docling_custom.py

import json
import logging
import time
from pathlib import Path

from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.models.ocr_mac_model import OcrMacOptions
from docling.models.tesseract_ocr_cli_model import TesseractCliOcrOptions
from docling.models.tesseract_ocr_model import TesseractOcrOptions

_log = logging.getLogger(__name__)

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

    input_doc_path = Path("input/sample-3.pdf")

    ###########################################################################

    # The following sections contain a combination of PipelineOptions
    # and PDF Backends for various configurations.
    # Uncomment one section at the time to see the differences in the output.

    # PyPdfium without EasyOCR
    # --------------------
    # pipeline_options = PdfPipelineOptions()
    # pipeline_options.do_ocr = False
    # pipeline_options.do_table_structure = True
    # pipeline_options.table_structure_options.do_cell_matching = False

    # doc_converter = DocumentConverter(
    #     format_options={
    #         InputFormat.PDF: PdfFormatOption(
    #             pipeline_options=pipeline_options, backend=PyPdfiumDocumentBackend
    #         )
    #     }
    # )

    # PyPdfium with EasyOCR
    # -----------------
    pipeline_options = PdfPipelineOptions()
    pipeline_options.do_ocr = True
    pipeline_options.do_table_structure = True
    pipeline_options.table_structure_options.do_cell_matching = True

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

    # Docling Parse without EasyOCR
    # -------------------------
    # pipeline_options = PdfPipelineOptions()
    # pipeline_options.do_ocr = False
    # pipeline_options.do_table_structure = True
    # pipeline_options.table_structure_options.do_cell_matching = True

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

    # Docling Parse with EasyOCR
    # ----------------------
    #pipeline_options = PdfPipelineOptions()
    #pipeline_options.do_ocr = True
    #pipeline_options.do_table_structure = True
    #pipeline_options.table_structure_options.do_cell_matching = True

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

    # Docling Parse with EasyOCR (CPU only)
    # ----------------------
    # pipeline_options = PdfPipelineOptions()
    # pipeline_options.do_ocr = True
    # pipeline_options.ocr_options.use_gpu = False  # <-- set this.
    # pipeline_options.do_table_structure = True
    # pipeline_options.table_structure_options.do_cell_matching = True

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

    # Docling Parse with Tesseract
    # ----------------------
    # pipeline_options = PdfPipelineOptions()
    # pipeline_options.do_ocr = True
    # pipeline_options.do_table_structure = True
    # pipeline_options.table_structure_options.do_cell_matching = True
    # pipeline_options.ocr_options = TesseractOcrOptions()

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

    # Docling Parse with Tesseract CLI
    # ----------------------
    # pipeline_options = PdfPipelineOptions()
    # pipeline_options.do_ocr = True
    # pipeline_options.do_table_structure = True
    # pipeline_options.table_structure_options.do_cell_matching = True
    # pipeline_options.ocr_options = TesseractCliOcrOptions()

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

    # Docling Parse with ocrmac(Mac only)
    # ----------------------
    # pipeline_options = PdfPipelineOptions()
    # pipeline_options.do_ocr = True
    # pipeline_options.do_table_structure = True
    # pipeline_options.table_structure_options.do_cell_matching = True
    # pipeline_options.ocr_options = OcrMacOptions()

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

    ###########################################################################

    start_time = time.time()
    conv_result = doc_converter.convert(input_doc_path)
    end_time = time.time() - start_time

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

    ## Export results
    output_dir = Path("scratch")
    output_dir.mkdir(parents=True, exist_ok=True)
    doc_filename = conv_result.input.file.stem

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

    # Export Text format:
    with (output_dir / f"{doc_filename}.txt").open("w", encoding="utf-8") as fp:
        fp.write(conv_result.document.export_to_text())

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

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

if __name__ == "__main__":
    main()