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 address, details, and summary tags (#1436)

Browse Source 
* fix(html): handle 'address' tag

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* fix(html): handle 'details' tag

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

---------

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-04-23 09:30:59 +02:00
committed by GitHub
parent c2470ed216
commit ed20124544
5 changed files with 82 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
tests/data/groundtruth/docling_v2/example_06.html.json
View File

@@ -4,7 +4,7 @@
"name": "example_06",
"origin": {
"mimetype": "text/html",
"binary_hash": 14574683870626799530,
"binary_hash": 10224930410364781672,
"filename": "example_06.html"
},
"furniture": {
@@ -30,14 +30,35 @@
"$ref": "#/texts/3"
},
{
"$ref": "#/texts/4"
"$ref": "#/groups/0"
},
{
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [],
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/4"
},
{
"$ref": "#/texts/5"
}
],
"content_layer": "body",
"name": "details",
"label": "section"
}
],
"texts": [
{
"self_ref": "#/texts/0",
@@ -89,6 +110,30 @@
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Heading for the details element",
"text": "Heading for the details element"
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Description of the details element.",
"text": "Description of the details element."
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/body"
},