1
0
Fork 0
mirror of https://codeberg.org/forgejo/forgejo.git synced 2024-12-27 13:39:19 -05:00
forgejo/tests/integration/api_packages_conda_test.go
Jason Song a627b885c7
Support compression for Actions logs (#31761)
Support compression for Actions logs to save storage space and
bandwidth. Inspired by
https://github.com/go-gitea/gitea/issues/24256#issuecomment-1521153015

The biggest challenge is that the compression format should support
[seekable](https://github.com/facebook/zstd/blob/dev/contrib/seekable_format/zstd_seekable_compression_format.md).
So when users are viewing a part of the log lines, Gitea doesn't need to
download the whole compressed file and decompress it.

That means gzip cannot help here. And I did research, there aren't too
many choices, like bgzip and xz, but I think zstd is the most popular
one. It has an implementation in Golang with
[zstd](https://github.com/klauspost/compress/tree/master/zstd) and
[zstd-seekable-format-go](https://github.com/SaveTheRbtz/zstd-seekable-format-go),
and what is better is that it has good compatibility: a seekable format
zstd file can be read by a regular zstd reader.

This PR introduces a new package `zstd` to combine and wrap the two
packages, to provide a unified and easy-to-use API.

And a new setting `LOG_COMPRESSION` is added to the config, although I
don't see any reason why not to use compression, I think's it's a good
idea to keep the default with `none` to be consistent with old versions.

`LOG_COMPRESSION` takes effect for only new log files, it adds `.zst` as
an extension to the file name, so Gitea can determine if it needs
decompression according to the file name when reading. Old files will
keep the format since it's not worth converting them, as they will be
cleared after #31735.

<img width="541" alt="image"
src="https://github.com/user-attachments/assets/e9598764-a4e0-4b68-8c2b-f769265183c9">

(cherry picked from commit 33cc5837a655ad544b936d4d040ca36d74092588)

Conflicts:
	assets/go-licenses.json
	go.mod
	go.sum
  resolved with make tidy
2024-08-13 06:51:49 +02:00

