mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
64ac043786
support running examples from root or subfolder Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
43 lines
1.4 KiB
Python
Vendored
43 lines
1.4 KiB
Python
Vendored
from pathlib import Path
|
|
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import (
|
|
PdfPipelineOptions,
|
|
TesseractCliOcrOptions,
|
|
)
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
def main():
|
|
data_folder = Path(__file__).parent / "../../tests/data"
|
|
input_doc_path = data_folder / "pdf/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_path).document
|
|
md = doc.export_to_markdown()
|
|
print(md)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|