mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 13:18:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: use first table row as col headers (#1156)

Browse Source 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-03-13 15:34:18 +01:00
committed by GitHub
parent 6eb718f849
commit 0945973b79
33 changed files with 286 additions and 310 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
tests/data/groundtruth/docling_v2/word_tables.docx.json
View File

@@ -261,7 +261,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -273,7 +273,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -285,7 +285,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -374,7 +374,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -386,7 +386,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -398,7 +398,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -504,7 +504,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -516,7 +516,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -528,7 +528,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -593,7 +593,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -605,7 +605,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -617,7 +617,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -723,7 +723,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -735,7 +735,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -747,7 +747,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -759,7 +759,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Header 0.3",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -848,7 +848,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -860,7 +860,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -872,7 +872,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -884,7 +884,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Header 0.3",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -1014,7 +1014,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1026,7 +1026,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1038,7 +1038,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1175,7 +1175,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1187,7 +1187,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1199,7 +1199,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -1381,7 +1381,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1393,7 +1393,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1405,7 +1405,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1417,7 +1417,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1429,7 +1429,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1818,7 +1818,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 0.0",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1830,7 +1830,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Header 0.1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1842,7 +1842,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "Header 0.2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1854,7 +1854,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1866,7 +1866,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -2372,5 +2372,6 @@
}
],
"key_value_items": [],
"form_items": [],
"pages": {}
}