Files
lyxy-document/scripts/readers/docx/__init__.py
lanyuanxiaoyao 7eab1dcef1 test: 添加全面的测试套件,覆盖所有 Reader 实现
- 测试数量从 83 个增加到 193 个 (+132%)
- 代码覆盖率从 48% 提升到 69% (+44%)
- 为每种文档格式的所有 Reader 实现创建独立测试
- 添加跨 Reader 的一致性验证测试
- 新增 4 个测试规范 (cli-testing, exception-testing, reader-testing, test-fixtures)
- 更新 README 测试统计信息

测试覆盖:
- DOCX: python-docx, markitdown, docling, native-xml, pypandoc, unstructured
- PDF: pypdf, markitdown, docling, docling-ocr, unstructured, unstructured-ocr
- HTML: html2text, markitdown, trafilatura, domscribe
- PPTX: python-pptx, markitdown, docling, native-xml, unstructured
- XLSX: pandas, markitdown, docling, native-xml, unstructured
- CLI: 所有命令行选项和错误处理

所有 193 个测试通过。
2026-03-08 22:20:21 +08:00

58 lines
1.5 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"""
@property
def supported_extensions(self) -> List[str]:
return [".docx"]
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