mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
5458a88464
* add coverage calculation and push Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * new codecov version and usage of token Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * enable ruff formatter instead of black and isort Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * apply ruff lint fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * apply ruff unsafe fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add removed imports Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * runs 1 on linter issues Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * finalize linter fixes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Update pyproject.toml Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
42 lines
1.3 KiB
Python
Vendored
42 lines
1.3 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():
|
|
input_doc = Path("./tests/data/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).document
|
|
md = doc.export_to_markdown()
|
|
print(md)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|