@willbooster/tree-sitter-html 1.0.0 → 1.0.2

package/README.md

@@ -10,13 +10,17 @@ HTML grammar for [tree-sitter](https://github.com/tree-sitter/tree-sitter), fork
 [tree-sitter/tree-sitter-html](https://github.com/tree-sitter/tree-sitter-html). We are grateful
 to its authors and contributors. This is not an official release of that project.
 
-This fork keeps the grammar and the external scanner of upstream's version 0.23.2 and generates the parser with the
+This fork is based on upstream's version 0.23.2 grammar and external scanner and generates the parser with the
 [WillBooster/tree-sitter](https://github.com/WillBooster/tree-sitter) generator. The parser carries that fork's own ABI
 number, so it loads only with the WillBooster runtime, version 2.0.0 or later
 ([willbooster-tree-sitter](https://crates.io/crates/willbooster-tree-sitter),
 [@willbooster/web-tree-sitter](https://www.npmjs.com/package/@willbooster/web-tree-sitter)); upstream's runtime rejects
 it. Input that contains NUL characters can parse to a different tree than with upstream's 0.23.2 parser, because the
-lexers that generator emits treat a NUL character as an ordinary character; other input parses to the same tree.
+lexers that generator emits treat a NUL character as an ordinary character. This grammar also accepts literal `>`
+characters in text nodes, which upstream 0.23.2 rejects. Its scanner requires an HTML tag-name boundary after
+`</script` and `</style`, so longer names and overlapping prefixes remain raw text. Closing-name comparisons
+fold only ASCII letters, and embedded NUL characters remain part of raw-text content. Incomplete elements
+retain their existing recovery behavior.
 
 ## Usage
 

package/grammar.js

@@ -126,9 +126,7 @@ module.exports = grammar({
 
     attribute_value: _ => /[^<>"'=\s]+/,
 
-    // An entity can be named, numeric (decimal), or numeric (hexacecimal). The
-    // longest entity name is 29 characters long, and the HTML spec says that
-    // no more will ever be added.
+    // HTML fixes the named-reference set: https://html.spec.whatwg.org/multipage/named-characters.html
     entity: _ => /&(#([xX][0-9a-fA-F]{1,6}|[0-9]{1,5})|[A-Za-z]{1,30});?/,
 
     quoted_attribute_value: $ => choice(
@@ -136,6 +134,6 @@ module.exports = grammar({
       seq('"', optional(alias(/[^"]+/, $.attribute_value)), '"'),
     ),
 
-    text: _ => /[^<>&\s]([^<>&]*[^<>&\s])?/,
+    text: _ => /[^<&\s]([^<&]*[^<&\s])?/,
   },
 });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@willbooster/tree-sitter-html",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "description": "HTML grammar for tree-sitter",
   "keywords": [
     "incremental",

package/tree-sitter.json

@@ -18,7 +18,7 @@
     }
   ],
   "metadata": {
-    "version": "1.0.0",
+    "version": "1.0.2",
     "license": "MIT",
     "description": "HTML grammar for tree-sitter",
     "authors": [