12dab0a1e8
* support image/webp file type Signed-off-by: Elwin <61868295+hzhaoy@users.noreply.github.com> Signed-off-by: Elwin <hzywong@gmail.com> * docs: add webp image format in supported_formats.md Signed-off-by: Elwin <61868295+hzhaoy@users.noreply.github.com> Signed-off-by: Elwin <hzywong@gmail.com> * test: add a test case for `image/webp` file Signed-off-by: Elwin <hzywong@gmail.com> * style: apply styling Signed-off-by: Elwin <hzywong@gmail.com> * test: update test case of converting `image/webp` file with more ocr engines Signed-off-by: Elwin <hzywong@gmail.com> * style: apply styling Signed-off-by: Elwin <hzywong@gmail.com> * rename test file Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Elwin <61868295+hzhaoy@users.noreply.github.com> Signed-off-by: Elwin <hzywong@gmail.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
1 line
1.2 KiB
JSON
1 line
1.2 KiB
JSON
{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.0, "t": 767.2550252278646, "r": 506.6666666666667, "b": 688.5883585611979, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}} |