lanyuanxiaoyao
09904aefdc
从 BaseReader 抽象基类及所有 Reader 子类中移除 supported_extensions 属性，该属性在代码库中从未被实际调用，仅作为元数据存在。
54 lines
1.4 KiB
Python
54 lines
1.4 KiB
Python
"""DOCX 文件阅读器，支持多种解析方法。"""
|
|
|
|
import os
|
|
from typing import List, Optional, Tuple
|
|
|
|
from scripts.readers.base import BaseReader
|
|
from scripts.utils import is_valid_docx
|
|
|
|
from . import docling
|
|
from . import unstructured
|
|
from . import markitdown
|
|
from . import pypandoc
|
|
from . import python_docx
|
|
from . import native_xml
|
|
|
|
|
|
PARSERS = [
|
|
("docling", docling.parse),
|
|
("unstructured", unstructured.parse),
|
|
("pypandoc-binary", pypandoc.parse),
|
|
("MarkItDown", markitdown.parse),
|
|
("python-docx", python_docx.parse),
|
|
("XML 原生解析", native_xml.parse),
|
|
]
|
|
|
|
|
|
class DocxReader(BaseReader):
|
|
"""DOCX 文件阅读器"""
|
|
|
|
def supports(self, file_path: str) -> bool:
|
|
return file_path.lower().endswith('.docx')
|
|
|
|
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_docx(file_path):
|
|
return None, ["不是有效的 DOCX 文件"]
|
|
|
|
content = None
|
|
|
|
for parser_name, parser_func in PARSERS:
|
|
content, error = parser_func(file_path)
|
|
if content is not None:
|
|
return content, failures
|
|
else:
|
|
failures.append(f"- {parser_name}: {error}")
|
|
|
|
return None, failures
|