Optimization: Avoid quadratic behavior in IdMaker.make_unique_parameterset_ids

changelog/14739.improvement.rst

@@ -0,0 +1 @@
+IdMaker.make_unique_parameterset_ids (used to generate ids for @pytest.mark.parametrize) no longer scales quadratically with the number of parameter sets when many of them produce colliding ids, significantly speeding up collection for large parametrized test suites with many duplicate ids.

src/_pytest/python.py

@@ -931,7 +931,8 @@ def make_unique_parameterset_ids(self) -> list[str | _HiddenParam]:
         """
         resolved_ids = list(self._resolve_ids())
         # All IDs must be unique!
-        if len(resolved_ids) != len(set(resolved_ids)):
+        all_ids = set(resolved_ids)
+        if len(resolved_ids) != len(all_ids):
             # Record the number of occurrences of each ID.
             id_counts = Counter(resolved_ids)
 
@@ -964,6 +965,8 @@ def make_unique_parameterset_ids(self) -> list[str | _HiddenParam]:
             # Map the ID to its next suffix.
             id_suffixes: dict[str, int] = defaultdict(int)
             # Suffix non-unique IDs to make them unique.
+            used_ids = set(all_ids)
+            remaining_id_counts = id_counts.copy()
             for index, id in enumerate(resolved_ids):
                 if id_counts[id] > 1:
                     if id is HIDDEN_PARAM:
@@ -972,10 +975,14 @@ def make_unique_parameterset_ids(self) -> list[str | _HiddenParam]:
                     if id and id[-1].isdigit():
                         suffix = "_"
                     new_id = f"{id}{suffix}{id_suffixes[id]}"
-                    while new_id in set(resolved_ids):
+                    while new_id in used_ids:
                         id_suffixes[id] += 1
                         new_id = f"{id}{suffix}{id_suffixes[id]}"
+                    remaining_id_counts[id] -= 1
+                    if remaining_id_counts[id] == 0:
+                        used_ids.discard(id)
                     resolved_ids[index] = new_id
+                    used_ids.add(new_id)
                     id_suffixes[id] += 1
         assert len(resolved_ids) == len(set(resolved_ids)), (
             f"Internal error: {resolved_ids=}"

testing/python/metafunc.py

@@ -785,6 +785,39 @@ def test_idmaker_duplicated_empty_str(self) -> None:
         ).make_unique_parameterset_ids()
         assert result == ["0", "1"]
 
+    def test_idmaker_unique_ids_frees_renamed_away_ids(self) -> None:
+        """Suffix collision must see ids freed after all duplicates are renamed.
+
+        Simplified resolved-id sequence: ["a10", "a10"] + ["a"] * 11
+        After renaming both "a10" entries, "a10" must be available again for
+        the 11th "a". A set that only .add()s new ids and never discards old
+        ones incorrectly yields "a11" as the last id.
+        """
+        ids = ["a10", "a10"] + ["a"] * 11
+        result = IdMaker(
+            ("x",),
+            [pytest.param(i) for i in range(len(ids))],
+            None,
+            ids,
+            None,
+            None,
+        ).make_unique_parameterset_ids()
+        assert result == [
+            "a10_0",
+            "a10_1",
+            "a0",
+            "a1",
+            "a2",
+            "a3",
+            "a4",
+            "a5",
+            "a6",
+            "a7",
+            "a8",
+            "a9",
+            "a10",
+        ]
+
     def test_parametrize_ids_exception(self, pytester: Pytester) -> None:
         """
         :param pytester: the instance of Pytester class, a temporary