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

10
tests/data/groundtruth/docling_v2/example_05.html.json
View File

@@ -68,7 +68,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -80,7 +80,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -181,7 +181,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Header 1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -193,7 +193,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -205,7 +205,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 3,
"text": "Header 2 & 3 (colspan)",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}