Merge branch 'dev' into fix/adaptive-autosave-indexerror

2026-06-07 15:53:47 +03:00
parent cd4cdc69e6 9c0c857245
commit 3d96baf284
20 changed files with 80 additions and 124 deletions
@@ -2,6 +2,7 @@
 Tests for Selector.find_similar() with non-default parameters.
 Target file: tests/parser/test_general.py (append to TestSimilarElements class)
 """
+
 import pytest
 from scrapling import Selector

@@ -61,14 +62,10 @@ class TestFindSimilarAdvanced:
        first = product_page.css("div.product")[0]
        # Ignore both data-price and data-category → only class matters → all 3 divs match
        ignore_all_data = first.find_similar(
-            similarity_threshold=0.2,
-            ignore_attributes=["data-price", "data-category"]
+            similarity_threshold=0.2, ignore_attributes=["data-price", "data-category"]
        )
        # Ignore nothing → data-category difference (fruit vs veggie) may reduce matches
-        ignore_nothing = first.find_similar(
-            similarity_threshold=0.9,
-            ignore_attributes=[]
-        )
+        ignore_nothing = first.find_similar(similarity_threshold=0.9, ignore_attributes=[])
        assert len(ignore_all_data) >= len(ignore_nothing)

    def test_find_similar_on_text_node_returns_empty(self, product_page):
@@ -76,3 +73,31 @@ class TestFindSimilarAdvanced:
        text_node = product_page.css(".name::text")[0]
        result = text_node.find_similar()
        assert len(result) == 0
+
+    def test_find_similar_attribute_count_mismatch_scoring(self):
+        """The similarity denominator uses max() of both attribute counts, so candidates
+        with fewer attributes don't get inflated scores and candidates with extra
+        attributes stay penalized."""
+        html = """
+        <html><body>
+            <div class="cards">
+                <div class="card" data-kind="primary" data-color="red" data-size="large">Alpha</div>
+                <div class="card">Beta</div>
+                <div class="card" data-kind="primary" data-color="red" data-size="large" data-id="x">Gamma</div>
+                <div class="card" data-kind="primary" data-color="red" data-size="large">Delta</div>
+            </div>
+        </body></html>
+        """
+        page = Selector(html, adaptive=False)
+        first = page.css("div.card")[0]  # Alpha
+
+        similar = first.find_similar(similarity_threshold=0.9, ignore_attributes=[])
+        texts = {el.text for el in similar}
+
+        # An exact attribute match must pass
+        assert "Delta" in texts
+        # Beta matches 1 of Alpha's 4 attributes; the old denominator counted candidate
+        # attributes only, inflating it to a perfect score (1.0 / 1)
+        assert "Beta" not in texts
+        # Gamma's extra attribute dilutes the score (4.0 / 5) - the intentional penalty
+        assert "Gamma" not in texts