df140227c3
* code for xlsm support
* updated support for xlsm
* updated code for xlsm support
* Update docling_parse_v4_backend.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Update docling_parse_v4_backend.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Update test_backend_msexcel_xlsm.py
updated the tests/test_backend_msexcel_xlsm.py:
have a function starting with test
removed all print statements
** To add an explicit assert {test}=={pred}
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Update base_models.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Update test_backend_msexcel.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Update test_backend_msexcel_xlsm.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Update document_converter.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* Delete tests/test_backend_msexcel_xlsm.py
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* xlsm file
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
* run tests
* ran tests
* Fix tests, upgrade XSLM example to a valid file
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
---------
Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
77 lines
1.6 KiB
JSON
Vendored
77 lines
1.6 KiB
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.3.0",
|
|
"name": "webp-test",
|
|
"origin": {
|
|
"mimetype": "application/pdf",
|
|
"binary_hash": 16115062463007057787,
|
|
"filename": "webp-test.webp",
|
|
"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": 234.08627147881114,
|
|
"t": 2570.0959833241664,
|
|
"r": 1696.0985042090742,
|
|
"b": 2319.1220927976665,
|
|
"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": 2000.0,
|
|
"height": 2829.0
|
|
},
|
|
"image": null,
|
|
"page_no": 1
|
|
}
|
|
}
|
|
} |