Class DocumentConverter

docling/document_converter.py:156–348

class DocumentConverter:
    _default_download_filename = "file"

    def __init__(
        self,
        allowed_formats: Optional[List[InputFormat]] = None,
        format_options: Optional[Dict[InputFormat, FormatOption]] = None,
    ):
        self.allowed_formats = (
            allowed_formats if allowed_formats is not None else [e for e in InputFormat]
        )
        self.format_to_options = {
            format: (
                _get_default_option(format=format)
                if (custom_option := (format_options or {}).get(format)) is None
                else custom_option
            )
            for format in self.allowed_formats
        }
        self.initialized_pipelines: Dict[Type[BasePipeline], BasePipeline] = {}

    def initialize_pipeline(self, format: InputFormat):
        """Initialize the conversion pipeline for the selected format."""
        pipeline = self._get_pipeline(doc_format=format)
        if pipeline is None:
            raise ConversionError(
                f"No pipeline could be initialized for format {format}"
            )

    @validate_call(config=ConfigDict(strict=True))
    def convert(
        self,
        source: Union[Path, str, DocumentStream],  # TODO review naming
        headers: Optional[Dict[str, str]] = None,
        raises_on_error: bool = True,
        max_num_pages: int = sys.maxsize,
        max_file_size: int = sys.maxsize,
        page_range: PageRange = DEFAULT_PAGE_RANGE,
    ) -> ConversionResult:
        all_res = self.convert_all(
            source=[source],
            raises_on_error=raises_on_error,
            max_num_pages=max_num_pages,
            max_file_size=max_file_size,
            headers=headers,
            page_range=page_range,
        )
        return next(all_res)

    @validate_call(config=ConfigDict(strict=True))
    def convert_all(
        self,
        source: Iterable[Union[Path, str, DocumentStream]],  # TODO review naming
        headers: Optional[Dict[str, str]] = None,
        raises_on_error: bool = True,  # True: raises on first conversion error; False: does not raise on conv error
        max_num_pages: int = sys.maxsize,
        max_file_size: int = sys.maxsize,
        page_range: PageRange = DEFAULT_PAGE_RANGE,