mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 03:55:00 +00:00
f542460af3
* add real e2e tests for html and docx Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the output of itxt Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the text Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests (2) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the examples (1) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the output of the test Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the tests, moved the ground-truth Signed-off-by: Peter Staar <taa@zurich.ibm.com> * moved the ground-truth data Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the html tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * restructure title fix (#187) Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
703 lines
13 KiB
JSON
703 lines
13 KiB
JSON
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.0.0",
|
|
"name": "unit_test_headers",
|
|
"origin": {
|
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
|
"binary_hash": 15606343257915737103,
|
|
"filename": "unit_test_headers.docx"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
}
|
|
],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [
|
|
{
|
|
"self_ref": "#/groups/0",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/33"
|
|
}
|
|
],
|
|
"name": "header-2",
|
|
"label": "section"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/27"
|
|
}
|
|
],
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Test Document",
|
|
"text": "Test Document"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/3"
|
|
},
|
|
{
|
|
"$ref": "#/texts/4"
|
|
},
|
|
{
|
|
"$ref": "#/texts/5"
|
|
},
|
|
{
|
|
"$ref": "#/texts/6"
|
|
},
|
|
{
|
|
"$ref": "#/texts/7"
|
|
},
|
|
{
|
|
"$ref": "#/texts/8"
|
|
},
|
|
{
|
|
"$ref": "#/texts/14"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 1",
|
|
"text": "Section 1",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.1",
|
|
"text": "Paragraph 1.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.2",
|
|
"text": "Paragraph 1.2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/7",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/8",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/9"
|
|
},
|
|
{
|
|
"$ref": "#/texts/10"
|
|
},
|
|
{
|
|
"$ref": "#/texts/11"
|
|
},
|
|
{
|
|
"$ref": "#/texts/12"
|
|
},
|
|
{
|
|
"$ref": "#/texts/13"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 1.1",
|
|
"text": "Section 1.1",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/9",
|
|
"parent": {
|
|
"$ref": "#/texts/8"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/10",
|
|
"parent": {
|
|
"$ref": "#/texts/8"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.1.1",
|
|
"text": "Paragraph 1.1.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/11",
|
|
"parent": {
|
|
"$ref": "#/texts/8"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/12",
|
|
"parent": {
|
|
"$ref": "#/texts/8"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.1.2",
|
|
"text": "Paragraph 1.1.2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/13",
|
|
"parent": {
|
|
"$ref": "#/texts/8"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/14",
|
|
"parent": {
|
|
"$ref": "#/texts/2"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/15"
|
|
},
|
|
{
|
|
"$ref": "#/texts/16"
|
|
},
|
|
{
|
|
"$ref": "#/texts/17"
|
|
},
|
|
{
|
|
"$ref": "#/texts/18"
|
|
},
|
|
{
|
|
"$ref": "#/texts/19"
|
|
},
|
|
{
|
|
"$ref": "#/texts/20"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 1.2",
|
|
"text": "Section 1.2",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/15",
|
|
"parent": {
|
|
"$ref": "#/texts/14"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/16",
|
|
"parent": {
|
|
"$ref": "#/texts/14"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.1.1",
|
|
"text": "Paragraph 1.1.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/17",
|
|
"parent": {
|
|
"$ref": "#/texts/14"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/18",
|
|
"parent": {
|
|
"$ref": "#/texts/14"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.1.2",
|
|
"text": "Paragraph 1.1.2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/19",
|
|
"parent": {
|
|
"$ref": "#/texts/14"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/20",
|
|
"parent": {
|
|
"$ref": "#/texts/14"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/21"
|
|
},
|
|
{
|
|
"$ref": "#/texts/22"
|
|
},
|
|
{
|
|
"$ref": "#/texts/23"
|
|
},
|
|
{
|
|
"$ref": "#/texts/24"
|
|
},
|
|
{
|
|
"$ref": "#/texts/25"
|
|
},
|
|
{
|
|
"$ref": "#/texts/26"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 1.2.3",
|
|
"text": "Section 1.2.3",
|
|
"level": 3
|
|
},
|
|
{
|
|
"self_ref": "#/texts/21",
|
|
"parent": {
|
|
"$ref": "#/texts/20"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/22",
|
|
"parent": {
|
|
"$ref": "#/texts/20"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.2.3.1",
|
|
"text": "Paragraph 1.2.3.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/23",
|
|
"parent": {
|
|
"$ref": "#/texts/20"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/24",
|
|
"parent": {
|
|
"$ref": "#/texts/20"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 1.2.3.1",
|
|
"text": "Paragraph 1.2.3.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/25",
|
|
"parent": {
|
|
"$ref": "#/texts/20"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/26",
|
|
"parent": {
|
|
"$ref": "#/texts/20"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/27",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/28"
|
|
},
|
|
{
|
|
"$ref": "#/texts/29"
|
|
},
|
|
{
|
|
"$ref": "#/texts/30"
|
|
},
|
|
{
|
|
"$ref": "#/texts/31"
|
|
},
|
|
{
|
|
"$ref": "#/texts/32"
|
|
},
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/39"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 2",
|
|
"text": "Section 2",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/28",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/29",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 2.1",
|
|
"text": "Paragraph 2.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/30",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/31",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 2.2",
|
|
"text": "Paragraph 2.2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/32",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/33",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/34"
|
|
},
|
|
{
|
|
"$ref": "#/texts/35"
|
|
},
|
|
{
|
|
"$ref": "#/texts/36"
|
|
},
|
|
{
|
|
"$ref": "#/texts/37"
|
|
},
|
|
{
|
|
"$ref": "#/texts/38"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 2.1.1",
|
|
"text": "Section 2.1.1",
|
|
"level": 3
|
|
},
|
|
{
|
|
"self_ref": "#/texts/34",
|
|
"parent": {
|
|
"$ref": "#/texts/33"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/35",
|
|
"parent": {
|
|
"$ref": "#/texts/33"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 2.1.1.1",
|
|
"text": "Paragraph 2.1.1.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/36",
|
|
"parent": {
|
|
"$ref": "#/texts/33"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/37",
|
|
"parent": {
|
|
"$ref": "#/texts/33"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 2.1.1.1",
|
|
"text": "Paragraph 2.1.1.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/38",
|
|
"parent": {
|
|
"$ref": "#/texts/33"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/39",
|
|
"parent": {
|
|
"$ref": "#/texts/27"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/40"
|
|
},
|
|
{
|
|
"$ref": "#/texts/41"
|
|
},
|
|
{
|
|
"$ref": "#/texts/42"
|
|
},
|
|
{
|
|
"$ref": "#/texts/43"
|
|
},
|
|
{
|
|
"$ref": "#/texts/44"
|
|
},
|
|
{
|
|
"$ref": "#/texts/45"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Section 2.1",
|
|
"text": "Section 2.1",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/40",
|
|
"parent": {
|
|
"$ref": "#/texts/39"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/41",
|
|
"parent": {
|
|
"$ref": "#/texts/39"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 2.1.1",
|
|
"text": "Paragraph 2.1.1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/42",
|
|
"parent": {
|
|
"$ref": "#/texts/39"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/43",
|
|
"parent": {
|
|
"$ref": "#/texts/39"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Paragraph 2.1.2",
|
|
"text": "Paragraph 2.1.2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/44",
|
|
"parent": {
|
|
"$ref": "#/texts/39"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/45",
|
|
"parent": {
|
|
"$ref": "#/texts/39"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [],
|
|
"key_value_items": [],
|
|
"pages": {}
|
|
} |