275 lines
9.2 KiB
Go

// Copyright 2022 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package integration
import (
"archive/tar"
"archive/zip"
"bytes"
"fmt"
"io"
"net/http"
"testing"
"code.gitea.io/gitea/models/db"
"code.gitea.io/gitea/models/packages"
"code.gitea.io/gitea/models/unittest"
user_model "code.gitea.io/gitea/models/user"
conda_module "code.gitea.io/gitea/modules/packages/conda"
"code.gitea.io/gitea/modules/zstd"
"code.gitea.io/gitea/tests"
"github.com/dsnet/compress/bzip2"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestPackageConda(t *testing.T) {
defer tests.PrepareTestEnv(t)()
user := unittest.AssertExistsAndLoadBean(t, &user_model.User{ID: 2})
packageName := "test_package"
packageVersion := "1.0.1"
channel := "test-channel"
root := fmt.Sprintf("/api/packages/%s/conda", user.Name)
t.Run("Upload", func(t *testing.T) {
tarContent := func() []byte {
var buf bytes.Buffer
tw := tar.NewWriter(&buf)
content := []byte(`{"name":"` + packageName + `","version":"` + packageVersion + `","subdir":"noarch","build":"xxx"}`)
hdr := &tar.Header{
Name: "info/index.json",
Mode: 0o600,
Size: int64(len(content)),
}
tw.WriteHeader(hdr)
tw.Write(content)
tw.Close()
return buf.Bytes()
}()
t.Run(".tar.bz2", func(t *testing.T) {
defer tests.PrintCurrentTest(t)()
var buf bytes.Buffer
bw, _ := bzip2.NewWriter(&buf, nil)
io.Copy(bw, bytes.NewReader(tarContent))
bw.Close()
filename := fmt.Sprintf("%s-%s.tar.bz2", packageName, packageVersion)
req := NewRequestWithBody(t, "PUT", root+"/"+filename, bytes.NewReader(buf.Bytes()))
MakeRequest(t, req, http.StatusUnauthorized)
req = NewRequestWithBody(t, "PUT", root+"/"+filename, bytes.NewReader(buf.Bytes())).
AddBasicAuth(user.Name)
MakeRequest(t, req, http.StatusCreated)
req = NewRequestWithBody(t, "PUT", root+"/"+filename, bytes.NewReader(buf.Bytes())).
AddBasicAuth(user.Name)
MakeRequest(t, req, http.StatusConflict)
pvs, err := packages.GetVersionsByPackageType(db.DefaultContext, user.ID, packages.TypeConda)
require.NoError(t, err)
assert.Len(t, pvs, 1)
pd, err := packages.GetPackageDescriptor(db.DefaultContext, pvs[0])
require.NoError(t, err)
assert.Nil(t, pd.SemVer)
assert.IsType(t, &conda_module.VersionMetadata{}, pd.Metadata)
assert.Equal(t, packageName, pd.Package.Name)
assert.Equal(t, packageVersion, pd.Version.Version)
assert.Empty(t, pd.PackageProperties.GetByName(conda_module.PropertyChannel))
})
t.Run(".conda", func(t *testing.T) {
defer tests.PrintCurrentTest(t)()
var infoBuf bytes.Buffer
zsw, _ := zstd.NewWriter(&infoBuf)
io.Copy(zsw, bytes.NewReader(tarContent))
zsw.Close()
var buf bytes.Buffer
zpw := zip.NewWriter(&buf)
w, _ := zpw.Create("info-x.tar.zst")
w.Write(infoBuf.Bytes())
zpw.Close()
fullName := channel + "/" + packageName
filename := fmt.Sprintf("%s-%s.conda", packageName, packageVersion)
req := NewRequestWithBody(t, "PUT", root+"/"+channel+"/"+filename, bytes.NewReader(buf.Bytes()))
MakeRequest(t, req, http.StatusUnauthorized)
req = NewRequestWithBody(t, "PUT", root+"/"+channel+"/"+filename, bytes.NewReader(buf.Bytes())).
AddBasicAuth(user.Name)
MakeRequest(t, req, http.StatusCreated)
req = NewRequestWithBody(t, "PUT", root+"/"+channel+"/"+filename, bytes.NewReader(buf.Bytes())).
AddBasicAuth(user.Name)
MakeRequest(t, req, http.StatusConflict)
pvs, err := packages.GetVersionsByPackageType(db.DefaultContext, user.ID, packages.TypeConda)
require.NoError(t, err)
assert.Len(t, pvs, 2)
pds, err := packages.GetPackageDescriptors(db.DefaultContext, pvs)
require.NoError(t, err)
assert.Condition(t, func() bool {
for _, pd := range pds {
if pd.Package.Name == fullName {
return true
}
}
return false
})
for _, pd := range pds {
if pd.Package.Name == fullName {
assert.Nil(t, pd.SemVer)
assert.IsType(t, &conda_module.VersionMetadata{}, pd.Metadata)
assert.Equal(t, fullName, pd.Package.Name)
assert.Equal(t, packageVersion, pd.Version.Version)
assert.Equal(t, channel, pd.PackageProperties.GetByName(conda_module.PropertyChannel))
}
}
})
})
t.Run("Download", func(t *testing.T) {
t.Run(".tar.bz2", func(t *testing.T) {
defer tests.PrintCurrentTest(t)()
req := NewRequest(t, "GET", fmt.Sprintf("%s/noarch/%s-%s-xxx.tar.bz2", root, packageName, packageVersion))
MakeRequest(t, req, http.StatusOK)
req = NewRequest(t, "GET", fmt.Sprintf("%s/%s/noarch/%s-%s-xxx.tar.bz2", root, channel, packageName, packageVersion))
