mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-25 19:44:34 +00:00
8543c22687
* Add "auto" language for TesseractOcr Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de> * Add tesseract-ocr-script-latn installation for the "auto" language Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de> * Modify "auto" language in TesseractOcr to initialize the script readers lazily Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de> * Finalize script readers Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de> * Fix script models prefix for Linux Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de> --------- Signed-off-by: Pavel Denisov <pavel.denisov@iais.fraunhofer.de> |
||
|---|---|---|
| .. | ||
| data | ||
| data_scanned | ||
| __init__.py | ||
| test_backend_asciidoc.py | ||
| test_backend_docling_parse_v2.py | ||
| test_backend_docling_parse.py | ||
| test_backend_html.py | ||
| test_backend_msexcel.py | ||
| test_backend_msword.py | ||
| test_backend_patent_uspto.py | ||
| test_backend_pdfium.py | ||
| test_backend_pptx.py | ||
| test_backend_pubmed.py | ||
| test_cli.py | ||
| test_e2e_conversion.py | ||
| test_e2e_ocr_conversion.py | ||
| test_input_doc.py | ||
| test_interfaces.py | ||
| test_invalid_input.py | ||
| test_legacy_format_transform.py | ||
| test_options.py | ||
| verify_utils.py | ||