mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: fix duplicate title and heading + add e2e tests for html and docx (#186)

Browse Source 
* 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
2024-10-30 13:14:56 +01:00
committed by GitHub
parent dda2645d4c
commit f542460af3
49 changed files with 13733 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

151
tests/data/groundtruth/docling_v2/unit_test_01.html.json Normal file
View File

@@ -0,0 +1,151 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"name": "unit_test_01",
"origin": {
"mimetype": "text/html",
"binary_hash": 11574357959810932112,
"filename": "unit_test_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/3"
},
"children": [
{
"$ref": "#/texts/4"
}
],
"name": "header-3",
"label": "section"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/3"
}
],
"label": "title",
"prov": [],
"orig": "Title",
"text": "Title"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/texts/2"
}
],
"label": "section_header",
"prov": [],
"orig": "section-1",
"text": "section-1",
"level": 2
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/texts/1"
},
"children": [],
"label": "section_header",
"prov": [],
"orig": "section-1.1",
"text": "section-1.1",
"level": 3
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/groups/0"
},
{
"$ref": "#/texts/5"
},
{
"$ref": "#/texts/6"
}
],
"label": "section_header",
"prov": [],
"orig": "section-2",
"text": "section-2",
"level": 2
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"label": "section_header",
"prov": [],
"orig": "section-2.0.1",
"text": "section-2.0.1",
"level": 4
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/texts/3"
},
"children": [],
"label": "section_header",
"prov": [],
"orig": "section-2.2",
"text": "section-2.2",
"level": 3
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/texts/3"
},
"children": [],
"label": "section_header",
"prov": [],
"orig": "section-2.3",
"text": "section-2.3",
"level": 3
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"pages": {}
}