1 /* |
|
2 * Copyright (c) 2001, 2003, 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 /* |
|
27 */ |
|
28 |
|
29 |
|
30 package sun.io; |
|
31 import sun.nio.cs.ext.GB18030; |
|
32 |
|
33 public class CharToByteGB18030 extends CharToByteConverter |
|
34 { |
|
35 |
|
36 private char highHalfZoneCode; |
|
37 boolean flushed = true; |
|
38 |
|
39 private final static int GB18030_SINGLE_BYTE = 1; |
|
40 private final static int GB18030_DOUBLE_BYTE = 2; |
|
41 private final static int GB18030_FOUR_BYTE = 3; |
|
42 private static short[] index1; |
|
43 private static String[] index2; |
|
44 private int currentState; |
|
45 |
|
46 public CharToByteGB18030() { |
|
47 GB18030 nioCoder = new GB18030(); |
|
48 currentState = GB18030_DOUBLE_BYTE; |
|
49 subBytes = new byte[1]; |
|
50 subBytes[0] = (byte)'?'; |
|
51 index1 = nioCoder.getEncoderIndex1(); |
|
52 index2 = nioCoder.getEncoderIndex2(); |
|
53 } |
|
54 |
|
55 public int flush(byte[] output, int outStart, int outEnd) |
|
56 throws MalformedInputException |
|
57 { |
|
58 if (highHalfZoneCode != 0) { |
|
59 highHalfZoneCode = 0; |
|
60 badInputLength = 0; |
|
61 throw new MalformedInputException(); |
|
62 } |
|
63 reset(); |
|
64 flushed = true; |
|
65 return 0; |
|
66 } |
|
67 |
|
68 public void reset() { |
|
69 byteOff = charOff = 0; |
|
70 currentState = GB18030_DOUBLE_BYTE; |
|
71 } |
|
72 |
|
73 public boolean canConvert(char c) { |
|
74 // converts all but unpaired surrogates |
|
75 // and illegal chars, U+FFFE & U+FFFF |
|
76 |
|
77 if ((c >= 0xd800 && c <=0xdfff) || (c >= 0xfffe)) |
|
78 return false; |
|
79 else |
|
80 return true; |
|
81 } |
|
82 |
|
83 /** |
|
84 * Character conversion |
|
85 */ |
|
86 public int convert(char[] input, int inOff, int inEnd, |
|
87 byte[] output, int outOff, int outEnd) |
|
88 throws UnknownCharacterException, MalformedInputException, |
|
89 ConversionBufferFullException |
|
90 { |
|
91 int linearDiffValue = 0; |
|
92 int hiByte = 0 , loByte = 0; // low and high order bytes |
|
93 char inputChar; // Input character to be converted |
|
94 charOff = inOff; |
|
95 byteOff = outOff; |
|
96 int inputSize; // Size of the input |
|
97 int outputSize; // Size of the output |
|
98 |
|
99 flushed = false; |
|
100 |
|
101 if (highHalfZoneCode != 0) { |
|
102 if (input[inOff] >= 0xDC00 && input[inOff] <= 0xDFFF) { |
|
103 |
|
104 // This is legal UTF16 sequence, so shunt in the high |
|
105 // surrogate for conversion by convert() loop. |
|
106 |
|
107 char[] newBuf = new char[inEnd - inOff + 1]; |
|
108 newBuf[0] = highHalfZoneCode; |
|
109 System.arraycopy(input, inOff, newBuf, 1, inEnd - inOff); |
|
110 charOff -= 1; |
|
111 input = newBuf; |
|
112 inOff = 0; |
|
113 inEnd = newBuf.length; |
|
114 highHalfZoneCode = 0; |
|
115 } else { |
|
116 // This is illegal UTF16 sequence. |
|
117 badInputLength = 0; |
|
118 throw new MalformedInputException(); |
|
119 } |
|
120 } |
|
121 |
|
122 // Main encode loop |
|
123 |
|
124 while (charOff < inEnd) { |
|
125 inputChar = input[charOff++]; |
|
126 |
|
127 if(inputChar >= '\uD800' && inputChar <= '\uDBFF') { |
|
128 // Is this the last character of the input? |
|
129 if (charOff + 1 > inEnd) { |
|
130 highHalfZoneCode = inputChar; |
|
131 break; |
|
132 } |
|
133 |
|
134 char previousChar = inputChar; |
|
135 inputChar = input[charOff]; |
|
136 |
|
137 // Is there a low surrogate following? |
|
138 if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { |
|
139 inputSize = 2; |
|
140 charOff++; |
|
141 linearDiffValue = ( previousChar - 0xD800) * 0x400 + |
|
142 ( inputChar - 0xDC00) + 0x2E248; |
