@willbooster/tree-sitter-html 3.0.0 → 4.0.0

package/README.md

@@ -20,18 +20,25 @@ number, so it loads only with the WillBooster runtime, version 2.x
 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. This grammar also accepts literal `>`
 characters and bare `&` in text nodes, which upstream 0.23.2 rejects. A bare `&` becomes its own `text` node beside
-surrounding text, while character references remain `entity` nodes. Text nodes include leading, trailing, and whitespace-only content, including whitespace between markup and character references. Its scanner requires an HTML tag-name boundary after
+surrounding text, while character references remain `entity` nodes. Text nodes include leading, trailing, and whitespace-only content, including whitespace between markup and character references. A DOCTYPE declaration exposes its uninterpreted body as a `doctype_value` child, including legacy PUBLIC or SYSTEM identifiers. Processing instructions use source-preserving
+`processing_instruction` nodes and directive highlights. Delimited `xml` and `xml-stylesheet` targets in any ASCII
+case, including XML declarations, and malformed targets produce `comment` nodes. Valid targets start with an ASCII
+letter or `_` and continue with ASCII letters, digits, `-` or `_`. A valid-target instruction without a closing `>`
+reports an error. In HTML-namespace `title` and `textarea`, tags, comments,
+and instructions stay `text`, while character references remain `entity` nodes. Content inside `iframe`, `xmp`,
+`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
 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
 recovery errors. Unterminated style elements still report an error. Void elements close
-before following text, entities, and complete comments, which become siblings instead of children.
+before following text, entities, complete comments, and processing instructions, which become siblings instead of children.
 Scanner serialization stores the open-tag stack from its innermost tag, compressing runs of identical tags, so active
-void, script, and style elements retain their identities when deeply nested. When deep nesting of distinct tags
-exceeds its fixed-size buffer, the outermost tag identities are lost, which can produce recovery errors when those
-tags close. Custom tag names longer than 255 bytes are truncated in serialized state.
+void, script, and style elements retain their identities when deeply nested. When distinct tags exceed the fixed-size
+buffer, serialization prioritizes inner tags and outer namespace boundaries, replacing ordinary outer tags with unknown
+runs. Lost tag identities can still produce recovery errors when those tags close. Custom tag names longer than 255 bytes are truncated in serialized state.
 Malformed input after a void element can replace its enclosing element with an `ERROR` node during recovery.
 
 Attribute values retain their complete `attribute_value` range and expose recognized named and numeric character
@@ -91,7 +98,7 @@ fuzzed with:
 ```toml
 [dependencies]
 tree-sitter = { package = "willbooster-tree-sitter", version = "2.0.0" }
-tree-sitter-html = { package = "willbooster-tree-sitter-html", version = "3" }
+tree-sitter-html = { package = "willbooster-tree-sitter-html", version = "4" }
 ```
 
 ```rust

package/grammar.js

@@ -25,6 +25,9 @@ module.exports = grammar({
     $._implicit_end_tag,
     $.raw_text,
     $.comment,
+    $.processing_instruction,
+    $._element_text,
+    $._unfinished_processing_instruction,
     $._attribute_entity,
     $._unquoted_attribute_entity,
     $._attribute_ampersand,
@@ -37,14 +40,19 @@ module.exports = grammar({
     doctype: $ => seq(
       '<!',
       alias($._doctype, 'doctype'),
-      /[^>]+/,
+      $.doctype_value,
       '>',
     ),
 
     _doctype: _ => /[Dd][Oo][Cc][Tt][Yy][Pp][Ee]/,
 
+    doctype_value: _ => repeat1(/[^>]+/),
+
     _node: $ => choice(
       $.doctype,
+      $.processing_instruction,
+      seq($._unfinished_processing_instruction, '>'),
+      alias($._element_text, $.text),
       $.comment,
       $.entity,
       $.text,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@willbooster/tree-sitter-html",
-  "version": "3.0.0",
+  "version": "4.0.0",
   "description": "HTML grammar for tree-sitter",
   "keywords": [
     "incremental",

package/queries/highlights.scm

@@ -1,6 +1,7 @@
 (tag_name) @tag
 (erroneous_end_tag_name) @tag.error
 (doctype) @constant
+(processing_instruction) @keyword.directive
 (attribute_name) @attribute
 (attribute_value) @string
 (comment) @comment

package/src/node-types.json

@@ -40,6 +40,21 @@
   {
     "type": "doctype",
     "named": true,
+    "fields": {},
+    "children": {
+      "multiple": false,
+      "required": true,
+      "types": [
+        {
+          "type": "doctype_value",
+          "named": true
+        }
+      ]
+    }
+  },
+  {
+    "type": "doctype_value",
+    "named": true,
     "fields": {}
   },
   {
@@ -71,6 +86,10 @@
           "type": "erroneous_end_tag",
           "named": true
         },
+        {
+          "type": "processing_instruction",
+          "named": true
+        },
         {
           "type": "script_element",
           "named": true
@@ -118,6 +137,10 @@
           "type": "erroneous_end_tag",
           "named": true
         },
+        {
+          "type": "processing_instruction",
+          "named": true
+        },
         {
           "type": "script_element",
           "named": true
@@ -322,6 +345,10 @@
     "type": "erroneous_end_tag_name",
     "named": true
   },
+  {
+    "type": "processing_instruction",
+    "named": true
+  },
   {
     "type": "raw_text",
     "named": true

package/tree-sitter.json

@@ -20,7 +20,7 @@
     }
   ],
   "metadata": {
-    "version": "3.0.0",
+    "version": "4.0.0",
     "license": "MIT",
     "description": "HTML grammar for tree-sitter",
     "authors": [