为所有 Reader 的 parser 循环添加 try-except 防护层,确保即使 parser 抛出意外异常,降级链也能继续尝试下一个 parser。 主要变更: - 所有 Reader (DocxReader/PdfReader/XlsxReader/PptxReader/HtmlReader) 的 parse 方法中添加防护层,捕获意外异常并标记为 [意外异常] - cleaner.clean_html_content() 添加异常处理,返回 (content, error) 元组 - HtmlReader.parse() 更新 cleaner 调用方式,处理新的返回值格式 - BaseReader 添加详细的异常处理规范文档 设计原则:双层异常保护 - Parser 层:捕获预期的解析失败(库未安装、格式不支持) - Reader 层:捕获意外的编程错误(NoneType、索引越界等)
57 lines
1.6 KiB
Python
57 lines
1.6 KiB
Python
"""PDF 文件阅读器,支持多种解析方法(OCR 优先)。"""
|
||
|
||
import os
|
||
from typing import List, Optional, Tuple
|
||
|
||
from scripts.readers.base import BaseReader
|
||
from scripts.utils import is_valid_pdf
|
||
|
||
from . import docling_ocr
|
||
from . import unstructured_ocr
|
||
from . import docling
|
||
from . import unstructured
|
||
from . import markitdown
|
||
from . import pypdf
|
||
|
||
|
||
PARSERS = [
|
||
("docling OCR", docling_ocr.parse),
|
||
("unstructured OCR", unstructured_ocr.parse),
|
||
("docling", docling.parse),
|
||
("unstructured", unstructured.parse),
|
||
("MarkItDown", markitdown.parse),
|
||
("pypdf", pypdf.parse),
|
||
]
|
||
|
||
|
||
class PdfReader(BaseReader):
|
||
"""PDF 文件阅读器"""
|
||
|
||
def supports(self, file_path: str) -> bool:
|
||
return file_path.lower().endswith('.pdf')
|
||
|
||
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
|
||
failures = []
|
||
|
||
# 检查文件是否存在
|
||
if not os.path.exists(file_path):
|
||
return None, ["文件不存在"]
|
||
|
||
# 验证文件格式
|
||
if not is_valid_pdf(file_path):
|
||
return None, ["不是有效的 PDF 文件"]
|
||
|
||
content = None
|
||
|
||
for parser_name, parser_func in PARSERS:
|
||
try:
|
||
content, error = parser_func(file_path)
|
||
if content is not None:
|
||
return content, failures
|
||
else:
|
||
failures.append(f"- {parser_name}: {error}")
|
||
except Exception as e:
|
||
failures.append(f"- {parser_name}: [意外异常] {type(e).__name__}: {str(e)}")
|
||
|
||
return None, failures
|