8310047: Add UTF-32 based Charsets into StandardCharsets

Reviewed-by: alanb, lancea, bpb, jpai, jlu
This commit is contained in:
Naoto Sato 2023-07-11 16:10:34 +00:00
parent caadad4fdc
commit 00c7f914c6
4 changed files with 60 additions and 10 deletions
src/java.base/share/classes
test/jdk/java/nio/charset/StandardCharsets

@ -168,37 +168,54 @@ import java.util.TreeMap;
* <tr><th scope="row" style="vertical-align:top">{@code UTF-16}</th>
* <td>Sixteen-bit UCS Transformation Format,
* byte&nbsp;order identified by an optional byte-order mark</td></tr>
* <tr><th scope="row" style="vertical-align:top">{@code UTF-32BE}</th>
* <td>Thirty-two-bit UCS Transformation Format,
* big-endian byte&nbsp;order</td></tr>
* <tr><th scope="row" style="vertical-align:top">{@code UTF-32LE}</th>
* <td>Thirty-two-bit UCS Transformation Format,
* little-endian byte&nbsp;order</td></tr>
* <tr><th scope="row" style="vertical-align:top">{@code UTF-32}</th>
* <td>Thirty-two-bit UCS Transformation Format,
* byte&nbsp;order identified by an optional byte-order mark</td></tr>
* </tbody>
* </table></blockquote>
*
* <p> The {@code UTF-8} charset is specified by <a
* href="http://www.ietf.org/rfc/rfc2279.txt"><i>RFC&nbsp;2279</i></a>; the
* transformation format upon which it is based is specified in
* Amendment&nbsp;2 of ISO&nbsp;10646-1 and is also described in the <a
* ISO&nbsp;10646-1 and is also described in the <a
* href="http://www.unicode.org/standard/standard.html"><i>Unicode
* Standard</i></a>.
*
* <p> The {@code UTF-16} charsets are specified by <a
* href="http://www.ietf.org/rfc/rfc2781.txt"><i>RFC&nbsp;2781</i></a>; the
* transformation formats upon which they are based are specified in
* Amendment&nbsp;1 of ISO&nbsp;10646-1 and are also described in the <a
* ISO&nbsp;10646-1 and are also described in the <a
* href="http://www.unicode.org/standard/standard.html"><i>Unicode
* Standard</i></a>.
*
* <p> The {@code UTF-16} charsets use sixteen-bit quantities and are
* <p> The {@code UTF-32} charsets are based upon transformation formats
* which are specified in
* ISO&nbsp;10646-1 and are also described in the <a
* href="http://www.unicode.org/standard/standard.html"><i>Unicode
* Standard</i></a>.
*
* <p> The {@code UTF-16} and {@code UTF-32} charsets use sixteen-bit and thirty-two-bit
* quantities respectively, and are
* therefore sensitive to byte order. In these encodings the byte order of a
* stream may be indicated by an initial <i>byte-order mark</i> represented by
* the Unicode character <code>'&#92;uFEFF'</code>. Byte-order marks are handled
* the Unicode character {@code U+FEFF}. Byte-order marks are handled
* as follows:
*
* <ul>
*
* <li><p> When decoding, the {@code UTF-16BE} and {@code UTF-16LE}
* <li><p> When decoding, the {@code UTF-16BE}, {@code UTF-16LE},
* {@code UTF-32BE}, and {@code UTF-32LE}
* charsets interpret the initial byte-order marks as a <small>ZERO-WIDTH
* NON-BREAKING SPACE</small>; when encoding, they do not write
* byte-order marks. </p></li>
*
* <li><p> When decoding, the {@code UTF-16} charset interprets the
* <li><p> When decoding, the {@code UTF-16} and {@code UTF-32} charsets interpret the
* byte-order mark at the beginning of the input stream to indicate the
* byte-order of the stream but defaults to big-endian if there is no
* byte-order mark; when encoding, it uses big-endian byte order and writes

