GH-131798: Type-propagate string/list/tuple slices (GH-134671)

diff --git a/Lib/test/test_capi/test_opt.py b/Lib/test/test_capi/test_opt.py
index ee8d261685d4632176fc339b07dcff0324ac09ee..8a3819dabe44ce41949a30892cff4e1624611d24 100644 (file)
--- a/Lib/test/test_capi/test_opt.py
+++ b/Lib/test/test_capi/test_opt.py
@@ -1666,13 +1666,11 @@ class TestUopsOptimization(unittest.TestCase):
         self.assertIn("_CONTAINS_OP_DICT", uops)
         self.assertNotIn("_TO_BOOL_BOOL", uops)
 
-
     def test_remove_guard_for_known_type_str(self):
         def f(n):
             for i in range(n):
                 false = i == TIER2_THRESHOLD
                 empty = "X"[:false]
-                empty += ""  # Make JIT realize this is a string.
                 if empty:
                     return 1
             return 0
@@ -2249,6 +2247,34 @@ class TestUopsOptimization(unittest.TestCase):
         self.assertNotIn("_LOAD_ATTR_METHOD_NO_DICT", uops)
         self.assertNotIn("_LOAD_ATTR_METHOD_LAZY_DICT", uops)
 
+    def test_remove_guard_for_slice_list(self):
+        def f(n):
+            for i in range(n):
+                false = i == TIER2_THRESHOLD
+                sliced = [1, 2, 3][:false]
+                if sliced:
+                    return 1
+            return 0
+
+        res, ex = self._run_with_optimizer(f, TIER2_THRESHOLD)
+        self.assertEqual(res, 0)
+        self.assertIsNotNone(ex)
+        uops = get_opnames(ex)
+        self.assertIn("_TO_BOOL_LIST", uops)
+        self.assertNotIn("_GUARD_TOS_LIST", uops)
+
+    def test_remove_guard_for_slice_tuple(self):
+        def f(n):
+            for i in range(n):
+                false = i == TIER2_THRESHOLD
+                a, b = (1, 2, 3)[: false + 2]
+
+        _, ex = self._run_with_optimizer(f, TIER2_THRESHOLD)
+        self.assertIsNotNone(ex)
+        uops = get_opnames(ex)
+        self.assertIn("_UNPACK_SEQUENCE_TWO_TUPLE", uops)
+        self.assertNotIn("_GUARD_TOS_TUPLE", uops)
+
 
 def global_identity(x):
     return x

diff --git a/Misc/NEWS.d/next/Core_and_Builtins/2025-05-25-19-32-15.gh-issue-131798.f5h8aI.rst b/Misc/NEWS.d/next/Core_and_Builtins/2025-05-25-19-32-15.gh-issue-131798.f5h8aI.rst
new file mode 100644 (file)
index 0000000..6ecbfb8
--- /dev/null
+++ b/Misc/NEWS.d/next/Core_and_Builtins/2025-05-25-19-32-15.gh-issue-131798.f5h8aI.rst
@@ -0,0 +1 @@
+Make the JIT optimizer understand that slicing a string/list/tuple returns the same type.

diff --git a/Python/optimizer_bytecodes.c b/Python/optimizer_bytecodes.c
index 12efaacd8f0dfcc6e2fe4b845fdefc1d472c774c..fbf4dfd3db629c33bac1b40ba09be8441ff3cc6a 100644 (file)
--- a/Python/optimizer_bytecodes.c
+++ b/Python/optimizer_bytecodes.c
@@ -1237,6 +1237,20 @@ dummy_func(void) {
         sym_set_const(callable, list_append);
     }
 
+    op(_BINARY_SLICE, (container, start, stop -- res)) {
+        // Slicing a string/list/tuple always returns the same type.
+        PyTypeObject *type = sym_get_type(container);
+        if (type == &PyUnicode_Type ||
+            type == &PyList_Type ||
+            type == &PyTuple_Type)
+        {
+            res = sym_new_type(ctx, type);
+        }
+        else {
+            res = sym_new_not_null(ctx);
+        }
+    }
+
 // END BYTECODES //
 
 }

diff --git a/Python/optimizer_cases.c.h b/Python/optimizer_cases.c.h
index 1a2d49973ee91625ee7d9a43f0ba44d6c50dc000..b42f47c75eaf50b9070537c3b0b13945a409848f 100644 (file)
--- a/Python/optimizer_cases.c.h
+++ b/Python/optimizer_cases.c.h
@@ -568,8 +568,19 @@
         }
 
         case _BINARY_SLICE: {
+            JitOptSymbol *container;
             JitOptSymbol *res;
-            res = sym_new_not_null(ctx);
+            container = stack_pointer[-3];
+            PyTypeObject *type = sym_get_type(container);
+            if (type == &PyUnicode_Type ||
+                type == &PyList_Type ||
+                type == &PyTuple_Type)
+            {
+                res = sym_new_type(ctx, type);
+            }
+            else {
+                res = sym_new_not_null(ctx);
+            }
             stack_pointer[-3] = res;
             stack_pointer += -2;
             assert(WITHIN_STACK_BOUNDS());