Improve sparse and structured catalog matching

tests/test_matcher.py

@@ -184,6 +184,55 @@ def test_product_type_survives_typos(matcher: CatalogMatcher, query: str) -> Non
     assert all(candidate.sku.startswith("INS-") for candidate in result.candidates)
 
 
+@pytest.mark.parametrize(
+    ("query", "skus"),
+    [
+        ("удар", ("INS-0008", "INS-0009", "INS-0022")),
+        ("ударная", ("INS-0008", "INS-0009", "INS-0022")),
+        ("удар мощный", ("INS-0008", "INS-0009", "INS-0022")),
+        (
+            "удар мощно 900 хромированый анус долбить",
+            ("INS-0009", "INS-0016", "INS-0023"),
+        ),
+        (
+            "дрель удар мощно 900 хромированый анус долбить",
+            ("INS-0009", "INS-0023", "INS-0002"),
+        ),
+    ],
+)
+def test_trigram_fallback_finds_product_type_from_sparse_or_noisy_text(
+    matcher: CatalogMatcher, query: str, skus: tuple[str, ...]
+) -> None:
+    result = matcher.match(query)
+
+    assert result.status == "ambiguous"
+    assert tuple(candidate.sku for candidate in result.candidates) == skus
+    items_by_sku = {item.sku: item for item in matcher.items}
+    assert {
+        items_by_sku[candidate.sku].product_type for candidate in result.candidates
+    } == {"дрель"}
+
+
+@pytest.mark.parametrize(
+    "query",
+    [
+        "анус",
+        "долбить",
+        "какой адрес",
+        "аквариум 125 мм",
+        "<script>alert(1)</script>",
+        "qwerty asdf zxcv",
+    ],
+)
+def test_trigram_fallback_rejects_weak_or_accidental_similarity(
+    matcher: CatalogMatcher, query: str
+) -> None:
+    result = matcher.match(query)
+
+    assert result.status == "not_found"
+    assert result.candidates == []
+
+
 def test_bare_size_is_parsed_without_unit(matcher: CatalogMatcher) -> None:
     assert matcher.match("бита ph2 50").candidates[0].sku == "BIT-0005"
     assert matcher.match("диск пильный 190 48 зубьев").candidates[0].sku == "DSK-0034"
@@ -195,3 +244,110 @@ def test_unknown_size_does_not_fall_back_to_nearest_product(
     result = matcher.match("ушм 150")
     assert result.status == "not_found"
     assert result.candidates == []
+
+
+@pytest.mark.parametrize(
+    ("query", "sku"),
+    [
+        ("165 мм 24 зуба", "DSK-0029"),
+        ("165 мм 36 зубов", "DSK-0030"),
+        ("165 мм 48 зубьев", "DSK-0031"),
+        ("190 мм 24 зуба", "DSK-0032"),
+        ("190 мм 36 зубов", "DSK-0033"),
+        ("190 мм 48 зубьев", "DSK-0034"),
+        ("210 мм 24 зуба", "DSK-0035"),
+        ("210 мм 36 зубов", "DSK-0036"),
+        ("210 мм 48 зубьев", "DSK-0037"),
+    ],
+)
+def test_tooth_count_infers_saw_blade_without_product_name(
+    matcher: CatalogMatcher, query: str, sku: str
+) -> None:
+    result = matcher.match(query)
+
+    assert result.status == "matched"
+    assert [candidate.sku for candidate in result.candidates] == [sku]
+
+
+@pytest.mark.parametrize(
+    ("query", "skus"),
+    [
+        ("24 зуба", ("DSK-0029", "DSK-0032", "DSK-0035")),
+        ("36 зубов", ("DSK-0030", "DSK-0033", "DSK-0036")),
+        ("48 зубьев", ("DSK-0031", "DSK-0034", "DSK-0037")),
+    ],
+)
+def test_bare_tooth_count_returns_all_matching_saw_blade_sizes(
+    matcher: CatalogMatcher, query: str, skus: tuple[str, ...]
+) -> None:
+    result = matcher.match(query)
+
+    assert result.status == "ambiguous"
+    assert tuple(candidate.sku for candidate in result.candidates) == skus
+
+
+def test_unknown_tooth_count_does_not_return_nearest_saw_blade(
+    matcher: CatalogMatcher,
+) -> None:
+    result = matcher.match("210 мм 25 зубьев")
+
+    assert result.status == "not_found"
+    assert result.candidates == []
+
+
+@pytest.mark.parametrize(
+    "query",
+    [
+        "пильный диск 190x48t",
+        "190x48T",
+        "190x48z",
+        "190 48t",
+        "190/48T",
+    ],
+)
+def test_compact_saw_notation_parses_diameter_and_teeth(
+    matcher: CatalogMatcher, query: str
+) -> None:
+    result = matcher.match(query)
+
+    assert result.status == "matched"
+    assert [candidate.sku for candidate in result.candidates] == ["DSK-0034"]
+
+
+def test_bare_t_suffix_infers_saw_blades(matcher: CatalogMatcher) -> None:
+    result = matcher.match("24T")
+
+    assert result.status == "ambiguous"
+    assert [candidate.sku for candidate in result.candidates] == [
+        "DSK-0029",
+        "DSK-0032",
+        "DSK-0035",
+    ]
+
+
+@pytest.mark.parametrize(
+    ("query", "status", "skus"),
+    [
+        ("125 мм", "ambiguous", ("INS-0013", "DSK-0025", "RAS-0054")),
+        ("12 В", "ambiguous", ("INS-0003", "INS-0010", "INS-0024")),
+        ("900 Вт", "ambiguous", ("INS-0009", "INS-0013")),
+        ("M10", "ambiguous", ("KRP-0030", "KRP-0020", "KRP-0009")),
+        ("P120", "ambiguous", ("DSK-0024", "RAS-0050", "RAS-0057")),
+        ("SDS-plus", "ambiguous", ("BIT-0073", "INS-0012")),
+        ("PH2", "ambiguous", ("BIT-0004", "RIN-0010")),
+        ("20x20x2", "matched", ("TRB-0003",)),
+        ("ToolKraft 125 мм", "matched", ("INS-0027",)),
+        ("99999 мм", "not_found", ()),
+        ("аквариум 125 мм", "not_found", ()),
+    ],
+)
+def test_attribute_only_queries_use_exact_catalog_values(
+    matcher: CatalogMatcher,
+    query: str,
+    status: str,
+    skus: tuple[str, ...],
+) -> None:
+    result = matcher.match(query)
+
+    assert result.status == status
+    assert tuple(candidate.sku for candidate in result.candidates) == skus