fix(salary): skip prose notes tabs instead of listing sentences as companies (#644)

* fix(salary): skip prose notes tabs instead of listing sentences as companies

A workbook's notes tab ("Each row is one company in the survey.") has no
table header, so the strict header pass finds nothing and the fallback
takes the first line mentioning a company word. With no salary column
beside it, every following sentence was emitted as a company entry and
showed up in --list-all and lookups. A fallback-detected header with no
salary columns now skips the sheet with a warning.

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

* docs(changelog): record fix for #644

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

* changelog: place the #644 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

@@ -102,6 +102,12 @@ per-file diff commands.
   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.
 
+- **Salary workbook conversion skips prose notes tabs** (#644, `tools/convert_salary_excel.py`,
+  `tests/test_salary_notes_sheet_cli.py`) - a "Notes" tab mentioning "company" in a sentence was
+  taken as a header row by the fallback pass, and every following sentence was emitted as a company
+  in `salary_data.json` and `--list-all`. A fallback-detected header with no salary column beside it
+  now skips the sheet with a warning; strictly detected headers are unchanged.
+
 ## [1.7.3] - 2026-10-19
 
 ### Added

tests/test_salary_notes_sheet_cli.py

@@ -0,0 +1,77 @@
+"""A workbook's prose notes tab must not be read as a company table."""
+import json
+from pathlib import Path
+import shutil
+import subprocess
+import sys
+from tempfile import TemporaryDirectory
+import unittest
+
+try:
+    import openpyxl
+except ImportError:
+    openpyxl = None
+
+REPO = Path(__file__).resolve().parent.parent
+
+NOTES = [
+    ["About this data"],
+    ["Each row is one company in the 2025 survey."],
+    ["Indexes are relative to the national median."],
+    ["Categories with fewer than five respondents are suppressed."],
+]
+
+
+@unittest.skipUnless(openpyxl, "requires optional openpyxl (installed in CI)")
+class NotesSheetCLI(unittest.TestCase):
+    def setUp(self):
+        directory = TemporaryDirectory()
+        self.addCleanup(directory.cleanup)
+        self.root = Path(directory.name)
+        shutil.copyfile(REPO / "salary_lookup.py", self.root / "salary_lookup.py")
+        self.output = self.root / "salary_data.json"
+
+    def convert(self, with_data):
+        workbook = self.root / "salary.xlsx"
+        book = openpyxl.Workbook()
+        try:
+            sheet = book.active
+            if with_data:
+                sheet.title = "Data"
+                sheet.append(["Company", "City", "Count", "Index"])
+                sheet.append(["Acme", "Aarhus", 10, 105])
+                sheet = book.create_sheet("Notes")
+            else:
+                sheet.title = "Notes"
+            for line in NOTES:
+                sheet.append(line)
+            book.save(workbook)
+        finally:
+            book.close()
+        return subprocess.run(
+            [sys.executable, str(REPO / "tools" / "convert_salary_excel.py"), str(workbook),
+             "--output", str(self.output)],
+            cwd=self.root, capture_output=True, text=True,
+        )
+
+    def test_notes_tab_sentences_are_not_listed_as_companies(self):
+        result = self.convert(with_data=True)
+        self.assertEqual(result.returncode, 0, result.stdout + result.stderr)
+        self.assertIn("Skipping sheet 'Notes'", result.stderr)
+        companies = json.loads(self.output.read_text(encoding="utf-8"))["companies"]
+        self.assertEqual([entry["company"] for entry in companies], ["Acme"])
+        listed = subprocess.run(
+            [sys.executable, "salary_lookup.py", "--list-all"],
+            cwd=self.root, capture_output=True, text=True,
+        )
+        self.assertEqual(listed.stdout.splitlines(), ["Acme (Aarhus)"])
+
+    def test_notes_only_workbook_fails_without_writing_output(self):
+        result = self.convert(with_data=False)
+        self.assertEqual(result.returncode, 1, result.stdout + result.stderr)
+        self.assertIn("No data could be parsed", result.stderr)
+        self.assertFalse(self.output.exists())
+
+
+if __name__ == "__main__":
+    unittest.main()

tools/convert_salary_excel.py

@@ -162,6 +162,7 @@ def parse_sheet(ws, sheet_label=None):
         return [str(cell.value).strip() for cell in row if cell.value]
 
     header_row = None
+    corroborated = True
     for row_idx, row in enumerate(rows, start=1):
         cell_texts = _cell_texts(row)
         company_idxs = {i for i, t in enumerate(cell_texts) if header_matches(t, COMPANY_PATTERNS)}
@@ -177,6 +178,7 @@ def parse_sheet(ws, sheet_label=None):
             break
 
     if header_row is None:
+        corroborated = False
         for row_idx, row in enumerate(rows, start=1):
             if any(header_matches(t, COMPANY_PATTERNS) for t in _cell_texts(row)):
                 header_row = row_idx
@@ -282,6 +284,18 @@ def parse_sheet(ws, sheet_label=None):
     for col_idx, col_header in untyped_cols:
         categories.append({"name": col_header.lower().replace(" ", "_"), "value_col": col_idx})
 
+    if not categories and not corroborated:
+        # The fallback pass matched a lone company word and no salary column
+        # sits beside it: this is prose (a "Notes" or "About the data" tab
+        # mentioning "company"), not a table. Reading it would turn every
+        # sentence below that line into a company entry.
+        print(
+            f"Warning: Skipping sheet '{ws.title}': no table header found "
+            "(a company word appears only in text, with no salary columns).",
+            file=sys.stderr,
+        )
+        return []
+
     if not categories:
         print(
             f"Warning: No salary data columns detected in sheet '{ws.title}' "