git/blob: GetContentBase64 with fewer allocations and no goroutine (#8297)

See #8222 for context.i

`GetBlobContentBase64` was using a pipe and a goroutine to read the blob content as base64. This can be replace by a pre-allocated buffer and a direct copy.

Note that although similar to `GetBlobContent`, it does not truncate the content if the blob size is over the limit (but returns an error). I think that `GetBlobContent` should adopt the same behavior at some point (error instead of truncating).

### Tests

- I added test coverage for Go changes...
  - [x] in their respective `*_test.go` for unit tests.
- [x] I did not document these changes and I do not expect someone else to do it.

### Release notes

- [x] I do not want this change to show in the release notes.

Reviewed-on: https://codeberg.org/forgejo/forgejo/pulls/8297
Reviewed-by: Earl Warren <earl-warren@noreply.codeberg.org>
Co-authored-by: oliverpool <git@olivier.pfad.fr>
Co-committed-by: oliverpool <git@olivier.pfad.fr>

modules/git/blob.go

@@ -8,6 +8,7 @@ import (
 	"bufio"
 	"bytes"
 	"encoding/base64"
+	"fmt"
 	"io"
 
 	"forgejo.org/modules/log"
@@ -172,33 +173,43 @@ func (b *Blob) GetBlobContent(limit int64) (string, error) {
 	return string(buf), err
 }
 
-// GetBlobContentBase64 Reads the content of the blob with a base64 encode and returns the encoded string
+type BlobTooLargeError struct {
-func (b *Blob) GetBlobContentBase64() (string, error) {
+	Size, Limit int64
-	dataRc, err := b.DataAsync()
+}
+
+func (b BlobTooLargeError) Error() string {
+	return fmt.Sprintf("blob: content larger than limit (%d > %d)", b.Size, b.Limit)
+}
+
+// GetContentBase64 Reads the content of the blob and returns it as base64 encoded string.
+// Returns [BlobTooLargeError] if the (unencoded) content is larger than the limit.
+func (b *Blob) GetContentBase64(limit int64) (string, error) {
+	if b.Size() > limit {
+		return "", BlobTooLargeError{
+			Size:  b.Size(),
+			Limit: limit,
+		}
+	}
+
+	rc, size, err := b.NewTruncatedReader(limit)
 	if err != nil {
 		return "", err
 	}
-	defer dataRc.Close()
+	defer rc.Close()
 
-	pr, pw := io.Pipe()
+	encoding := base64.StdEncoding
-	encoder := base64.NewEncoder(base64.StdEncoding, pw)
+	buf := bytes.NewBuffer(make([]byte, 0, encoding.EncodedLen(int(size))))
 
-	go func() {
+	encoder := base64.NewEncoder(encoding, buf)
-		_, err := io.Copy(encoder, dataRc)
-		_ = encoder.Close()
 
-		if err != nil {
+	if _, err := io.Copy(encoder, rc); err != nil {
-			_ = pw.CloseWithError(err)
-		} else {
-			_ = pw.Close()
-		}
-	}()
-
-	out, err := io.ReadAll(pr)
-	if err != nil {
 		return "", err
 	}
-	return string(out), nil
+	if err := encoder.Close(); err != nil {
+		return "", err
+	}
+
+	return buf.String(), nil
 }
 
 // GuessContentType guesses the content type of the blob.

modules/git/blob_test.go

@@ -63,6 +63,24 @@ func TestBlob(t *testing.T) {
 		require.Equal(t, "file2\n", r)
 	})
 
+	t.Run("GetContentBase64", func(t *testing.T) {
+		r, err := testBlob.GetContentBase64(100)
+		require.NoError(t, err)
+		require.Equal(t, "ZmlsZTIK", r)
+
+		r, err = testBlob.GetContentBase64(-1)
+		require.ErrorAs(t, err, &BlobTooLargeError{})
+		require.Empty(t, r)
+
+		r, err = testBlob.GetContentBase64(4)
+		require.ErrorAs(t, err, &BlobTooLargeError{})
+		require.Empty(t, r)
+
+		r, err = testBlob.GetContentBase64(6)
+		require.NoError(t, err)
+		require.Equal(t, "ZmlsZTIK", r)
+	})
+
 	t.Run("NewTruncatedReader", func(t *testing.T) {
 		// read fewer than available
 		rc, size, err := testBlob.NewTruncatedReader(100)

routers/api/v1/repo/wiki.go

@@ -5,6 +5,7 @@ package repo
 
 import (
 	"encoding/base64"
+	"errors"
 	"fmt"
 	"net/http"
 	"net/url"
@@ -506,11 +507,8 @@ func findWikiRepoCommit(ctx *context.APIContext) (*git.Repository, *git.Commit)
 // given tree entry, encoded with base64. Writes to ctx if an error occurs.
 func wikiContentsByEntry(ctx *context.APIContext, entry *git.TreeEntry) string {
 	blob := entry.Blob()
-	if blob.Size() > setting.API.DefaultMaxBlobSize {
+	content, err := blob.GetContentBase64(setting.API.DefaultMaxBlobSize)
-		return ""
+	if err != nil && !errors.As(err, &git.BlobTooLargeError{}) {
-	}
-	content, err := blob.GetBlobContentBase64()
-	if err != nil {
 		ctx.Error(http.StatusInternalServerError, "GetBlobContentBase64", err)
 		return ""
 	}

services/repository/files/content.go

@@ -5,6 +5,7 @@ package files
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"net/url"
 	"path"
@@ -273,13 +274,11 @@ func GetBlobBySHA(ctx context.Context, repo *repo_model.Repository, gitRepo *git
 	if err != nil {
 		return nil, err
 	}
-	content := ""
+	content, err := gitBlob.GetContentBase64(setting.API.DefaultMaxBlobSize)
-	if gitBlob.Size() <= setting.API.DefaultMaxBlobSize {
+	if err != nil && !errors.As(err, &git.BlobTooLargeError{}) {
-		content, err = gitBlob.GetBlobContentBase64()
-		if err != nil {
 		return nil, err
 	}
-	}
+
 	return &api.GitBlob{
 		SHA:      gitBlob.ID.String(),
 		URL:      repo.APIURL() + "/git/blobs/" + url.PathEscape(gitBlob.ID.String()),