[GR-74062] Ascii builtin should return a subclass

graalpython/com.oracle.graal.python.test/src/tests/test_builtin.py

@@ -54,6 +54,18 @@ def test_ascii(self):
         self.assertEqual(ascii(1), "1")
         self.assertEqual(ascii("錦蛇 \t \0 a \x03"), "'\\u9326\\u86c7 \\t \\x00 a \\x03'")
 
+    def test_ascii_preserves_str_subclass_for_ascii_repr(self):
+        class MyStr(str):
+            pass
+
+        class Foo:
+            def __repr__(self):
+                return MyStr("hello")
+
+        result = ascii(Foo())
+        self.assertEqual(result, "hello")
+        self.assertIs(type(result), MyStr)
+
     def test_input(self):
         import sys
         class AlwaysLine:

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/builtins/modules/BuiltinFunctions.java

@@ -188,7 +188,7 @@
 import com.oracle.graal.python.lib.PyNumberDivmodNode;
 import com.oracle.graal.python.lib.PyNumberIndexNode;
 import com.oracle.graal.python.lib.PyNumberPowerNode;
-import com.oracle.graal.python.lib.PyObjectAsciiNode;
+import com.oracle.graal.python.lib.PyObjectAsciiAsObjectNode;
 import com.oracle.graal.python.lib.PyObjectCallMethodObjArgs;
 import com.oracle.graal.python.lib.PyObjectDir;
 import com.oracle.graal.python.lib.PyObjectGetAttr;
@@ -1918,9 +1918,9 @@ public static FormatNode create() {
     abstract static class AsciiNode extends PythonUnaryBuiltinNode {
 
         @Specialization
-        public static TruffleString ascii(VirtualFrame frame, Object obj,
+        public static Object ascii(VirtualFrame frame, Object obj,
                         @Bind Node inliningTarget,
-                        @Cached PyObjectAsciiNode asciiNode) {
+                        @Cached PyObjectAsciiAsObjectNode asciiNode) {
             return asciiNode.execute(frame, inliningTarget, obj);
         }
     }

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/builtins/modules/cext/PythonCextObjectBuiltins.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, 2025, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2021, 2026, Oracle and/or its affiliates. All rights reserved.
  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
  *
  * The Universal Permissive License (UPL), Version 1.0
@@ -110,7 +110,7 @@
 import com.oracle.graal.python.lib.PyCallableCheckNode;
 import com.oracle.graal.python.lib.PyLongCheckNode;
 import com.oracle.graal.python.lib.PyObjectAsFileDescriptor;
-import com.oracle.graal.python.lib.PyObjectAsciiNode;
+import com.oracle.graal.python.lib.PyObjectAsciiAsObjectNode;
 import com.oracle.graal.python.lib.PyObjectCallMethodObjArgs;
 import com.oracle.graal.python.lib.PyObjectDelItem;
 import com.oracle.graal.python.lib.PyObjectDir;
@@ -669,9 +669,9 @@ int doGeneric(Object ptrObject,
     @CApiBuiltin(ret = PyObjectTransfer, args = {PyObject}, call = Direct)
     abstract static class PyObject_ASCII extends CApiUnaryBuiltinNode {
         @Specialization(guards = "!isNoValue(obj)")
-        static TruffleString ascii(Object obj,
+        static Object ascii(Object obj,
                         @Bind Node inliningTarget,
-                        @Cached PyObjectAsciiNode asciiNode) {
+                        @Cached PyObjectAsciiAsObjectNode asciiNode) {
             return asciiNode.execute(null, inliningTarget, obj);
         }
 

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/builtins/modules/re/PatternBuiltins.java

