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

* 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

View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.6.0",
"version": "1.7.0",
"name": "csv-too-many-columns",
"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": "4",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -101,7 +105,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -113,7 +118,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -125,7 +131,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -137,7 +144,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -149,7 +157,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -161,7 +170,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -173,7 +183,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -185,7 +196,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -197,7 +209,8 @@
"text": "e",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -209,7 +222,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -221,7 +235,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -233,7 +248,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -245,7 +261,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -257,7 +274,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -269,7 +287,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -281,7 +300,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -293,7 +313,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
"num_rows": 5,
@@ -310,7 +331,8 @@
"text": "1",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -322,7 +344,8 @@
"text": "2",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -334,7 +357,8 @@
"text": "3",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -346,7 +370,8 @@
"text": "4",
"column_header": true,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -358,7 +383,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -372,7 +398,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -384,7 +411,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -396,7 +424,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -408,7 +437,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -420,7 +450,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -434,7 +465,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -446,7 +478,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -458,7 +491,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -470,7 +504,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -482,7 +517,8 @@
"text": "e",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -496,7 +532,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -508,7 +545,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -520,7 +558,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -532,7 +571,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -544,7 +584,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -558,7 +599,8 @@
"text": "a",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -570,7 +612,8 @@
"text": "b",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -582,7 +625,8 @@
"text": "c",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -594,7 +638,8 @@
"text": "d",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -606,7 +651,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
]
]