tegwick
e4fbba8a57
Uses markitdown-no-magika (lighter fork without magika/onnxruntime) to handle PDF, HTML, DOCX, PPTX, XLSX, XLS, CSV, JSON, and XML files. Specialized extractors (pymupdf4llm, markdownify) remain as fallbacks when markitdown is not installed. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
31 lines
1.1 KiB
Python
31 lines
1.1 KiB
Python
"""
|
|
Built-in extractor registration.
|
|
|
|
Importing this module registers all built-in extractors with the global registry.
|
|
|
|
Registration order matters: specialized extractors are registered first, then
|
|
markitdown (if available) overwrites the overlapping extensions so it becomes
|
|
the default backend. If markitdown is not installed, the specialized extractors
|
|
remain active for their extensions.
|
|
"""
|
|
|
|
from markitect.proxy.registry import registry
|
|
from markitect.proxy.extractors.pdf import PdfExtractor
|
|
from markitect.proxy.extractors.html import HtmlExtractor
|
|
from markitect.proxy.extractors.markdown import MarkdownNormalizer
|
|
|
|
# 1. Specialized extractors (baseline)
|
|
registry.register(PdfExtractor())
|
|
registry.register(HtmlExtractor())
|
|
registry.register(MarkdownNormalizer())
|
|
|
|
# 2. Markitdown as default backend — overrides .pdf, .html, .htm and adds
|
|
# new types (.docx, .pptx, .xlsx, .xls, .csv, .json, .xml)
|
|
try:
|
|
from markitect.proxy.extractors.markitdown_ext import MarkitdownExtractor
|
|
_ext = MarkitdownExtractor()
|
|
if _ext.check_dependencies():
|
|
registry.register(_ext)
|
|
except ImportError:
|
|
pass
|