mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 13:18:24 +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

11
tests/data/groundtruth/docling_v2/test_emf_docx.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "test_emf_docx",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -38,6 +39,7 @@
"$ref": "#/pictures/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -49,6 +51,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Test with three images in unusual formats",
@@ -60,6 +63,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Raster in emf:",
@@ -71,6 +75,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Vector in emf:",
@@ -82,6 +87,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Raster in webp:",
@@ -95,6 +101,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@@ -108,6 +115,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@@ -121,6 +129,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],