mirror of
https://github.com/alibaba/open-code-review.git
synced 2026-08-08 08:14:26 +00:00
Some checks are pending
CI / cross-compile (arm64, darwin) (push) Waiting to run
CI / cross-compile (arm64, linux) (push) Waiting to run
CI / cross-compile (arm64, windows) (push) Waiting to run
CI / test (push) Waiting to run
CI / cross-compile (amd64, darwin) (push) Waiting to run
CI / cross-compile (amd64, windows) (push) Waiting to run
CodeQL Advanced / Analyze (go) (push) Waiting to run
CodeQL Advanced / Analyze (actions) (push) Waiting to run
CodeQL Advanced / Analyze (javascript-typescript) (push) Waiting to run
Deploy Pages / build (push) Waiting to run
Deploy Pages / deploy (push) Blocked by required conditions
* chore: add SPDX license headers to all source files
Add Apache-2.0 SPDX license identifiers and copyright notices to all
tracked .go, .sh, .js, .mjs, .ts, and .tsx source files.
Introduce scripts/verify-license.sh and scripts/add-license.sh for
automated verification and bulk addition of license headers. Integrate
the check into CI (ci.yml) and the Makefile (license-check target as
a prerequisite of the existing check target).
This satisfies the OpenSSF Best Practices Badge requirements for
copyright_per_file and license_per_file.
* fix: restore execute permissions on scripts
* docs: add license header instructions to CONTRIBUTING guides
* docs: add license header instructions to pages contributing guides
* fix(pages): strip unclosed HTML comment markers to satisfy CodeQL
* fix: apply code review suggestions for license scripts
- Fix portability: detect macOS vs Linux stat for permission copy
- Fix has_header: check both SPDX and copyright (match verify logic)
- Fix is_ignored: match on path boundaries to avoid false positives
- Fix year extraction: use consistent pipeline across both scripts
- Fix Bash 3.2 compat: quote array length expansion for set -u
* fix(pages): use loop-until-clean for HTML comment stripping (CodeQL)
* fix(pages): use split/join instead of replace to avoid CodeQL false positive
CodeQL's js/incomplete-multi-character-sanitization rule flags any
.replace() that removes multi-character sequences like '<!--...-->',
regardless of context. The data here comes from readFileSync on the
project's own index.html (no untrusted input), making this a false
positive. Using split(regex).join('') achieves the same result without
triggering the taint-tracking rule.
150 lines
5 KiB
Go
150 lines
5 KiB
Go
// SPDX-License-Identifier: Apache-2.0
|
|
// Copyright 2026 alibaba/open-code-review Contributors
|
|
|
|
// Package diff parses unified git diff output into structured Diff objects.
|
|
package diff
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os"
|
|
"os/exec"
|
|
"regexp"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/alibaba/open-code-review/internal/gitcmd"
|
|
"github.com/alibaba/open-code-review/internal/model"
|
|
)
|
|
|
|
var (
|
|
diffHeaderRe = regexp.MustCompile(`^diff --git a/(.+?) b/(.+)$`)
|
|
// Anchored: git emits the marker at column 0 ("Binary files a/x and b/y
|
|
// differ"). Content lines inside hunks always carry a leading "+", "-"
|
|
// or " " prefix, so an anchored match can never misfire on file content.
|
|
binaryRe = regexp.MustCompile(`^Binary files `)
|
|
)
|
|
|
|
// ParseDiffText splits the unified diff text into per-file Diff structs.
|
|
// ref, if non-empty, is a git ref used to read new-file content via
|
|
// git show instead of reading from the working tree.
|
|
// runner, if non-nil, is used to execute git subprocesses through a
|
|
// shared concurrency limiter.
|
|
func ParseDiffText(ctx context.Context, diffText string, repoDir string, ref string, runner *gitcmd.Runner) ([]model.Diff, error) {
|
|
lines := strings.Split(diffText, "\n")
|
|
var diffs []model.Diff
|
|
var current *model.Diff
|
|
var buf strings.Builder
|
|
// inHunk tracks whether the current line sits inside a "@@" hunk of the
|
|
// current file's section. Only hunk content lines carry a leading
|
|
// "+"/"-"/" " marker, so insertion/deletion counting and the binary
|
|
// marker must look at hunk state: outside a hunk, "+++ b/file" and
|
|
// "--- a/file" are headers, not content; inside a hunk, an added line
|
|
// like "++i" renders as "+++i" and still counts as an insertion.
