1 /* 2 * Copyright (c) 2014, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package jdk.internal.jimage; 27 28 import java.io.ByteArrayInputStream; 29 import java.io.ByteArrayOutputStream; 30 import java.io.DataInputStream; 31 import java.io.DataOutputStream; 32 import java.io.IOException; 33 import java.nio.ByteBuffer; 34 import java.nio.ByteOrder; 35 import java.nio.charset.Charset; 36 import java.util.Arrays; 37 38 public final class UTF8String implements CharSequence { 39 // Same as StandardCharsets.UTF_8 without loading all of the standard charsets 40 static final Charset UTF_8 = Charset.forName("UTF-8"); 41 42 public static final int NOT_FOUND = -1; 43 public static final int HASH_MULTIPLIER = 0x01000193; 44 public static final UTF8String EMPTY_STRING = new UTF8String(""); 45 public static final UTF8String SLASH_STRING = new UTF8String("/"); 46 public static final UTF8String DOT_STRING = new UTF8String("."); 47 48 // TODO This strings are implementation specific and should be defined elsewhere. 49 public static final UTF8String MODULES_STRING = new UTF8String("/modules"); 50 public static final UTF8String PACKAGES_STRING = new UTF8String("/packages"); 51 52 final byte[] bytes; 53 final int offset; 54 final int count; 55 int hashcode; 56 57 public UTF8String(byte[] bytes, int offset, int count) { 58 if (offset < 0 || count < 0 || (offset + count) > bytes.length) { 59 throw new IndexOutOfBoundsException("offset/count out of range"); 60 } 61 this.bytes = bytes; 62 this.offset = offset; 63 this.count = count; 64 this.hashcode = -1; 65 } 66 67 public UTF8String(byte[] bytes, int offset) { 68 this(bytes, offset, bytes.length - offset); 69 } 70 71 public UTF8String(byte[] bytes) { 72 this(bytes, 0, bytes.length); 73 } 74 75 public UTF8String(String string) { 76 this(stringToBytes(string)); 77 } 78 79 @Override 80 public int length() { 81 return count; 82 } 83 84 public boolean isEmpty() { 85 return count == 0; 86 } 87 88 public int byteAt(int index) { 89 return bytes[offset + index] & 0xFF; 90 } 91 92 public UTF8String concat(UTF8String s) { 93 int total = count + s.count; 94 byte[] combined = new byte[total]; 95 System.arraycopy(bytes, offset, combined, 0, count); 96 System.arraycopy(s.bytes, s.offset, combined, count, s.count); 97 98 return new UTF8String(combined, 0, total); 99 } 100 101 public UTF8String concat(UTF8String... s) { 102 int total = count; 103 104 for (UTF8String i : s) { 105 total += i.count; 106 } 107 108 byte[] combined = new byte[total]; 109 System.arraycopy(bytes, offset, combined, 0, count); 110 int next = count; 111 112 for (UTF8String i : s) { 113 System.arraycopy(i.bytes, i.offset, combined, next, i.count); 114 next += i.count; 115 } 116 117 return new UTF8String(combined, 0, total); 118 } 119 120 public UTF8String substring(int offset) { 121 return substring(offset, this.count - offset); 122 } 123 124 public UTF8String substring(int offset, int count) { 125 int newOffset = this.offset + offset; 126 return new UTF8String(bytes, newOffset, count); 127 } 128 129 public UTF8String trimToSize() { 130 return offset == 0 && bytes.length == count ? this : 131 new UTF8String(Arrays.copyOfRange(bytes, offset, offset + count)); 132 } 133 134 public int indexOf(int ch) { 135 return indexOf(ch, 0); 136 } 137 138 public int indexOf(int ch, int start) { 139 for (int i = Math.max(start, 0); i < count; i++) { 140 if (byteAt(i) == ch) { 141 return i; 142 } 143 } 144 145 return NOT_FOUND; 146 } 147 148 public int lastIndexOf(int ch) { 149 return lastIndexOf(ch, count - 1); 150 } 151 152 public int lastIndexOf(int ch, int start) { 153 for (int i = Math.min(start, count); i > 0; i--) { 154 if (byteAt(i) == ch) { 155 return i; 156 } 157 } 158 159 return NOT_FOUND; 160 } 161 162 public void writeTo(ImageStream buffer) { 163 buffer.put(bytes, offset, count); 164 } 165 166 public static int hashCode(int seed, byte[] bytes, int offset, int count) { 167 for (int i = offset, limit = offset + count; i < limit; i++) { 168 seed = (seed * HASH_MULTIPLIER) ^ (bytes[i] & 0xFF); 169 } 170 171 return seed & 0x7FFFFFFF; 172 } 173 174 public int hashCode(int seed) { 175 return hashCode(seed, bytes, offset, count); 176 } 177 178 @Override 179 public int hashCode() { 180 if (hashcode < 0) { 181 hashcode = hashCode(HASH_MULTIPLIER, bytes, offset, count); 182 } 183 184 return hashcode; 185 } 186 187 @Override 188 public boolean equals(Object obj) { 189 if (obj == null) { 190 return false; 191 } 192 193 if (getClass() != obj.getClass()) { 194 return false; 195 } 196 197 return equals(this, (UTF8String)obj); 198 } 199 200 public static boolean equals(UTF8String a, UTF8String b) { 201 if (a == b) { 202 return true; 203 } 204 205 int count = a.count; 206 207 if (count != b.count) { 208 return false; 209 } 210 211 byte[] aBytes = a.bytes; 212 byte[] bBytes = b.bytes; 213 int aOffset = a.offset; 214 int bOffset = b.offset; 215 216 for (int i = 0; i < count; i++) { 217 if (aBytes[aOffset + i] != bBytes[bOffset + i]) { 218 return false; 219 } 220 } 221 222 return true; 223 } 224 225 public byte[] getBytesCopy() { 226 return Arrays.copyOfRange(bytes, offset, offset + count); 227 } 228 229 byte[] getBytes() { 230 if (offset != 0 || bytes.length != count) { 231 return Arrays.copyOfRange(bytes, offset, offset + count); 232 } 233 234 return bytes; 235 } 236 237 /** 238 * Convert the string bytes into Modified UTF-8 encoding (as defined in 239 * <code>java.io.DataInput</code> 240 * @param string 241 * @return bytes encoded into modified UTF-8 242 */ 243 private static byte[] stringToBytes(String string) { 244 try { 245 ByteArrayOutputStream bos = new ByteArrayOutputStream(); 246 DataOutputStream ss = new DataOutputStream(bos); 247 ss.writeUTF(string); 248 byte[] content = bos.toByteArray(); 249 // first 2 items are length; 250 if(content.length <= 2) { 251 return new byte[0]; 252 } 253 return Arrays.copyOfRange(content, 2, content.length); 254 } catch (IOException ex) { 255 throw new RuntimeException(ex); 256 } 257 } 258 259 @Override 260 public String toString() { 261 ByteBuffer buffer = ByteBuffer.allocate(bytes.length+2); 262 buffer.order(ByteOrder.BIG_ENDIAN); 263 buffer.putShort((short)bytes.length); 264 buffer.put(bytes); 265 ByteArrayInputStream stream = new ByteArrayInputStream(buffer.array()); 266 DataInputStream in = new DataInputStream(stream); 267 try { 268 return in.readUTF(); 269 } catch (IOException ex) { 270 throw new RuntimeException(ex); 271 } 272 } 273 274 @Override 275 public char charAt(int index) { 276 int ch = byteAt(index); 277 278 return (ch & 0x80) == 0 ? (char)ch : '\0'; 279 } 280 281 @Override 282 public CharSequence subSequence(int start, int end) { 283 return (CharSequence)substring(start, end - start); 284 } 285 }