@@ -89,7 +89,7 @@
 import com.oracle.graal.python.builtins.objects.type.slots.TpSlotHashFun;
 import com.oracle.graal.python.builtins.objects.type.slots.TpSlotRichCompare;
 import com.oracle.graal.python.lib.PyCallableCheckNode;
-import com.oracle.graal.python.lib.PyObjectAsciiNode;
+import com.oracle.graal.python.lib.PyObjectAsciiAsTruffleStringNode;
 import com.oracle.graal.python.lib.PyObjectGetAttr;
 import com.oracle.graal.python.lib.PyObjectHashNode;
 import com.oracle.graal.python.lib.PyObjectReprAsTruffleStringNode;
@@ -1408,7 +1408,7 @@ static ParsedReplacement parseReplacement(Node inliningTarget, VirtualFrame fram
                         if (!isIdentifierNode.execute(inliningTarget, name) || binary && !ascii) {
                             errorProfile.enter(inliningTarget);
                             throw raiseRegexErrorNode.executeFormatted(frame, BAD_CHAR_IN_GROUP_NAME, replacement, toCodepointIndex(nameStartPos, binary),
-                                            binary ? PyObjectAsciiNode.executeUncached(name) : PyObjectReprAsTruffleStringNode.executeUncached(name));
+                                            binary ? PyObjectAsciiAsTruffleStringNode.executeUncached(name) : PyObjectReprAsTruffleStringNode.executeUncached(name));
                         }
                         Object namedCaptureGroups = TRegexUtil.TRegexCompiledRegexAccessor.namedCaptureGroups(tregexCompiledRegex, inliningTarget, readNamedGroupsNode);
                         if (!TRegexUtil.TRegexNamedCaptureGroupsAccessor.hasGroup(namedCaptureGroups, name, genericInteropLib)) {

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/builtins/objects/str/TemplateFormatter.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, 2025, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2021, 2026, Oracle and/or its affiliates. All rights reserved.
  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
  *
  * The Universal Permissive License (UPL), Version 1.0
@@ -69,11 +69,11 @@
 import com.oracle.graal.python.builtins.modules.SysModuleBuiltins;
 import com.oracle.graal.python.builtins.objects.PNone;
 import com.oracle.graal.python.builtins.objects.function.PKeyword;
-import com.oracle.graal.python.lib.PyObjectAsciiNode;
+import com.oracle.graal.python.lib.PyObjectAsciiAsObjectNode;
 import com.oracle.graal.python.lib.PyObjectGetItem;
 import com.oracle.graal.python.lib.PyObjectLookupAttr;
 import com.oracle.graal.python.lib.PyObjectReprAsObjectNode;
-import com.oracle.graal.python.lib.PyObjectStrAsTruffleStringNode;
+import com.oracle.graal.python.lib.PyObjectStrAsObjectNode;
 import com.oracle.graal.python.nodes.PRaiseNode;
 import com.oracle.truffle.api.CompilerDirectives.TruffleBoundary;
 import com.oracle.truffle.api.nodes.Node;
@@ -458,9 +458,9 @@ private static Object convert(Node node, Object obj, char conversion) {
             case 'r':
                 return PyObjectReprAsObjectNode.executeUncached(obj);
             case 's':
-                return PyObjectStrAsTruffleStringNode.executeUncached(obj);
+                return PyObjectStrAsObjectNode.executeUncached(obj);
             case 'a':
-                return PyObjectAsciiNode.executeUncached(obj);
+                return PyObjectAsciiAsObjectNode.executeUncached(obj);
             default:
                 throw PRaiseNode.raiseStatic(node, ValueError, INVALID_CONVERSION);
         }

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/lib/PyObjectAsciiAsObjectNode.java

