fix(salary): skip non-numeric and identifier columns in Excel conversion (#152)

parse_sheet treated every column that was not company/city as a salary category, with no check that the column actually held numeric salary data. This turned free-text columns (e.g. Notes) into bogus string categories and numeric identifier columns (e.g. Id) into mistaken salary indexes.

- Drop identifier headers (ID_PATTERNS = {id, personnummer}) at classification time.

- Skip non-numeric standalone values and fully-null count/index pairs at row-processing time.

- Adds regression tests (skips_free_text_column, skips_numeric_identifier_column, keeps_numeric_salary_column) that fail on master and pass after the fix.

tools/convert_salary_excel.py

@@ -48,6 +48,10 @@ INDEX_PATTERNS = {"indeks", "index", "idx", "salary", "løn", "median", "average
 # Ships populated for this repo's Danish demonstration data; a fork targeting
 # another locale edits this constant.
 COMPOUND_PATTERNS = {"antal", "indeks", "løn", "gennemsnit", "medarbejdere"}
+# Identifier columns (employee id, Danish "personnummer", etc.) are never salary
+# data. They are dropped at classification so they are not mistaken for a salary
+# category. Matched as whole tokens only, like other pattern sets.
+ID_PATTERNS = {"id", "personnummer"}
 
 
 def header_matches(header, patterns):
@@ -120,11 +124,13 @@ def parse_sheet(ws, sheet_label=None):
         print(f"Warning: Could not find company column in sheet '{ws.title}'.", file=sys.stderr)
         return []
 
-    # Identify data columns (everything that's not company/city)
+    # Identify data columns (everything that's not company/city or an identifier)
     data_cols = []
     for i, h in enumerate(headers):
         if i == company_col or i == city_col or not h:
             continue
+        if header_matches(h, ID_PATTERNS):
+            continue
         data_cols.append((i, h))
 
     # Try to detect paired count/index columns per category
@@ -205,6 +211,10 @@ def parse_sheet(ws, sheet_label=None):
                         index_val = float(row[cat["index_col"]])
                     except (ValueError, TypeError):
                         pass
+                # A count/index pair that is entirely empty for this row carries
+                # no salary information, so skip it rather than emit nulls.
+                if count_val is None and index_val is None:
+                    continue
                 entry["categories"][cat_name] = {"count": count_val, "index": index_val}
             elif "value_col" in cat:
                 if cat["value_col"] < len(row) and row[cat["value_col"]] is not None:
@@ -212,7 +222,9 @@ def parse_sheet(ws, sheet_label=None):
                     try:
                         val = float(val)
                     except (ValueError, TypeError):
-                        val = str(val)
+                        # Non-numeric standalone value (e.g. a free-text "Notes"
+                        # column) is not salary data; skip it for this row.
+                        continue
                     entry["categories"][cat_name] = {"index": val}
 
         companies.append(entry)