mdformat-space-control 0.3.2__tar.gz → 0.4.1__tar.gz

{mdformat_space_control-0.3.2 → mdformat_space_control-0.4.1}/CLAUDE.md

@@ -32,7 +32,7 @@ uv run python -m pytest tests/test_editorconfig.py    # Run specific test file
 mdformat_space_control/
 ├── __init__.py    # Public API exports, version
 ├── config.py      # EditorConfig lookup, file context tracking
-└── plugin.py      # List renderers (RENDERERS dict)
+└── plugin.py      # Renderers, postprocessors, parser extensions
 ```
 
 **Key components:**

{mdformat_space_control-0.3.2 → mdformat_space_control-0.4.1}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: mdformat_space_control
-Version: 0.3.2
-Summary: An mdformat plugin for space control: EditorConfig indentation, tight lists, frontmatter spacing, and wikilinks.
+Version: 0.4.1
+Summary: An mdformat plugin for space control: EditorConfig indentation, tight lists, frontmatter spacing, smart dash conversion, explicit line breaks, and wikilinks.
 Project-URL: Homepage, https://github.com/jdmonaco/mdformat-space-control
 Author-email: Joseph Monaco <joe@selfmotion.net>
 License-File: LICENSE
-Keywords: editorconfig,formatter,frontmatter,indentation,lists,markdown,mdformat,obsidian,wikilink
+Keywords: editorconfig,formatter,frontmatter,indentation,lists,markdown,mdformat,obsidian,typography,wikilink
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -39,6 +39,7 @@ An [mdformat](https://github.com/executablebooks/mdformat) plugin that provides
 - **Consecutive blank line normalization**: Limits runs of 3+ empty lines to a maximum of 2
 - **Trailing whitespace removal**: Strips trailing whitespace outside code blocks
 - **Escaped link repair**: Fixes malformed multi-line links from web-clipped content
+- **Smart dash conversion**: Converts `--` to en-dash (–) and `---` to em-dash (—), preserving code blocks and inline code
 - **Wikilink preservation**: Handles Obsidian-style `[[links]]`, `[[links|aliases]]`, `[[page#heading]]`, `[[page#^blockid]]`, and `![[embeds]]`
 - **Explicit line breaks**: Converts soft breaks to hard breaks (`\` + newline) so source line breaks render visually in all Markdown renderers
 
@@ -173,6 +174,27 @@ finally:
     set_current_file(None)
 ```
 
+### Smart Dash Conversion
+
+Markdown dash sequences are automatically converted to their Unicode equivalents:
+
+- `--` → en-dash (–, U+2013)
+- `---` → em-dash (—, U+2014)
+
+**Before:**
+```markdown
+The result---unexpected as it was---changed everything.
+Pages 10--20 of the report.
+```
+
+**After:**
+```markdown
+The result—unexpected as it was—changed everything.
+Pages 10–20 of the report.
+```
+
+Dashes are preserved inside fenced code blocks and inline code spans. Thematic breaks (`---`) and frontmatter delimiters are not affected. Sequences of 4+ dashes are left unchanged.
+
 ### Wikilink Preservation
 
 Obsidian-style wikilinks are preserved during formatting:

{mdformat_space_control-0.3.2 → mdformat_space_control-0.4.1}/README.md

@@ -11,6 +11,7 @@ An [mdformat](https://github.com/executablebooks/mdformat) plugin that provides
 - **Consecutive blank line normalization**: Limits runs of 3+ empty lines to a maximum of 2
 - **Trailing whitespace removal**: Strips trailing whitespace outside code blocks
 - **Escaped link repair**: Fixes malformed multi-line links from web-clipped content
+- **Smart dash conversion**: Converts `--` to en-dash (–) and `---` to em-dash (—), preserving code blocks and inline code
 - **Wikilink preservation**: Handles Obsidian-style `[[links]]`, `[[links|aliases]]`, `[[page#heading]]`, `[[page#^blockid]]`, and `![[embeds]]`
 - **Explicit line breaks**: Converts soft breaks to hard breaks (`\` + newline) so source line breaks render visually in all Markdown renderers
 
