Add local ML models and document suggestions (#13)

automatic-pdf-renamer/tests/test_pipeline_date_extraction.py

@@ -0,0 +1,45 @@
+"""Tests for configured-regex emission-date extraction."""
+
+import re
+import unittest
+from types import SimpleNamespace
+
+from app.pipeline import DocumentProcessor
+
+
+class EmissionDateExtractionTests(unittest.TestCase):
+    def processor(self, patterns):
+        processor = object.__new__(DocumentProcessor)
+        processor.registry = SimpleNamespace(
+            get_date_extraction_compiled=lambda: [re.compile(pattern) for pattern in patterns]
+        )
+        return processor
+
+    def test_uses_first_date_in_document_order_not_earliest_calendar_date(self):
+        processor = self.processor([
+            r"([0-9]{1,2})/([0-9]{1,2})/([0-9]{4})",
+            r"([0-9]{4})-([0-9]{2})-([0-9]{2})",
+        ])
+        date, error = processor._extract_emission_date(
+            "Issued 2025-02-03; reference date 01/01/2024"
+        )
+        self.assertIsNone(error)
+        self.assertEqual(date, "2025-02-03")
+
+    def test_normalizes_french_month_names(self):
+        processor = self.processor([
+            r"([0-9]{1,2}) (janvier|fevrier|mars|avril|mai|juin|juillet|aout|septembre|octobre|novembre|decembre) ([0-9]{4})"
+        ])
+        date, error = processor._extract_emission_date("Émis le 1 janvier 2025")
+        self.assertIsNone(error)
+        self.assertEqual(date, "2025-01-01")
+
+    def test_does_not_fall_back_when_no_configured_regex_matches(self):
+        processor = self.processor([r"([0-9]{4})-([0-9]{2})-([0-9]{2})"])
+        date, error = processor._extract_emission_date("Date: 01/02/2025")
+        self.assertEqual(date, "")
+        self.assertIsNotNone(error)
+
+
+if __name__ == "__main__":
+    unittest.main()