html-to-markdown 1.14.0__tar.gz → 1.14.1__tar.gz

{html_to_markdown-1.14.0 → html_to_markdown-1.14.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.14.0
+Version: 1.14.1
 Summary: A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options
 Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
 License: MIT

{html_to_markdown-1.14.0 → html_to_markdown-1.14.1}/html_to_markdown/processing.py

@@ -314,11 +314,12 @@ def _process_text(
             if len(ancestor_names) > 10:
                 break
 
-    in_pre = bool(ancestor_names.intersection({"pre"}))
+    in_pre = bool(ancestor_names.intersection({"pre"})) or parent_name == "pre"
 
     text = whitespace_handler.process_text_whitespace(text, el, in_pre=in_pre)
 
-    if not ancestor_names.intersection({"pre", "code", "kbd", "samp"}):
+    code_like_tags = {"pre", "code", "kbd", "samp"}
+    if not (ancestor_names.intersection(code_like_tags) or parent_name in code_like_tags):
         text = escape(
             text=text,
             escape_misc=escape_misc,
@@ -617,7 +618,6 @@ def convert_to_markdown(
                         first_child.replace_with(new_text)
                         needs_leading_space_fix = False
 
-            # Fix html5lib whitespace handling to match other parsers
             if parser == "html5lib":
                 body = source.find("body")
                 if body and isinstance(body, Tag):
@@ -632,7 +632,6 @@ def convert_to_markdown(
                         first_child = children[0]
                         original_text = str(first_child)
 
-                        # Preserve leading whitespace from original if html5lib stripped it
                         leading_ws = ""
                         for char in original_source:
                             if char in " \t\n\r":
@@ -640,7 +639,6 @@ def convert_to_markdown(
                             else:
                                 break
 
-                        # Create normalized text: restore leading whitespace only
                         normalized_text = original_text
                         if leading_ws and not normalized_text.startswith(leading_ws):
                             normalized_text = leading_ws + normalized_text

{html_to_markdown-1.14.0 → html_to_markdown-1.14.1}/html_to_markdown.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.14.0
+Version: 1.14.1
 Summary: A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options
 Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
 License: MIT

{html_to_markdown-1.14.0 → html_to_markdown-1.14.1}/pyproject.toml

@@ -5,7 +5,7 @@ requires = [ "setuptools>=78.1" ]
 
 [project]
 name = "html-to-markdown"
-version = "1.14.0"
+version = "1.14.1"
 description = "A modern, type-safe Python library for converting HTML to Markdown with comprehensive tag support and customizable options"
 readme = "README.md"
 keywords = [
@@ -61,8 +61,10 @@ dev = [
   "beautifulsoup4[html5lib]>=4.13.5",
   "beautifulsoup4[lxml]>=4.13.5",
   "covdefaults>=2.3",
+  "memray>=1.18; sys_platform!='win32'",
   "mypy>=1.18.2",
   "pre-commit>=4.3",
+  "psutil>=7.1; sys_platform!='win32'",
   "pytest>=8.4.2",
   "pytest-benchmark>=5.1",
   "pytest-cov>=7",