docs: added regression tests for metric parser and documented them in GEMINI.md

company-explorer/backend/tests/test_metric_parser.py

@@ -0,0 +1,70 @@
+import sys
+import os
+import unittest
+
+# Ensure the app's root is in the path to allow imports
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+from lib.metric_parser import MetricParser
+
+class TestMetricParser(unittest.TestCase):
+
+    def test_wolfra_concatenated_year_bug(self):
+        """
+        Catches the "802020" bug where a number and a year were concatenated.
+        The parser should now recognize and strip the trailing year.
+        """
+        text = "802020"
+        result = MetricParser.extract_numeric_value(text, is_revenue=False)
+        self.assertEqual(result, 80.0)
+
+        text_with_space = "Mitarbeiter: 80 2020"
+        result_space = MetricParser.extract_numeric_value(text_with_space, is_revenue=False)
+        self.assertEqual(result_space, 80.0)
+
+    def test_erding_year_prefix_bug(self):
+        """
+        Handles cases where a year appears before the actual metric.
+        The "Smart Year Skip" logic should ignore "2022" and find "200.000".
+        """
+        text = "2022 lagen die Besucherzahlen bei knapp 200.000."
+        result = MetricParser.extract_numeric_value(text, is_revenue=False, expected_value="200000")
+        self.assertEqual(result, 200000.0)
+        
+        # Test without expected value, relying on fallback
+        # Note: Current fallback takes the *first* non-year, which would be 2022 if not for the smart skip.
+        # This test ensures the smart skip works even without LLM guidance.
+        result_no_expected = MetricParser.extract_numeric_value(text, is_revenue=False)
+        self.assertEqual(result_no_expected, 200000.0)
+
+
+    def test_greilmeier_multiple_numbers_bug(self):
+        """
+        Ensures the parser picks the correct number when multiple are present,
+        guided by the `expected_value` provided by the LLM. It should ignore "2"
+        and correctly parse "8.000".
+        """
+        text = "An 2 Standorten - in Schwindegg und in Erding – bieten wir unseren Kunden 8.000 m² Lagerkapazität."
+        
+        # Simulate LLM providing a clean number string
+        result_clean_expected = MetricParser.extract_numeric_value(text, is_revenue=False, expected_value="8000")
+        self.assertEqual(result_clean_expected, 8000.0)
+        
+        # Simulate LLM providing a string with units
+        result_unit_expected = MetricParser.extract_numeric_value(text, is_revenue=False, expected_value="8.000 m²")
+        self.assertEqual(result_unit_expected, 8000.0)
+
+    def test_german_decimal_comma(self):
+        """Tests standard German decimal format."""
+        text = "Umsatz: 14,5 Mio. Euro"
+        result = MetricParser.extract_numeric_value(text, is_revenue=True)
+        self.assertEqual(result, 14.5)
+
+    def test_german_thousands_dot(self):
+        """Tests standard German thousands separator."""
+        text = "1.005 Mitarbeiter"
+        result = MetricParser.extract_numeric_value(text, is_revenue=False)
+        self.assertEqual(result, 1005.0)
+
+if __name__ == '__main__':
+    unittest.main()