jesseduffield.lazygit/pkg/gui/controllers/helpers/diff_line_parser.go
Stefan Haller cf8e5fd27e Recover diff-line identity by parsing the buffer, behind a swappable seam
The focused main view's click/enter/e/G handlers all need the same thing: given
a rendered diff row, the patch-space line it corresponds to. Until now that came
solely from delta's lazygit-edit:// hyperlinks, which only carry a path and a
single line number — no side. That's lossy: for a deletion the number is the old
line, but the consumers fed it into new-file lookups, and two consecutive
deletions (which share a new-file line number) couldn't be told apart at all.

Replace GetFileAndLineForClickedDiffLine with GetDiffLineInfo, returning the
fuller (file, type, new-line, old-line) record from diff-line-metadata-notes.md.
This is mechanism #1: parse the decolorized view buffer — walk up to the file's
"diff --git" section, reuse patch.Parse on it (splitting multi-file commit diffs
on the "diff --git" boundaries), and read the type and line numbers off the patch
arithmetic. It serves the structure-preserving renderings — no pager, git diff
--color, and delta --color-only without line numbers — with no external
dependency.

To avoid trusting a mis-parse, the parser bails when a hunk's body no longer
matches its header (Patch.IsWellFormed). That's what happens when a pager keeps
the diff/hunk headers but restructures the body: delta's line-number gutters push
the +/- marker off the start of each line, so every body line reads as context.
Such renderings fall through to the next backend rather than yielding a confident
wrong answer. (diff-so-fancy goes further and rewrites the headers too, so it
fails even earlier, on the missing "diff --git".)

GetDiffLineInfo is a seam with swappable backends: the buffer parser first, then
the old hyperlink reader as a fallback for renderings the parser can't handle
(delta's default mode, or delta with line-number gutters). The future #2 OSC
per-cell metadata reader plugs in ahead of both, behind the same record shape.

Wire the consumers to the record per that doc's field mapping:
- dive into staging/patch building lands on the exact patch line, looking a
  deletion up by its old-file line number (PatchLineForOldLineNumber) so the
  two-deletions case resolves correctly;
- `e` edits at the new-file line;
- `G` anchors the PR link on the left (old) side for a deletion, the right (new)
  side otherwise.

The hyperlink fallback can't convey the side, so it reports DiffLineOther, which
the consumers treat as a non-deletion — i.e. exactly today's behavior.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-08-08 12:58:59 +02:00

