justhtml 2.4.0__tar.gz → 2.4.1__tar.gz

{justhtml-2.4.0 → justhtml-2.4.1}/CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.4.1] - 2026-06-21
+
+### Fixed
+- Prevent the leading-line-feed exception for `<pre>`, `<listing>`, and `<textarea>` from leaking past intervening non-character tokens and removing a later newline.
+- Apply paragraph closing and leading-line-feed handling to `<pre>` and `<listing>` inside customizable `<select>` content.
+- Preserve U+000C FORM FEED in HTML text like browsers do, while retaining its intentional conversion to a space in XML-coercion mode.
+
 ## [2.4.0] - 2026-06-20
 
 ### Fixed

{justhtml-2.4.0 → justhtml-2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: justhtml
-Version: 2.4.0
+Version: 2.4.1
 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-2.4.0 → justhtml-2.4.1}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "justhtml"
 authors = [{ name = "Emil Stenström", email = "emil@emilstenstrom.se" }]
-version = "2.4.0"
+version = "2.4.1"
 description = "A pure Python HTML5 parser that just works."
 readme = "README.md"
 license = { file = "LICENSE" }

{justhtml-2.4.0 → justhtml-2.4.1}/src/justhtml/treebuilder/core.py

@@ -411,6 +411,11 @@ class TreeBuilder(TreeBuilderModesMixin):
     def process_token(self, token: Any) -> Any:
         # Optimization: Use type() identity check instead of isinstance
         token_type = type(token)
+        # The leading-LF exception for <pre>, <listing>, and <textarea>
+        # applies only to the immediately following token. Character tokens
+        # consume it in _append_text; any other token cancels it.
+        if self.ignore_lf and token_type is not CharacterTokens:
+            self.ignore_lf = False
         if token_type is DoctypeToken:
             # Check for foreign content first - DOCTYPE in SVG/MathML is a parse error
             if self.open_elements:
@@ -668,9 +673,6 @@ class TreeBuilder(TreeBuilderModesMixin):
                 if not text:
                     return
 
-        if "\f" in text:
-            text = text.replace("\f", " ")
-
         # Guard against empty stack
         if not self.open_elements:  # pragma: no cover
             return

{justhtml-2.4.0 → justhtml-2.4.1}/src/justhtml/treebuilder/modes.py

@@ -1677,6 +1677,10 @@ class TreeBuilderModesMixin:
                     self.ignore_lf = True
                     self.frameset_ok = False
                     return None
+                if name in {"pre", "listing"}:
+                    self._parse_error("unexpected-start-tag-in-select", tag_name=name)
+                    self._handle_body_start_pre_listing(token)
+                    return None
                 # Any other start tag is part of customizable select content.
                 self._parse_error("unexpected-start-tag-in-select", tag_name=name)
                 self._reconstruct_active_formatting_elements()

{justhtml-2.4.0 → justhtml-2.4.1}/tests/justhtml-tests/branch_coverage.dat

@@ -24,7 +24,7 @@
 |   <body>
 |     <math math>
 |       <math mi>
-|         " "
+|         ""
 
 
 #data

{justhtml-2.4.0 → justhtml-2.4.1}/tests/justhtml-tests/treebuilder_coverage.dat

@@ -21,7 +21,7 @@
 |   <body>
 |     <math math>
 |       <math mi>
-|         " text"
+|         "text"
 
 
 #data
@@ -75,7 +75,7 @@
 |   <head>
 |   <body>
 |     <select>
-|       " text"
+|       "text"
 
 
 #data
@@ -175,7 +175,7 @@
 |   <head>
 |   <body>
 |     <table>
-|       " "
+|       ""
 
 
 #data

{justhtml-2.4.0 → justhtml-2.4.1}/tests/test_treebuilder.py

@@ -250,6 +250,63 @@ class TestTreeBuilder(unittest.TestCase):
             [error.code for error in doc.errors],
         )
 
+    def test_leading_lf_skip_does_not_leak_past_non_character_tokens(self) -> None:
+        cases = {
+            "<div><pre></pre>\nX</div>": "<div><pre></pre>\nX</div>",
+            "<div><pre><code></code></pre>\nX</div>": "<div><pre><code></code></pre>\nX</div>",
+            "<div><pre><!--x--></pre>\nX</div>": "<div><pre><!--x--></pre>\nX</div>",
+            "<div><listing></listing>\nX</div>": "<div><listing></listing>\nX</div>",
+            "<div><textarea></textarea>\nX</div>": "<div><textarea></textarea>\nX</div>",
+            "<div><pre>\nX</pre></div>": "<div><pre>X</pre></div>",
+            "<div><listing>\nX</listing></div>": "<div><listing>X</listing></div>",
+            "<div><textarea>\nX</textarea></div>": "<div><textarea>X</textarea></div>",
+        }
+
+        for html, expected in cases.items():
+            with self.subTest(html=html):
+                doc = JustHTML(html, fragment=True, sanitize=False)
+                self.assertEqual(doc.to_html(pretty=False), expected)
+
+    def test_pre_and_listing_in_select_use_their_in_body_start_rules(self) -> None:
+        cases = {
+            "<select><pre>\nX</pre></select>": "<select><pre>X</pre></select>",
+            "<select><listing>\nX</listing></select>": "<select><listing>X</listing></select>",
+            "<select><p>P<pre>\nX</pre></select>": "<select><p>P</p><pre>X</pre></select>",
+            "<select><p>P<listing>\nX</listing></select>": "<select><p>P</p><listing>X</listing></select>",
+            "<select><pre><code></code>\nX</pre></select>": ("<select><pre><code></code>\nX</pre></select>"),
+        }
+
+        for html, expected in cases.items():
+            with self.subTest(html=html):
+                doc = JustHTML(html, fragment=True, sanitize=False)
+                self.assertEqual(doc.to_html(pretty=False), expected)
+
+    def test_form_feed_is_preserved_in_html_text_like_chromium(self) -> None:
+        cases = {
+            "<div>A\fB</div>": "<div>A\fB</div>",
+            "<pre>A\fB</pre>": "<pre>A\fB</pre>",
+            "<textarea>A\fB</textarea>": "<textarea>A\fB</textarea>",
+            "<style>A\fB</style>": "<style>A\fB</style>",
+            "<script>A\fB</script>": "<script>A\fB</script>",
+            "<table>A\fB<tr><td>C\fD</td></tr></table>": ("A\fB<table><tbody><tr><td>C\fD</td></tr></tbody></table>"),
+            "<svg><text>A\fB</text></svg>": "<svg><text>A\fB</text></svg>",
+        }
+
+        for html, expected in cases.items():
+            with self.subTest(html=html):
+                doc = JustHTML(html, fragment=True, sanitize=False)
+                self.assertEqual(doc.to_html(pretty=False), expected)
+
+    def test_form_feed_is_still_coerced_for_xml_output(self) -> None:
+        doc = JustHTML(
+            "<div>A\fB</div>",
+            fragment=True,
+            sanitize=False,
+            _tokenizer_opts=TokenizerOpts(xml_coercion=True),
+        )
+
+        self.assertEqual(doc.to_html(pretty=False), "<div>A B</div>")
+
     def test_select_end_tags_create_p_and_close_custom_children_like_chromium(self) -> None:
         cases = {
             "<select>x</p>": "<select>x<p></p></select>",