DESKTOP-72TV0V4\caoxiaozhu
d24b29afe4
- 添加多种文档解析器 (PDF, Word, Excel, Markdown 等) - 添加基础解析器和链式解析器 - 添加存储和注册机制 - 添加 gRPC 服务实现 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
|