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

23
tests/data/groundtruth/docling_v2/example_03.html.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "example_03",
"origin": {
"mimetype": "text/html",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -37,6 +39,7 @@
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@@ -53,6 +56,7 @@
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@@ -69,6 +73,7 @@
"$ref": "#/texts/12"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
},
@@ -85,6 +90,7 @@
"$ref": "#/texts/11"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
}
@@ -106,6 +112,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Example Document",
@@ -121,6 +128,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Introduction",
@@ -133,6 +141,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is the first paragraph of the introduction.",
@@ -154,6 +163,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Background",
@@ -166,6 +176,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Some background information here.",
@@ -181,6 +192,7 @@
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in unordered list",
@@ -194,6 +206,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested item 1",
@@ -207,6 +220,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested item 2",
@@ -220,6 +234,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in unordered list",
@@ -237,6 +252,7 @@
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in ordered list",
@@ -250,6 +266,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested ordered item 1",
@@ -263,6 +280,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested ordered item 2",
@@ -276,6 +294,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in ordered list",
@@ -293,6 +312,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Data Table",
@@ -308,6 +328,7 @@
"$ref": "#/texts/13"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],