@ -1,5 +1,5 @@
/*
* Copyright (c) 2011, 2019, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2011, 2023, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
@ -74,4 +74,23 @@ public final class StandardCharsets {
* optional byte-order mark.
*/
public static final Charset UTF_16 = new sun.nio.cs.UTF_16();
/**
* Thirty-two-bit UCS Transformation Format, big-endian byte order.
* @since 22
*/
public static final Charset UTF_32BE = new sun.nio.cs.UTF_32BE();
/**
* Thirty-two-bit UCS Transformation Format, little-endian byte order.
* @since 22
*/
public static final Charset UTF_32LE = new sun.nio.cs.UTF_32LE();
/**
* Thirty-two-bit UCS Transformation Format, byte order identified by an
* optional byte-order mark.
* @since 22
*/
public static final Charset UTF_32 = new sun.nio.cs.UTF_32();
}

@ -93,6 +93,9 @@ public class StandardCharsets extends CharsetProvider {
map.put("utf-16", java.nio.charset.StandardCharsets.UTF_16);
map.put("utf-16be", java.nio.charset.StandardCharsets.UTF_16BE);
map.put("utf-16le", java.nio.charset.StandardCharsets.UTF_16LE);
map.put("utf-32", java.nio.charset.StandardCharsets.UTF_32);
map.put("utf-32be", java.nio.charset.StandardCharsets.UTF_32BE);
map.put("utf-32le", java.nio.charset.StandardCharsets.UTF_32LE);
cache = map;
}
return map;

@ -1,5 +1,5 @@
/*
* Copyright (c) 2011, 2014, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2011, 2023, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
@ -23,7 +23,7 @@
/*
* @test
* @bug 4884238
* @bug 4884238 8310047
* @summary Test standard charset name constants.
* @author Mike Duigou
* @run main Standard
@ -41,7 +41,9 @@ public class Standard {
private final static String standardCharsets[] = {
"US-ASCII", "ISO-8859-1", "UTF-8",
"UTF-16BE", "UTF-16LE", "UTF-16" };
"UTF-16BE", "UTF-16LE", "UTF-16",
"UTF-32BE", "UTF-32LE", "UTF-32",
};
public static void realMain(String[] args) {
check(StandardCharsets.US_ASCII instanceof Charset);
@ -50,6 +52,9 @@ public class Standard {
check(StandardCharsets.UTF_16BE instanceof Charset);
check(StandardCharsets.UTF_16LE instanceof Charset);
check(StandardCharsets.UTF_16 instanceof Charset);
check(StandardCharsets.UTF_32BE instanceof Charset);
check(StandardCharsets.UTF_32LE instanceof Charset);
check(StandardCharsets.UTF_32 instanceof Charset);
check("US-ASCII".equals(StandardCharsets.US_ASCII.name()));
check("ISO-8859-1".equals(StandardCharsets.ISO_8859_1.name()));
@ -57,6 +62,9 @@ public class Standard {
check("UTF-16BE".equals(StandardCharsets.UTF_16BE.name()));
check("UTF-16LE".equals(StandardCharsets.UTF_16LE.name()));
check("UTF-16".equals(StandardCharsets.UTF_16.name()));
check("UTF-32BE".equals(StandardCharsets.UTF_32BE.name()));
check("UTF-32LE".equals(StandardCharsets.UTF_32LE.name()));
check("UTF-32".equals(StandardCharsets.UTF_32.name()));
check(Charset.forName("US-ASCII") == StandardCharsets.US_ASCII);
check(Charset.forName("ISO-8859-1") == StandardCharsets.ISO_8859_1);
@ -64,6 +72,9 @@ public class Standard {
check(Charset.forName("UTF-16BE") == StandardCharsets.UTF_16BE);
check(Charset.forName("UTF-16LE") == StandardCharsets.UTF_16LE);
check(Charset.forName("UTF-16") == StandardCharsets.UTF_16);
check(Charset.forName("UTF-32BE") == StandardCharsets.UTF_32BE);
check(Charset.forName("UTF-32LE") == StandardCharsets.UTF_32LE);
check(Charset.forName("UTF-32") == StandardCharsets.UTF_32);
Set<String> charsets = new HashSet<>();
Field standardCharsetFields[] = StandardCharsets.class.getFields();