Automatic OCR language detection with tesseract

In [ ]:

from pathlib import Path

from pathlib import Path

In [ ]:

from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
    PdfPipelineOptions,
    TesseractCliOcrOptions,
    TesseractOcrOptions,
)
from docling.document_converter import DocumentConverter, PdfFormatOption

from docling.datamodel.base_models import InputFormat from docling.datamodel.pipeline_options import ( PdfPipelineOptions, TesseractCliOcrOptions, TesseractOcrOptions, ) from docling.document_converter import DocumentConverter, PdfFormatOption

In [ ]:

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

    # Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions
    # ocr_options = TesseractOcrOptions(lang=["auto"])
    ocr_options = TesseractCliOcrOptions(lang=["auto"])

    pipeline_options = PdfPipelineOptions(
        do_ocr=True, force_full_page_ocr=True, 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/pdf/2206.01062.pdf") # Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions # ocr_options = TesseractOcrOptions(lang=["auto"]) ocr_options = TesseractCliOcrOptions(lang=["auto"]) pipeline_options = PdfPipelineOptions( do_ocr=True, force_full_page_ocr=True, 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()