Files
Enterprise-Knowledge-Base/docreader/parser/pdf_parser.py
T
begoniezhao 3e31fdeefd style: add necessary comments to improve code quality
- Add docstrings and inline comments for key functions and complex logic
- Unify comment style, eliminate magic numbers and ambiguous variable names
- No functional changes, only improve maintainability
2025-12-01 17:43:26 +08:00

17 lines
645 B
Python

from docreader.parser.chain_parser import FirstParser
from docreader.parser.markitdown_parser import MarkitdownParser
from docreader.parser.mineru_parser import MinerUParser
class PDFParser(FirstParser):
"""PDF Parser using chain of responsibility pattern
Attempts to parse PDF files using multiple parser backends in order:
1. MinerUParser - Primary parser for PDF documents
2. MarkitdownParser - Fallback parser if MinerU fails
The first successful parser result will be returned.
"""
# Parser classes to try in order (chain of responsibility pattern)
_parser_cls = (MinerUParser, MarkitdownParser)