org.enhydra.xml.io.ShiftJisCharacterSet Maven / Gradle / Ivy
/*
* Enhydra Java Application Server Project
*
* The contents of this file are subject to the Enhydra Public License
* Version 1.1 (the "License"); you may not use this file except in
* compliance with the License. You may obtain a copy of the License on
* the Enhydra web site ( http://www.enhydra.org/ ).
*
* Software distributed under the License is distributed on an "AS IS"
* basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
* the License for the specific terms governing rights and limitations
* under the License.
*
* The Initial Developer of the Enhydra Application Server is Lutris
* Technologies, Inc. The Enhydra Application Server and portions created
* by Lutris Technologies, Inc. are Copyright Lutris Technologies, Inc.
* All Rights Reserved.
*
* Contributor(s):
*
* $Id: ShiftJisCharacterSet.java,v 1.2 2003/06/29 05:58:48 jkjome Exp $
*/
package org.enhydra.xml.io;
/**
* Class that implements special character handling for Shift_JIS.
* This detects invalid ranges so that they can be encoded by character
* entity references.
*
* Required to support i-mode Emoji characters. These are character codes
* that represent symbols on i-mode phones. The characters codes are invalid
* Shift-JIS character and must be encoded in HTML pages as numeric character
* entity references. Special handling is required on formatting to detect
* these characters.
*
* See http://www.nttdocomo.com/i/tag/emoji/ for details.
*/
class ShiftJisCharacterSet extends CharacterSet {
/** Constructor */
public ShiftJisCharacterSet(String name,
int charSize,
String mimePreferred,
String[] aliases) {
super(name, charSize, mimePreferred, aliases);
}
/**
* @see CharacterSet#isValid
*/
public boolean isValid(char ch) {
int byte1 = ((ch >> 8) & 0xFF);
int byte2 = (ch & 0xFF);
// FIXME: Right now, we just exclude the user defined range,
// which will result them being encoded as char entity refs
// This partial solution was done for safety, due to limited
// time to develop tests.
if (((0xF0 <= byte1) && (byte1 <= 0xFC))
&& (((0x40 <= byte2) && (byte2 <= 0x7e))
|| ((0x80 <= byte2) && (byte2 <= 0xFC)))) {
// User defined range
return false;
} else {
return true; // FIXME: see above
}
}
/**
* @see CharacterSet#sameValidCharRange
*/
public boolean sameValidCharRange(CharacterSet otherSet) {
// Only valid if Shift_JIS (only one of these objects should
// exists, so we can compare pointers).
return (otherSet == this);
}
}