mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 21:28:17 +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

14
tests/data/groundtruth/docling_v2/test-01.xlsx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "test-01",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -26,6 +27,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -40,6 +42,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"name": "sheet: Sheet1",
"label": "section"
},
@@ -59,6 +62,7 @@
"$ref": "#/tables/3"
}
],
"content_layer": "body",
"name": "sheet: Sheet2",
"label": "section"
},
@@ -78,6 +82,7 @@
"$ref": "#/pictures/0"
}
],
"content_layer": "body",
"name": "sheet: Sheet3",
"label": "section"
}
@@ -90,6 +95,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@@ -114,6 +120,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -652,6 +659,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -1554,6 +1562,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -1944,6 +1953,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -2334,6 +2344,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -2800,6 +2811,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],