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

22
tests/data/groundtruth/docling_v2/word_tables.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "word_tables",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -20,6 +21,7 @@
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -34,6 +36,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
}
@@ -94,6 +97,7 @@
"$ref": "#/texts/11"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test with tables",
@@ -106,6 +110,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A uniform table",
@@ -117,6 +122,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -128,6 +134,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with horizontal spans",
@@ -139,6 +146,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -150,6 +158,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with horizontal spans in inner columns",
@@ -161,6 +170,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -172,6 +182,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with vertical spans",
@@ -183,6 +194,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -194,6 +206,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with all kinds of spans and empty cells",
@@ -205,6 +218,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -216,6 +230,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -230,6 +245,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -472,6 +488,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -690,6 +707,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -980,6 +998,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@@ -1346,6 +1365,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],