mirror of
https://github.com/docling-project/docling.git
synced 2025-07-03 15:18:01 +00:00
c6b3763ecb
- When the OCR is forced, any existing PDF cells are rejected. - Introduce the force-ocr cmd parameter in docling CLI. - Update unit tests. - Add the full_page_ocr.py example in mkdocs. Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
from pathlib import Path
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import (
|
|
EasyOcrOptions,
|
|
PdfPipelineOptions,
|
|
TesseractCliOcrOptions,
|
|
TesseractOcrOptions,
|
|
)
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
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
|
|
# ocr_options = EasyOcrOptions(force_full_page_ocr=True)
|
|
# ocr_options = TesseractOcrOptions(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()
|