begoniezhao
2d66abedf0
移除日志设置与冗余代码，优化导入、类型提示及OCR后端管理 统一调整各文件模块导入路径为绝对导入 调整导入路径，移除部分导入，优化日志及注释 升级文档解析器为 Docx2Parser，优化超时与图片处理逻辑
71 lines
2.4 KiB
Python
71 lines
2.4 KiB
Python
import logging
|
|
from typing import List, Tuple, Type
|
|
|
|
from docreader.models.document import Document
|
|
from docreader.parser.base_parser import BaseParser
|
|
from docreader.utils import endecode
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class FirstParser(BaseParser):
|
|
_parser_cls: Tuple[Type["BaseParser"], ...] = ()
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
super().__init__(*args, **kwargs)
|
|
|
|
self._parsers: List[BaseParser] = []
|
|
for parser_cls in self._parser_cls:
|
|
try:
|
|
parser = parser_cls(*args, **kwargs)
|
|
self._parsers.append(parser)
|
|
except Exception as e:
|
|
logger.error(f"Failed to create parser {parser_cls.__name__}: {e}")
|
|
|
|
def parse_into_text(self, content: bytes) -> Document:
|
|
for p in self._parsers:
|
|
document = p.parse_into_text(content)
|
|
if document.is_valid():
|
|
return document
|
|
return Document()
|
|
|
|
@classmethod
|
|
def create(cls, *parser_classes: Type["BaseParser"]) -> Type["FirstParser"]:
|
|
names = "_".join([p.__name__ for p in parser_classes])
|
|
return type(f"FirstParser_{names}", (cls,), {"_parser_cls": parser_classes})
|
|
|
|
|
|
class PipelineParser(BaseParser):
|
|
_parser_cls: Tuple[Type["BaseParser"], ...] = ()
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
super().__init__(*args, **kwargs)
|
|
|
|
self._parsers: List[BaseParser] = []
|
|
for parser_cls in self._parser_cls:
|
|
try:
|
|
parser = parser_cls(*args, **kwargs)
|
|
self._parsers.append(parser)
|
|
except Exception as e:
|
|
logger.error(f"Failed to create parser {parser_cls.__name__}: {e}")
|
|
|
|
def parse_into_text(self, content: bytes) -> Document:
|
|
document = Document()
|
|
for p in self._parsers:
|
|
document = p.parse_into_text(content)
|
|
content = endecode.encode_bytes(document.content)
|
|
return document
|
|
|
|
@classmethod
|
|
def create(cls, *parser_classes: Type["BaseParser"]) -> Type["PipelineParser"]:
|
|
names = "_".join([p.__name__ for p in parser_classes])
|
|
return type(f"PipelineParser_{names}", (cls,), {"_parser_cls": parser_classes})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from docreader.parser.markdown_parser import MarkdownParser
|
|
|
|
cls = FirstParser.create(MarkdownParser)
|
|
parser = cls()
|
|
print(parser.parse_into_text(b"aaa"))
|