mirror of
https://github.com/go-gitea/gitea.git
synced 2026-10-15 23:52:17 +09:00
26f537dea6
Backport #39781 by @SudhanshuMatrix ## What `parseGitDiffTreeLine` (`services/gitdiff/git_diff_tree.go`) read `BasePath`/`HeadPath` straight from `git diff-tree --raw` output without undoing git's C-quoting, unlike its sibling `parseLsTreeLine` (`modules/git/parse.go`), which already does this with `strconv.Unquote`. This fix applies the same unquoting to both paths in the diff-tree parser. ## Why With the default `core.quotePath=true`, git C-quotes **any path containing a non-ASCII byte** — not just tabs/newlines/backslashes. That means any file with a CJK, Cyrillic, accented-Latin, or emoji name gets octal-escaped, e.g.: ``` :100644 100644 b6fc4c6... 04fea06... M "\346\227\245\346\234\254\350\252\236.txt" ``` (`日本語.txt`, confirmed against real `git diff-tree --raw` output) `GetDiffTree` backs the file-tree sidebar on the commit, compare, and pull request diff pages (`routers/web/repo/commit.go`, `compare.go`, `pull.go`). Without unquoting, any such file shows its mangled, escaped name instead of the real one, and the wrong path can throw off jump-to-file and viewed-file-state behavior that key off the path. Co-authored-by: Shudhanshu Singh <sudhanshuwriterblc@gmail.com> Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
73 lines
1.9 KiB
Go
73 lines
1.9 KiB
Go
// Copyright 2024 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package git
|
|
|
|
import (
|
|
"bytes"
|
|
"fmt"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"gitea.dev/modules/optional"
|
|
)
|
|
|
|
var sepSpace = []byte{' '}
|
|
|
|
type LsTreeEntry struct {
|
|
ID ObjectID
|
|
EntryMode EntryMode
|
|
Name string
|
|
Size optional.Option[int64]
|
|
}
|
|
|
|
func parseLsTreeLine(line []byte) (*LsTreeEntry, error) {
|
|
// expect line to be of the form:
|
|
// <mode> <type> <sha> <space-padded-size>\t<filename>
|
|
// <mode> <type> <sha>\t<filename>
|
|
|
|
var err error
|
|
before, after, ok := bytes.Cut(line, []byte{'\t'})
|
|
if !ok {
|
|
return nil, fmt.Errorf("invalid ls-tree output (no tab): %q", line)
|
|
}
|
|
|
|
entry := new(LsTreeEntry)
|
|
|
|
entryAttrs := before
|
|
entryName := after
|
|
|
|
entryMode, entryAttrs, _ := bytes.Cut(entryAttrs, sepSpace)
|
|
_ /* entryType */, entryAttrs, _ = bytes.Cut(entryAttrs, sepSpace) // the type is not used, the mode is enough to determine the type
|
|
entryObjectID, entryAttrs, _ := bytes.Cut(entryAttrs, sepSpace)
|
|
if len(entryAttrs) > 0 {
|
|
entrySize := entryAttrs // the last field is the space-padded-size
|
|
size, _ := strconv.ParseInt(strings.TrimSpace(string(entrySize)), 10, 64)
|
|
entry.Size = optional.Some(size)
|
|
}
|
|
|
|
entry.EntryMode = ParseEntryMode(string(entryMode))
|
|
if entry.EntryMode == EntryModeNoEntry {
|
|
return nil, fmt.Errorf("invalid ls-tree output (invalid mode): %q, err: %w", line, err)
|
|
}
|
|
|
|
entry.ID, err = NewIDFromString(string(entryObjectID))
|
|
if err != nil {
|
|
return nil, fmt.Errorf("invalid ls-tree output (invalid object id): %q, err: %w", line, err)
|
|
}
|
|
|
|
entry.Name, err = UnquoteDiffFilePath(string(entryName))
|
|
if err != nil {
|
|
return nil, fmt.Errorf("invalid ls-tree output (invalid name): %q, err: %w", line, err)
|
|
}
|
|
return entry, nil
|
|
}
|
|
|
|
func UnquoteDiffFilePath(path string) (string, error) {
|
|
// ref: see the document of git config's "core.quotepath"
|
|
if !strings.HasPrefix(path, `"`) {
|
|
return path, nil
|
|
}
|
|
return strconv.Unquote(path)
|
|
}
|