mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-25 03:24:59 +00:00
7d3302cb48
* Keep page.parsed_page.textline_cells and page.cells in sync, including OCR Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Make page.parsed_page the only source of truth for text cells Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Small fix Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Correctly compute PDF boxes from pymupdf Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use different OCR engine order Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add type hints and fix mypy Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * One more test fix Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Remove with pypdfium2_lock from caller sites Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix typing Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> |
||
|---|---|---|
| .. | ||
| data | ||
| data_scanned | ||
| __init__.py | ||
| test_backend_asciidoc.py | ||
| test_backend_csv.py | ||
| test_backend_docling_json.py | ||
| test_backend_docling_parse_v2.py | ||
| test_backend_docling_parse_v4.py | ||
| test_backend_docling_parse.py | ||
| test_backend_html.py | ||
| test_backend_jats.py | ||
| test_backend_markdown.py | ||
| test_backend_msexcel.py | ||
| test_backend_msword.py | ||
| test_backend_patent_uspto.py | ||
| test_backend_pdfium.py | ||
| test_backend_pptx.py | ||
| test_backend_webp.py | ||
| test_cli.py | ||
| test_code_formula.py | ||
| test_data_gen_flag.py | ||
| test_document_picture_classifier.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 | ||
| test_settings_load.py | ||
| verify_utils.py | ||