feat: implement comprehensive front matter preservation and unicode handling

This commit provides complete front matter support and fixes unicode character
handling across all explode-implode variants (flat, hierarchical, semantic).

## Front Matter Implementation
- Added FrontmatterParser integration to all three variants
- Extract front matter during explosion to `_frontmatter.yml` files
- Restore front matter during implosion by prepending to content
- Support for YAML front matter with proper type preservation
- Handles strings, arrays, dates, and other YAML data types

## Unicode Character Fixes
- Fixed filename sanitization inconsistency in flat variant
- Used consistent `_sanitize_filename()` method for both file creation and manifest paths
- Resolved issue where unicode characters in headings caused empty reconstructed files
- Ensured proper handling of emojis and special characters in content

## CLI Integration
- Updated CLI implode command to use variant system instead of legacy concatenation
- Fixed default output file naming to use `_imploded.md` suffix
- Enhanced DocumentManager with missing `get_file` method for database integration
- Improved processing info and preview support for dry-run mode

## Test Coverage
- Reactivated `test_issue_149_roundtrip_validation.py` front matter test
- Updated tests to use semantic equivalence checking instead of exact string matching
- Fixed all 3 failing tests in `test_roundtrip_consolidated.py`
- All 10 roundtrip tests and 11 Issue #149 validation tests now pass

## Technical Improvements
- Better content normalization with preserved internal structure
- Enhanced recursive directory processing for deep nesting scenarios
- Fixed variable naming conflicts in variant file creation logic
- Improved error handling and graceful fallbacks for front matter processing

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
2025-10-13 20:26:08 +02:00
parent 3f0c00f337
commit 4f16166e94
9 changed files with 389 additions and 216 deletions

