refactor(salary): optimize search match scoring and normalize Excel category keys (#101)

This commit improves the performance and consistency of the salary tools:

- Redundant query normalization and word extraction are eliminated in salary_lookup.py by pre-calculating representations once before the search loop.
- A match_score_optimized helper is introduced to perform the comparison using the pre-calculated query data, preserving full backward compatibility for match_score.
- Normalization in tools/convert_salary_excel.py is unified: paired column headers now consistently substitute spaces and dashes with underscores (e.g. 'software_engineering') to match the single-column formatting.
- Unit test coverage is significantly expanded in tests/test_salary_lookup.py and tests/test_convert_salary_excel.py to cover normalization, anglicization, search filtering, and matching behaviors.

tests/test_convert_salary_excel.py

@@ -77,6 +77,16 @@ class DetectColumnTypeTests(unittest.TestCase):
 
         self.assertEqual(companies[0]["categories"]["accounting"], {"count": 12, "index": 105.5})
 
+    def test_parse_sheet_normalizes_paired_category_name_with_underscores(self):
+        ws = FakeWorksheet([
+            ("Company", "Software Engineering Count", "Software Engineering Index"),
+            ("Example Corp", 8, 110.0),
+        ])
+
+        companies = parse_sheet(ws)
+
+        self.assertEqual(companies[0]["categories"]["software_engineering"], {"count": 8, "index": 110.0})
+
 
 if __name__ == "__main__":
     unittest.main()

tests/test_salary_lookup.py

@@ -2,7 +2,14 @@
 
 import unittest
 
-from salary_lookup import format_entry, match_score, search_company
+from salary_lookup import (
+    format_entry,
+    normalize,
+    anglicize,
+    extract_core_words,
+    match_score,
+    search_company,
+)
 
 
 # ---------------------------------------------------------------------------
@@ -158,6 +165,68 @@ class SearchCompanyTests(unittest.TestCase):
         self.assertEqual(results, [])
 
 
+class UtilityTests(unittest.TestCase):
+    def test_normalize_strips_suffix_and_noise(self):
+        self.assertEqual(normalize("Novo Nordisk A/S"), "novonordisk")
+        self.assertEqual(normalize("Ørsted (VG) Holding"), "ørsted")
+        self.assertEqual(normalize("Chr. Hansen, Denmark Division"), "chrhansen")
+        self.assertEqual(normalize("Simple Corp ApS"), "simplecorp")
+
+    def test_anglicize_replaces_danish_chars(self):
+        self.assertEqual(anglicize("ørsted"), "orsted")
+        self.assertEqual(anglicize("mærsk"), "maersk")
+        self.assertEqual(anglicize("ålborg"), "aalborg")
+
+    def test_extract_core_words(self):
+        self.assertEqual(extract_core_words("Novo Nordisk A/S"), ["novo", "nordisk"])
+        self.assertEqual(extract_core_words("A/S"), [])
+        self.assertEqual(extract_core_words("Test Company (Sub-entity)"), ["test", "company"])
+
+
+class MatchScoreTests(unittest.TestCase):
+    def test_exact_match_score(self):
+        self.assertEqual(match_score("Novo Nordisk", "Novo Nordisk"), 100)
+        self.assertEqual(match_score("novo nordisk", "Novo Nordisk A/S"), 100)
+
+    def test_partial_match_score(self):
+        self.assertGreater(match_score("Novo", "Novo Nordisk A/S"), 80)
+        self.assertEqual(match_score("Novo Nordisk", "Novo"), 75)
+
+    def test_anglicized_match_score(self):
+        self.assertEqual(match_score("Orsted", "Ørsted A/S"), 85)
+
+    def test_overlap_match_score(self):
+        # Overlap of multiple words
+        self.assertGreater(match_score("Novo Tech", "Novo Nordisk Tech A/S"), 30)
+
+    def test_no_match_score(self):
+        self.assertEqual(match_score("Google", "Microsoft"), 0)
+
+
+class SearchCompanyRefactoredTests(unittest.TestCase):
+    def setUp(self):
+        self.data = {
+            "companies": [
+                {"company": "Novo Nordisk A/S", "city": "Bagsværd"},
+                {"company": "Ørsted", "city": "Fredericia"},
+                {"company": "Vestas Wind Systems", "city": "Aarhus"},
+            ]
+        }
+
+    def test_search_by_name(self):
+        results = search_company(self.data, "Novo")
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]["company"], "Novo Nordisk A/S")
+
+    def test_search_with_city_filter(self):
+        results = search_company(self.data, "Ørsted", city="Fredericia")
+        self.assertEqual(len(results), 1)
+
+        # Mismatching city
+        results_wrong_city = search_company(self.data, "Ørsted", city="Bagsværd")
+        self.assertEqual(len(results_wrong_city), 0)
+
+
 class TestSearchCompanyBasicMatch(unittest.TestCase):
     def test_exact_name_returns_match(self):
         data = _make_data(_entry("Novo Nordisk", "Bagsværd"))