fix(salary): prefer exact workbook identity headers (#571)

* fix(salary): prefer exact workbook identity headers

* docs(changelog): record fix for #571

CHANGELOG.md

@@ -211,6 +211,8 @@ per-file diff commands.
   RFC 9309 section 2.2.3, `$` is an end anchor only at the end of the pattern, and internal `$`
   characters are now matched literally.
 
+- **Salary workbook conversion prefers exact identity headers** (#571) - exact company column names take precedence over incidental substring matches in other headers.
+
 - **CV template guidance aligns geometry scale with master template** (#553,
   `.claude/skills/job-application-assistant/05-cv-templates.md`, `tests/test_latex_guidance.py`) -
   the preamble snippet in `05-cv-templates.md` specified `\usepackage[scale=0.77]{geometry}`,

tests/test_salary_company_header_cli.py

@@ -0,0 +1,53 @@
+"""A salary category must not steal the workbook's company-name column."""
+import json
+import subprocess
+import sys
+import unittest
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+try:
+    import openpyxl
+except ImportError:
+    openpyxl = None
+
+TOOL = Path(__file__).resolve().parent.parent / "tools" / "convert_salary_excel.py"
+
+
+@unittest.skipUnless(openpyxl, "requires optional openpyxl (installed in CI)")
+class CompanyHeaderCLI(unittest.TestCase):
+    def convert(self, header):
+        with TemporaryDirectory() as directory:
+            root = Path(directory)
+            workbook, output = root / "salary.xlsx", root / "salary.json"
+            book = openpyxl.Workbook()
+            try:
+                book.active.append(header)
+                book.active.append(["Acme Corp", "Berlin", 25, 108.5])
+                book.save(workbook)
+            finally:
+                book.close()
+            result = subprocess.run(
+                [sys.executable, str(TOOL), str(workbook), "--output", str(output)],
+                capture_output=True, text=True, encoding="utf-8",
+            )
+            self.assertEqual(result.returncode, 0, result.stderr)
+            return json.loads(output.read_text(encoding="utf-8"))["companies"]
+
+    def test_company_prefixed_salary_columns_do_not_replace_the_company(self):
+        self.assertEqual(self.convert(["Company", "City", "Company Count", "Company Index"]), [
+            {"company": "Acme Corp", "city": "Berlin", "categories": {
+                "company": {"count": 25, "index": 108.5}}}
+        ])
+
+    def test_existing_named_category_control(self):
+        self.assertEqual(self.convert(["Company Name", "City", "Engineering Count", "Engineering Index"]), [
+            {"company": "Acme Corp", "city": "Berlin", "categories": {
+                "engineering": {"count": 25, "index": 108.5}}}
+        ])
+
+    def test_city_prefixed_salary_columns_do_not_replace_the_city(self):
+        self.assertEqual(self.convert(["Company", "City", "City Count", "City Index"]), [
+            {"company": "Acme Corp", "city": "Berlin", "categories": {
+                "city": {"count": 25, "index": 108.5}}}
+        ])

tools/convert_salary_excel.py

@@ -191,6 +191,12 @@ def parse_sheet(ws, sheet_label=None):
         elif header_matches(h, CITY_PATTERNS):
             city_col = i
 
+    # A qualified salary header such as "Company Index" may also contain a
+    # metadata token. Prefer an unqualified metadata column when one exists,
+    # leaving the qualified column available as salary data.
+    company_col = next((i for i, h in enumerate(headers) if h.lower() in COMPANY_PATTERNS), company_col)
+    city_col = next((i for i, h in enumerate(headers) if h.lower() in CITY_PATTERNS), city_col)
+
     if company_col is None:
         print(f"Warning: Could not find company column in sheet '{ws.title}'.", file=sys.stderr)
         return []