[GR-52759] Preserve undecodable launcher argv bytes.

graalpython/com.oracle.graal.python.shell/src/com/oracle/graal/python/shell/GraalPythonMain.java

@@ -34,6 +34,12 @@
 import java.io.InputStream;
 import java.io.OutputStream;
 import java.lang.management.ManagementFactory;
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CoderResult;
+import java.nio.charset.CodingErrorAction;
 import java.nio.file.Files;
 import java.nio.file.InvalidPathException;
 import java.nio.file.NoSuchFileException;
@@ -80,6 +86,56 @@ public static void main(String[] args) {
         new GraalPythonMain().launch(args);
     }
 
+    @Override
+    protected String decodeArgument(byte[] argument) {
+        Charset charset = Charset.defaultCharset();
+        String decoded = new String(argument, charset);
+        if (decoded.indexOf('\uFFFD') < 0) {
+            return decoded;
+        }
+        return decodeArgument(argument, charset);
+    }
+
+    /*
+     * Match documented Unix sys.argv behavior:
+     * https://docs.python.org/3.12/library/sys.html#sys.argv
+     * "When you need original bytes, you can get it by `[os.fsencode(arg) for arg in sys.argv]`."
+     */
+    private static String decodeArgument(byte[] argument, Charset charset) {
+        CharsetDecoder decoder = charset.newDecoder().onMalformedInput(CodingErrorAction.REPORT).onUnmappableCharacter(CodingErrorAction.REPORT);
+        StringBuilder builder = new StringBuilder(argument.length);
+        ByteBuffer in = ByteBuffer.wrap(argument);
+        CharBuffer out = CharBuffer.allocate(Math.max(1, (int) Math.ceil(argument.length * decoder.maxCharsPerByte())));
+        while (true) {
+            CoderResult result = decoder.decode(in, out, true);
+            appendDecodedChars(builder, out);
+            if (result.isUnderflow()) {
+                break;
+            } else if (result.isOverflow()) {
+                continue;
+            } else if (result.isError()) {
+                int errorLength = result.length();
+                for (int i = 0; i < errorLength && in.hasRemaining(); i++) {
+                    builder.append((char) (0xDC00 + (in.get() & 0xff)));
+                }
+            }
+        }
+        while (true) {
+            CoderResult result = decoder.flush(out);
+            appendDecodedChars(builder, out);
+            if (result.isUnderflow()) {
+                break;
+            }
+        }
+        return builder.toString();
+    }
+
+    private static void appendDecodedChars(StringBuilder builder, CharBuffer out) {
+        out.flip();
+        builder.append(out);
+        out.clear();
+    }
+
     private static final String LANGUAGE_ID = "python";
 
     private static final String J_PYENVCFG = "pyvenv.cfg";

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

@@ -1,4 +1,4 @@
-# Copyright (c) 2018, 2025, Oracle and/or its affiliates.
+# Copyright (c) 2018, 2026, Oracle and/or its affiliates.
 # Copyright (C) 1996-2017 Python Software Foundation
 #
 # Licensed under the PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
@@ -75,6 +75,17 @@ def test_check_output(self):
                 [sys.executable, "-c", "print('BDFL')"])
         self.assertIn(b'BDFL', output)
 
+    @unittest.skipIf(sys.platform == 'win32', "POSIX argv bytes specific")
+    def test_surrogateescape_non_utf8_argv(self):
+        code = (
+            "import os, sys; "
+            "assert os.fsencode(sys.argv[-1]) == b'\\x8av'; "
+            "print(repr(sys.argv[-1]))"
+        )
+        cmd = f"{shlex.quote(sys.executable)} -c {shlex.quote(code)} \"$(printf '\\212v')\""
+        output = subprocess.check_output(cmd, shell=True, stderr=subprocess.PIPE, text=True)
+        self.assertEqual("'\\udc8av'\n", output)
+
     def test_check_output_nonzero(self):
         # check_call() function with non-zero return code
         with self.assertRaises(subprocess.CalledProcessError) as c:

graalpython/com.oracle.graal.python/src/com/oracle/graal/python/builtins/modules/ast/Validator.java

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2022, 2025, Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2022, 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
@@ -1006,9 +1006,9 @@ public Void visit(TypeVarTuple node) {
         return null;
     }
 
-/*-
-// Validation of sequences
-*/
+    /*-
+    // Validation of sequences
+    */
 
     // Equivalent of validate_stmts
     private void validateStmts(StmtTy[] stmts) {