From b3b351605c9462e90ae3c0450a8f3121f8be50e6 Mon Sep 17 00:00:00 2001
From: Oscar Madera <80536682+oscarbol09@users.noreply.github.com>
Date: Mon, 20 Jul 2026 13:20:53 -0500
Subject: [PATCH] fix(salary): detect city column from header token, not exact
 match (#201)

convert_salary_excel.py detected the city column via exact membership (h_lower in CITY_PATTERNS), so real headers like "City Name", "City/Kommune", or "Kommune <suffix>" never matched and every company was written with an empty city field. Switches to header_matches(h, CITY_PATTERNS) - the same whole-token matcher already used for the company, count, index, and ID columns. Same bug class as #151 (company column); bare "City"/"Kommune" inputs are unaffected. Regression test covers bare and suffixed headers.

By @oscarbol09.
---
 tests/test_convert_salary_excel.py | 16 ++++++++++++++++
 tools/convert_salary_excel.py      |  3 +--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/tests/test_convert_salary_excel.py b/tests/test_convert_salary_excel.py
index 7a2394f..2ce1ca2 100644
--- a/tests/test_convert_salary_excel.py
+++ b/tests/test_convert_salary_excel.py
@@ -104,6 +104,22 @@ class DetectColumnTypeTests(unittest.TestCase):
                     companies[0]["categories"]["salary"], {"index": 105.5}
                 )
 
+    def test_parse_sheet_detects_city_column_with_token_header(self):
+        # City headers are matched with the same token-based header_matches()
+        # used for the company column, not exact string equality. Real-world
+        # sheets rarely use the bare token "City" or "Kommune" alone; headers
+        # like "City Name" / "City/Kommune" must still be detected as the city
+        # column (previously silently left as city_col=None -> empty city).
+        for header in ("City", "City Name", "Kommune", "City/Kommune"):
+            with self.subTest(header=header):
+                ws = FakeWorksheet([
+                    ("Company", header, "Salary"),
+                    ("Example Corp", "Aarhus", 105.5),
+                ])
+                companies = parse_sheet(ws)
+                self.assertEqual(len(companies), 1)
+                self.assertEqual(companies[0]["city"], "Aarhus")
+
     def test_skips_free_text_column(self):
         # A free-text "Notes" column must not become a bogus salary category.
         ws = FakeWorksheet([
diff --git a/tools/convert_salary_excel.py b/tools/convert_salary_excel.py
index 88e8fbf..30e28ab 100644
--- a/tools/convert_salary_excel.py
+++ b/tools/convert_salary_excel.py
@@ -114,10 +114,9 @@ def parse_sheet(ws, sheet_label=None):
     company_col = None
     city_col = None
     for i, h in enumerate(headers):
-        h_lower = h.lower()
         if header_matches(h, COMPANY_PATTERNS):
             company_col = i
-        elif h_lower in CITY_PATTERNS:
+        elif header_matches(h, CITY_PATTERNS):
             city_col = i
 
     if company_col is None: