ISO_8859_1.java, [...]: Fixed canonical names and aliases according to...

2005-02-07  Robert Schuster  <thebohemian@gmx.net>

        * gnu/java/nio/charset/ISO_8859_1.java,
        gnu/java/nio/charset/US_ASCII.java,
        gnu/java/nio/charset/UTF_16.java,
        gnu/java/nio/charset/UTF_16_LE.java,
        gnu/java/nio/charset/UTF_16_BE.java,
        gnu/java/nio/charset/UTF_8.java: Fixed canonical names
         and aliases according to
         "http://www.iana.org/assignments/character-sets",
         "http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html"
         and "http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL".
        * gnu/java/nio/charset/Provider.java: Made charset lookup
         case-insensitive which fixes bug #11740.

From-SVN: r94711
This commit is contained in:
Robert Schuster 2005-02-07 20:34:17 +00:00 committed by Anthony Green
parent f0d87cdad8
commit c686e630c3
8 changed files with 139 additions and 26 deletions

View File

@ -1,3 +1,18 @@
2005-02-07 Robert Schuster <thebohemian@gmx.net>
* gnu/java/nio/charset/ISO_8859_1.java,
gnu/java/nio/charset/US_ASCII.java,
gnu/java/nio/charset/UTF_16.java,
gnu/java/nio/charset/UTF_16_LE.java,
gnu/java/nio/charset/UTF_16_BE.java,
gnu/java/nio/charset/UTF_8.java: Fixed canonical names
and aliases according to
"http://www.iana.org/assignments/character-sets",
"http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html"
and "http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL".
* gnu/java/nio/charset/Provider.java: Made charset lookup
case-insensitive which fixes bug #11740.
2005-02-07 Tom Tromey <tromey@redhat.com>
PR libgcj/19611:

View File

@ -1,5 +1,5 @@
/* ISO_8859_1.java --
Copyright (C) 2002, 2004 Free Software Foundation, Inc.
Copyright (C) 2002, 2004, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -53,7 +53,28 @@ final class ISO_8859_1 extends Charset
{
ISO_8859_1 ()
{
super ("ISO-8859-1", new String[]{"ISO-LATIN-1"});
/* Canonical charset name chosen according to:
* http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html
*/
super ("ISO-8859-1", new String[] {
/* These names are provided by
* http://www.iana.org/assignments/character-sets
*/
"iso-ir-100",
"ISO_8859-1",
"latin1",
"l1",
"IBM819",
"CP819",
"csISOLatin1",
"8859_1",
/* These names are provided by
* http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL
*/
"ISO8859_1", "ISO_8859_1", "ibm-819", "ISO_8859-1:1987",
"819"
});
}
public boolean contains (Charset cs)

View File

@ -1,5 +1,5 @@
/* Provider.java --
Copyright (C) 2002 Free Software Foundation, Inc.
Copyright (C) 2002, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -48,6 +48,7 @@ import java.util.Iterator;
* {@link Charset#charsetForName} and * {@link Charset#availableCharsets}.
*
* @author Jesse Rosenstock
* @author Robert Schuster (thebohemian@gmx.net)
* @see Charset
*/
public final class Provider extends CharsetProvider
@ -63,12 +64,14 @@ public final class Provider extends CharsetProvider
}
/**
* Map from charset name to charset canonical name.
* Map from charset name to charset canonical name. The strings
* are all lower-case to allow case-insensitive retrieval of
* Charset instances.
*/
private final HashMap canonicalNames;
/**
* Map from canonical name to Charset.
* Map from lower-case canonical name to Charset.
* TODO: We may want to use soft references. We would then need to keep
* track of the class name to regenerate the object.
*/
@ -76,8 +79,6 @@ public final class Provider extends CharsetProvider
private Provider ()
{
// FIXME: We might need to make the name comparison case insensitive.
// Verify this with the Sun JDK.
canonicalNames = new HashMap ();
charsets = new HashMap ();
@ -106,24 +107,42 @@ public final class Provider extends CharsetProvider
.iterator ();
}
/**
* Returns a Charset instance by converting the given
* name to lower-case, looking up the canonical charset
* name and finally looking up the Charset with that name.
*
* <p>The lookup is therefore case-insensitive.</p>
*
* @returns The Charset having <code>charsetName</code>
* as its alias or null if no such Charset exist.
*/
public Charset charsetForName (String charsetName)
{
return (Charset) charsets.get (canonicalize (charsetName));
}
private Object canonicalize (String charsetName)
{
Object o = canonicalNames.get (charsetName);
return o == null ? charsetName : o;
return (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase()));
}
/**
* Puts a Charset under its canonical name into the 'charsets' map.
* Then puts a mapping from all its alias names to the canonical name.
*
* <p>All names are converted to lower-case</p>.
*
* @param cs
*/
private void addCharset (Charset cs)
{
String canonicalName = cs.name ();
String canonicalName = cs.name().toLowerCase();
charsets.put (canonicalName, cs);
/* Adds a mapping between the canonical name
* itself making a lookup using that name
* no special case.
*/
canonicalNames.put(canonicalName, canonicalName);
for (Iterator i = cs.aliases ().iterator (); i.hasNext (); )
canonicalNames.put (i.next (), canonicalName);
canonicalNames.put (((String) i.next()).toLowerCase(), canonicalName);
}
public static synchronized Provider provider ()

