fix(salary): collapse line breaks in wrapped workbook headers (#643)

* fix(salary): collapse line breaks in wrapped workbook headers

A wrapped header cell ("Median\nsalary", "Løn-\nindeks") kept its line
break, so the converter derived a category name containing a newline:
the column no longer paired with its count column, and salary_lookup
printed the category label across two lines.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs(changelog): record fix for #643

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* changelog: place the #643 entry under [Unreleased]

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>

CHANGELOG.md

@@ -96,6 +96,12 @@ per-file diff commands.
   "newly expired" by the sweep, then re-ranked by `apply` from its fresh deadline, so the same job appeared
   as both expired and shortlisted. Keys are now stripped before matching.
 
+- **Salary workbook conversion handles wrapped header cells** (#643, `tools/convert_salary_excel.py`,
+  `tests/test_salary_wrapped_header_cli.py`) - a header cell with a line break inside it
+  ("Median⏎salary", "Løn-⏎indeks") kept the break in the derived category name, so the column no
+  longer paired with its count column and `salary_lookup.py` printed the label across two lines.
+  Header whitespace runs now collapse to one space, so a wrapped header converts like its one-line spelling.
+
 ## [1.7.3] - 2026-10-19
 
 ### Added

tests/test_salary_wrapped_header_cli.py

@@ -0,0 +1,50 @@
+"""Wrapped workbook header cells must convert like their one-line spelling."""
+import json
+from pathlib import Path
+import subprocess
+import sys
+from tempfile import TemporaryDirectory
+import unittest
+
+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 WrappedHeaderCLI(unittest.TestCase):
+    def convert(self, header):
+        with TemporaryDirectory() as directory:
+            root = Path(directory)
+            workbook, output = root / "salary.xlsx", root / "salary_data.json"
+            book = openpyxl.Workbook()
+            try:
+                book.active.append(header)
+                book.active.append(["Acme", "Aarhus", 12, 104.5])
+                book.save(workbook)
+            finally:
+                book.close()
+            result = subprocess.run(
+                [sys.executable, str(TOOL), str(workbook), "--output", str(output)],
+                cwd=root, capture_output=True, text=True,
+            )
+            self.assertEqual(result.returncode, 0, result.stdout + result.stderr)
+            return json.loads(output.read_text(encoding="utf-8"))["companies"][0]["categories"]
+
+    def test_wrapped_headers_pair_like_their_single_line_spelling(self):
+        expected = {"all_employees": {"count": 12, "index": 104.5}}
+        self.assertEqual(self.convert(["Company", "City", "Employees", "Median salary"]), expected)
+        self.assertEqual(self.convert(["Company", "City", "Employees", "Median\nsalary"]), expected)
+        self.assertEqual(self.convert(["Firma", "By", "Antal\nmedarbejdere", "Løn-\nindeks"]), expected)
+
+    def test_wrapped_category_name_has_no_line_break(self):
+        categories = self.convert(["Company", "City", "Count\nengineers", "Index\nengineers"])
+        self.assertEqual(categories, {"engineers": {"count": 12, "index": 104.5}})
+
+
+if __name__ == "__main__":
+    unittest.main()

tools/convert_salary_excel.py

@@ -186,10 +186,12 @@ def parse_sheet(ws, sheet_label=None):
         print(f"Warning: Could not find header row in sheet '{ws.title}'. Skipping.", file=sys.stderr)
         return []
 
-    # Read headers
+    # Read headers. Wrapped header cells carry a line break ("Median\nsalary"),
+    # which would survive into the category name and keep the column from
+    # pairing with its count, so collapse every whitespace run to one space.
     headers = []
     for cell in ws[header_row]:
-        headers.append(str(cell.value).strip() if cell.value else "")
+        headers.append(" ".join(str(cell.value).split()) if cell.value else "")
 
     # Find company and city columns
     company_col = None