docling/docs/examples/batch_convert.py

import json
import logging
import time
from pathlib import Path
from typing import Iterable

import yaml
from docling_core.types.doc import ImageRefMode

from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.datamodel.settings import settings
from docling.document_converter import DocumentConverter, PdfFormatOption

_log = logging.getLogger(__name__)

USE_V2 = True
USE_LEGACY = False


def export_documents(
    conv_results: Iterable[ConversionResult],
    output_dir: Path,
):
    output_dir.mkdir(parents=True, exist_ok=True)

    success_count = 0
    failure_count = 0
    partial_success_count = 0

    for conv_res in conv_results:
        if conv_res.status == ConversionStatus.SUCCESS:
            success_count += 1
            doc_filename = conv_res.input.file.stem

            if USE_V2:
                conv_res.document.save_as_json(
                    output_dir / f"{doc_filename}.json",
                    image_mode=ImageRefMode.PLACEHOLDER,
                )
                conv_res.document.save_as_html(
                    output_dir / f"{doc_filename}.html",
                    image_mode=ImageRefMode.EMBEDDED,
                )
                conv_res.document.save_as_document_tokens(
                    output_dir / f"{doc_filename}.doctags.txt"
                )
                conv_res.document.save_as_markdown(
                    output_dir / f"{doc_filename}.md",
                    image_mode=ImageRefMode.PLACEHOLDER,
                )
                conv_res.document.save_as_markdown(
                    output_dir / f"{doc_filename}.txt",
                    image_mode=ImageRefMode.PLACEHOLDER,
                    strict_text=True,
                )

                # Export Docling document format to YAML:
                with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
                    fp.write(yaml.safe_dump(conv_res.document.export_to_dict()))

            if USE_LEGACY:
                # Export Deep Search document JSON format:
                with (output_dir / f"{doc_filename}.legacy.json").open(
                    "w", encoding="utf-8"
                ) as fp:
                    fp.write(json.dumps(conv_res.legacy_document.export_to_dict()))

                # Export Text format:
                with (output_dir / f"{doc_filename}.legacy.txt").open(
                    "w", encoding="utf-8"
                ) as fp:
                    fp.write(
                        conv_res.legacy_document.export_to_markdown(strict_text=True)
                    )

                # Export Markdown format:
                with (output_dir / f"{doc_filename}.legacy.md").open(
                    "w", encoding="utf-8"
                ) as fp:
                    fp.write(conv_res.legacy_document.export_to_markdown())

                # Export Document Tags format:
                with (output_dir / f"{doc_filename}.legacy.doctags.txt").open(
                    "w", encoding="utf-8"
                ) as fp:
                    fp.write(conv_res.legacy_document.export_to_document_tokens())

        elif conv_res.status == ConversionStatus.PARTIAL_SUCCESS:
            _log.info(
                f"Document {conv_res.input.file} was partially converted with the following errors:"
            )
            for item in conv_res.errors:
                _log.info(f"\t{item.error_message}")
            partial_success_count += 1
        else:
            _log.info(f"Document {conv_res.input.file} failed to convert.")
            failure_count += 1

    _log.info(
        f"Processed {success_count + partial_success_count + failure_count} docs, "
        f"of which {failure_count} failed "
        f"and {partial_success_count} were partially converted."
    )
    return success_count, partial_success_count, failure_count


def main():
    logging.basicConfig(level=logging.INFO)

    input_doc_paths = [
        Path("./tests/data/pdf/2206.01062.pdf"),
        Path("./tests/data/pdf/2203.01017v2.pdf"),
        Path("./tests/data/pdf/2305.03393v1.pdf"),
        Path("./tests/data/pdf/redp5110_sampled.pdf"),
    ]

    # buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read())
    # docs = [DocumentStream(name="my_doc.pdf", stream=buf)]
    # input = DocumentConversionInput.from_streams(docs)

    # # Turn on inline debug visualizations:
    # settings.debug.visualize_layout = True
    # settings.debug.visualize_ocr = True
    # settings.debug.visualize_tables = True
    # settings.debug.visualize_cells = True

    pipeline_options = PdfPipelineOptions()
    pipeline_options.generate_page_images = True

    doc_converter = DocumentConverter(
        format_options={
            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
        }
    )

    start_time = time.time()

    conv_results = doc_converter.convert_all(
        input_doc_paths,
        raises_on_error=True,  # to let conversion run through all and examine results at the end
    )
    success_count, partial_success_count, failure_count = export_documents(
        conv_results, output_dir=Path("scratch")
    )

    end_time = time.time() - start_time

    _log.info(f"Document conversion complete in {end_time:.2f} seconds.")

    if failure_count > 0:
        raise RuntimeError(
            f"The example failed converting {failure_count} on {len(input_doc_paths)}."
        )


if __name__ == "__main__":
    main()