chore: Issue closure 125 cleanup

capabilities/markitect-content/src/markitect_content/__init__.py

@@ -0,0 +1,9 @@
+"""
+Content module for MarkdownMatters CLI.
+Handles content extraction without frontmatter and tailmatter zones.
+"""
+
+from .parser import ContentParser
+from .stats import ContentStats
+
+__all__ = ['ContentParser', 'ContentStats']

capabilities/markitect-content/src/markitect_content/commands.py

@@ -0,0 +1,57 @@
+"""
+CLI commands for content operations.
+"""
+
+import click
+import json
+from pathlib import Path
+from .parser import ContentParser
+
+
+@click.command('content-get')
+@click.option('--file', 'file_path', required=True, type=click.Path(exists=True),
+              help='Path to markdown file')
+def content_get(file_path):
+    """Extract content without frontmatter and tailmatter."""
+    try:
+        file_path = Path(file_path)
+        with open(file_path, 'r', encoding='utf-8') as f:
+            text = f.read()
+
+        parser = ContentParser()
+        content = parser.extract_content(text)
+
+        click.echo(content)
+
+    except Exception as e:
+        click.echo(f"Error: {e}", err=True)
+        raise click.ClickException(f"Failed to extract content from {file_path}")
+
+
+@click.command('content-stats')
+@click.option('--file', 'file_path', required=True, type=click.Path(exists=True),
+              help='Path to markdown file')
+@click.option('--format', 'output_format', default='json', type=click.Choice(['json', 'text']),
+              help='Output format (json or text)')
+def content_stats(file_path, output_format):
+    """Calculate content statistics."""
+    try:
+        file_path = Path(file_path)
+        with open(file_path, 'r', encoding='utf-8') as f:
+            text = f.read()
+
+        parser = ContentParser()
+        content = parser.extract_content(text)
+        stats = parser.calculate_stats(content)
+
+        if output_format == 'json':
+            click.echo(json.dumps(stats.to_dict(), indent=2))
+        else:
+            click.echo(f"Word count: {stats.word_count}")
+            click.echo(f"Line count: {stats.line_count}")
+            click.echo(f"Paragraph count: {stats.paragraph_count}")
+            click.echo(f"Character count: {stats.character_count}")
+
+    except Exception as e:
+        click.echo(f"Error: {e}", err=True)
+        raise click.ClickException(f"Failed to calculate stats for {file_path}")

capabilities/markitect-content/src/markitect_content/parser.py

@@ -0,0 +1,90 @@
+"""
+Content parser for extracting markdown content without matter zones.
+"""
+
+import re
+from typing import Optional
+from .stats import ContentStats
+
+
+class ContentParser:
+    """Parser for extracting content from MarkdownMatters documents."""
+
+    def extract_content(self, text: str) -> str:
+        """
+        Extract main content without frontmatter and tailmatter.
+
+        Args:
+            text: Full markdown document text
+
+        Returns:
+            Content without frontmatter and tailmatter zones
+        """
+        # Remove frontmatter
+        content = self._remove_frontmatter(text)
+
+        # Remove tailmatter
+        content = self._remove_tailmatter(content)
+
+        return content.strip()
+
+    def calculate_stats(self, content: str) -> ContentStats:
+        """
+        Calculate statistics for content.
+
+        Args:
+            content: The content text to analyze
+
+        Returns:
+            ContentStats object with calculated statistics
+        """
+        # Count lines
+        lines = content.split('\n')
+        line_count = len(lines)
+
+        # Count words (split by whitespace)
+        words = content.split()
+        word_count = len(words)
+
+        # Count paragraphs (non-empty text blocks separated by blank lines)
+        paragraphs = [p.strip() for p in content.split('\n\n') if p.strip()]
+        paragraph_count = len(paragraphs)
+
+        # Count characters
+        character_count = len(content)
+
+        return ContentStats(
+            word_count=word_count,
+            line_count=line_count,
+            paragraph_count=paragraph_count,
+            character_count=character_count
+        )
+
+    def _remove_frontmatter(self, text: str) -> str:
+        """Remove YAML/TOML/JSON frontmatter from text."""
+        # Pattern for YAML frontmatter (---...---)
+        yaml_pattern = r'^---\s*\n.*?\n---\s*\n'
+
+        # Remove YAML frontmatter if present
+        text = re.sub(yaml_pattern, '', text, flags=re.DOTALL | re.MULTILINE)
+
+        # TODO: Add support for TOML and JSON frontmatter in future cycles
+
+        return text
+
+    def _remove_tailmatter(self, text: str) -> str:
+        """Remove tailmatter blocks from text."""
+        # Pattern for tailmatter: ```yaml tailmatter or ```json tailmatter
+        # Usually preceded by horizontal rule (---)
+
+        # Look for the pattern: --- followed by ```yaml tailmatter or ```json tailmatter
+        tailmatter_pattern = r'\n---\s*\n\s*```(?:yaml|json)\s+tailmatter\s*\n.*?```\s*$'
+
+        # Remove tailmatter if present
+        text = re.sub(tailmatter_pattern, '', text, flags=re.DOTALL | re.MULTILINE)
+
+        # Also handle cases where tailmatter is at the end without preceding ---
+        simple_tailmatter_pattern = r'\n\s*```(?:yaml|json)\s+tailmatter\s*\n.*?```\s*$'
+        text = re.sub(simple_tailmatter_pattern, '', text, flags=re.DOTALL | re.MULTILINE)
+
+        return text

capabilities/markitect-content/src/markitect_content/stats.py

@@ -0,0 +1,25 @@
+"""
+Content statistics data structures.
+"""
+
+from dataclasses import dataclass
+from typing import Dict, Any
+
+
+@dataclass
+class ContentStats:
+    """Statistics about markdown content."""
+
+    word_count: int
+    line_count: int
+    paragraph_count: int
+    character_count: int
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert stats to dictionary."""
+        return {
+            "word_count": self.word_count,
+            "line_count": self.line_count,
+            "paragraph_count": self.paragraph_count,
+            "character_count": self.character_count
+        }