feat: 添加 doc/xls/ppt 旧格式文档支持
- 新增 DocReader,支持 markitdown 和 pypandoc-binary 解析器 - 新增 XlsReader,支持 unstructured、markitdown 和 pandas+xlrd 解析器 - 新增 PptReader,支持 markitdown 解析器 - 添加 olefile 依赖用于验证 OLE2 格式 - 更新 config.py 添加 doc/xls/ppt 依赖配置 - 更新 --advice 支持 doc/xls/ppt 格式 - 添加相应的测试用例 - 同步 specs 到主目录
This commit is contained in:
48
scripts/readers/doc/__init__.py
Normal file
48
scripts/readers/doc/__init__.py
Normal file
@@ -0,0 +1,48 @@
|
||||
"""DOC 文件阅读器,支持多种解析方法。"""
|
||||
|
||||
import os
|
||||
from typing import List, Optional, Tuple
|
||||
|
||||
from readers.base import BaseReader
|
||||
from utils import is_valid_doc
|
||||
|
||||
from . import markitdown
|
||||
from . import pypandoc
|
||||
|
||||
|
||||
PARSERS = [
|
||||
("MarkItDown", markitdown.parse),
|
||||
("pypandoc-binary", pypandoc.parse),
|
||||
]
|
||||
|
||||
|
||||
class DocReader(BaseReader):
|
||||
"""DOC 文件阅读器"""
|
||||
|
||||
def supports(self, file_path: str) -> bool:
|
||||
return file_path.lower().endswith('.doc')
|
||||
|
||||
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_doc(file_path):
|
||||
return None, ["不是有效的 DOC 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
|
||||
10
scripts/readers/doc/markitdown.py
Normal file
10
scripts/readers/doc/markitdown.py
Normal file
@@ -0,0 +1,10 @@
|
||||
"""使用 MarkItDown 库解析 DOC 文件"""
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from readers._utils import parse_via_markitdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 MarkItDown 库解析 DOC 文件"""
|
||||
return parse_via_markitdown(file_path)
|
||||
29
scripts/readers/doc/pypandoc.py
Normal file
29
scripts/readers/doc/pypandoc.py
Normal file
@@ -0,0 +1,29 @@
|
||||
"""使用 pypandoc-binary 库解析 DOC 文件"""
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 pypandoc-binary 库解析 DOC 文件"""
|
||||
try:
|
||||
import pypandoc
|
||||
except ImportError:
|
||||
return None, "pypandoc-binary 库未安装"
|
||||
|
||||
try:
|
||||
content = pypandoc.convert_file(
|
||||
source_file=file_path,
|
||||
to="md",
|
||||
format="doc",
|
||||
outputfile=None,
|
||||
extra_args=["--wrap=none"],
|
||||
)
|
||||
except OSError as exc:
|
||||
return None, f"pypandoc-binary 缺少 Pandoc 可执行文件: {exc}"
|
||||
except RuntimeError as exc:
|
||||
return None, f"pypandoc-binary 解析失败: {exc}"
|
||||
|
||||
content = content.strip()
|
||||
if not content:
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
Reference in New Issue
Block a user