src/main/java/org/lwes/util/CharacterEncoding.java

   1 /*======================================================================*
   2  * Copyright (c) 2008, Yahoo! Inc. All rights reserved.                 *
   3  *                                                                      *
   4  * Licensed under the New BSD License (the "License"); you may not use  *
   5  * this file except in compliance with the License.  Unless required    *
   6  * by applicable law or agreed to in writing, software distributed      *
   7  * under the License is distributed on an "AS IS" BASIS, WITHOUT        *
   8  * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.     *
   9  * See the License for the specific language governing permissions and  *
  10  * limitations under the License. See accompanying LICENSE file.        *
  11  *======================================================================*/
  12
  13 package org.lwes.util;
  14
  15 import java.io.UnsupportedEncodingException;
  16 import java.util.HashMap;
  17
  18 /**
  19  * This is a little class to abstract the character encoding strings that Java
  20  * uses into classes which can be checked at compile time.
  21  *
  22  * @author Kevin Scaldeferri
  23  */
  24 public abstract class CharacterEncoding {
  25
  26         // static loading
  27         private static final HashMap<String, CharacterEncoding> ENCODING_HASH = new HashMap<String, CharacterEncoding>();
  28         private static final String CANONICAL_ASCII_NAME = "ASCII";
  29         private static final String CANONICAL_ISO_8859_1_NAME = "ISO8859_1";
  30         private static final String CANONICAL_UTF_8_NAME = "UTF8";
  31         private static final String CANONICAL_SHIFT_JIS_NAME = "SJIS";
  32         private static final String CANONICAL_EUC_JP_NAME = "EUC_JP";
  33         private static final String CANONICAL_EUC_KR_NAME = "EUC_KR";
  34         private static final String[] ASCII_ALIASES = { CANONICAL_ASCII_NAME,
  35                         "US-ASCII", "ISO646-US" };
  36         private static final String[] ISO_8859_1_ALIASES = {
  37                         CANONICAL_ISO_8859_1_NAME, "ISO-8859-1", "ISO-LATIN-1", "8859_1" };
  38         private static final String[] UTF_8_ALIASES = { CANONICAL_UTF_8_NAME,
  39                         "UTF-8" };
  40         private static final String[] SHIFT_JIS_ALIASES = {
  41                         CANONICAL_SHIFT_JIS_NAME, "SHIFTJIS", "SHIFT-JIS", "SHIFT_JIS" };
  42         private static final String[] EUC_JP_ALIASES = { CANONICAL_EUC_JP_NAME,
  43                         "EUC-JP" };
  44         private static final String[] EUC_KR_ALIASES = { CANONICAL_EUC_KR_NAME,
  45                         "EUC-KR" };
  46
  47         /*
  48          * Returns Java's canonical form of the encoding.
  49          */
  50         public abstract String getEncodingString();
  51
  52         /*
  53          * Returns the official IANA name for the encoding. Everything expect Java
  54          * expects this form.
  55          */
  56         public abstract String getIANAString();
  57
  58         public static final CharacterEncoding ISO_8859_1 = new CharacterEncoding() {
  59                 public String getEncodingString() {
  60                         return "ISO-8859-1";
  61                 }
  62
  63                 public String getIANAString() {
  64                         return "ISO-8859-1";
  65                 }
  66         };
  67
  68         public static final CharacterEncoding UTF_8 = new CharacterEncoding() {
  69                 public String getEncodingString() {
  70                         return "UTF-8";
  71                 }
  72
  73                 public String getIANAString() {
  74                         return "UTF-8";
  75                 }
  76         };
  77
  78         public static final CharacterEncoding ASCII = new CharacterEncoding() {
  79                 public String getEncodingString() {
  80                         return "ASCII";
  81                 }
  82
  83                 public String getIANAString() {
  84                         return "US-ASCII";
  85                 }
  86         };
  87
  88         public static final CharacterEncoding SHIFT_JIS = new CharacterEncoding() {
  89                 public String getEncodingString() {
  90                         return "SJIS";
  91                 }
  92
  93                 public String getIANAString() {
  94                         return "Shift_JIS";
  95                 }
  96         };
  97
  98         public static final CharacterEncoding EUC_JP = new CharacterEncoding() {
  99                 public String getEncodingString() {
 100                         return "EUC_JP";
 101                 }
 102
 103                 public String getIANAString() {
 104                         return "EUC-JP";
 105                 }
 106         };
 107
 108         public static final CharacterEncoding EUC_KR = new CharacterEncoding() {
 109                 public String getEncodingString() {
 110                         return "EUC_KR";
 111                 }
 112
 113                 public String getIANAString() {
 114                         return "EUC-KR";
 115                 }
 116         };
 117
 118         /**
 119          * This is a highly limited implementation at the moment, so don't expect
 120          * too much from it.
 121      * @param enc the String representation of the encoding.
 122      * @return CharacterEncoding
 123      * @throws java.io.UnsupportedEncodingException if the encoding doesnt exist.
 124      */
 125         public static CharacterEncoding getInstance(String enc)
 126                         throws UnsupportedEncodingException {
 127                 if (ENCODING_HASH.containsKey(enc.toUpperCase())) {
 128                         return ENCODING_HASH.get(enc.toUpperCase());
 129                 } else {
 130                         throw new UnsupportedEncodingException(enc);
 131                 }
 132         }
 133
 134     @Override
 135     public int hashCode() {
 136         return getEncodingString().hashCode();
 137     }
 138
 139     public boolean equals(Object o) {
 140                 return (o instanceof CharacterEncoding)
 141                                 && getEncodingString().equals(((CharacterEncoding) o).getEncodingString());
 142         }
 143
 144         static {
 145                 int i;
 146                 for (i = 0; i < ASCII_ALIASES.length; i++) {
 147                         ENCODING_HASH.put(ASCII_ALIASES[i], ASCII);
 148                 }
 149                 for (i = 0; i < ISO_8859_1_ALIASES.length; i++) {
 150                         ENCODING_HASH.put(ISO_8859_1_ALIASES[i], ISO_8859_1);
 151                 }
 152                 for (i = 0; i < UTF_8_ALIASES.length; i++) {
 153                         ENCODING_HASH.put(UTF_8_ALIASES[i], UTF_8);
 154                 }
 155                 for (i = 0; i < SHIFT_JIS_ALIASES.length; i++) {
 156                         ENCODING_HASH.put(SHIFT_JIS_ALIASES[i], SHIFT_JIS);
 157                 }
 158                 for (i = 0; i < EUC_JP_ALIASES.length; i++) {
 159                         ENCODING_HASH.put(EUC_JP_ALIASES[i], EUC_JP);
 160                 }
 161                 for (i = 0; i < EUC_KR_ALIASES.length; i++) {
 162                         ENCODING_HASH.put(EUC_KR_ALIASES[i], EUC_KR);
 163                 }
 164         }
 165 }