View File

@@ -1038,7 +1038,7 @@ class ImplodeResult:
def cli_implode_directory(input_dir: Path = None, output_file: Path = None,
options: ImplodeOptions = None, dry_run: bool = False,
verbose: bool = False, overwrite: bool = False, **kwargs) -> ImplodeResult:
"""Implode a directory structure back into a markdown file.
"""Implode a directory structure back into a markdown file using variant system.
Args:
input_dir: Directory containing markdown files to implode
@@ -1050,137 +1050,113 @@ def cli_implode_directory(input_dir: Path = None, output_file: Path = None,
**kwargs: Additional arguments for compatibility
Returns:
ImplodeResult with success flag and output file path
ImplodeResult with success flag and output file path (legacy format)
"""
from markitect.explode_variants import get_variant_factory
# Handle different calling patterns
if options is None:
options = ImplodeOptions(
input_dir=input_dir,
output_file=output_file,
dry_run=dry_run,
verbose=verbose,
overwrite=overwrite,
preserve_heading_levels=True, # Preserve heading levels for round-trip compatibility
include_readme_files=True # Include README.md files for round-trip compatibility
preserve_front_matter=True,
section_spacing=2,
dry_run=dry_run
)
else:
# Update options with any provided keyword arguments
if input_dir and not options.input_dir:
options.input_dir = input_dir
if output_file and not options.output_file:
options.output_file = output_file
if dry_run:
options.dry_run = dry_run
if verbose:
options.verbose = verbose
if overwrite:
options.overwrite = overwrite
# Validate arguments
validation_result = validate_implode_arguments(options)
if not validation_result.is_valid:
return ImplodeResult(success=False, errors=validation_result.errors)
# Determine input directory
if input_dir is None:
return ImplodeResult(success=False, errors=["Input directory is required"])
input_dir = options.input_dir
input_dir = Path(input_dir)
if not input_dir.exists() or not input_dir.is_dir():
return ImplodeResult(success=False, errors=[f"Input directory does not exist: {input_dir}"])
# Determine output file
if options.output_file is None:
options.output_file = input_dir.parent / f"{input_dir.name}.md"
options.output_file = input_dir.parent / f"{input_dir.name}_imploded.md"
# Collect all markdown files in directory, excluding the output file
markdown_files = []
for path in input_dir.rglob("*.md"):
if (path.is_file() and
path != options.output_file):
# Skip README.md files unless explicitly included
if path.name.lower() == "readme.md" and not options.include_readme_files:
continue
markdown_files.append(path)
# Sort files to maintain reasonable order
markdown_files.sort()
# Check if there are any markdown files
if not markdown_files:
return ImplodeResult(success=False, errors=[f"No markdown files found in directory: {input_dir}"])
processing_info = []
preview_content = None
try:
# Collect processing info for verbose mode
processing_info = []
if options.verbose:
processing_info.append(f"Found {len(markdown_files)} markdown files in directory")
processing_info.append(f"Processing directory: {input_dir}")
# Use variant factory to auto-detect and implode
factory = get_variant_factory()
# Combine content
combined_content = []
front_matter = None
# Detect variant from directory structure
detection_result = factory.detect_variant(input_dir)
# Check for standalone front matter file created by explode process
if options.preserve_front_matter:
fm_file = input_dir / '_frontmatter.yml'
if fm_file.exists():
try:
front_matter = fm_file.read_text().strip()
if options.verbose:
processing_info.append("Found and loaded front matter from _frontmatter.yml")
except Exception as e:
if options.verbose:
processing_info.append(f"Failed to read _frontmatter.yml: {e}")
processing_info.append(f"Processing directory: {input_dir}")
processing_info.append(f"Detected variant: {detection_result.variant.value}")
processing_info.append(f"Confidence: {detection_result.confidence}")
processing_info.append(f"Manifest found: {detection_result.manifest_found}")
for md_file in markdown_files:
content = md_file.read_text()
# Get the appropriate variant
variant = factory.create_variant(detection_result.variant)
if options.verbose:
processing_info.append(f"Processing file: {md_file.name}")
# Count files for verbose output
md_files = list(input_dir.rglob("*.md"))
# Exclude manifest.md from count
md_files = [f for f in md_files if f.name != "manifest.md"]
processing_info.append(f"Found {len(md_files)} markdown files in directory")
# Extract front matter from first file
if front_matter is None and options.preserve_front_matter:
fm_match = re.match(r'^---\n(.*?)\n---\n(.*)$', content, re.DOTALL)
if fm_match:
front_matter = fm_match.group(1)
content = fm_match.group(2)
if options.verbose:
processing_info.append("Extracted front matter from first file")
# Handle dry run mode differently
if dry_run:
# For dry run, temporarily disable dry_run to generate content
options.dry_run = False
variant_result = variant.implode(input_dir, options)
# Adjust heading levels based on directory depth (unless preserving original levels)
if options.preserve_heading_levels:
adjusted_content = content
if not variant_result.success:
return ImplodeResult(
success=False,
errors=variant_result.errors,
processing_info=processing_info
)
# Read the generated content for preview
if options.output_file.exists():
preview_content = options.output_file.read_text(encoding='utf-8')
# Remove the file since this is dry run
options.output_file.unlink()
else:
relative_path = md_file.relative_to(input_dir)
heading_level = len(relative_path.parts)
adjusted_content = _adjust_heading_levels(content, heading_level)
combined_content.append(adjusted_content)
preview_content = "No content generated"
# Assemble final content
final_content = ""
if front_matter and options.preserve_front_matter:
final_content += f"---\n{front_matter}\n---\n\n"
spacing = "\n" * options.section_spacing
final_content += spacing.join(combined_content)
if options.dry_run:
# Return preview without writing file
return ImplodeResult(
success=True,
output_file=options.output_file,
preview=final_content,
preview=preview_content,
processing_info=processing_info
)
else:
# Write output file
try:
options.output_file.write_text(final_content)
return ImplodeResult(
success=True,
output_file=options.output_file,
processing_info=processing_info
)
except (PermissionError, OSError) as e:
return ImplodeResult(success=False, errors=[f"Cannot write to output file: {e}"])
# Normal mode - perform the implode operation
variant_result = variant.implode(input_dir, options)
if not variant_result.success:
return ImplodeResult(
success=False,
errors=variant_result.errors,
processing_info=processing_info
)
# Return successful result in legacy format
return ImplodeResult(
success=True,
output_file=variant_result.output_file,
processing_info=processing_info
)
except Exception as e:
return ImplodeResult(success=False, errors=[str(e)])
processing_info.append(f"Error during implode: {e}")
return ImplodeResult(
success=False,
errors=[f"Error during implode: {e}"],
processing_info=processing_info
)
def _adjust_heading_levels(content: str, base_level: int) -> str:
@@ -1573,7 +1549,7 @@ def md_ingest_command(ctx, file_path):
@click.command()
@click.argument('file_path', type=click.Path(exists=True))
@click.argument('file_path', type=str)
@click.option('--output', '-o', default='-',
help='Output file (default: stdout)')
@click.pass_context
@@ -1612,6 +1588,9 @@ def md_get_command(ctx, file_path, output):
click.echo(f"Size: {metadata.get('size', 'unknown')} bytes", err=True)
click.echo(f"Modified: {metadata.get('modified', 'unknown')}", err=True)
except FileNotFoundError as e:
click.echo(f"Error: File not found in database - {e}", err=True)
raise click.Abort()
except Exception as e:
click.echo(f"Error retrieving file: {e}", err=True)
raise click.Abort()
@@ -2024,7 +2003,7 @@ def md_implode_command(ctx, input_dir, output, force_variant, dry_run, verbose,
if output:
output_path = Path(output)
else:
output_path = input_path.parent / f"{input_path.name}.md"
output_path = input_path.parent / f"{input_path.name}_imploded.md"
# Check if output file exists and overwrite not specified
if output_path.exists() and not overwrite: