mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 21:28:17 +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

128
tests/data/groundtruth/docling_v2/pa20010031492.json vendored
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.6.0",
"version": "1.7.0",
"name": "pa20010031492.xml",
"origin": {
"mimetype": "application/xml",
@@ -1616,7 +1616,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1628,7 +1629,8 @@
"text": "SENSITIVITY-EC50 VALUES",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1640,7 +1642,8 @@
"text": "SENSITIVITY-EC50 VALUES",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1652,7 +1655,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1664,7 +1668,8 @@
"text": "GROWTH STAGE OF",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1676,7 +1681,8 @@
"text": "ZEOCIN",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1688,7 +1694,8 @@
"text": "CONTROL",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1700,7 +1707,8 @@
"text": "CONTROL",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1712,7 +1720,8 @@
"text": "ASSAY REAGENT",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1724,7 +1733,8 @@
"text": "TREATED",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1736,7 +1746,8 @@
"text": "CELLS",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1748,7 +1759,8 @@
"text": "CELLS",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1760,7 +1772,8 @@
"text": "Lag Phase",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1772,7 +1785,8 @@
"text": "1.445 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1784,7 +1798,8 @@
"text": "1.580 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1796,7 +1811,8 @@
"text": "1.580 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1808,7 +1824,8 @@
"text": "Expotential phase",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1820,7 +1837,8 @@
"text": "0.446 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1832,7 +1850,8 @@
"text": "0.446 ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1844,7 +1863,8 @@
"text": "0.446 ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1856,7 +1876,8 @@
"text": "Stationary phase",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1868,7 +1889,8 @@
"text": "0.426 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1880,7 +1902,8 @@
"text": "0.457 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1892,7 +1915,8 @@
"text": "0.457 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
"num_rows": 6,
@@ -1909,7 +1933,8 @@
"text": "",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1921,7 +1946,8 @@
"text": "SENSITIVITY-EC50 VALUES",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1933,7 +1959,8 @@
"text": "SENSITIVITY-EC50 VALUES",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -1947,7 +1974,8 @@
"text": "GROWTH STAGE OF",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1959,7 +1987,8 @@
"text": "ZEOCIN",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1971,7 +2000,8 @@
"text": "CONTROL",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -1985,7 +2015,8 @@
"text": "ASSAY REAGENT",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -1997,7 +2028,8 @@
"text": "TREATED",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2009,7 +2041,8 @@
"text": "CELLS",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -2023,7 +2056,8 @@
"text": "Lag Phase",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2035,7 +2069,8 @@
"text": "1.445 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2047,7 +2082,8 @@
"text": "1.580 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -2061,7 +2097,8 @@
"text": "Expotential phase",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2073,7 +2110,8 @@
"text": "0.446 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2085,7 +2123,8 @@
"text": "0.446 ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
],
[
@@ -2099,7 +2138,8 @@
"text": "Stationary phase",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2111,7 +2151,8 @@
"text": "0.426 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
},
{
"row_span": 1,
@@ -2123,7 +2164,8 @@
"text": "0.457 ppm ZnSO4",
"column_header": false,
"row_header": false,
"row_section": false
"row_section": false,
"fillable": false
}
]
]