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

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

12
tests/data/groundtruth/docling_v2/unit_test_01.html.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "unit_test_01",
"origin": {
"mimetype": "text/html",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -34,6 +36,7 @@
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"name": "header-3",
"label": "section"
}
@@ -52,6 +55,7 @@
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Title",
@@ -67,6 +71,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-1",
@@ -79,6 +84,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-1.1",
@@ -101,6 +107,7 @@
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2",
@@ -113,6 +120,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.0.1",
@@ -125,6 +133,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.2",
@@ -137,6 +146,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.3",