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: 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

48
tests/data/groundtruth/docling_v2/csv-tab.csv.json
View File

@@ -51,7 +51,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -63,7 +63,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -75,7 +75,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -87,7 +87,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -99,7 +99,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -111,7 +111,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -123,7 +123,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -135,7 +135,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -147,7 +147,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -159,7 +159,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -171,7 +171,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -183,7 +183,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -920,7 +920,7 @@
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "Index",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -932,7 +932,7 @@
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "Customer Id",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -944,7 +944,7 @@
"start_col_offset_idx": 2,
"end_col_offset_idx": 3,
"text": "First Name",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -956,7 +956,7 @@
"start_col_offset_idx": 3,
"end_col_offset_idx": 4,
"text": "Last Name",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -968,7 +968,7 @@
"start_col_offset_idx": 4,
"end_col_offset_idx": 5,
"text": "Company",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -980,7 +980,7 @@
"start_col_offset_idx": 5,
"end_col_offset_idx": 6,
"text": "City",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -992,7 +992,7 @@
"start_col_offset_idx": 6,
"end_col_offset_idx": 7,
"text": "Country",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1004,7 +1004,7 @@
"start_col_offset_idx": 7,
"end_col_offset_idx": 8,
"text": "Phone 1",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1016,7 +1016,7 @@
"start_col_offset_idx": 8,
"end_col_offset_idx": 9,
"text": "Phone 2",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1028,7 +1028,7 @@
"start_col_offset_idx": 9,
"end_col_offset_idx": 10,
"text": "Email",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1040,7 +1040,7 @@
"start_col_offset_idx": 10,
"end_col_offset_idx": 11,
"text": "Subscription Date",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
},
@@ -1052,7 +1052,7 @@
"start_col_offset_idx": 11,
"end_col_offset_idx": 12,
"text": "Website",
"column_header": false,
"column_header": true,
"row_header": false,
"row_section": false
}