From 362ef6a522b30ce72d8c87bf492b8c7a21cb1b8e Mon Sep 17 00:00:00 2001
From: Ayobami Adegoke <adegokeayobamiseun@gmail.com>
Date: Mon, 21 Sep 2026 07:20:50 +0100
Subject: [PATCH] test(salary): exercise real workbook conversion through the
 CLI (#489)

---
 .github/workflows/ci.yml                      |  2 +
 CHANGELOG.md                                  |  9 ++
 .../test_convert_salary_excel_integration.py  | 90 +++++++++++++++++++
 3 files changed, 101 insertions(+)
 create mode 100644 tests/test_convert_salary_excel_integration.py

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index dbd03c57..89f8d059 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -73,6 +73,8 @@ jobs:
       - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
         with:
           python-version: ${{ matrix.python-version }}
+      - name: Install Excel integration test dependency
+        run: python -m pip install openpyxl==3.1.5
       - run: python -m unittest discover -s tests -t . -v
 
   dependency-review:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index f01f9423..32639980 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -15,6 +15,15 @@ per-file diff commands.
 
 ### Added
 
+- **Real Excel workbook integration tests for the salary converter**
+  (`tests/test_convert_salary_excel_integration.py`, `.github/workflows/ci.yml`) -
+  generate temporary `.xlsx` files and invoke the documented converter CLI,
+  checking multiple worksheets, metadata options, Unicode text, localized
+  numbers, and compatibility with salary lookup. A workbook without salary
+  headers must fail without creating an output file. CI installs `openpyxl`
+  across the Python matrix; local runs without this optional dependency skip
+  the two integration cases while retaining the existing dependency-free tests.
+
 - **`documents/projects/` portfolio ingestion in `/setup` (Path A)** (`documents/README.md`,
   `.claude/commands/setup.md`, `.claude/commands/reset.md`, `tests/test_setup_command.py`) -
   onboards project writeups, case studies, and documentation (`.md`, `.txt`, `.pdf`)
diff --git a/tests/test_convert_salary_excel_integration.py b/tests/test_convert_salary_excel_integration.py
new file mode 100644
index 00000000..d1e3e751
--- /dev/null
+++ b/tests/test_convert_salary_excel_integration.py
@@ -0,0 +1,90 @@
+"""Exercise the documented Excel -> converter CLI -> salary JSON path."""
+import json
+import subprocess
+import sys
+import unittest
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+try:
+    import openpyxl
+except ImportError:
+    openpyxl = None
+
+from salary_lookup import collect_validation_issues, format_entry
+
+TOOL = Path(__file__).resolve().parent.parent / "tools" / "convert_salary_excel.py"
+
+
+@unittest.skipUnless(openpyxl, "requires optional openpyxl (installed in CI)")
+class ConverterCLI(unittest.TestCase):
+    def setUp(self):
+        directory = TemporaryDirectory()
+        self.addCleanup(directory.cleanup)
+        self.root = Path(directory.name)
+        self.workbook = self.root / "salary input.xlsx"
+        self.output = self.root / "salary output.json"
+
+    def run_converter(self, *args):
+        return subprocess.run(
+            [sys.executable, str(TOOL), str(self.workbook),
+             "--output", str(self.output), *args],
+            cwd=self.root, capture_output=True, text=True,
+        )
+
+    def test_real_workbook_round_trips_multiple_sheets_and_metadata(self):
+        book = openpyxl.Workbook()
+        try:
+            first = book.active
+            first.title = "All employees"
+            first.append(["Company", "City", "Count", "Index"])
+            first.append(["Acme Corp", "Copenhagen", 500, 108.5])
+            first.append(["Café Étoile", "Paris", 12, "102,5"])
+            second = book.create_sheet("Engineering")
+            second.append(["Company", "City", "Engineering Count", "Engineering Index"])
+            second.append(["Other Corp", "Berlin", 8, 112.5])
+            book.save(self.workbook)
+        finally:
+            book.close()
+
+        result = self.run_converter(
+            "--source", "Integration fixture", "--baseline", "100",
+            "--baseline-desc", "Index 100 = median salary",
+        )
+        self.assertEqual(result.returncode, 0, result.stderr)
+        data = json.loads(self.output.read_text(encoding="utf-8"))
+        self.assertEqual(data["metadata"], {
+            "source": "Integration fixture", "index_baseline": 100,
+            "index_label": "Index", "baseline_description": "Index 100 = median salary",
+        })
+        self.assertEqual(data["companies"], [
+            {"company": "Acme Corp", "city": "Copenhagen", "categories": {
+                "all_employees": {"count": 500, "index": 108.5}}},
+            {"company": "Café Étoile", "city": "Paris", "categories": {
+                "all_employees": {"count": 12, "index": 102.5}}},
+            {"company": "Other Corp", "city": "Berlin", "categories": {
+                "engineering": {"count": 8, "index": 112.5}}},
+        ])
+        self.assertEqual(collect_validation_issues(data), ([], []))
+        rendered = format_entry(data["companies"][0], data["metadata"])
+        self.assertIn("All Employees", rendered)
+        self.assertIn("+8.5%", rendered)
+        self.assertNotIn("N/A*", rendered)
+
+    def test_workbook_without_salary_headers_fails_without_writing_output(self):
+        book = openpyxl.Workbook()
+        try:
+            book.active.append(["Notes", "Comments"])
+            book.active.append(["No salary data", "Just a worksheet"])
+            book.save(self.workbook)
+        finally:
+            book.close()
+
+        result = self.run_converter()
+        self.assertEqual(result.returncode, 1, result.stderr)
+        self.assertIn("No data could be parsed", result.stderr)
+        self.assertFalse(self.output.exists())
+
+
+if __name__ == "__main__":
+    unittest.main()