|
143 |
|
144 currentState = GB18030_FOUR_BYTE; |
|
145 } else { |
|
146 // We have a malformed surrogate pair |
|
147 badInputLength = 1; |
|
148 throw new MalformedInputException(); |
|
149 } |
|
150 } |
|
151 // Is this an unaccompanied low surrogate? |
|
152 else if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') { |
|
153 badInputLength = 1; |
|
154 throw new MalformedInputException(); |
|
155 } |
|
156 |
|
157 // Not part of a surrogate |
|
158 else if (inputChar >= 0x0000 && inputChar <= 0x007F) { |
|
159 if (byteOff >= outEnd) { |
|
160 throw new ConversionBufferFullException(); |
|
161 } |
|
162 currentState = GB18030_SINGLE_BYTE; |
|
163 output[byteOff++] = (byte) inputChar; |
|
164 } |
|
165 else if (inputChar <= 0xA4C6 || inputChar >= 0xE000) { |
|
166 int outByteVal = getGB18030(index1, index2, inputChar); |
|
167 |
|
168 if (outByteVal == 0xFFFD ) { |
|
169 if (subMode) { |
|
170 if (byteOff >= outEnd) { |
|
171 throw new ConversionBufferFullException(); |
|
172 } else { |
|
173 output[byteOff++] = subBytes[0]; |
|
174 continue; |
|
175 } |
|
176 } else { |
|
177 badInputLength = 1; |
|
178 throw new UnknownCharacterException(); |
|
179 } |
|
180 } |
|
181 |
|
182 hiByte = (outByteVal & 0xFF00) >> 8; |
|
183 loByte = (outByteVal & 0xFF); |
|
184 |
|
185 linearDiffValue = (hiByte - 0x20) * 256 + loByte; |
|
186 |
|
187 if (inputChar >= 0xE000 && inputChar < 0xF900) |
|
188 linearDiffValue += 0x82BD; |
|
189 else if (inputChar >= 0xF900) |
|
190 linearDiffValue += 0x93A9; |
|
191 |
|
192 if (hiByte > 0x80) |
|
193 currentState = GB18030_DOUBLE_BYTE; |
|
194 else |
|
195 currentState = GB18030_FOUR_BYTE; |
|
196 } |
|
197 else if (inputChar >= 0xA4C7 && inputChar <= 0xD7FF) { |
|
198 linearDiffValue = inputChar - 0x5543; |
|
199 currentState = GB18030_FOUR_BYTE; |
|
200 } |
|
201 else { |
|
202 badInputLength = 1; |
|
203 throw new MalformedInputException(); |
|
204 } |
|
205 |
|
206 if (currentState == GB18030_SINGLE_BYTE) |
|
207 continue; |
|
208 |
|
209 if (currentState == GB18030_DOUBLE_BYTE) { |
|
210 if (byteOff + 2 > outEnd) { |
|
211 throw new ConversionBufferFullException(); |
|
212 } |
|
213 output[byteOff++] = (byte)hiByte; |
|
214 output[byteOff++] = (byte)loByte; |
|
215 } |
|
216 else { // Four Byte encoding |
|
217 if (byteOff + 4 > outEnd) { |
|
218 throw new ConversionBufferFullException(); |
|
219 } |
|
220 |
|
221 byte b1, b2, b3, b4; |
|
222 |
|
223 b4 = (byte)((linearDiffValue % 10) + 0x30); |
|
224 linearDiffValue /= 10; |
|
225 b3 = (byte)((linearDiffValue % 126) + 0x81); |
|
226 linearDiffValue /= 126; |
|
227 b2 = (byte)((linearDiffValue % 10) + 0x30); |
|
228 b1 = (byte)((linearDiffValue / 10) + 0x81); |
|
229 output[byteOff++] = b1; |
|
230 output[byteOff++] = b2; |
|
231 output[byteOff++] = b3; |
|
232 output[byteOff++] = b4; |
|
233 } |
|
234 } |
|
235 // Return number of bytes written to the output buffer. |
|
236 return byteOff - outOff; |
|
237 } |
|
238 |
|
239 |
|
240 /** |
|
241 * returns the maximum number of bytes needed to convert a char |
|
242 */ |
|
243 public int getMaxBytesPerChar() { |
|
244 return 4; |
|
245 } |
|
246 |
|
247 |
|
248 /** |
|
249 * Return the character set ID |
|
250 */ |
|
251 public String getCharacterEncoding() { |
|
252 return "GB18030"; |
|
253 } |
|
254 |
|
255 private int getGB18030(short[] outerIndex, String[] innerIndex, char ch) { |
|
256 int offset = outerIndex[((ch & 0xff00) >> 8 )] << 8; |
|
257 |
|
258 return innerIndex[offset >> 12].charAt((offset & 0xfff) + (ch & 0xff)); |
|
259 } |
|
260 |
|
261 } |
|