mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 05:08:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: add table raw content when no table structure model is used (#1815)

Browse Source 
* add table raw cells when no table structure model was used

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Add RichTableCell instance for tables with missing structure.

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-10-02 13:46:42 +02:00
committed by GitHub
parent f0b630e24e
commit 4f295ed051
34 changed files with 6835 additions and 3389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

119
tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json vendored
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.6.0",
"version": "1.7.0",
"name": "csv-inconsistent-header",
"origin": {
"mimetype": "text/csv",
@@ -53,7 +53,8 @@
"text": "1",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -65,7 +66,8 @@
"text": "2",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -77,7 +79,8 @@
"text": "3",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -89,7 +92,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -101,7 +105,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -113,7 +118,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -125,7 +131,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -137,7 +144,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -149,7 +157,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -161,7 +170,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -173,7 +183,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -185,7 +196,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -197,7 +209,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -209,7 +222,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -221,7 +235,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -233,7 +248,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -245,7 +261,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -257,7 +274,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -269,7 +287,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
"num_rows": 5,
@@ -286,7 +305,8 @@
"text": "1",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -298,7 +318,8 @@
"text": "2",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -310,7 +331,8 @@
"text": "3",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -322,7 +344,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -336,7 +359,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -348,7 +372,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -360,7 +385,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -372,7 +398,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -386,7 +413,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -398,7 +426,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -410,7 +439,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -422,7 +452,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -436,7 +467,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -448,7 +480,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -460,7 +493,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -472,7 +506,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -486,7 +521,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -498,7 +534,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -510,7 +547,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -522,7 +560,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
]
]