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.
62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
# -*- coding: utf-8 -*-
|
|
import logging
|
|
import os
|
|
from abc import ABC, abstractmethod
|
|
from typing import Optional
|
|
|
|
from docreader.models.document import Document
|
|
|
|
logger = logging.getLogger(__name__)
|
|
logger.setLevel(logging.INFO)
|
|
|
|
|
|
class BaseParser(ABC):
|
|
"""Base parser interface.
|
|
|
|
After the lightweight refactoring, BaseParser only extracts markdown text
|
|
and raw image references from documents. Chunking, image storage, OCR,
|
|
and VLM caption are handled by the Go App module.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_name: str = "",
|
|
file_type: Optional[str] = None,
|
|
**kwargs,
|
|
):
|
|
self.file_name = file_name
|
|
self.file_type = file_type or os.path.splitext(file_name)[1].lstrip(".")
|
|
|
|
logger.info(
|
|
"Initializing parser for file=%s, type=%s",
|
|
file_name,
|
|
self.file_type,
|
|
)
|
|
|
|
@abstractmethod
|
|
def parse_into_text(self, content: bytes) -> Document:
|
|
"""Parse document content into markdown text.
|
|
|
|
Returns:
|
|
Document with ``content`` (markdown string) and optional
|
|
``images`` dict mapping storage-relative paths to base64 data.
|
|
"""
|
|
|
|
def parse(self, content: bytes) -> Document:
|
|
"""Parse document and return markdown + image references.
|
|
|
|
No chunking, no OCR, no VLM caption — those are done in Go.
|
|
"""
|
|
logger.info(
|
|
"Parsing document with %s, bytes: %d",
|
|
self.__class__.__name__,
|
|
len(content),
|
|
)
|
|
document = self.parse_into_text(content)
|
|
logger.info(
|
|
"Extracted %d characters from %s",
|
|
len(document.content),
|
|
self.file_name,
|
|
)
|
|
return document
|