mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +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

24
tests/data/groundtruth/docling_v2/wiki_duck.html.json
View File

@@ -7914,7 +7914,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -7950,7 +7950,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8130,7 +8130,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8159,7 +8159,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8171,7 +8171,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Duck\n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -8237,7 +8237,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8249,7 +8249,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Scientific classification \n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -8445,7 +8445,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8457,7 +8457,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Subfamilies\n",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}
@@ -8513,7 +8513,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8578,7 +8578,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -8590,7 +8590,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 2,
"text": "Authority control databases ",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}