This is an archive of the discontinued Mercurial Phabricator instance.

Differential D6489

rust-regex: fix shortcut for exact matches
ClosedPublic

Authored by Alphare on Jun 7 2019, 5:50 AM.

Details

Reviewers
kevincox
Group Reviewers
hg-reviewers
Commits
rHG48f1f864d928: rust-regex: fix shortcut for exact matches
Summary

The current shortcut for rootglobs that can be simplified to exact matches
does not work, it instead treats the pattern as a regex, which is not the
same thing.
This changes fixes the behavior and introduces a test for this behavior.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

Alphare created this revision.Jun 7 2019, 5:50 AM
kevincox accepted this revision.Jun 10 2019, 9:14 AM
Closed by commit rHG48f1f864d928: rust-regex: fix shortcut for exact matches (authored by Alphare). · Explain WhyJun 10 2019, 10:57 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

Diff 15418

rust/hg-core/src/filepatterns.rs

/// that don't need to be transformed into a regex. /// that don't need to be transformed into a regex.
pub fn build_single_regex( pub fn build_single_regex(
kind: &[u8], kind: &[u8],
pat: &[u8], pat: &[u8],
globsuffix: &[u8], globsuffix: &[u8],
) -> Result<Vec<u8>, PatternError> { ) -> Result<Vec<u8>, PatternError> {
let enum_kind = parse_pattern_syntax(kind)?; let enum_kind = parse_pattern_syntax(kind)?;
if enum_kind == PatternSyntax::RootGlob if enum_kind == PatternSyntax::RootGlob
&& pat.iter().all(|b| GLOB_SPECIAL_CHARACTERS.contains(b)) && !pat.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b))
{ {
Ok(pat.to_vec()) let mut escaped = escape_pattern(pat);
escaped.extend(b"(?:/|$)");
Ok(escaped)
} else { } else {
Ok(_build_single_regex(enum_kind, pat, globsuffix)) Ok(_build_single_regex(enum_kind, pat, globsuffix))
} }
} }
lazy_static! { lazy_static! {
static ref SYNTAXES: HashMap<&'static [u8], &'static [u8]> = { static ref SYNTAXES: HashMap<&'static [u8], &'static [u8]> = {
let mut m = HashMap::new(); let mut m = HashMap::new();
vec![] vec![]
); );
let lines = b"glob:**.o"; let lines = b"glob:**.o";
assert_eq!( assert_eq!(
parse_pattern_file_contents(lines, b"file_path", false).0, parse_pattern_file_contents(lines, b"file_path", false).0,
vec![(b"relglob:**.o".to_vec(), 1, b"**.o".to_vec())] vec![(b"relglob:**.o".to_vec(), 1, b"**.o".to_vec())]
); );
} }
#[test]
fn test_build_single_regex_shortcut() {
assert_eq!(
br"(?:/|$)".to_vec(),
build_single_regex(b"rootglob", b"", b"").unwrap()
);
assert_eq!(
br"whatever(?:/|$)".to_vec(),
build_single_regex(b"rootglob", b"whatever", b"").unwrap()
);
assert_eq!(
br"[^/]*\.o".to_vec(),
build_single_regex(b"rootglob", b"*.o", b"").unwrap()
);
}
} }