| 1 | /* |
| 2 | Copyright (C) 2002-2004 MySQL AB |
| 3 | |
| 4 | This program is free software; you can redistribute it and/or modify |
| 5 | it under the terms of version 2 of the GNU General Public License as |
| 6 | published by the Free Software Foundation. |
| 7 | |
| 8 | There are special exceptions to the terms and conditions of the GPL |
| 9 | as it is applied to this software. View the full text of the |
| 10 | exception in file EXCEPTIONS-CONNECTOR-J in the directory of this |
| 11 | software distribution. |
| 12 | |
| 13 | This program is distributed in the hope that it will be useful, |
| 14 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 15 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 16 | GNU General Public License for more details. |
| 17 | |
| 18 | You should have received a copy of the GNU General Public License |
| 19 | along with this program; if not, write to the Free Software |
| 20 | Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
| 21 | |
| 22 | |
| 23 | |
| 24 | */ |
| 25 | package com.mysql.jdbc; |
| 26 | |
| 27 | import java.io.UnsupportedEncodingException; |
| 28 | |
| 29 | import java.sql.SQLException; |
| 30 | import java.util.HashMap; |
| 31 | import java.util.Map; |
| 32 | |
| 33 | /** |
| 34 | * Converter for char[]->byte[] and byte[]->char[] for single-byte character |
| 35 | * sets. |
| 36 | * |
| 37 | * Much faster (5-6x) than the built-in solution that ships with the JVM, even |
| 38 | * with JDK-1.4.x and NewIo. |
| 39 | * |
| 40 | * @author Mark Matthews |
| 41 | */ |
| 42 | public class SingleByteCharsetConverter { |
| 43 | |
| 44 | private static final int BYTE_RANGE = (1 + Byte.MAX_VALUE) - Byte.MIN_VALUE; |
| 45 | private static byte[] allBytes = new byte[BYTE_RANGE]; |
| 46 | private static final Map CONVERTER_MAP = new HashMap(); |
| 47 | |
| 48 | private final static byte[] EMPTY_BYTE_ARRAY = new byte[0]; |
| 49 | |
| 50 | // The initial charToByteMap, with all char mappings mapped |
| 51 | // to (byte) '?', so that unknown characters are mapped to '?' |
| 52 | // instead of '\0' (which means end-of-string to MySQL). |
| 53 | private static byte[] unknownCharsMap = new byte[65536]; |
| 54 | |
| 55 | static { |
| 56 | for (int i = Byte.MIN_VALUE; i <= Byte.MAX_VALUE; i++) { |
| 57 | allBytes[i - Byte.MIN_VALUE] = (byte) i; |
| 58 | } |
| 59 | |
| 60 | for (int i = 0; i < unknownCharsMap.length; i++) { |
| 61 | unknownCharsMap[i] = (byte) '?'; // use something 'sane' for |
| 62 | // unknown chars |
| 63 | } |
| 64 | } |
| 65 | |
| 66 | // ~ Instance fields |
| 67 | // -------------------------------------------------------- |
| 68 | |
| 69 | /** |
| 70 | * Get a converter for the given encoding name |
| 71 | * |
| 72 | * @param encodingName |
| 73 | * the Java character encoding name |
| 74 | * |
| 75 | * @return a converter for the given encoding name |
| 76 | * @throws UnsupportedEncodingException |
| 77 | * if the character encoding is not supported |
| 78 | */ |
| 79 | public static synchronized SingleByteCharsetConverter getInstance( |
| 80 | String encodingName, Connection conn) |
| 81 | throws UnsupportedEncodingException, SQLException { |
| 82 | SingleByteCharsetConverter instance = (SingleByteCharsetConverter) CONVERTER_MAP |
| 83 | .get(encodingName); |
| 84 | |
| 85 | if (instance == null) { |
| 86 | instance = initCharset(encodingName); |
| 87 | } |
| 88 | |
| 89 | return instance; |
| 90 | } |
| 91 | |
| 92 | /** |
| 93 | * Initialize the shared instance of a converter for the given character |
| 94 | * encoding. |
| 95 | * |
| 96 | * @param javaEncodingName |
| 97 | * the Java name for the character set to initialize |
| 98 | * @return a converter for the given character set |
| 99 | * @throws UnsupportedEncodingException |
| 100 | * if the character encoding is not supported |
| 101 | */ |
| 102 | public static SingleByteCharsetConverter initCharset(String javaEncodingName) |
| 103 | throws UnsupportedEncodingException, SQLException { |
| 104 | if (CharsetMapping.isMultibyteCharset(javaEncodingName)) { |
| 105 | return null; |
| 106 | } |
| 107 | |
| 108 | SingleByteCharsetConverter converter = new SingleByteCharsetConverter( |
| 109 | javaEncodingName); |
| 110 | |
| 111 | CONVERTER_MAP.put(javaEncodingName, converter); |
| 112 | |
| 113 | return converter; |
| 114 | } |
| 115 | |
| 116 | // ~ Constructors |
| 117 | // ----------------------------------------------------------- |
| 118 | |
| 119 | /** |
| 120 | * Convert the byte buffer from startPos to a length of length to a string |
| 121 | * using the default platform encoding. |
| 122 | * |
| 123 | * @param buffer |
| 124 | * the bytes to convert |
| 125 | * @param startPos |
| 126 | * the index to start at |
| 127 | * @param length |
| 128 | * the number of bytes to convert |
| 129 | * @return the String representation of the given bytes |