155 lines
4.9 KiB
Go

package helpers
import (
"strings"
"github.com/jesseduffield/lazygit/pkg/commands/patch"
"github.com/jesseduffield/lazygit/pkg/gui/types"
)
// diffFilePrefix marks the start of a file's section in a (possibly multi-file)
// unified diff.
const diffFilePrefix = "diff --git "
// parsedDiffLine is what parseDiffLineFromBuffer recovers about a rendered diff
// row. RelPath is repo-relative (as the diff header spells it); the caller turns
// it into the absolute path of types.DiffLineInfo.
type parsedDiffLine struct {
RelPath string
Type types.DiffLineType
NewLine int
OldLine int
}
// parseDiffLineFromBuffer recovers a rendered diff row's patch-space identity by
// parsing the decolorized diff buffer (mechanism #1 in diff-line-metadata-notes.md).
//
// bufferLines is the full unwrapped view buffer; targetIdx is the buffer line to
// resolve. A commit diff spans multiple files, so we first split on the
// "diff --git" boundaries to isolate the file section containing targetIdx, then
// reuse patch.Parse on that single-file section: its patch line indices line up
// 1:1 with the section's buffer lines, so the type and old/new line numbers fall
// straight out of the patch arithmetic.
//
// ok is false when the buffer isn't a parseable unified diff at targetIdx (e.g.
// a pager that restructures the diff, like delta's default mode), so the caller
// can fall back to another backend.
func parseDiffLineFromBuffer(bufferLines []string, targetIdx int) (parsedDiffLine, bool) {
if targetIdx < 0 || targetIdx >= len(bufferLines) {
return parsedDiffLine{}, false
}
// Find the file section containing the target: the nearest "diff --git" at or
// above it, up to the next one (or the end of the buffer).
fileStart := -1
for i := targetIdx; i >= 0; i-- {
if strings.HasPrefix(bufferLines[i], diffFilePrefix) {
fileStart = i
break
}
}
if fileStart == -1 {
return parsedDiffLine{}, false
}
fileEnd := len(bufferLines)
for i := fileStart + 1; i < len(bufferLines); i++ {
if strings.HasPrefix(bufferLines[i], diffFilePrefix) {
fileEnd = i
break
}
}
fileLines := bufferLines[fileStart:fileEnd]
relPath := pathFromDiffHeader(fileLines)
if relPath == "" {
return parsedDiffLine{}, false
}
p := patch.Parse(strings.Join(fileLines, "\n"))
// Bail if the body doesn't match the hunk headers: the rendering restructured
// the diff (e.g. delta's line-number gutters push the +/- marker off the
// start of the line, so every body line reads as context), and trusting the
// mis-parse would land us on the wrong line. Better to fall back.
if !p.IsWellFormed() {
return parsedDiffLine{}, false
}
patchLines := p.Lines()
patchLineIdx := targetIdx - fileStart
if patchLineIdx < 0 || patchLineIdx >= len(patchLines) {
return parsedDiffLine{}, false
}
result := parsedDiffLine{
RelPath: relPath,
Type: diffLineTypeForKind(patchLines[patchLineIdx].Kind),
NewLine: p.LineNumberOfLine(patchLineIdx),
}
if result.Type == types.DiffLineDeleted {
result.OldLine = p.OldLineNumberOfLine(patchLineIdx)
}
return result, true
}
func diffLineTypeForKind(kind patch.PatchLineKind) types.DiffLineType {
switch kind {
case patch.PATCH_HEADER:
return types.DiffLineFileHeader
case patch.HUNK_HEADER:
return types.DiffLineHunkHeader
case patch.ADDITION:
return types.DiffLineAdded
case patch.DELETION:
return types.DiffLineDeleted
case patch.CONTEXT:
return types.DiffLineContext
default:
return types.DiffLineOther
}
}
// pathFromDiffHeader extracts the new-file path of a single file's diff section.
// It prefers the "+++ b/<path>" line (falling back to "--- a/<path>" when the
// new path is /dev/null, i.e. a deleted file), and as a last resort the
// "diff --git" line. Paths with characters git C-quotes are not handled (this is
// a prototype); the common unquoted case is.
func pathFromDiffHeader(fileLines []string) string {
var oldPath, newPath string
for _, line := range fileLines {
if strings.HasPrefix(line, "@@") {
break // past the header
}
switch {
case strings.HasPrefix(line, "+++ "):
newPath = stripDiffPathPrefix(strings.TrimPrefix(line, "+++ "))
case strings.HasPrefix(line, "--- "):
oldPath = stripDiffPathPrefix(strings.TrimPrefix(line, "--- "))
}
}
if newPath != "" && newPath != "/dev/null" {
return newPath
}
if oldPath != "" && oldPath != "/dev/null" {
return oldPath
}
return pathFromDiffGitLine(fileLines[0])
}
// stripDiffPathPrefix removes git's default a/ or b/ diff path prefix if present.
func stripDiffPathPrefix(path string) string {
if strings.HasPrefix(path, "a/") || strings.HasPrefix(path, "b/") {
return path[2:]
}
return path
}
// pathFromDiffGitLine extracts the new-file path from a "diff --git a/X b/X"
// line, used only when the +++/--- lines are absent.
func pathFromDiffGitLine(line string) string {
rest := strings.TrimPrefix(line, diffFilePrefix)
if idx := strings.LastIndex(rest, " b/"); idx != -1 {
return rest[idx+len(" b/"):]
}
return ""
}