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): fix HTML parsed heading level (#1244)

Browse Source 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-03-26 10:30:23 +01:00
committed by GitHub
parent 9eb1686f93
commit 85c4df887b
13 changed files with 68 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
tests/data/groundtruth/docling_v2/wiki_duck.html.json
View File

@@ -1932,7 +1932,7 @@
"prov": [],
"orig": "Contents",
"text": "Contents",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/23",
@@ -4785,7 +4785,7 @@
"prov": [],
"orig": "Etymology",
"text": "Etymology",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/215",
@@ -4895,7 +4895,7 @@
"prov": [],
"orig": "Taxonomy",
"text": "Taxonomy",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/223",
@@ -4966,7 +4966,7 @@
"prov": [],
"orig": "Morphology",
"text": "Morphology",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/228",
@@ -5028,7 +5028,7 @@
"prov": [],
"orig": "Distribution and habitat",
"text": "Distribution and habitat",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/232",
@@ -5102,7 +5102,7 @@
"prov": [],
"orig": "Behaviour",
"text": "Behaviour",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/237",
@@ -5140,7 +5140,7 @@
"prov": [],
"orig": "Feeding",
"text": "Feeding",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/238",
@@ -5256,7 +5256,7 @@
"prov": [],
"orig": "Breeding",
"text": "Breeding",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/247",
@@ -5300,7 +5300,7 @@
"prov": [],
"orig": "Communication",
"text": "Communication",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/250",
@@ -5347,7 +5347,7 @@
"prov": [],
"orig": "Predators",
"text": "Predators",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/253",
@@ -5409,7 +5409,7 @@
"prov": [],
"orig": "Relationship with humans",
"text": "Relationship with humans",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/257",
@@ -5429,7 +5429,7 @@
"prov": [],
"orig": "Hunting",
"text": "Hunting",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/258",
@@ -5473,7 +5473,7 @@
"prov": [],
"orig": "Domestication",
"text": "Domestication",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/261",
@@ -5517,7 +5517,7 @@
"prov": [],
"orig": "Heraldry",
"text": "Heraldry",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/264",
@@ -5561,7 +5561,7 @@
"prov": [],
"orig": "Cultural references",
"text": "Cultural references",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/267",
@@ -5605,7 +5605,7 @@
"prov": [],
"orig": "See also",
"text": "See also",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/270",
@@ -5723,7 +5723,7 @@
"prov": [],
"orig": "Notes",
"text": "Notes",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/278",
@@ -5740,7 +5740,7 @@
"prov": [],
"orig": "Citations",
"text": "Citations",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/279",
@@ -6527,7 +6527,7 @@
"prov": [],
"orig": "Sources",
"text": "Sources",
"level": 3
"level": 2
},
{
"self_ref": "#/texts/335",
@@ -6860,7 +6860,7 @@
"prov": [],
"orig": "External links",
"text": "External links",
"level": 2
"level": 1
},
{
"self_ref": "#/texts/356",