mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
fix: fix duplicate title and heading + add e2e tests for html and docx (#186)
* 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>
This commit is contained in:
Peter W. J. Staar
committed by
GitHub
GitHub
parent
dda2645d4c
commit
f542460af3
197
tests/data/groundtruth/docling_v2/example_01.html.json
Normal file
197
tests/data/groundtruth/docling_v2/example_01.html.json
Normal file
@@ -0,0 +1,197 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.0.0",
|
||||
"name": "example_01",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
"binary_hash": 13782069548509991617,
|
||||
"filename": "example_01.html"
|
||||
},
|
||||
"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/2"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/4"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/5"
|
||||
}
|
||||
],
|
||||
"name": "list",
|
||||
"label": "list"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/1",
|
||||
"parent": {
|
||||
"$ref": "#/texts/2"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/6"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/7"
|
||||
}
|
||||
],
|
||||
"name": "ordered list",
|
||||
"label": "ordered_list"
|
||||
}
|
||||
],
|
||||
"texts": [
|
||||
{
|
||||
"self_ref": "#/texts/0",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/2"
|
||||
}
|
||||
],
|
||||
"label": "title",
|
||||
"prov": [],
|
||||
"orig": "Introduction",
|
||||
"text": "Introduction"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/1",
|
||||
"parent": {
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
"children": [],
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "This is the first paragraph of the introduction.",
|
||||
"text": "This is the first paragraph of the introduction."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/2",
|
||||
"parent": {
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/3"
|
||||
},
|
||||
{
|
||||
"$ref": "#/pictures/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/1"
|
||||
}
|
||||
],
|
||||
"label": "section_header",
|
||||
"prov": [],
|
||||
"orig": "Background",
|
||||
"text": "Background",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/3",
|
||||
"parent": {
|
||||
"$ref": "#/texts/2"
|
||||
},
|
||||
"children": [],
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "Some background information here.",
|
||||
"text": "Some background information here."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/4",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "First item in unordered list",
|
||||
"text": "First item in unordered list",
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/5",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "Second item in unordered list",
|
||||
"text": "Second item in unordered list",
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/6",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "First item in ordered list",
|
||||
"text": "First item in ordered list",
|
||||
"enumerated": true,
|
||||
"marker": "1."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/7",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "Second item in ordered list",
|
||||
"text": "Second item in ordered list",
|
||||
"enumerated": true,
|
||||
"marker": "2."
|
||||
}
|
||||
],
|
||||
"pictures": [
|
||||
{
|
||||
"self_ref": "#/pictures/0",
|
||||
"parent": {
|
||||
"$ref": "#/texts/2"
|
||||
},
|
||||
"children": [],
|
||||
"label": "picture",
|
||||
"prov": [],
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"tables": [],
|
||||
"key_value_items": [],
|
||||
"pages": {}
|
||||
}
|
||||
Reference in New Issue
Block a user