| 130 | */ |
| 131 | public static String toStringDefaultEncoding(byte[] buffer, int startPos, |
| 132 | int length) { |
| 133 | return new String(buffer, startPos, length); |
| 134 | } |
| 135 | |
| 136 | // ~ Methods |
| 137 | // ---------------------------------------------------------------- |
| 138 | |
| 139 | private char[] byteToChars = new char[BYTE_RANGE]; |
| 140 | |
| 141 | private byte[] charToByteMap = new byte[65536]; |
| 142 | |
| 143 | /** |
| 144 | * Prevent instantiation, called out of static method initCharset(). |
| 145 | * |
| 146 | * @param encodingName |
| 147 | * a JVM character encoding |
| 148 | * @throws UnsupportedEncodingException |
| 149 | * if the JVM does not support the encoding |
| 150 | */ |
| 151 | private SingleByteCharsetConverter(String encodingName) |
| 152 | throws UnsupportedEncodingException { |
| 153 | String allBytesString = new String(allBytes, 0, BYTE_RANGE, |
| 154 | encodingName); |
| 155 | int allBytesLen = allBytesString.length(); |
| 156 | |
| 157 | System.arraycopy(unknownCharsMap, 0, this.charToByteMap, 0, |
| 158 | this.charToByteMap.length); |
| 159 | |
| 160 | for (int i = 0; i < BYTE_RANGE && i < allBytesLen; i++) { |
| 161 | char c = allBytesString.charAt(i); |
| 162 | this.byteToChars[i] = c; |
| 163 | this.charToByteMap[c] = allBytes[i]; |
| 164 | } |
| 165 | } |
| 166 | |
| 167 | public final byte[] toBytes(char[] c) { |
| 168 | if (c == null) { |
| 169 | return null; |
| 170 | } |
| 171 | |
| 172 | int length = c.length; |
| 173 | byte[] bytes = new byte[length]; |
| 174 | |
| 175 | for (int i = 0; i < length; i++) { |
| 176 | bytes[i] = this.charToByteMap[c[i]]; |
| 177 | } |
| 178 | |
| 179 | return bytes; |
| 180 | } |
| 181 | |
| 182 | public final byte[] toBytes(char[] chars, int offset, int length) { |
| 183 | if (chars == null) { |
| 184 | return null; |
| 185 | } |
| 186 | |
| 187 | if (length == 0) { |
| 188 | return EMPTY_BYTE_ARRAY; |
| 189 | } |
| 190 | |
| 191 | byte[] bytes = new byte[length]; |
| 192 | |
| 193 | for (int i = 0; (i < length); i++) { |
| 194 | bytes[i] = this.charToByteMap[chars[i + offset]]; |
| 195 | } |
| 196 | |
| 197 | return bytes; |
| 198 | } |
| 199 | |
| 200 | /** |
| 201 | * Convert the given string to an array of bytes. |
| 202 | * |
| 203 | * @param s |
| 204 | * the String to convert |
| 205 | * @return the bytes that make up the String |
| 206 | */ |
| 207 | public final byte[] toBytes(String s) { |
| 208 | if (s == null) { |
| 209 | return null; |
| 210 | } |
| 211 | |
| 212 | int length = s.length(); |
| 213 | byte[] bytes = new byte[length]; |
| 214 | |
| 215 | for (int i = 0; i < length; i++) { |
| 216 | bytes[i] = this.charToByteMap[s.charAt(i)]; |
| 217 | } |
| 218 | |
| 219 | return bytes; |
| 220 | } |
| 221 | |
| 222 | /** |
| 223 | * Convert the given string to an array of bytes. |
| 224 | * |
| 225 | * @param s |
| 226 | * the String to convert |
| 227 | * @param offset |
| 228 | * the offset to start at |
| 229 | * @param length |
| 230 | * length (max) to convert |
| 231 | * |
| 232 | * @return the bytes that make up the String |
| 233 | */ |
| 234 | public final byte[] toBytes(String s, int offset, int length) { |
| 235 | if (s == null) { |
| 236 | return null; |
| 237 | } |
| 238 | |
| 239 | if (length == 0) { |
| 240 | return EMPTY_BYTE_ARRAY; |
| 241 | } |
| 242 | |
| 243 | byte[] bytes = new byte[length]; |
| 244 | |
| 245 | for (int i = 0; (i < length); i++) { |
| 246 | char c = s.charAt(i + offset); |
| 247 | bytes[i] = this.charToByteMap[c]; |
| 248 | } |
| 249 | |
| 250 | return bytes; |
| 251 | } |
| 252 | |
| 253 | /** |
| 254 | * Convert the byte buffer to a string using this instance's character |
| 255 | * encoding. |
| 256 | * |
| 257 | * @param buffer |
| 258 | * the bytes to convert to a String |
| 259 | * @return the converted String |
| 260 | */ |
| 261 | public final String toString(byte[] buffer) { |
| 262 | return toString(buffer, 0, buffer.length); |
| 263 | } |
| 264 | |
| 265 | /** |
| 266 | * Convert the byte buffer from startPos to a length of length to a string |
| 267 | * using this instance's character encoding. |
| 268 | * |
| 269 | * @param buffer |
| 270 | * the bytes to convert |
| 271 | * @param startPos |
| 272 | * the index to start at |
| 273 | * @param length |
| 274 | * the number of bytes to convert |
| 275 | * @return the String representation of the given bytes |
| 276 | */ |
| 277 | public final String toString(byte[] buffer, int startPos, int length) { |
| 278 | char[] charArray = new char[length]; |
| 279 | int readpoint = startPos; |
| 280 | |
| 281 | for (int i = 0; i < length; i++) { |
| 282 | charArray[i] = this.byteToChars[buffer[readpoint] - Byte.MIN_VALUE]; |
| 283 | readpoint++; |
| 284 | } |
| 285 | |
| 286 | return new String(charArray); |
| 287 | } |
| 288 | } |