@willbooster/tree-sitter-html 4.0.1 → 6.0.0

package/README.md

@@ -14,7 +14,7 @@ to its authors and contributors. This is not an official release of that project
 
 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.x
+number `0x57420006`, so it loads with the WillBooster runtime, version 7.0.5 or later in the 7.x series
 ([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
@@ -29,7 +29,11 @@ and instructions stay `text`, while character references remain `entity` nodes.
 `noembed`, and `noframes` also stays `text` up to the element's own closing tag. `plaintext` retains all remaining
 input as `text`, including closing tags. The grammar's 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. Script content follows
+fold only ASCII letters, and embedded NUL characters remain part of raw-text content. In the HTML namespace, a trailing
+slash on a `script` or `style` opening tag remains part of its `start_tag`; it does not close the element, so subsequent
+content remains raw text until the matching end tag. Self-closing foreign-namespace `script` and `style` use ordinary element nodes. Complete foreign
+elements retain raw-text nodes and injection ranges, including CDATA delimiters. MathML `annotation-xml` with an `encoding` value of `text/html` or `application/xhtml+xml`
+uses HTML parsing for its children. Encoding comparisons ignore ASCII case and decode character references. Script content follows
 HTML escaped and double-escaped states, so closing-tag text inside a double escape remains raw text. A script that reaches
 EOF while scanning raw content closes implicitly without an error: its `script_element` has no `end_tag` child, and its
 remaining content stays available for JavaScript injection. Incomplete closing tags such as `</script` still report
@@ -51,7 +55,8 @@ between attributes. Comment-shaped text inside a quoted value remains part of th
 ## Usage
 
 The npm package ships `tree-sitter-html.wasm` for
-[@willbooster/web-tree-sitter](https://www.npmjs.com/package/@willbooster/web-tree-sitter) version 2.x, which runs in Node.js, Bun, browsers, and Cloudflare Workers. In Node.js and Bun, load the grammar from its path:
+[@willbooster/web-tree-sitter](https://www.npmjs.com/package/@willbooster/web-tree-sitter) version 7.0.5 or later in the 7.x series, which runs in Node.js, Bun, browsers, and Cloudflare Workers.
+In Node.js and Bun, load the grammar from its path:
 
 ```js
 import { fileURLToPath } from 'node:url';
@@ -97,8 +102,8 @@ fuzzed with:
 
 ```toml
 [dependencies]
-tree-sitter = { package = "willbooster-tree-sitter", version = "2.0.0" }
-tree-sitter-html = { package = "willbooster-tree-sitter-html", version = "4" }
+tree-sitter = { package = "willbooster-tree-sitter", version = "7.0.5" }
+tree-sitter-html = { package = "willbooster-tree-sitter-html", version = "5" }
 ```
 
 ```rust

package/grammar.js

@@ -56,6 +56,7 @@ module.exports = grammar({
       $.comment,
       $.entity,
       $.text,
+      alias('&', $.text),
       $.element,
       $.script_element,
       $.style_element,
@@ -94,14 +95,14 @@ module.exports = grammar({
       '<',
       alias($._script_start_tag_name, $.tag_name),
       repeat($.attribute),
-      '>',
+      choice('>', '/>'),
     ),
 
     style_start_tag: $ => seq(
       '<',
       alias($._style_start_tag_name, $.tag_name),
       repeat($.attribute),
-      '>',
+      choice('>', '/>'),
     ),
 
     self_closing_tag: $ => seq(
@@ -164,6 +165,6 @@ module.exports = grammar({
       )), $.attribute_value)), '"'),
     ),
 
-    text: _ => token.immediate(/[^<&]+|&/),
+    text: _ => token(prec(1, /[^<&]+/)),
   },
 });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@willbooster/tree-sitter-html",
-  "version": "4.0.1",
+  "version": "6.0.0",
   "description": "HTML grammar for tree-sitter",
   "keywords": [
     "incremental",
@@ -47,7 +47,7 @@
     "@willbooster/oxfmt-config": "1.2.2",
     "@willbooster/oxlint-config": "1.4.8",
     "@willbooster/wb": "22.26.1",
-    "@willbooster/web-tree-sitter": "2.0.27",
+    "@willbooster/web-tree-sitter": "7.0.5",
     "conventional-changelog-conventionalcommits": "10.4.1",
     "lefthook": "2.2.1",
     "oxfmt": "0.72.0",
@@ -60,7 +60,7 @@
     "wrangler": "4.149.0"
   },
   "peerDependencies": {
-    "@willbooster/web-tree-sitter": "^2.0.0"
+    "@willbooster/web-tree-sitter": "^7.0.5"
   },
   "peerDependenciesMeta": {
     "@willbooster/web-tree-sitter": {

package/tree-sitter.json

@@ -20,7 +20,7 @@
     }
   ],
   "metadata": {
-    "version": "4.0.1",
+    "version": "6.0.0",
     "license": "MIT",
     "description": "HTML grammar for tree-sitter",
     "authors": [