View File

@ -1,5 +1,5 @@
/* US_ASCII.java --
Copyright (C) 2002, 2004 Free Software Foundation, Inc.
Copyright (C) 2002, 2004, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -53,7 +53,29 @@ final class US_ASCII extends Charset
{
US_ASCII ()
{
super ("US-ASCII", new String[]{"ISO646-US"});
/* Canonical charset name chosen according to:
* http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html
*/
super ("US-ASCII", new String[] {
/* These names are provided by
* http://www.iana.org/assignments/character-sets
*/
"iso-ir-6",
"ANSI_X3.4-1986",
"ISO_646.irv:1991",
"ASCII",
"ISO646-US",
"ASCII",
"us",
"IBM367",
"cp367",
"csASCII",
/* These names are provided by
* http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL
*/
"ANSI_X3.4-1968", "iso_646.irv:1983", "ascii7", "646",
"windows-20127"
});
}
public boolean contains (Charset cs)

View File

@ -1,5 +1,5 @@
/* UTF_16.java --
Copyright (C) 2002, 2004 Free Software Foundation, Inc.
Copyright (C) 2002, 2004, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -51,7 +51,14 @@ final class UTF_16 extends Charset
{
UTF_16 ()
{
super ("UTF-16", null);
super ("UTF-16", new String[] {
// witnessed by the internet
"UTF16",
/* These names are provided by
* http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL
*/
"ISO-10646-UCS-2", "unicode", "csUnicode", "ucs-2"
});
}
public boolean contains (Charset cs)

View File

@ -1,5 +1,5 @@
/* UTF_16BE.java --
Copyright (C) 2002, 2004 Free Software Foundation, Inc.
Copyright (C) 2002, 2004, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -51,7 +51,18 @@ final class UTF_16BE extends Charset
{
UTF_16BE ()
{
super ("UTF-16BE", null);
super ("UTF-16BE", new String[] {
// witnessed by the internet
"UTF16BE",
/* These names are provided by
* http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL
*/
"x-utf-16be", "ibm-1200", "ibm-1201", "ibm-5297",
"ibm-13488", "ibm-17584", "windows-1201", "cp1200", "cp1201",
"UTF16_BigEndian",
// see http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html
"UnicodeBigUnmarked"
});
}
public boolean contains (Charset cs)

View File

@ -1,5 +1,5 @@
/* UTF_16LE.java --
Copyright (C) 2002, 2004 Free Software Foundation, Inc.
Copyright (C) 2002, 2004, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -51,7 +51,17 @@ final class UTF_16LE extends Charset
{
UTF_16LE ()
{
super ("UTF-16LE", null);
super ("UTF-16LE", new String[] {
// witnessed by the internet
"UTF16LE",
/* These names are provided by
* http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL
*/
"x-utf-16le", "ibm-1202", "ibm-13490", "ibm-17586",
"UTF16_LittleEndian",
// see http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html
"UnicodeLittleUnmarked"
});
}
public boolean contains (Charset cs)

View File

@ -1,5 +1,5 @@
/* UTF_8.java --
Copyright (C) 2002, 2004 Free Software Foundation, Inc.
Copyright (C) 2002, 2004, 2005 Free Software Foundation, Inc.
This file is part of GNU Classpath.
@ -62,7 +62,15 @@ final class UTF_8 extends Charset
{
UTF_8 ()
{
super ("UTF-8", null);
super ("UTF-8", new String[] {
/* These names are provided by
* http://oss.software.ibm.com/cgi-bin/icu/convexp?s=ALL
*/
"ibm-1208", "ibm-1209", "ibm-5304", "ibm-5305",
"windows-65001", "cp1208",
// see http://java.sun.com/j2se/1.5.0/docs/guide/intl/encoding.doc.html
"UTF8"
});
}
public boolean contains (Charset cs)