MakeRequest(t, req, http.StatusNotFound)
})
t.Run(".conda", func(t *testing.T) {
defer tests.PrintCurrentTest(t)()
req := NewRequest(t, "GET", fmt.Sprintf("%s/noarch/%s-%s-xxx.conda", root, packageName, packageVersion))
MakeRequest(t, req, http.StatusNotFound)
req = NewRequest(t, "GET", fmt.Sprintf("%s/%s/noarch/%s-%s-xxx.conda", root, channel, packageName, packageVersion))
MakeRequest(t, req, http.StatusOK)
})
})
t.Run("EnumeratePackages", func(t *testing.T) {
type Info struct {
Subdir string `json:"subdir"`
}
type PackageInfo struct {
Name string `json:"name"`
Version string `json:"version"`
NoArch string `json:"noarch"`
Subdir string `json:"subdir"`
Timestamp int64 `json:"timestamp"`
Build string `json:"build"`
BuildNumber int64 `json:"build_number"`
Dependencies []string `json:"depends"`
License string `json:"license"`
LicenseFamily string `json:"license_family"`
HashMD5 string `json:"md5"`
HashSHA256 string `json:"sha256"`
Size int64 `json:"size"`
}
type RepoData struct {
Info Info `json:"info"`
Packages map[string]*PackageInfo `json:"packages"`
PackagesConda map[string]*PackageInfo `json:"packages.conda"`
Removed map[string]*PackageInfo `json:"removed"`
}
req := NewRequest(t, "GET", fmt.Sprintf("%s/noarch/repodata.json", root))
resp := MakeRequest(t, req, http.StatusOK)
assert.Equal(t, "application/json", resp.Header().Get("Content-Type"))
req = NewRequest(t, "GET", fmt.Sprintf("%s/noarch/repodata.json.bz2", root))
resp = MakeRequest(t, req, http.StatusOK)
assert.Equal(t, "application/x-bzip2", resp.Header().Get("Content-Type"))
req = NewRequest(t, "GET", fmt.Sprintf("%s/noarch/current_repodata.json", root))
resp = MakeRequest(t, req, http.StatusOK)
assert.Equal(t, "application/json", resp.Header().Get("Content-Type"))
req = NewRequest(t, "GET", fmt.Sprintf("%s/noarch/current_repodata.json.bz2", root))
resp = MakeRequest(t, req, http.StatusOK)
assert.Equal(t, "application/x-bzip2", resp.Header().Get("Content-Type"))
t.Run(".tar.bz2", func(t *testing.T) {
defer tests.PrintCurrentTest(t)()
pv, err := packages.GetVersionByNameAndVersion(db.DefaultContext, user.ID, packages.TypeConda, packageName, packageVersion)
require.NoError(t, err)
pd, err := packages.GetPackageDescriptor(db.DefaultContext, pv)
require.NoError(t, err)
req := NewRequest(t, "GET", fmt.Sprintf("%s/noarch/repodata.json", root))
resp := MakeRequest(t, req, http.StatusOK)
var result RepoData
DecodeJSON(t, resp, &result)
assert.Equal(t, "noarch", result.Info.Subdir)
assert.Empty(t, result.PackagesConda)
assert.Empty(t, result.Removed)
filename := fmt.Sprintf("%s-%s-xxx.tar.bz2", packageName, packageVersion)
assert.Contains(t, result.Packages, filename)
packageInfo := result.Packages[filename]
assert.Equal(t, packageName, packageInfo.Name)
assert.Equal(t, packageVersion, packageInfo.Version)
assert.Equal(t, "noarch", packageInfo.Subdir)
assert.Equal(t, "xxx", packageInfo.Build)
assert.Equal(t, pd.Files[0].Blob.HashMD5, packageInfo.HashMD5)
assert.Equal(t, pd.Files[0].Blob.HashSHA256, packageInfo.HashSHA256)
assert.Equal(t, pd.Files[0].Blob.Size, packageInfo.Size)
})
t.Run(".conda", func(t *testing.T) {
defer tests.PrintCurrentTest(t)()
pv, err := packages.GetVersionByNameAndVersion(db.DefaultContext, user.ID, packages.TypeConda, channel+"/"+packageName, packageVersion)
require.NoError(t, err)
pd, err := packages.GetPackageDescriptor(db.DefaultContext, pv)
require.NoError(t, err)
req := NewRequest(t, "GET", fmt.Sprintf("%s/%s/noarch/repodata.json", root, channel))
resp := MakeRequest(t, req, http.StatusOK)
var result RepoData
DecodeJSON(t, resp, &result)
assert.Equal(t, "noarch", result.Info.Subdir)
assert.Empty(t, result.Packages)
assert.Empty(t, result.Removed)
filename := fmt.Sprintf("%s-%s-xxx.conda", packageName, packageVersion)
assert.Contains(t, result.PackagesConda, filename)
packageInfo := result.PackagesConda[filename]
assert.Equal(t, packageName, packageInfo.Name)
assert.Equal(t, packageVersion, packageInfo.Version)
assert.Equal(t, "noarch", packageInfo.Subdir)
assert.Equal(t, "xxx", packageInfo.Build)
assert.Equal(t, pd.Files[0].Blob.HashMD5, packageInfo.HashMD5)
assert.Equal(t, pd.Files[0].Blob.HashSHA256, packageInfo.HashSHA256)
assert.Equal(t, pd.Files[0].Blob.Size, packageInfo.Size)
})
})
}