fix(convert_salary_excel): pair count/index columns by category name, not adjacency (#219)

The sequential scan assumed count/index pairs are always adjacent.
Interleaved columns like Count_A, Count_B, Index_A, Index_B produced
wrong pairings (Count_B ↔ Index_A), silently corrupting data.

Now columns are grouped by type, then matched by the category name
derived from stripping type words. Unmatched columns fall back to
standalone value columns using the original header name.

tests/test_convert_salary_excel.py

@@ -157,5 +157,30 @@ class DetectColumnTypeTests(unittest.TestCase):
         self.assertEqual(companies[0]["categories"]["salary_index"], {"index": 105.5})
 
 
+    def test_parse_sheet_pairs_interleaved_count_index_columns_by_name(self):
+        ws = FakeWorksheet([
+            ("Company", "Antal kvinder", "Antal mænd", "Kvinder indeks", "Mænd indeks"),
+            ("Example Corp", 15, 20, 95.0, 108.0),
+        ])
+
+        companies = parse_sheet(ws)
+
+        categories = companies[0]["categories"]
+        self.assertEqual(categories["kvinder"], {"count": 15, "index": 95.0})
+        self.assertEqual(categories["mænd"], {"count": 20, "index": 108.0})
+
+    def test_parse_sheet_non_adjacent_columns_no_cross_match(self):
+        ws = FakeWorksheet([
+            ("Company", "Count_A", "Count_B", "Index_A", "Index_B"),
+            ("Example Corp", 10, 20, 100.0, 200.0),
+        ])
+
+        companies = parse_sheet(ws)
+
+        categories = companies[0]["categories"]
+        self.assertEqual(categories["a"], {"count": 10, "index": 100.0})
+        self.assertEqual(categories["b"], {"count": 20, "index": 200.0})
+
+
 if __name__ == "__main__":
     unittest.main()

tools/convert_salary_excel.py

@@ -132,53 +132,55 @@ def parse_sheet(ws, sheet_label=None):
             continue
         data_cols.append((i, h))
 
-    # Try to detect paired count/index columns per category
+    # Group data columns by detected type and derive category names
-    # Heuristic: if columns come in pairs and alternate count/index, group them
+    count_cols = []
-    categories = []
+    index_cols = []
-    i = 0
+    untyped_cols = []
-    while i < len(data_cols):
+
-        col_idx, col_header = data_cols[i]
+    for col_idx, col_header in data_cols:
         col_type = detect_column_type(col_header)
-
+        if col_type == "count":
-        if i + 1 < len(data_cols):
-            next_col_idx, next_col_header = data_cols[i + 1]
-            next_col_type = detect_column_type(next_col_header)
-
-            # If we have a count/index pair, group them
-            if col_type == "count" and next_col_type == "index":
-                # Use the header minus the count/index suffix as category name
             cat_name = strip_type_patterns(col_header, COUNT_PATTERNS)
-                if not cat_name:
+            count_cols.append((col_idx, col_header, cat_name))
-                    cat_name = f"category_{len(categories)+1}"
+        elif col_type == "index":
-                else:
-                    cat_name = cat_name.replace(" ", "_").replace("-", "_")
-                categories.append({
-                    "name": cat_name,
-                    "count_col": col_idx,
-                    "index_col": next_col_idx,
-                })
-                i += 2
-                continue
-            elif col_type == "index" and next_col_type == "count":
             cat_name = strip_type_patterns(col_header, INDEX_PATTERNS)
-                if not cat_name:
+            index_cols.append((col_idx, col_header, cat_name))
-                    cat_name = f"category_{len(categories)+1}"
         else:
-                    cat_name = cat_name.replace(" ", "_").replace("-", "_")
+            untyped_cols.append((col_idx, col_header))
+
+    # Pair count/index columns by matching category name
+    categories = []
+    used_counts = set()
+    used_indexes = set()
+
+    for ci, (c_idx, c_header, c_cat) in enumerate(count_cols):
+        for ii, (i_idx, i_header, i_cat) in enumerate(index_cols):
+            if ii in used_indexes:
+                continue
+            if c_cat and i_cat and c_cat == i_cat:
+                cat_name = c_cat.replace(" ", "_").replace("-", "_")
                 categories.append({
                     "name": cat_name,
-                    "index_col": col_idx,
+                    "count_col": c_idx,
-                    "count_col": next_col_idx,
+                    "index_col": i_idx,
                 })
-                i += 2
+                used_counts.add(ci)
-                continue
+                used_indexes.add(ii)
+                break
 
-        # Single column - treat as a standalone value
+    # Remaining unmatched count columns become standalone (use original header)
-        categories.append({
+    for ci, (c_idx, c_header, _) in enumerate(count_cols):
-            "name": col_header.lower().replace(" ", "_"),
+        if ci not in used_counts:
-            "value_col": col_idx,
+            categories.append({"name": c_header.lower().replace(" ", "_"), "value_col": c_idx})
-        })
+
-        i += 1
+    # Remaining unmatched index columns become standalone (use original header)
+    for ii, (i_idx, i_header, _) in enumerate(index_cols):
+        if ii not in used_indexes:
+            categories.append({"name": i_header.lower().replace(" ", "_"), "value_col": i_idx})
+
+    # Untyped columns become standalone
+    for col_idx, col_header in untyped_cols:
+        categories.append({"name": col_header.lower().replace(" ", "_"), "value_col": col_idx})
 
     # Parse data rows
     companies = []