idk

pipeline/utils/test_fuzzy_join.py

@@ -134,6 +134,91 @@ def test_fuzzy_join_on_postcode_rejects_blank_and_invalid_match_keys():
     ]
 
 
+def test_fuzzy_join_rejects_mid_score_number_less_match():
+    # "THE COACH HOUSE" vs "THE OLD COACH HOUSE" scores 88 via token_sort_ratio:
+    # above the old MIN_FUZZY_SCORE of 60 (so it used to falsely match) but below
+    # the number-less threshold of 90, so it must NOT match now.
+    left = pl.LazyFrame(
+        {
+            "left_address": ["The Coach House"],
+            "left_postcode": ["AB1 2CD"],
+        }
+    )
+    right = pl.LazyFrame(
+        {
+            "right_address": ["The Old Coach House"],
+            "right_postcode": ["AB1 2CD"],
+        }
+    )
+
+    result = fuzzy_join_on_postcode(
+        left=left,
+        right=right,
+        left_address_col="left_address",
+        right_address_col="right_address",
+        left_postcode_col="left_postcode",
+        right_postcode_col="right_postcode",
+    ).collect()
+
+    assert result["right_address"].to_list() == [None]
+
+
+def test_fuzzy_join_matches_numbered_pair_at_baseline_threshold():
+    # "10 ACACIA AVENUE" vs "FLAT A 10 ACACIA AVENUE" scores exactly 82 and the
+    # house number is compatible, so the numbered baseline (>= 82) still matches.
+    left = pl.LazyFrame(
+        {
+            "left_address": ["10 Acacia Avenue"],
+            "left_postcode": ["AB1 2CD"],
+        }
+    )
+    right = pl.LazyFrame(
+        {
+            "right_address": ["Flat A, 10 Acacia Avenue"],
+            "right_postcode": ["AB1 2CD"],
+        }
+    )
+
+    result = fuzzy_join_on_postcode(
+        left=left,
+        right=right,
+        left_address_col="left_address",
+        right_address_col="right_address",
+        left_postcode_col="left_postcode",
+        right_postcode_col="right_postcode",
+    ).collect()
+
+    assert result["right_address"].to_list() == ["Flat A, 10 Acacia Avenue"]
+
+
+def test_fuzzy_join_matches_high_score_number_less_pair():
+    # A number-less pair that clears the 90 threshold (here an exact token match,
+    # score 100) must still match.
+    left = pl.LazyFrame(
+        {
+            "left_address": ["The Old Rectory"],
+            "left_postcode": ["AB1 2CD"],
+        }
+    )
+    right = pl.LazyFrame(
+        {
+            "right_address": ["THE OLD RECTORY"],
+            "right_postcode": ["AB1 2CD"],
+        }
+    )
+
+    result = fuzzy_join_on_postcode(
+        left=left,
+        right=right,
+        left_address_col="left_address",
+        right_address_col="right_address",
+        left_postcode_col="left_postcode",
+        right_postcode_col="right_postcode",
+    ).collect()
+
+    assert result["right_address"].to_list() == ["THE OLD RECTORY"]
+
+
 def test_normalize_postcode_key_requires_full_postcode():
     df = pl.DataFrame(
         {