mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 05:08:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(html): Parse text in div elements as TextItem (#1041)

Browse Source 
feat(html): Parse text in div elements as TextItem

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-02-24 12:38:29 +01:00
committed by GitHub
parent 1d17e7397a
commit 1b0ead6907
8 changed files with 2291 additions and 1804 deletions
Download Patch File Download Diff File Expand all files Collapse all files

108
tests/data/groundtruth/docling_v2/example_06.html.json Normal file
View File

@@ -0,0 +1,108 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"name": "example_06",
"origin": {
"mimetype": "text/html",
"binary_hash": 14574683870626799530,
"filename": "example_06.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
},
{
"$ref": "#/texts/3"
},
{
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is a div with text.",
"text": "This is a div with text."
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is another div with text.",
"text": "This is another div with text."
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is a regular paragraph.",
"text": "This is a regular paragraph."
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is a third div\nwith a new line.",
"text": "This is a third div\nwith a new line."
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is a fourth div with a bold paragraph.",
"text": "This is a fourth div with a bold paragraph."
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}