justhtml 3.6.0__tar.gz → 3.6.1__tar.gz

{justhtml-3.6.0 → justhtml-3.6.1}/CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [3.6.1] - 2026-07-13
+
+### Fixed
+
+- Keep processing instructions inside a scripting-disabled head `noscript`, and process them in body mode inside templates as required by the latest WHATWG parsing rules.
+
+### Changed
+
+- Move raw parser input/output regressions from Python unit tests into the shared tree-construction fixture format.
+
 ## [3.6.0] - 2026-07-13
 
 ### Fixed

{justhtml-3.6.0 → justhtml-3.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: justhtml
-Version: 3.6.0
+Version: 3.6.1
 Summary: A pure Python HTML5 parser that just works.
 Project-URL: Homepage, https://github.com/emilstenstrom/justhtml
 Project-URL: Issues, https://github.com/emilstenstrom/justhtml/issues

{justhtml-3.6.0 → justhtml-3.6.1}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "justhtml"
 authors = [{ name = "Emil Stenström", email = "emil@emilstenstrom.se" }]
-version = "3.6.0"
+version = "3.6.1"
 description = "A pure Python HTML5 parser that just works."
 readme = "README.md"
 license = { file = "LICENSE" }

{justhtml-3.6.0 → justhtml-3.6.1}/src/justhtml/parser/engine.py

@@ -1253,8 +1253,32 @@ class ParseEngine:
         if self._has_null and "\0" in data:
             data = data.replace("\0", "\ufffd")
         node = ProcessingInstruction(data=data)
+        self._move_head_template_to_body_for_processing_instruction()
         self._append_misc_node(node, source_pos)
 
+    def _move_head_template_to_body_for_processing_instruction(self) -> None:
+        if self._fragment or self._head is None or self._html is None:
+            return
+        stack = self._stack
+        template_idx = self._open_template_index()
+        if template_idx is None:
+            return
+        outer_template_idx = template_idx
+        for idx in range(template_idx, 0, -1):
+            candidate = stack[idx]
+            if type(candidate) is Template and candidate.parent is self._head:
+                outer_template_idx = idx
+        template = stack[outer_template_idx]
+        if type(template) is not Template or template.parent is not self._head:
+            return
+        head_children = self._head.children
+        if head_children is not None:  # pragma: no branch - Document head always owns a children list
+            head_children.remove(template)
+        self._append(self._body, template)
+        self._stack = _CountingStack([self._doc, self._html, self._body, *stack[outer_template_idx:]])  # type: ignore[list-item]
+        self._body_mode_seen = True
+        self._after_head = False
+
     def _processing_instruction_data(self, content_start: int, content_end: int) -> str | None:
         html = self._html_input
         if content_start >= content_end or not _is_processing_instruction_name_start(html[content_start]):
@@ -1632,7 +1656,7 @@ class ParseEngine:
                     append_text(html[lt:end] if gt == -1 else html[lt : gt + 1], lt)
                     pos = end if gt == -1 else gt + 1
                     continue
-                if self._raw_mode and len(self._stack) > 1 and self._stack[-1].name in _RAWTEXT_ELEMENT_TAGS:
+                if self._raw_mode and len(self._stack) > 1 and self._stack[-1].name in self._rawtext_element_tags:
                     comment_end = end if gt == -1 else gt
                     append_text(html[lt:comment_end] if gt == -1 else html[lt : gt + 1], lt)
                     pos = end if gt == -1 else gt + 1