@@ -0,0 +1,115 @@
+/*
+ * Copyright (c) 2021, 2026, Oracle and/or its affiliates. All rights reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * The Universal Permissive License (UPL), Version 1.0
+ *
+ * Subject to the condition set forth below, permission is hereby granted to any
+ * person obtaining a copy of this software, associated documentation and/or
+ * data (collectively the "Software"), free of charge and under any and all
+ * copyright rights in the Software, and any and all patent rights owned or
+ * freely licensable by each licensor hereunder covering either (i) the
+ * unmodified Software as contributed to or provided by such licensor, or (ii)
+ * the Larger Works (as defined below), to deal in both
+ *
+ * (a) the Software, and
+ *
+ * (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+ * one is included with the Software each a "Larger Work" to which the Software
+ * is contributed by such licensors),
+ *
+ * without restriction, including without limitation the rights to copy, create
+ * derivative works of, display, perform, and distribute the Software and make,
+ * use, sell, offer for sale, import, export, have made, and have sold the
+ * Software and the Larger Work(s), and to sublicense the foregoing rights on
+ * either these or other terms.
+ *
+ * This license is subject to the following condition:
+ *
+ * The above copyright notice and either this complete permission notice or at a
+ * minimum a reference to the UPL must be included in all copies or substantial
+ * portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+package com.oracle.graal.python.lib;
+
+import static com.oracle.graal.python.builtins.objects.bytes.BytesUtils.unicodeNonAsciiEscape;
+import static com.oracle.graal.python.util.PythonUtils.TS_ENCODING;
+
+import com.oracle.graal.python.nodes.PNodeWithContext;
+import com.oracle.graal.python.nodes.util.CastToTruffleStringNode;
+import com.oracle.truffle.api.dsl.Cached;
+import com.oracle.truffle.api.dsl.GenerateCached;
+import com.oracle.truffle.api.dsl.GenerateInline;
+import com.oracle.truffle.api.dsl.GenerateUncached;
+import com.oracle.truffle.api.dsl.NeverDefault;
+import com.oracle.truffle.api.dsl.Specialization;
+import com.oracle.truffle.api.frame.Frame;
+import com.oracle.truffle.api.frame.VirtualFrame;
+import com.oracle.truffle.api.nodes.Node;
+import com.oracle.truffle.api.strings.TruffleString;
+import com.oracle.truffle.api.strings.TruffleStringIterator;
+
+/**
+ * Equivalent of CPython's PyObject_ASCII.
+ */
+@GenerateUncached
+@GenerateInline(inlineByDefault = true)
+@GenerateCached
+public abstract class PyObjectAsciiAsObjectNode extends PNodeWithContext {
+    public static Object executeUncached(Object object) {
+        return PyObjectAsciiAsObjectNodeGen.getUncached().execute(null, null, object);
+    }
+
+    public final Object executeCached(Frame frame, Object object) {
+        return execute(frame, this, object);
+    }
+
+    public abstract Object execute(Frame frame, Node inliningTarget, Object object);
+
+    @Specialization
+    public static Object ascii(VirtualFrame frame, Node inliningTarget, Object obj,
+                    @Cached PyObjectReprAsObjectNode reprNode,
+                    @Cached CastToTruffleStringNode castToTruffleStringNode,
+                    @Cached TruffleString.GetCodeRangeNode getCodeRangeNode,
+                    @Cached TruffleString.CreateCodePointIteratorNode createCodePointIteratorNode,
+                    @Cached TruffleStringIterator.NextNode nextNode,
+                    @Cached TruffleString.CodePointLengthNode codePointLengthNode,
+                    @Cached TruffleString.FromByteArrayWithCompactionUTF32Node fromByteArrayNode) {
+        Object reprObj = reprNode.execute(frame, inliningTarget, obj);
+        TruffleString repr = castToTruffleStringNode.castKnownString(inliningTarget, reprObj);
+        if (getCodeRangeNode.execute(repr, TS_ENCODING) == TruffleString.CodeRange.ASCII) {
+            return reprObj;
+        }
+        return convertToAscii(repr, createCodePointIteratorNode, nextNode, codePointLengthNode, fromByteArrayNode);
+    }
+
+    public static TruffleString convertToAscii(TruffleString repr, TruffleString.CreateCodePointIteratorNode createCodePointIteratorNode, TruffleStringIterator.NextNode nextNode,
+                    TruffleString.CodePointLengthNode codePointLengthNode, TruffleString.FromByteArrayWithCompactionUTF32Node fromByteArrayNode) {
+        // TODO GR-37220: rewrite using TruffleStringBuilder?
+        byte[] bytes = new byte[codePointLengthNode.execute(repr, TS_ENCODING) * 10];
+        TruffleStringIterator it = createCodePointIteratorNode.execute(repr, TS_ENCODING);
+        int j = 0;
+        while (it.hasNext()) {
+            int ch = nextNode.execute(it, TS_ENCODING);
+            j = unicodeNonAsciiEscape(ch, j, bytes);
+        }
+        return fromByteArrayNode.execute(bytes, 0, j, TruffleString.CompactionLevel.S1, true);
+    }
+
+    @NeverDefault
+    public static PyObjectAsciiAsObjectNode create() {
+        return PyObjectAsciiAsObjectNodeGen.create();
+    }
+
+    public static PyObjectAsciiAsObjectNode getUncached() {
+        return PyObjectAsciiAsObjectNodeGen.getUncached();
+    }
+}

