt6Y1hDOWh0"
_, err = s.Save("test.txt", strings.NewReader(data), int64(len(data)))