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

32
tests/data/groundtruth/docling_v2/word_sample.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "word_sample",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -23,6 +24,7 @@
"$ref": "#/texts/1"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -43,6 +45,7 @@
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@@ -62,6 +65,7 @@
"$ref": "#/texts/12"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@@ -81,6 +85,7 @@
"$ref": "#/texts/22"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@@ -92,6 +97,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Summer activities",
@@ -116,6 +122,7 @@
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Swimming in the lake",
@@ -127,6 +134,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Duck",
@@ -138,6 +146,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Figure 1: This is a cute duckling",
@@ -168,6 +177,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Let\u2019s swim!",
@@ -180,6 +190,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "To get started with swimming, first lay down in a water and try not to drown:",
@@ -191,6 +202,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "You can relax and look around",
@@ -204,6 +216,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Paddle about",
@@ -217,6 +230,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Enjoy summer warmth",
@@ -230,6 +244,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Also, don\u2019t forget:",
@@ -241,6 +256,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Wear sunglasses",
@@ -254,6 +270,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Don\u2019t forget to drink water",
@@ -267,6 +284,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Use sun cream",
@@ -280,6 +298,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Hmm, what else\u2026",
@@ -313,6 +332,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Let\u2019s eat",
@@ -325,6 +345,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "After we had a good day of swimming in the lake, it\u2019s important to eat something nice",
@@ -336,6 +357,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "I like to eat leaves",
@@ -347,6 +369,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Here are some interesting things a respectful duck could eat:",
@@ -358,6 +381,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -369,6 +393,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "And let\u2019s add another list in the end:",
@@ -380,6 +405,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Leaves",
@@ -393,6 +419,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Berries",
@@ -406,6 +433,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Grain",
@@ -421,6 +449,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@@ -445,6 +474,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],