mirror of
https://github.com/Tencent/WeKnora.git
synced 2026-06-04 21:34:31 +08:00
397689d2f3
- Added a new `.env.lite.example` file for the Lite version, providing a minimal configuration template. - Updated `.env.example` to remove deprecated variables and include new Docreader settings. - Enhanced Docker configurations to support the Lite version, including a new Dockerfile for the Docreader service. - Introduced a Makefile target for building and running the Lite version, along with packaging capabilities. - Created GitHub workflows for building and releasing Lite binaries, including Homebrew formula support. - Implemented a new service file for managing the Lite version as a system service. This update enables a streamlined, single-binary deployment of WeKnora, reducing external dependencies and simplifying setup.
39 lines
972 B
Python
39 lines
972 B
Python
"""
|
|
Parser module for WeKnora document processing system.
|
|
|
|
This module provides document parsers for various file formats including:
|
|
- Microsoft Word documents (.doc, .docx)
|
|
- PDF documents
|
|
- Markdown files
|
|
- Plain text files
|
|
- Images with text content
|
|
- Web pages
|
|
|
|
The parsers extract content from documents and can split them into
|
|
meaningful chunks for further processing and indexing.
|
|
"""
|
|
|
|
from .doc_parser import DocParser
|
|
from .docx2_parser import Docx2Parser
|
|
from .excel_parser import ExcelParser
|
|
from .image_parser import ImageParser
|
|
from .markdown_parser import MarkdownParser
|
|
from .parser import Parser
|
|
from .pdf_parser import PDFParser
|
|
from .registry import ParserEngineRegistry, registry
|
|
from .web_parser import WebParser
|
|
|
|
# Export public classes and modules
|
|
__all__ = [
|
|
"Docx2Parser",
|
|
"DocParser",
|
|
"PDFParser",
|
|
"MarkdownParser",
|
|
"ImageParser",
|
|
"WebParser",
|
|
"Parser",
|
|
"ExcelParser",
|
|
"ParserEngineRegistry",
|
|
"registry",
|
|
]
|