7c5614a37a
* fix(markdown): fix formatting & inline edge cases (show behavior before change) Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> * add change and updated test data Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> * update lock Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> * improve test case Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> --------- Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
77 lines
1.6 KiB
JSON
Vendored
77 lines
1.6 KiB
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.4.0",
|
|
"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": 69.6796630536824,
|
|
"t": 764.9216921155637,
|
|
"r": 504.8720051760782,
|
|
"b": 689.0124221922704,
|
|
"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
|
|
}
|
|
}
|
|
} |