tegwick
ac334c679d
Introduces a new `markitect/proxy/` module with pluggable extractors that convert non-markdown sources (PDF, HTML) into tracked markdown proxy files. Proxy files preserve origin metadata (path, checksum, timestamp) so they can be kept in sync when the original changes. CLI commands: `proxy create`, `proxy update`, `proxy status`, `proxy extractors`. Built-in extractors: PDF (pymupdf4llm), HTML (markdownify), Markdown (built-in). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
30 lines
826 B
Python
30 lines
826 B
Python
"""
|
|
Markdown normalizer — passes through Markdown with minimal transformation.
|
|
|
|
No external dependencies required.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
from markitect.proxy.extractors.base import BaseExtractor
|
|
from markitect.proxy.models import ExtractionResult
|
|
|
|
|
|
class MarkdownNormalizer(BaseExtractor):
|
|
"""Normalizes other Markdown files (built-in, no optional deps)."""
|
|
|
|
name = "markdown"
|
|
version = "1.0"
|
|
extensions = (".md", ".markdown", ".mdown")
|
|
|
|
def check_dependencies(self) -> bool:
|
|
return True
|
|
|
|
def extract(self, source_path: Path) -> ExtractionResult:
|
|
content = source_path.read_text(encoding="utf-8")
|
|
return ExtractionResult(
|
|
content=content,
|
|
extractor=self.name,
|
|
extractor_version=self.version,
|
|
)
|