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/lib/PyObjectAsciiNode.java → graalpython/com.oracle.graal.python/src/com/oracle/graal/python/lib/PyObjectAsciiAsTruffleStringNode.java

@@ -40,7 +40,6 @@
  */
 package com.oracle.graal.python.lib;
 
-import static com.oracle.graal.python.builtins.objects.bytes.BytesUtils.unicodeNonAsciiEscape;
 import static com.oracle.graal.python.util.PythonUtils.TS_ENCODING;
 
 import com.oracle.graal.python.nodes.PNodeWithContext;
@@ -62,9 +61,9 @@
 @GenerateUncached
 @GenerateInline(inlineByDefault = true)
 @GenerateCached
-public abstract class PyObjectAsciiNode extends PNodeWithContext {
+public abstract class PyObjectAsciiAsTruffleStringNode extends PNodeWithContext {
     public static TruffleString executeUncached(Object object) {
-        return PyObjectAsciiNodeGen.getUncached().execute(null, null, object);
+        return PyObjectAsciiAsTruffleStringNodeGen.getUncached().execute(null, null, object);
     }
 
     public final TruffleString executeCached(Frame frame, Object object) {
@@ -81,27 +80,19 @@ public static TruffleString ascii(VirtualFrame frame, Node inliningTarget, Objec
                     @Cached TruffleStringIterator.NextNode nextNode,
                     @Cached TruffleString.CodePointLengthNode codePointLengthNode,
                     @Cached TruffleString.FromByteArrayWithCompactionUTF32Node fromByteArrayNode) {
-        // TODO GR-37220: rewrite using TruffleStringBuilder?
         TruffleString repr = reprNode.execute(frame, inliningTarget, obj);
         if (getCodeRangeNode.execute(repr, TS_ENCODING) == TruffleString.CodeRange.ASCII) {
             return repr;
         }
-        byte[] bytes = new byte[codePointLengthNode.execute(repr, TS_ENCODING) * 10];
-        TruffleStringIterator it = createCodePointIteratorNode.execute(repr, TS_ENCODING);
-        int j = 0;
-        while (it.hasNext()) {
-            int ch = nextNode.execute(it, TS_ENCODING);
-            j = unicodeNonAsciiEscape(ch, j, bytes);
-        }
-        return fromByteArrayNode.execute(bytes, 0, j, TruffleString.CompactionLevel.S1, true);
+        return PyObjectAsciiAsObjectNode.convertToAscii(repr, createCodePointIteratorNode, nextNode, codePointLengthNode, fromByteArrayNode);
     }
 
     @NeverDefault
-    public static PyObjectAsciiNode create() {
-        return PyObjectAsciiNodeGen.create();
+    public static PyObjectAsciiAsTruffleStringNode create() {
+        return PyObjectAsciiAsTruffleStringNodeGen.create();
     }
 
-    public static PyObjectAsciiNode getUncached() {
-        return PyObjectAsciiNodeGen.getUncached();
+    public static PyObjectAsciiAsTruffleStringNode getUncached() {
+        return PyObjectAsciiAsTruffleStringNodeGen.getUncached();
     }
 }

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/nodes/bytecode/PBytecodeRootNode.java

@@ -62,8 +62,8 @@
 import com.oracle.graal.python.PythonLanguage;
 import com.oracle.graal.python.builtins.PythonBuiltinClassType;
 import com.oracle.graal.python.builtins.modules.BuiltinFunctions.FormatNode;
-import com.oracle.graal.python.builtins.modules.BuiltinFunctionsFactory.FormatNodeFactory.FormatNodeGen;
 import com.oracle.graal.python.builtins.modules.MarshalModuleBuiltins;
+import com.oracle.graal.python.builtins.modules.BuiltinFunctionsFactory.FormatNodeFactory.FormatNodeGen;
 import com.oracle.graal.python.builtins.objects.PNone;
 import com.oracle.graal.python.builtins.objects.asyncio.GetAwaitableNode;
 import com.oracle.graal.python.builtins.objects.asyncio.GetAwaitableNodeGen;
@@ -143,8 +143,8 @@
 import com.oracle.graal.python.lib.PyNumberSubtractNode;
 import com.oracle.graal.python.lib.PyNumberTrueDivideNode;
 import com.oracle.graal.python.lib.PyNumberXorNode;
-import com.oracle.graal.python.lib.PyObjectAsciiNode;
-import com.oracle.graal.python.lib.PyObjectAsciiNodeGen;
+import com.oracle.graal.python.lib.PyObjectAsciiAsObjectNode;
+import com.oracle.graal.python.lib.PyObjectAsciiAsObjectNodeGen;
 import com.oracle.graal.python.lib.PyObjectDelItem;
 import com.oracle.graal.python.lib.PyObjectDelItemNodeGen;
 import com.oracle.graal.python.lib.PyObjectGetAttr;
@@ -401,8 +401,8 @@ public final class PBytecodeRootNode extends PRootNode implements BytecodeOSRNod
     private static final NodeSupplier<PyObjectStrAsObjectNode> NODE_STR = PyObjectStrAsObjectNode::create;
     private static final PyObjectReprAsObjectNode UNCACHED_REPR = PyObjectReprAsObjectNode.getUncached();
     private static final NodeSupplier<PyObjectReprAsObjectNode> NODE_REPR = PyObjectReprAsObjectNode::create;
-    private static final PyObjectAsciiNode UNCACHED_ASCII = PyObjectAsciiNode.getUncached();
-    private static final NodeSupplier<PyObjectAsciiNode> NODE_ASCII = PyObjectAsciiNode::create;
+    private static final PyObjectAsciiAsObjectNode UNCACHED_ASCII = PyObjectAsciiAsObjectNode.getUncached();
+    private static final NodeSupplier<PyObjectAsciiAsObjectNode> NODE_ASCII = PyObjectAsciiAsObjectNode::create;
     private static final NodeSupplier<FormatNode> NODE_FORMAT = FormatNode::create;
     private static final NodeSupplier<SendNode> NODE_SEND = SendNode::create;
     private static final NodeSupplier<ThrowNode> NODE_THROW = ThrowNode::create;
@@ -4989,7 +4989,7 @@ private int bytecodeFormatValue(VirtualFrame virtualFrame, int initialStackTop,
                 value = insertChildNode(localNodes, bci, UNCACHED_REPR, PyObjectReprAsObjectNodeGen.class, NODE_REPR, useCachedNodes).executeCached(virtualFrame, value);
                 break;
             case FormatOptions.FVC_ASCII:
-                value = insertChildNode(localNodes, bci, UNCACHED_ASCII, PyObjectAsciiNodeGen.class, NODE_ASCII, useCachedNodes).executeCached(virtualFrame, value);
+                value = insertChildNode(localNodes, bci, UNCACHED_ASCII, PyObjectAsciiAsObjectNodeGen.class, NODE_ASCII, useCachedNodes).executeCached(virtualFrame, value);
                 break;
             default:
                 assert type == FormatOptions.FVC_NONE;