- 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
36 lines
621 B
Python
36 lines
621 B
Python
"""Readers module for lyxy-document."""
|
|
|
|
from .base import BaseReader
|
|
from .docx import DocxReader
|
|
from .xlsx import XlsxReader
|
|
from .pptx import PptxReader
|
|
from .pdf import PdfReader
|
|
from .html import HtmlReader
|
|
from .doc import DocReader
|
|
from .xls import XlsReader
|
|
from .ppt import PptReader
|
|
|
|
READERS = [
|
|
DocxReader,
|
|
XlsxReader,
|
|
PptxReader,
|
|
PdfReader,
|
|
HtmlReader,
|
|
DocReader,
|
|
XlsReader,
|
|
PptReader,
|
|
]
|
|
|
|
__all__ = [
|
|
"BaseReader",
|
|
"DocxReader",
|
|
"XlsxReader",
|
|
"PptxReader",
|
|
"PdfReader",
|
|
"HtmlReader",
|
|
"DocReader",
|
|
"XlsReader",
|
|
"PptReader",
|
|
"READERS",
|
|
]
|