@@ -145,6 +146,27 @@ finally:
     set_current_file(None)
 ```
 
+### Smart Dash Conversion
+
+Markdown dash sequences are automatically converted to their Unicode equivalents:
+
+- `--` → en-dash (–, U+2013)
+- `---` → em-dash (—, U+2014)
+
+**Before:**
+```markdown
+The result---unexpected as it was---changed everything.
+Pages 10--20 of the report.
+```
+
+**After:**
+```markdown
+The result—unexpected as it was—changed everything.
+Pages 10–20 of the report.
+```
+
+Dashes are preserved inside fenced code blocks and inline code spans. Thematic breaks (`---`) and frontmatter delimiters are not affected. Sequences of 4+ dashes are left unchanged.
+
 ### Wikilink Preservation
 
 Obsidian-style wikilinks are preserved during formatting:

{mdformat_space_control-0.3.2 → mdformat_space_control-0.4.1}/mdformat_space_control/__init__.py

@@ -1,6 +1,6 @@
-"""An mdformat plugin for space control: EditorConfig indentation, tight lists, frontmatter spacing, explicit line breaks, and wikilinks."""
+"""An mdformat plugin for space control: EditorConfig indentation, tight lists, frontmatter spacing, smart dash conversion, explicit line breaks, and wikilinks."""
 
-__version__ = "0.3.2"
+__version__ = "0.4.1"
 
 from .config import (
     get_current_file,

{mdformat_space_control-0.3.2 → mdformat_space_control-0.4.1}/mdformat_space_control/plugin.py

@@ -4,6 +4,7 @@ Provides custom renderers that combine:
 - EditorConfig-based indentation settings
 - Tight list formatting with multi-paragraph awareness
 - Frontmatter spacing normalization
+- Smart dash conversion (-- → en-dash, --- → em-dash)
 - Trailing whitespace removal (outside code blocks)
 - Wikilink preservation ([[link]] and ![[embed]] syntax)
 """
@@ -112,12 +113,55 @@ def _get_indent(default_width: int) -> tuple[str, int]:
         return (" " * size, size)
 
 
+def _is_task_list_item(node: RenderTreeNode) -> bool:
+    """Check if a list item is a GFM task list item.
+
+    When mdformat-gfm is installed, the tasklists markdown-it plugin annotates
+    task list items with a 'task-list-item' CSS class.
+    """
+    classes = node.attrs.get("class", "")
+    return isinstance(classes, str) and "task-list-item" in classes
+
+
+def _extract_task_checkbox(node: RenderTreeNode) -> str | None:
+    """Extract and remove the task checkbox HTML from a task list item node.
+
+    The tasklists markdown-it plugin injects an HTML <input> element as the
+    first child of the inline token. This function extracts the checked state
+    and removes the HTML node so it doesn't appear in the rendered output.
+
+    Returns:
+        "x" for checked, " " for unchecked, or None if not a task list item.
+    """
+    if not _is_task_list_item(node):
+        return None
+
+    paragraph_node = node.children[0]
+    inline_node = paragraph_node.children[0]
+    if inline_node.type != "inline" or not inline_node.children:
+        return None
+
+    html_inline_node = inline_node.children[0]
+    if 'class="task-list-item-checkbox"' not in getattr(html_inline_node, "content", ""):
+        return None
+
+    # Remove the HTML checkbox node before rendering
+    inline_node.children.remove(html_inline_node)
+    return "x" if 'checked="checked"' in html_inline_node.content else " "
+
+
 def _render_list_item(node: RenderTreeNode, context: RenderContext) -> str:
     """Render a list item with appropriate tight/loose formatting.
 
     For single-paragraph items in tight lists, use tight formatting.
     For multi-paragraph items, preserve loose formatting.
+
+    Handles GFM task list items when mdformat-gfm is installed: extracts the
+    checkbox state from the HTML token and prepends [x] or [ ] to the output.
     """
+    # Extract task checkbox before rendering (mutates the node tree)
+    checkmark = _extract_task_checkbox(node)
+
     # Check if this item has multiple paragraphs
     if has_multiple_paragraphs(node):
         # Use loose list formatting for multi-paragraph items
@@ -136,6 +180,13 @@ def _render_list_item(node: RenderTreeNode, context: RenderContext) -> str:
 
     if not text.strip():
         return ""
+
+    if checkmark is not None:
+        # Strip leading space entities left after removing the HTML checkbox node
+        text = re.sub(r"^(&#32;)+", "", text)
+        text = text.lstrip()
+        return f"[{checkmark}] {text}"
+
     return text
 
 
@@ -336,6 +387,84 @@ def _strip_trailing_whitespace(text: str) -> str:
     return "\n".join(result)
 
 
+def _convert_dash_sequences(text: str) -> str:
+    """Convert markdown dash sequences to Unicode em-dash and en-dash.
+
+    Converts ``---`` to em-dash (U+2014) and ``--`` to en-dash (U+2013).
+    Preserves dashes inside fenced code blocks, inline code spans,
+    HTML comments, and HTML tags.
+    Skips lines that are only dashes (thematic breaks, frontmatter delimiters).
+
