Skip to content

unified: include all non-whitespace tokens in extracted file path #63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jelmer merged 1 commit into from
May 5, 2026
+35 −103
Merged

unified: include all non-whitespace tokens in extracted file path #63

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions src/edit/lossless.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -797,6 +797,24 @@ index ccc..ddd 100644
assert_eq!(hunk.header().unwrap().check_counts(&hunk), vec![]);
}

#[test]
fn test_path_with_special_characters() {
// Filenames legitimately contain `-`, `+`, `@`, `,` etc. The lexer
// emits each as its own token; the path parser must include them.
let text = "\
--- a/foo-bar+baz@1.0,v
+++ b/foo-bar+baz@1.0,v
@@ -1 +1 @@
-old
+new
";
let parsed = parse(text);
let patch = parsed.tree();
let file = patch.patch_files().next().unwrap();
assert_eq!(file.old_path().as_deref(), Some("a/foo-bar+baz@1.0,v"));
assert_eq!(file.new_path().as_deref(), Some("b/foo-bar+baz@1.0,v"));
}

#[test]
fn test_check_counts_mismatch() {
let text = "--- a/f\n+++ b/f\n@@ -1,99 +1,99 @@\n ctx\n-old\n+new\n";
Expand Down
120 changes: 17 additions & 103 deletions src/edit/parse.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,48 +103,9 @@ impl<'a> Parser<'a> {
self.advance(); // -
self.advance(); // -

// Skip whitespace
self.skip_whitespace();

// Parse path - collect all tokens that make up the path
let mut path_parts = Vec::new();
let mut collecting_path = true;
while !self.at(SyntaxKind::NEWLINE) && !self.at_end() && collecting_path {
match self.current_kind() {
Some(SyntaxKind::TEXT)
| Some(SyntaxKind::SLASH)
| Some(SyntaxKind::DOT)
| Some(SyntaxKind::NUMBER)
| Some(SyntaxKind::COLON)
| Some(SyntaxKind::BACKSLASH) => {
if let Some(text) = self.current_text() {
path_parts.push(text.to_string());
}
self.advance_without_emit();
}
Some(SyntaxKind::WHITESPACE) if !path_parts.is_empty() => {
// Stop at whitespace after we've collected some path parts (timestamp follows)
collecting_path = false;
}
_ => {
collecting_path = false;
}
}
}

if !path_parts.is_empty() {
let path = path_parts.join("");
self.builder.token(SyntaxKind::PATH.into(), &path);
}

// Skip to end of line
while !self.at(SyntaxKind::NEWLINE) && !self.at_end() {
self.advance();
}

if self.at(SyntaxKind::NEWLINE) {
self.advance();
}
self.parse_file_path();
self.skip_to_eol();

self.builder.finish_node();
}
Expand All @@ -157,48 +118,9 @@ impl<'a> Parser<'a> {
self.advance(); // +
self.advance(); // +

// Skip whitespace
self.skip_whitespace();

// Parse path - collect all tokens that make up the path
let mut path_parts = Vec::new();
let mut collecting_path = true;
while !self.at(SyntaxKind::NEWLINE) && !self.at_end() && collecting_path {
match self.current_kind() {
Some(SyntaxKind::TEXT)
| Some(SyntaxKind::SLASH)
| Some(SyntaxKind::DOT)
| Some(SyntaxKind::NUMBER)
| Some(SyntaxKind::COLON)
| Some(SyntaxKind::BACKSLASH) => {
if let Some(text) = self.current_text() {
path_parts.push(text.to_string());
}
self.advance_without_emit();
}
Some(SyntaxKind::WHITESPACE) if !path_parts.is_empty() => {
// Stop at whitespace after we've collected some path parts (timestamp follows)
collecting_path = false;
}
_ => {
collecting_path = false;
}
}
}

if !path_parts.is_empty() {
let path = path_parts.join("");
self.builder.token(SyntaxKind::PATH.into(), &path);
}

// Skip to end of line
while !self.at(SyntaxKind::NEWLINE) && !self.at_end() {
self.advance();
}

if self.at(SyntaxKind::NEWLINE) {
self.advance();
}
self.parse_file_path();
self.skip_to_eol();

self.builder.finish_node();
}
Expand Down Expand Up @@ -905,36 +827,28 @@ impl<'a> Parser<'a> {
self.builder.finish_node();
}

/// Emit a single PATH token for the file path on a header line.
///
/// The path runs from the current position to the next whitespace (which
/// separates it from an optional timestamp) or to end of line. Filenames
/// legitimately contain `-`, `+`, `@`, `,`, etc.; the lexer emits those
/// as their own token kinds, so we stitch any non-whitespace tokens back
/// together rather than maintaining an accept-list per character.
fn parse_file_path(&mut self) {
let mut path_parts = Vec::new();
let mut collecting_path = true;

while !self.at(SyntaxKind::NEWLINE) && !self.at_end() && collecting_path {
let mut path = String::new();
while !self.at_end() {
match self.current_kind() {
Some(SyntaxKind::TEXT)
| Some(SyntaxKind::SLASH)
| Some(SyntaxKind::DOT)
| Some(SyntaxKind::NUMBER)
| Some(SyntaxKind::MINUS)
| Some(SyntaxKind::STAR)
| Some(SyntaxKind::COLON)
| Some(SyntaxKind::BACKSLASH) => {
Some(SyntaxKind::WHITESPACE) | Some(SyntaxKind::NEWLINE) | None => break,
Some(_) => {
if let Some(text) = self.current_text() {
path_parts.push(text.to_string());
path.push_str(text);
}
self.advance_without_emit();
}
Some(SyntaxKind::WHITESPACE) if !path_parts.is_empty() => {
collecting_path = false;
}
_ => {
collecting_path = false;
}
}
}

if !path_parts.is_empty() {
let path = path_parts.join("");
if !path.is_empty() {
self.builder.token(SyntaxKind::PATH.into(), &path);
}
}
Expand Down