hilite duplicate header column

validata_ui/views.py

@@ -7,6 +7,7 @@ import json
 import logging
 import subprocess
 import tempfile
+from collections import defaultdict
 from datetime import datetime
 from operator import itemgetter
 from pathlib import Path
@@ -139,6 +140,18 @@ def extract_source_data(source: ValidataResource, schema_descriptor, preview_row
         """Transform value into string"""
         return '' if val is None else str(val)
 
+    def compute_duplicate_header_column_indices(source_header, duplicate_header_names):
+        column_name_to_indices = defaultdict(list)
+        for i, h in enumerate(source_header):
+            if h in duplicate_header_names:
+                column_name_to_indices[h].append(i)
+        
+        col_indices = set()
+        for v in column_name_to_indices.values():
+            col_indices.update(v[1:])
+
+        return col_indices
+
     header = None
     rows = []
     nb_rows = 0
@@ -166,11 +179,21 @@ def extract_source_data(source: ValidataResource, schema_descriptor, preview_row
     preview_rows_nb = min(preview_rows_nb, nb_rows)
 
     # Computes original_headers display
+    # wrong headers order: display all headers as in error
     if any([err.code == 'wrong-headers-order' for err in repair_report]):
         source_header_info = [(h, True) for h in source_header]
+
+    # else display header error for:
+    # - blank-header
+    # - unknown-header
+    # - duplicate-header
     else:
         schema_field_names = [f['name'] for f in schema_descriptor.get('fields') or []]
-        source_header_info = [(h, not h or h not in schema_field_names) for h in source_header]
+        #import ipdb; ipdb.set_trace()
+        duplicate_header_names = [err._message_substitutions['column-name'] for err in repair_report if err.code == 'duplicate-header']
+        duplicate_col_indices = compute_duplicate_header_column_indices(source_header, duplicate_header_names)
+
+        source_header_info = [(h, not h or h not in schema_field_names or i in duplicate_col_indices) for i, h in enumerate(source_header)]
 
     return {
         'source_header_info': source_header_info,