jython · jeff5 · May 18, 2026 · Dec 15, 2025 · Dec 15, 2025 · Dec 15, 2025
diff --git a/ACKNOWLEDGMENTS b/ACKNOWLEDGMENTS
@@ -207,7 +207,7 @@ In no particular order they are:
     lifebarier (GitHub: lifebarier)                 C, 2024-03-06
     Adrian Ross (GitHub: R077A6r1an)                C, 2024-04-09
     John Hubbard (GitHub: jhubbardbnso)             C, 2024-06-06
-
+    Werner Fouché (GitHub: wfouche)                 C, 2025-05-27
 
 Since about 2012 we have been asking contributors to sign the Python
 Contributor Agreement. The part following names above records evidence

diff --git a/NEWS b/NEWS
@@ -29,10 +29,11 @@ New Features
       deprecated for removal in Java 26. See https://github.com/jnr/jffi/issues/165
 
 Jython 2.7.5a1 Bugs fixed
+    - [ GH-404 ] Windows code page 65001 (UTF-8) not supported by Jython
+    - [ GH-384 ] Console encoding inferred incorrectly on Java 21
     - [ GH-382 ] Java EE Servlet Namespace Has Been Changed From javax.servlet to jakarta.servlet
     - [ GH-84 ] PyServlet Will Need To Use The jakarta.servlet Namespace #84
 
-
 ==============================================================================
 Jython 2.7.4
 ==============================================================================

diff --git a/src/org/python/core/PySystemState.java b/src/org/python/core/PySystemState.java
@@ -1022,14 +1022,29 @@ private static void initRegistry(Properties preProperties, Properties postProper
      */
     private static String getConsoleEncoding(Properties props) {
 
-        // From Java 8 onwards, the answer may already be to hand in the registry:
-        String encoding = props.getProperty("sun.stdout.encoding");
-        String os = props.getProperty("os.name");
+        // Java 19+
+        String encoding = props.getProperty("stdout.encoding");
+        if (encoding != null) {
+            // Windows: cp65001 is automatically mapped to UTF-8
+            // https://github.com/openjdk/jdk25u/blob/master/src/java.base/windows/native/libjava/java_props_md.c#L131
+            // C function: getConsoleEncoding()
+            encoding = encoding.toLowerCase();
+            return encoding;
+        }
 
+        // Java 8 to 18
+        encoding = props.getProperty("sun.stdout.encoding");
         if (encoding != null) {
+            // Windows: some of the older versions of Java return "cp65001" for UTF-8
+            if (encoding.equals("cp65001")) {
+                encoding = "utf-8";
+            }
             return encoding;
+        }
 
-        } else if (os != null && os.startsWith("Windows")) {
+        String os = props.getProperty("os.name");
+        boolean isWindows = os != null && os.startsWith("Windows");
+        if (isWindows) {
             // Go via the Windows code page built-in command "chcp".
             String output = Py.getCommandResultWindows("chcp");
             /*
@@ -1039,10 +1054,14 @@ private static String getConsoleEncoding(Properties props) {
             final Pattern DIGITS_PATTERN = Pattern.compile("[1-9]\\d+");
             Matcher matcher = DIGITS_PATTERN.matcher(output);
             if (matcher.find()) {
-                return "cp".concat(output.substring(matcher.start(), matcher.end()));
+                encoding = "cp".concat(output.substring(matcher.start(), matcher.end()));
+                if (encoding.equals("cp65001")) {
+                    encoding = "utf-8";
+                }
+                return encoding;
             }
-
         } else {
+            // On Linux and macOS, sun.stdout.encoding and stdout.encoding are undefined for Java 8 and 11
             // Try a Unix-like "locale charmap".
             String output = Py.getCommandResult("locale", "charmap");
             // The result of "locale charmap" is just the charmap name ~ Charset or codec name.