|
|
inHunk := false
|
|
|
|
ctx, cancel := context.WithTimeout(ctx, 2*time.Minute)
|
|
defer cancel()
|
|
|
|
for _, line := range lines {
|
|
if m := diffHeaderRe.FindStringSubmatch(line); m != nil {
|
|
// Flush previous diff
|
|
if current != nil {
|
|
current.Diff = strings.TrimSuffix(buf.String(), "\n")
|
|
finalizeDiff(ctx, current, repoDir, ref, runner)
|
|
diffs = append(diffs, *current)
|
|
buf.Reset()
|
|
}
|
|
current = &model.Diff{
|
|
OldPath: m[1],
|
|
NewPath: m[2],
|
|
}
|
|
inHunk = false
|
|
}
|
|
if current == nil {
|
|
continue
|
|
}
|
|
|
|
switch {
|
|
case strings.HasPrefix(line, "@@"):
|
|
inHunk = true
|
|
// The object IDs and mode in Git's extended "index" header are not
|
|
// useful review context. Keep index text in hunks, where it is file
|
|
// content and therefore carries a diff prefix.
|
|
case !inHunk && strings.HasPrefix(line, "index "):
|
|
continue
|
|
case !inHunk && binaryRe.MatchString(line):
|
|
current.IsBinary = true
|
|
// Extended header lines (unambiguous: content lines always carry a
|
|
// leading "+", "-" or " " prefix, so a bare prefix match is safe).
|
|
case strings.HasPrefix(line, "new file mode "):
|
|
current.IsNew = true
|
|
case strings.HasPrefix(line, "deleted file mode "):
|
|
current.IsDeleted = true
|
|
case strings.HasPrefix(line, "rename from "):
|
|
// Authoritative old path for renames; more reliable than the
|
|
// "diff --git" header when paths contain spaces.
|
|
current.OldPath = strings.TrimPrefix(line, "rename from ")
|
|
current.IsRenamed = true
|
|
case strings.HasPrefix(line, "rename to "):
|
|
current.NewPath = strings.TrimPrefix(line, "rename to ")
|
|
current.IsRenamed = true
|
|
// git emits "--- /dev/null" / "+++ /dev/null" without a/ b/ prefixes.
|
|
// Guarded by inHunk: inside a hunk the same strings can be content
|
|
// (e.g. an added line "++ /dev/null").
|
|
case !inHunk && line == "--- /dev/null":
|
|
current.IsNew = true
|
|
case !inHunk && line == "+++ /dev/null":
|
|
current.IsDeleted = true
|
|
case inHunk && strings.HasPrefix(line, "+"):
|
|
current.Insertions++
|
|
case inHunk && strings.HasPrefix(line, "-"):
|
|
current.Deletions++
|
|
}
|
|
buf.WriteString(line)
|
|
buf.WriteString("\n")
|
|
}
|
|
|
|
// Flush last diff
|
|
if current != nil {
|
|
current.Diff = strings.TrimSuffix(buf.String(), "\n")
|
|
finalizeDiff(ctx, current, repoDir, ref, runner)
|
|
diffs = append(diffs, *current)
|
|
}
|
|
|
|
return diffs, nil
|
|
}
|
|
|
|
// finalizeDiff reads the new file content. When ref is non-empty it uses
|
|
// git show to read the file at that ref; otherwise it reads from disk.
|
|
func finalizeDiff(ctx context.Context, d *model.Diff, repoDir string, ref string, runner *gitcmd.Runner) {
|
|
if d.IsDeleted || d.NewPath == "/dev/null" {
|
|
d.NewPath = "/dev/null"
|
|
return
|
|
}
|
|
if ref != "" {
|
|
args := []string{"-c", "core.quotepath=false", "show", "--end-of-options", ref + ":" + d.NewPath}
|
|
var output []byte
|
|
var err error
|
|
if runner != nil {
|
|
output, err = runner.Output(ctx, repoDir, args...)
|
|
} else {
|
|
cmd := exec.CommandContext(ctx, "git", args...)
|
|
cmd.Dir = repoDir
|
|
output, err = cmd.Output()
|
|
}
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "[ocr] WARNING: cannot read file %s at ref %s: %v\n",
|
|
d.NewPath, ref, err)
|
|
return
|
|
}
|
|
d.NewFileContent = string(output)
|
|
return
|
|
}
|
|
content, err := readWorkspaceFileForDiff(repoDir, d.NewPath)
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "[ocr] WARNING: cannot read file %s for review: %v\n", d.NewPath, err)
|
|
return
|
|
}
|
|
d.NewFileContent = string(content)
|
|
}
|