Method encode_example

src/datasets/features/pdf.py:78–111

Encode example into a format for Arrow. Args: value (`str`, `bytes`, `pdfplumber.pdf.PDF` or `dict`): Data passed as input to Pdf feature. Returns: `dict` with "path" and "bytes" fields

(self, value: Union[str, bytes, bytearray, dict, "pdfplumber.pdf.PDF"])

        return self.pa_type

    def encode_example(self, value: Union[str, bytes, bytearray, dict, "pdfplumber.pdf.PDF"]) -> dict:
        """Encode example into a format for Arrow.

        Args:
            value (`str`, `bytes`, `pdfplumber.pdf.PDF` or `dict`):
                Data passed as input to Pdf feature.

        Returns:
            `dict` with "path" and "bytes" fields
        """
        if config.PDFPLUMBER_AVAILABLE:
            import pdfplumber
        else:
            pdfplumber = None

        if isinstance(value, str):
            return {"path": value, "bytes": None}
        elif isinstance(value, Path):
            return {"path": str(value.absolute()), "bytes": None}
        elif isinstance(value, (bytes, bytearray)):
            return {"path": None, "bytes": value}
        elif pdfplumber is not None and isinstance(value, pdfplumber.pdf.PDF):
            # convert the pdfplumber.pdf.PDF to bytes
            return encode_pdfplumber_pdf(value)
        elif value.get("path") is not None and os.path.isfile(value["path"]):
            # we set "bytes": None to not duplicate the data if they're already available locally
            return {"bytes": None, "path": value.get("path")}
        elif value.get("bytes") is not None or value.get("path") is not None:
            # store the pdf bytes, and path is used to infer the pdf format using the file extension
            return {"bytes": value.get("bytes"), "path": value.get("path")}
        else:
            raise ValueError(
                f"A pdf sample should have one of 'path' or 'bytes' but they are missing or None in {value}."
            )

    def decode_example(self, value: dict, token_per_repo_id=None) -> "pdfplumber.pdf.PDF":
        """Decode example pdf file into pdf data.