Force full page OCR

In [ ]:

from pathlib import Path

from pathlib import Path

In [ ]:

from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
    EasyOcrOptions,
    OcrMacOptions,
    PdfPipelineOptions,
    RapidOcrOptions,
    TesseractCliOcrOptions,
    TesseractOcrOptions,
)
from docling.document_converter import DocumentConverter, PdfFormatOption

from docling.backend.docling_parse_backend import DoclingParseDocumentBackend from docling.datamodel.base_models import InputFormat from docling.datamodel.pipeline_options import ( EasyOcrOptions, OcrMacOptions, PdfPipelineOptions, RapidOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions, ) from docling.document_converter import DocumentConverter, PdfFormatOption

In [ ]:

def main():
    input_doc = Path("./tests/data/2206.01062.pdf")

    pipeline_options = PdfPipelineOptions()
    pipeline_options.do_ocr = True
    pipeline_options.do_table_structure = True
    pipeline_options.table_structure_options.do_cell_matching = True

    # Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), RapidOcrOptions
    # ocr_options = EasyOcrOptions(force_full_page_ocr=True)
    # ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
    # ocr_options = OcrMacOptions(force_full_page_ocr=True)
    # ocr_options = RapidOcrOptions(force_full_page_ocr=True)
    ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True)
    pipeline_options.ocr_options = ocr_options

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

    doc = converter.convert(input_doc).document
    md = doc.export_to_markdown()
    print(md)

def main(): input_doc = Path("./tests/data/2206.01062.pdf") pipeline_options = PdfPipelineOptions() pipeline_options.do_ocr = True pipeline_options.do_table_structure = True pipeline_options.table_structure_options.do_cell_matching = True # Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), RapidOcrOptions # ocr_options = EasyOcrOptions(force_full_page_ocr=True) # ocr_options = TesseractOcrOptions(force_full_page_ocr=True) # ocr_options = OcrMacOptions(force_full_page_ocr=True) # ocr_options = RapidOcrOptions(force_full_page_ocr=True) ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True) pipeline_options.ocr_options = ocr_options converter = DocumentConverter( format_options={ InputFormat.PDF: PdfFormatOption( pipeline_options=pipeline_options, ) } ) doc = converter.convert(input_doc).document md = doc.export_to_markdown() print(md)

In [ ]:

if __name__ == "__main__":
    main()

if __name__ == "__main__": main()