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(html): handle nested empty lists (#1154)
Some checks failed
Run Docs CD / build-deploy-docs (push) Failing after 1m20s
Run Docs CI / build-docs (push) Failing after 49s

Browse Source 
Address the case of nested lists in empty list items.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-03-13 16:56:58 +01:00
committed by GitHub
parent 0945973b79
commit f94da44ec5
5 changed files with 456 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

374
tests/data/groundtruth/docling_v2/example_07.html.json Normal file
View File

@@ -0,0 +1,374 @@
{
"schema_name": "DoclingDocument",
"version": "1.2.0",
"name": "example_07",
"origin": {
"mimetype": "text/html",
"binary_hash": 623628706615267627,
"filename": "example_07.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/texts/4"
},
{
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/1",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
},
{
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/2",
"parent": {
"$ref": "#/texts/4"
},
"children": [
{
"$ref": "#/texts/5"
},
{
"$ref": "#/texts/6"
},
{
"$ref": "#/texts/7"
},
{
"$ref": "#/texts/10"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/3",
"parent": {
"$ref": "#/texts/7"
},
"children": [
{
"$ref": "#/groups/4"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/4",
"parent": {
"$ref": "#/groups/3"
},
"children": [
{
"$ref": "#/texts/8"
},
{
"$ref": "#/texts/9"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/5",
"parent": {
"$ref": "#/texts/10"
},
"children": [
{
"$ref": "#/groups/6"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/6",
"parent": {
"$ref": "#/groups/5"
},
"children": [
{
"$ref": "#/texts/11"
},
{
"$ref": "#/texts/12"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/groups/0"
},
"children": [
{
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Asia",
"text": "Asia",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "China",
"text": "China",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Japan",
"text": "Japan",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Thailand",
"text": "Thailand",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/0"
},
"children": [
{
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Europe",
"text": "Europe",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "UK",
"text": "UK",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Germany",
"text": "Germany",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Switzerland",
"text": "Switzerland",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Bern",
"text": "Bern",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Aargau",
"text": "Aargau",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/10",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/groups/5"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Italy",
"text": "Italy",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/11",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Piedmont",
"text": "Piedmont",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/12",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Liguria",
"text": "Liguria",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/13",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Africa",
"text": "Africa",
"enumerated": false,
"marker": "-"
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}