From cfa882557eb24cf0bed0485d0811d3f35832ba4b Mon Sep 17 00:00:00 2001
From: A-Walrus <58790821+A-Walrus@users.noreply.github.com>
Date: Fri, 5 Aug 2022 03:12:14 +0300
Subject: [PATCH] Fix nondeterministic highlighting (#3275)

* Fix nondeterministic highlighting

This is done by prefering matches in the begining, ie for
`keyword.function`, `keyword` is a better match than `function`.

* Use all positions and not just leftmost

Fixes possible edgecase with something like `function.method.builtin`
and the queries `function.builtin` and `function.method`

* Switch to bitmask for slightly better performance

* Make matches from the start of string

Also change comments to match new behaviour
---
 helix-core/src/syntax.rs | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/helix-core/src/syntax.rs b/helix-core/src/syntax.rs
index 4188d1481..99922d377 100644
--- a/helix-core/src/syntax.rs
+++ b/helix-core/src/syntax.rs
@@ -1356,8 +1356,8 @@ impl HighlightConfiguration {
     /// Tree-sitter syntax-highlighting queries specify highlights in the form of dot-separated
     /// highlight names like `punctuation.bracket` and `function.method.builtin`. Consumers of
     /// these queries can choose to recognize highlights with different levels of specificity.
-    /// For example, the string `function.builtin` will match against `function.method.builtin`
-    /// and `function.builtin.constructor`, but will not match `function.method`.
+    /// For example, the string `function.builtin` will match against `function.builtin.constructor`
+    /// but will not match `function.method.builtin` and `function.method`.
     ///
     /// When highlighting, results are returned as `Highlight` values, which contain the index
     /// of the matched highlight this list of highlight names.
@@ -1377,11 +1377,13 @@ impl HighlightConfiguration {
                     let recognized_name = recognized_name;
                     let mut len = 0;
                     let mut matches = true;
-                    for part in recognized_name.split('.') {
-                        len += 1;
-                        if !capture_parts.contains(&part) {
-                            matches = false;
-                            break;
+                    for (i, part) in recognized_name.split('.').enumerate() {
+                        match capture_parts.get(i) {
+                            Some(capture_part) if *capture_part == part => len += 1,
+                            _ => {
+                                matches = false;
+                                break;
+                            }
                         }
                     }
                     if matches && len > best_match_len {