html-to-markdown 1.3.1__tar.gz → 1.3.3__tar.gz

{html_to_markdown-1.3.1 → html_to_markdown-1.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.3.1
+Version: 1.3.3
 Summary: Convert HTML to markdown
 Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
 License: MIT

{html_to_markdown-1.3.1 → html_to_markdown-1.3.3}/html_to_markdown/__main__.py

@@ -1,6 +1,6 @@
 import sys
 
-if __name__ == "__main__":
+def cli():
     from html_to_markdown.cli import main
 
     try:
@@ -9,3 +9,6 @@ if __name__ == "__main__":
     except ValueError as e:
         print(str(e), file=sys.stderr)  # noqa: T201
         sys.exit(1)
+
+if __name__ == "__main__":
+    cli()

{html_to_markdown-1.3.1 → html_to_markdown-1.3.3}/html_to_markdown/processing.py

@@ -89,6 +89,7 @@ def _process_tag(
     escape_misc: bool,
     escape_underscores: bool,
     strip: set[str] | None,
+    context_before: str = "",
 ) -> str:
     should_convert_tag = _should_convert_tag(tag_name=tag.name, strip=strip, convert=convert)
     tag_name: SupportedTag | None = (
@@ -129,12 +130,21 @@ def _process_tag(
                 escape_misc=escape_misc,
                 escape_underscores=escape_underscores,
                 strip=strip,
+                context_before=(context_before + text)[-2:],
             )
 
     if tag_name and should_convert_tag:
-        return converters_map[tag_name](  # type: ignore[call-arg]
+        rendered = converters_map[tag_name](  # type: ignore[call-arg]
             tag=tag, text=text, convert_as_inline=convert_as_inline
         )
+        # For headings, ensure two newlines before if not already present
+        # Edge case where the document starts with a \n and then a heading
+        if is_heading and context_before not in {"", "\n"}:
+            n_eol_to_add = 2 - (len(context_before) - len(context_before.rstrip("\n")))
+            if n_eol_to_add > 0:
+                prefix = "\n" * n_eol_to_add
+                return f"{prefix}{rendered}"
+        return rendered
 
     return text
 
@@ -275,13 +285,25 @@ def convert_to_markdown(
     if custom_converters:
         converters_map.update(cast("ConvertersMap", custom_converters))
 
-    return _process_tag(
-        source,
-        converters_map,
-        convert=_as_optional_set(convert),
-        convert_as_inline=convert_as_inline,
-        escape_asterisks=escape_asterisks,
-        escape_misc=escape_misc,
-        escape_underscores=escape_underscores,
-        strip=_as_optional_set(strip),
-    )
+    text = ""
+    for el in filter(lambda value: not isinstance(value, (Comment, Doctype)), source.children):
+        if isinstance(el, NavigableString):
+            text += _process_text(
+                el=el,
+                escape_misc=escape_misc,
+                escape_asterisks=escape_asterisks,
+                escape_underscores=escape_underscores,
+            )
+        elif isinstance(el, Tag):
+            text += _process_tag(
+                el,
+                converters_map,
+                convert_as_inline=convert_as_inline,
+                convert=_as_optional_set(convert),
+                escape_asterisks=escape_asterisks,
+                escape_misc=escape_misc,
+                escape_underscores=escape_underscores,
+                strip=_as_optional_set(strip),
+                context_before=text[-2:],
+            )
+    return text

{html_to_markdown-1.3.1 → html_to_markdown-1.3.3}/html_to_markdown.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: html-to-markdown
-Version: 1.3.1
+Version: 1.3.3
 Summary: Convert HTML to markdown
 Author-email: Na'aman Hirschfeld <nhirschfeld@gmail.com>
 License: MIT

{html_to_markdown-1.3.1 → html_to_markdown-1.3.3}/html_to_markdown.egg-info/SOURCES.txt

@@ -12,5 +12,6 @@ html_to_markdown/utils.py
 html_to_markdown.egg-info/PKG-INFO
 html_to_markdown.egg-info/SOURCES.txt
 html_to_markdown.egg-info/dependency_links.txt
+html_to_markdown.egg-info/entry_points.txt
 html_to_markdown.egg-info/requires.txt
 html_to_markdown.egg-info/top_level.txt

html_to_markdown-1.3.3/html_to_markdown.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+html_to_markdown = html_to_markdown.__main__:cli

{html_to_markdown-1.3.1 → html_to_markdown-1.3.3}/pyproject.toml

@@ -5,7 +5,7 @@ requires = [ "setuptools>=78.1" ]
 
 [project]
 name = "html-to-markdown"
-version = "1.3.1"
+version = "1.3.3"
 description = "Convert HTML to markdown"
 readme = "README.md"
 keywords = [ "converter", "html", "markdown", "text-extraction", "text-processing" ]
@@ -29,6 +29,7 @@ classifiers = [
   "Topic :: Utilities",
   "Typing :: Typed",
 ]
+scripts.html_to_markdown = "html_to_markdown.__main__:cli"
 
 dependencies = [
   "beautifulsoup4>=4.13.4",
@@ -58,8 +59,6 @@ html_to_markdown = [ "py.typed" ]
 [tool.hatch.build]
 skip-excluded-dirs = true
 
-scripts.html_to_markdown = "html_to_markdown.__main__:cli"
-
 [tool.ruff]
 target-version = "py39"
 line-length = 120