Mercurial > public > mercurial-scm > hg

diff rust/hg-core/src/filepatterns.rs @ 44802:e0414fcd35e0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
rust-filepatterns: match exact `rootglob`s with a `HashSet`, not in the regex This optimization yields some very interesting results in `rootglob`-heavy repositories. I build a test repository of the following structure: ``` root /<uuid>/build/empty_file ... repeat for 4000 entries ``` and a `.hgignore` containing the corresponding 4000 `rootglob` entries pointing to all `build/` folders. Rust+c `hg status` goes from 350ms down to 110ms. Differential Revision: https://phab.mercurial-scm.org/D8491
author Rapha?l Gom?s <rgomes@octobus.net>
date Wed, 06 May 2020 11:17:27 +0200
parents 496868f1030c
children ad1ec40975aa
line wrap: on
line diff
--- a/rust/hg-core/src/filepatterns.rs	Wed Apr 15 16:43:05 2020 -0400
+++ b/rust/hg-core/src/filepatterns.rs	Wed May 06 11:17:27 2020 +0200
@@ -271,7 +271,7 @@
 /// that don't need to be transformed into a regex.
 pub fn build_single_regex(
     entry: &IgnorePattern,
-) -> Result<Vec<u8>, PatternError> {
+) -> Result<Option<Vec<u8>>, PatternError> {
     let IgnorePattern {
         pattern, syntax, ..
     } = entry;
@@ -288,16 +288,11 @@
     if *syntax == PatternSyntax::RootGlob
         && !pattern.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b))
     {
-        // The `regex` crate adds `.*` to the start and end of expressions
-        // if there are no anchors, so add the start anchor.
-        let mut escaped = vec![b'^'];
-        escaped.extend(escape_pattern(&pattern));
-        escaped.extend(GLOB_SUFFIX);
-        Ok(escaped)
+        Ok(None)
     } else {
         let mut entry = entry.clone();
         entry.pattern = pattern;
-        Ok(_build_single_regex(&entry))
+        Ok(Some(_build_single_regex(&entry)))
     }
 }
 
@@ -628,7 +623,7 @@
                 Path::new("")
             ))
             .unwrap(),
-            br"(?:.*/)?rust/target(?:/|$)".to_vec(),
+            Some(br"(?:.*/)?rust/target(?:/|$)".to_vec()),
         );
     }
 
@@ -641,7 +636,7 @@
                 Path::new("")
             ))
             .unwrap(),
-            br"^\.(?:/|$)".to_vec(),
+            None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
@@ -650,7 +645,7 @@
                 Path::new("")
             ))
             .unwrap(),
-            br"^whatever(?:/|$)".to_vec(),
+            None,
         );
         assert_eq!(
             build_single_regex(&IgnorePattern::new(
@@ -659,7 +654,7 @@
                 Path::new("")
             ))
             .unwrap(),
-            br"^[^/]*\.o(?:/|$)".to_vec(),
+            Some(br"^[^/]*\.o(?:/|$)".to_vec()),
         );
     }
 }