lyxy-document/readers/docx/__init__.py

"""DOCX 文件阅读器，支持多种解析方法。"""

from typing import List, Optional, Tuple

from readers.base import BaseReader
from utils import is_valid_docx

from . import docling
from . import unstructured
from . import markitdown
from . import pypandoc
from . import python_docx
from . import native_xml


PARSERS = [
    ("docling", docling.parse),
    ("unstructured", unstructured.parse),
    ("pypandoc-binary", pypandoc.parse),
    ("MarkItDown", markitdown.parse),
    ("python-docx", python_docx.parse),
    ("XML 原生解析", native_xml.parse),
]


class DocxReader(BaseReader):
    """DOCX 文件阅读器"""

    @property
    def supported_extensions(self) -> List[str]:
        return [".docx"]

    def supports(self, file_path: str) -> bool:
        return is_valid_docx(file_path)

    def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
        failures = []
        content = None

        for parser_name, parser_func in PARSERS:
            content, error = parser_func(file_path)
            if content is not None:
                return content, failures
            else:
                failures.append(f"- {parser_name}: {error}")

        return None, failures