+    Em-dash is matched first (longer sequence) to prevent ``---`` from being
+    partially converted as en-dash + hyphen.
+    """
+    # Patterns for inline code span placeholders
+    inline_code_re = re.compile(r"(`+)(.+?)\1")
+
+    # HTML protection patterns
+    html_comment_re = re.compile(r"<!--.*?-->")
+    html_tag_re = re.compile(r"<[^>]+>")
+
+    # Dash conversion patterns: negative lookahead/behind prevent matching
+    # 4+ dash sequences (e.g., ---- horizontal rules in some contexts)
+    em_dash_re = re.compile(r"(?<!-)---(?!-)")
+    en_dash_re = re.compile(r"(?<!-)--(?!-)")
+
+    # Lines that are only dashes (thematic breaks, frontmatter delimiters)
+    only_dashes_re = re.compile(r"^-{2,}\s*$")
+
+    lines = text.split("\n")
+    result = []
+    in_code_block = False
+    in_html_comment = False
+
+    for line in lines:
+        stripped = line.lstrip()
+        if stripped.startswith("```") or stripped.startswith("~~~"):
+            in_code_block = not in_code_block
+            result.append(line)
+        elif in_code_block:
+            result.append(line)
+        elif in_html_comment:
+            # Inside a multi-line HTML comment, skip dash conversion
+            if "-->" in line:
+                in_html_comment = False
+            result.append(line)
+        elif only_dashes_re.match(line):
+            result.append(line)
+        else:
+            # Check for multi-line HTML comment opening (no closing on same line)
+            if "<!--" in line and "-->" not in line:
+                in_html_comment = True
+                result.append(line)
+                continue
+
+            # Protect inline code spans and HTML elements with placeholders
+            placeholders = []
+
+            def _save_placeholder(m: re.Match) -> str:
+                placeholders.append(m.group(0))
+                return f"\x00CODE{len(placeholders) - 1}\x00"
+
+            protected = inline_code_re.sub(_save_placeholder, line)
+
+            # Protect HTML comments first (longer matches), then tags
+            protected = html_comment_re.sub(_save_placeholder, protected)
+            protected = html_tag_re.sub(_save_placeholder, protected)
+
+            # Convert em-dash first (longer match), then en-dash
+            protected = em_dash_re.sub("\u2014", protected)
+            protected = en_dash_re.sub("\u2013", protected)
+
+            # Restore placeholders
+            for i, original in enumerate(placeholders):
+                protected = protected.replace(f"\x00CODE{i}\x00", original)
+
+            result.append(protected)
+
+    return "\n".join(result)
+
+
 def _normalize_consecutive_blank_lines(text: str) -> str:
     """Limit consecutive blank lines to a maximum of 2.
 
@@ -375,8 +504,9 @@ def _postprocess_root(text: str, node: RenderTreeNode, context: RenderContext) -
     Applies the following transformations in order:
     1. Frontmatter spacing normalization
     2. Escaped link repair
-    3. Consecutive blank line normalization
-    4. Trailing whitespace removal
+    3. Smart dash conversion (-- → en-dash, --- → em-dash)
+    4. Consecutive blank line normalization
+    5. Trailing whitespace removal
     """
     # 1. Frontmatter spacing
     text = _normalize_frontmatter_spacing(text)
@@ -384,10 +514,13 @@ def _postprocess_root(text: str, node: RenderTreeNode, context: RenderContext) -
     # 2. Repair escaped links (before trailing whitespace removal)
     text = _repair_escaped_links(text)
 
-    # 3. Limit consecutive blank lines to 2
+    # 3. Smart dash conversion
+    text = _convert_dash_sequences(text)
+
+    # 4. Limit consecutive blank lines to 2
     text = _normalize_consecutive_blank_lines(text)
 
-    # 4. Trailing whitespace removal
+    # 5. Trailing whitespace removal
     text = _strip_trailing_whitespace(text)
 
     return text

{mdformat_space_control-0.3.2 → mdformat_space_control-0.4.1}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 [project]
 name = "mdformat_space_control"
 dynamic = ["version"]
-description = "An mdformat plugin for space control: EditorConfig indentation, tight lists, frontmatter spacing, and wikilinks."
+description = "An mdformat plugin for space control: EditorConfig indentation, tight lists, frontmatter spacing, smart dash conversion, explicit line breaks, and wikilinks."
 authors = [
     { name = "Joseph Monaco", email = "joe@selfmotion.net" },
 ]
@@ -22,7 +22,7 @@ classifiers = [
     "Topic :: Software Development :: Libraries :: Python Modules",
     "Topic :: Text Processing :: Markup :: Markdown",
 ]
-keywords = ["mdformat", "markdown", "formatter", "editorconfig", "indentation", "lists", "frontmatter", "wikilink", "obsidian"]
+keywords = ["mdformat", "markdown", "formatter", "editorconfig", "indentation", "lists", "frontmatter", "wikilink", "obsidian", "typography"]
 requires-python = ">=3.10"
 dependencies = [
     "mdformat>=0.7.0",