NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions 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
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.json
+54 -1
View File
@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "unit_test_headers_numbered",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -56,6 +57,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@@ -73,6 +75,7 @@
"$ref": "#/texts/27"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
},
@@ -89,6 +92,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"name": "header-1",
"label": "section"
},
@@ -102,6 +106,7 @@
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
},
@@ -118,6 +123,7 @@
"$ref": "#/texts/39"
}
],
"content_layer": "body",
"name": "header-1",
"label": "section"
},
@@ -131,6 +137,7 @@
"$ref": "#/texts/33"
}
],
"content_layer": "body",
"name": "header-2",
"label": "section"
}
@@ -149,6 +156,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Test Document",
@@ -160,6 +168,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -171,6 +180,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1",
@@ -183,6 +193,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -194,6 +205,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1",
@@ -205,6 +217,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -216,6 +229,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2",
@@ -227,6 +241,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -254,6 +269,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.1",
@@ -266,6 +282,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -277,6 +294,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.1",
@@ -288,6 +306,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -299,6 +318,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.2",
@@ -310,6 +330,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -340,6 +361,7 @@
"$ref": "#/texts/20"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2",
@@ -352,6 +374,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -363,6 +386,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.1",
@@ -374,6 +398,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -385,6 +410,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.2",
@@ -396,6 +422,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -426,6 +453,7 @@
"$ref": "#/texts/26"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2.3",
@@ -438,6 +466,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -449,6 +478,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2.3.1",
@@ -460,6 +490,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -471,6 +502,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2.3.1",
@@ -482,6 +514,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -493,6 +526,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -504,6 +538,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2",
@@ -516,6 +551,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -527,6 +563,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1",
@@ -538,6 +575,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -549,6 +587,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.2",
@@ -560,6 +599,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -587,6 +627,7 @@
"$ref": "#/texts/38"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1.1",
@@ -599,6 +640,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -610,6 +652,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1.1",
@@ -621,6 +664,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -632,6 +676,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1.1",
@@ -643,6 +688,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -673,6 +719,7 @@
"$ref": "#/texts/45"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1",
@@ -685,6 +732,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -696,6 +744,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1",
@@ -707,6 +756,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -718,6 +768,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.2",
@@ -729,6 +780,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -740,6 +792,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",