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

feat: Add content_layer property to items to address body, furniture and other roles (#735)

Browse Source 
* feat: Pass predicted page-headers and page-footers through to DoclingDocument furniture

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* chore: Update all test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: update all test cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: update all test cases again

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update lock

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update lock to final docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-02-10 12:07:49 +01:00
committed by GitHub
parent 3e26597995
commit cf78d5b7b9
43 changed files with 2082 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "powerpoint_sample",
"origin": {
"mimetype": "application/vnd.ms-powerpoint",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -26,6 +27,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -46,6 +48,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"name": "slide-0",
"label": "chapter"
},
@@ -74,6 +77,7 @@
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "slide-1",
"label": "chapter"
},
@@ -105,6 +109,7 @@
"$ref": "#/groups/7"
}
],
"content_layer": "body",
"name": "slide-2",
"label": "chapter"
},
@@ -124,6 +129,7 @@
"$ref": "#/texts/10"
}
],
"content_layer": "body",
"name": "list",
"label": "ordered_list"
},
@@ -146,6 +152,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@@ -162,6 +169,7 @@
"$ref": "#/texts/17"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@@ -181,6 +189,7 @@
"$ref": "#/texts/21"
}
],
"content_layer": "body",
"name": "list",
"label": "ordered_list"
},
@@ -200,6 +209,7 @@
"$ref": "#/texts/24"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@@ -211,6 +221,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "title",
"prov": [
{
@@ -237,6 +248,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -263,6 +275,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "title",
"prov": [
{
@@ -289,6 +302,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -315,6 +329,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -341,6 +356,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -367,6 +383,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -393,6 +410,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -419,6 +437,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -447,6 +466,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -475,6 +495,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -503,6 +524,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -531,6 +553,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -559,6 +582,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -587,6 +611,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -615,6 +640,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -641,6 +667,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -669,6 +696,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -697,6 +725,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@@ -723,6 +752,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -751,6 +781,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -779,6 +810,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -807,6 +839,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -835,6 +868,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -863,6 +897,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@@ -894,6 +929,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [
{