From 4128ca03189e19f9e2e54a5be63653f6065dbb87 Mon Sep 17 00:00:00 2001
From: Alaa-Taieb <93670187+Alaa-Taieb@users.noreply.github.com>
Date: Tue, 14 Jul 2026 13:35:45 +0100
Subject: [PATCH] fix(salary): detect company column from header token, not
 exact match (#151)

convert_salary_excel.py detected the company column via exact membership
in COMPANY_PATTERNS, so common real-world headers like "Company Name" or
"Employer Name" were never matched. parse_sheet then returned [] for that
sheet, silently dropping it from salary_data.json (or exiting with no
output for a single-sheet file).

Route company-column detection through the existing header_matches()
token matcher (already used for count/index detection). This only adds
detections; inputs that already worked (bare "Company"/"Firma"/...) are
unaffected.

Adds a regression test in tests/test_convert_salary_excel.py that fails
on master (returns []) and passes after the fix.
---
 tests/test_convert_salary_excel.py | 17 +++++++++++++++++
 tools/convert_salary_excel.py      |  4 ++--
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/tests/test_convert_salary_excel.py b/tests/test_convert_salary_excel.py
index 6b50dde..790221b 100644
--- a/tests/test_convert_salary_excel.py
+++ b/tests/test_convert_salary_excel.py
@@ -87,6 +87,23 @@ class DetectColumnTypeTests(unittest.TestCase):
 
         self.assertEqual(companies[0]["categories"]["software_engineering"], {"count": 8, "index": 110.0})
 
+    def test_parse_sheet_detects_company_column_with_token_header(self):
+        # Real-world salary sheets rarely use the bare token "Company";
+        # headers like "Company Name" / "Employer Name" must still be
+        # detected as the company column (previously silently skipped -> []).
+        for header in ("Company", "Company Name", "Employer Name"):
+            with self.subTest(header=header):
+                ws = FakeWorksheet([
+                    (header, "Salary"),
+                    ("Example Corp", 105.5),
+                ])
+                companies = parse_sheet(ws)
+                self.assertEqual(len(companies), 1)
+                self.assertEqual(companies[0]["company"], "Example Corp")
+                self.assertEqual(
+                    companies[0]["categories"]["salary"], {"index": 105.5}
+                )
+
 
 if __name__ == "__main__":
     unittest.main()
diff --git a/tools/convert_salary_excel.py b/tools/convert_salary_excel.py
index ec4af97..b921e92 100644
--- a/tools/convert_salary_excel.py
+++ b/tools/convert_salary_excel.py
@@ -91,7 +91,7 @@ def parse_sheet(ws, sheet_label=None):
     header_row = None
     for row_idx, row in enumerate(ws.iter_rows(min_row=1, max_row=10, values_only=False), start=1):
         for cell in row:
-            if cell.value and str(cell.value).strip().lower() in COMPANY_PATTERNS:
+            if cell.value and header_matches(str(cell.value), COMPANY_PATTERNS):
                 header_row = row_idx
                 break
         if header_row:
@@ -111,7 +111,7 @@ def parse_sheet(ws, sheet_label=None):
     city_col = None
     for i, h in enumerate(headers):
         h_lower = h.lower()
-        if h_lower in COMPANY_PATTERNS:
+        if header_matches(h, COMPANY_PATTERNS):
             company_col = i
         elif h_lower in CITY_PATTERNS:
             city_col = i