justhtml-3.6.1/tests/justhtml-tests/character_preprocessing.dat

@@ -0,0 +1,252 @@
+#data
+<math><mi>\x00</mi></math>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+(1,11): unexpected-null-character
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <math math>
+|       <math mi>
+
+#data
+<math><mi>\x00\x0c</mi></math>
+#errors
+(1,6): expected-doctype-but-got-start-tag
+(1,11): unexpected-null-character
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <math math>
+|       <math mi>
+|         ""
+
+#data
+<math><mi>   </mi></math>
+#errors
+(1,1): expected-doctype-but-got-start-tag
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <math math>
+|       <math mi>
+|         "   "
+
+#data
+<math><mi>\x0ctext</mi></math>
+#errors
+(1,1): expected-doctype-but-got-start-tag
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <math math>
+|       <math mi>
+|         "text"
+
+#data
+<select>\x0ctext</select>
+#errors
+(1,1): expected-doctype-but-got-start-tag
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <select>
+|       "text"
+
+#data
+<table>\x00</table>
+#errors
+(1,7): expected-doctype-but-got-start-tag
+(1,8): unexpected-null-character
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <table>
+
+#data
+<head></head>\x00
+#errors
+(1,6): expected-doctype-but-got-start-tag
+(1,14): unexpected-null-character
+
+#document
+| <html>
+|   <head>
+|   <body>
+
+#data
+<table>\x0c</table>
+#errors
+(1,1): expected-doctype-but-got-start-tag
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <table>
+|       ""
+
+#data
+<!doctype html>\x00
+#errors
+(1,16): unexpected-null-character
+
+#document
+| <!DOCTYPE html>
+| <html>
+|   <head>
+|   <body>
+
+
+#data
+<!--a\x00b-->
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,6): unexpected-null-character
+#document
+| <!-- a�b -->
+| <html>
+|   <head>
+|   <body>
+
+#data
+<frameset>\x0d\x0a
+#errors
+#document
+| <html>
+|   <head>
+|   <frameset>
+|     "
+"
+#data
+<!--a-
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,6): eof-in-comment
+#document
+| <!-- a -->
+| <html>
+|   <head>
+|   <body>
+
+#data
+<!x\x0d\x0ay>
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <!-- x
+y -->
+| <html>
+|   <head>
+|   <body>
+
+#data
+<\x00div>
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,2): unexpected-null-character
+#document
+| <html>
+|   <head>
+|   <body>
+|     "<�div>"
+
+#data
+</>
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <html>
+|   <head>
+|   <body>
+
+#data
+\x00\x0cA
+#errors
+(1,1): unexpected-null-character
+(1,1): expected-doctype-but-got-chars
+#document
+| <html>
+|   <head>
+|   <body>
+|     "A"
+
+#data
+<!DOCTYPE\x00html>
+#errors
+(1,10): unexpected-null-character
+(1,15): unknown-doctype
+#document
+| <!DOCTYPE �html>
+| <html>
+|   <head>
+|   <body>
+
+#data
+&#x;
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <html>
+|   <head>
+|   <body>
+|     "&#x;"
+
+#data
+<!--first--><!DOCTYPE\x0d\x0ahtml>
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <!-- first -->
+| <!DOCTYPE html>
+| <html>
+|   <head>
+|   <body>
+
+#data
+<o\x0ce="\x0d">
+#errors
+(1,9): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <o>
+|       e="
+"
+
+#data
+<d 2="\x0d">
+#errors
+(1,9): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <d>
+|       2="
+"
+
+#data
+<a 8=&#13\x0d>
+#errors
+(1,11): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <a>
+|       8="
+"

justhtml-3.6.1/tests/justhtml-tests/document_shell_recovery.dat

@@ -0,0 +1,366 @@
+#data
+</template>
+#errors
+(1,1): expected-doctype-but-got-end-tag
+(1,11): unexpected-end-tag-before-html
+
+#document
+| <html>
+|   <head>
+|   <body>
+
+#data
+<body><input type="hidden">
+#errors
+(1,1): expected-doctype-but-got-start-tag
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     <input>
+|       type="hidden"
+
+#data
+<html><body><html attr="test">
+#errors
+(1,1): expected-doctype-but-got-start-tag
+(1,30): unexpected-start-tag
+
+#document
+| <html>
+|   attr="test"
+|   <head>
+|   <body>
+
+#data
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//" "http://www.w3.org/TR/html4/loose.dtd">
+#errors
+(1,100): unknown-doctype
+
+#document
+| <!DOCTYPE html "-//W3C//DTD HTML 4.01 Transitional//" "http://www.w3.org/TR/html4/loose.dtd">
+| <html>
+|   <head>
+|   <body>
+
+#data
+<head></head></template>text
+#errors
+(1,1): expected-doctype-but-got-start-tag
+(1,24): unexpected-end-tag
+
+#document
+| <html>
+|   <head>
+|   <body>
+|     "text"
+
+#data
+<meta><!--x-->
+#errors
+(1,1): expected-doctype-but-got-start-tag
+
+#document
+| <html>
+|   <head>
+|     <meta>
+|     <!-- x -->
+|   <body>
+
+#data
+<!DOCTYPE 
+#errors
+(1,10): eof-in-tag
+(1,10): unknown-doctype
+
+#document
+| <!DOCTYPE  >
+| <html>
+|   <head>
+|   <body>
+
+#data
+<!doctype html>x<head><meta>
+#errors
+
+#document
+| <!DOCTYPE html>
+| <html>
+|   <head>
+|   <body>
+|     "x"
+|     <meta>
+
+#data
+<!DOCTYPE html foo><p><table>
+#errors
+(1,19): unknown-doctype
+
+#document
+| <!DOCTYPE html>
+| <html>
+|   <head>
+|   <body>
+|     <p>
+|       <table>
+
+
+#data
+<div a="unterminated
+#errors
+#document
+| <html>
+|   <head>
+|   <body>
+
+#data
+<DIV A=1 a=2>x</DIV>
+#errors
+#document
+| <html>
+|   <head>
+|   <body>
+|     <div>
+|       a="1"
+|       "x"
+
+#data
+<! first><?second
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <!--  first -->
+| <html>
+|   <head>
+|   <body>
+
+#data
+<div \x00name=value>
+#errors
+(1,6): unexpected-null-character
+(1,17): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <div>
+|       �name="value"
+
+#data
+<source\x00 x=y>
+#errors
+(1,8): unexpected-null-character
+(1,13): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <source�>
+|       x="y"
+
+#data
+<html 1name='\x00'>
+#errors
+(1,14): unexpected-null-character
+(1,16): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   1name="�"
+|   <head>
+|   <body>
+
+#data
+<source\x00 '='<script>alert(1)</script>'>
+#errors
+(1,8): unexpected-null-character
+(1,20): expected-doctype-but-got-start-tag
+(1,29): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <source�>
+|       '="<script>alert(1)</script>"
+
+#data
+</html><script>
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,1): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <script>
+
+#data
+</head></html><y>
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,1): unexpected-end-tag
+(1,8): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <y>
+
+#data
+</html><</\x20
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,1): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     "<"
+|     <!--   -->
+
+#data
+<i></body></f><
+#errors
+(1,3): expected-doctype-but-got-start-tag
+(1,4): unexpected-end-tag
+(1,11): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <i>
+|       "<"
+
+#data
+</>&#9
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <html>
+|   <head>
+|   <body>
+
+#data
+<!>&#xD
+#errors
+(1,1): expected-doctype-but-got-chars
+#document
+| <!--  -->
+| <html>
+|   <head>
+|   <body>
+
+#data
+<!DOCTYPE>&#xD
+#errors
+(1,10): unknown-doctype
+#document
+| <!DOCTYPE >
+| <html>
+|   <head>
+|   <body>
+
+#data
+</e>&#9
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,1): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+
+#data
+</head></html>2</t></-
+#errors
+(1,1): expected-doctype-but-got-chars
+(1,1): unexpected-end-tag
+(1,8): unexpected-end-tag
+(1,16): unexpected-end-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     "2"
+|     <!-- - -->
+
+#data
+<body id='a'><div><body id='b'>x</div>
+#errors
+(1,13): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     id="a"
+|     <div>
+|       "x"
+
+#data
+<div><li>x<body class='late'>y
+#errors
+(1,5): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     class="late"
+|     <div>
+|       <li>
+|         "xy"
+
+#data
+<div>x<head><title>ignored</title></head>y
+#errors
+(1,5): expected-doctype-but-got-start-tag
+#document
+| <html>
+|   <head>
+|   <body>
+|     <div>
+|       "x"
+|       <title>
+|         "ignored"
+|       "y"
+
+#data
+<!DOCTYPE html><body><command>A
+#errors
+#document
+| <!DOCTYPE html>
+| <html>
+|   <head>
+|   <body>
+|     <command>
+|       "A"
+
+#data
+<head></head>\x0a
+#errors
+#document
+| <html>
+|   <head>
+|   "
+"
+|   <body>
+
+#data
+<!doctype html><div></span\x0a>
+#errors
+#document
+| <!DOCTYPE html>
+| <html>
+|   <head>
+|   <body>
+|     <div>
+
+#data
+İ<!DOCTYPE html><p>x</p>
+#errors
+#document
+| <html>
+|   <head>
+|   <body>
+|     "İ"
+|     <p>
+|       "x"