1 /* |
|
2 * Copyright (c) 1997, 2010, 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 package sun.io; |
|
26 |
|
27 import sun.nio.cs.ext.DoubleByte; |
|
28 import static sun.nio.cs.CharsetMapping.*; |
|
29 |
|
30 public abstract class CharToByteDBCS_EBCDIC extends CharToByteConverter |
|
31 { |
|
32 private static final int SBCS = 0; |
|
33 private static final int DBCS = 1; |
|
34 |
|
35 private static final byte SO = 0x0e; |
|
36 private static final byte SI = 0x0f; |
|
37 |
|
38 private int currentState; |
|
39 private char highHalfZoneCode; |
|
40 private byte[] outputByte = new byte[2]; |
|
41 |
|
42 private DoubleByte.Encoder enc; |
|
43 |
|
44 public CharToByteDBCS_EBCDIC(DoubleByte.Encoder enc) { |
|
45 super(); |
|
46 highHalfZoneCode = 0; |
|
47 currentState = SBCS; |
|
48 this.enc = enc; |
|
49 } |
|
50 |
|
51 int encodeChar(char c) { |
|
52 return enc.encodeChar(c); |
|
53 } |
|
54 |
|
55 /** |
|
56 * flush out any residual data and reset the buffer state |
|
57 */ |
|
58 public int flush(byte [] output, int outStart, int outEnd) |
|
59 throws MalformedInputException, ConversionBufferFullException |
|
60 { |
|
61 int bytesOut = 0; |
|
62 |
|
63 if (highHalfZoneCode != 0) { |
|
64 reset(); |
|
65 badInputLength = 0; |
|
66 throw new MalformedInputException(); |
|
67 } |
|
68 |
|
69 if (currentState == DBCS) { |
|
70 if (outStart >= outEnd) |
|
71 throw new ConversionBufferFullException(); |
|
72 output[outStart] = SI; |
|
73 bytesOut++; |
|
74 } |
|
75 |
|
76 reset(); |
|
77 return bytesOut; |
|
78 } |
|
79 |
|
80 /** |
|
81 * Character conversion |
|
82 */ |
|
83 public int convert(char[] input, int inOff, int inEnd, |
|
84 byte[] output, int outOff, int outEnd) |
|
85 throws UnknownCharacterException, MalformedInputException, |
|
86 ConversionBufferFullException |
|
87 { |
|
88 char inputChar; |
|
89 int inputSize; |
|
90 |
|
91 byteOff = outOff; |
|
92 charOff = inOff; |
|
93 |
|
94 while(charOff < inEnd) { |
|
95 |
|
96 int index; |
|
97 int theBytes; |
|
98 int spaceNeeded; |
|
99 |
|
100 if (highHalfZoneCode == 0) { |
|
101 inputChar = input[charOff]; |
|
102 inputSize = 1; |
|
103 } else { |
|
104 inputChar = highHalfZoneCode; |
|
105 inputSize = 0; |
|
106 highHalfZoneCode = 0; |
|
107 } |
|
108 |
|
109 // Is this a high surrogate? |
|
110 if (Character.isHighSurrogate(inputChar)) { |
|
111 // Is this the last character of the input? |
|
112 if (charOff + inputSize >= inEnd) { |
|
113 highHalfZoneCode = inputChar; |
|
114 charOff += inputSize; |
|
115 break; |
|
116 } |
|
117 |
|
118 // Is there a low surrogate following? |
|
119 inputChar = input[charOff + inputSize]; |
|
120 if (Character.isLowSurrogate(inputChar)) { |
|
121 // We have a valid surrogate pair. Too bad we don't do |
|
122 // surrogates. Is substitution enabled? |
|
123 if (subMode) { |
|
124 if (subBytes.length == 1) { |
|
125 outputByte[0] = 0x00; |
|
126 outputByte[1] = subBytes[0]; |
|
127 } |
|
128 else { |
|
129 outputByte[0] = subBytes[0]; |
|
130 outputByte[1] = subBytes[1]; |
|
131 } |
|
132 inputSize++; |
|
133 } else { |
|
134 badInputLength = 2; |
|
135 throw new UnknownCharacterException(); |
|
136 } |
|
137 } else { |
|
138 // We have a malformed surrogate pair |
|
139 badInputLength = 1; |
|
140 throw new MalformedInputException(); |
|
141 } |
|
142 } |
|
143 // Is this an unaccompanied low surrogate? |
|
144 else if (Character.isLowSurrogate(inputChar)) { |
|
145 badInputLength = 1; |
|
146 throw new MalformedInputException(); |
|
147 } else { |
|
148 |
|
149 // We have a valid character, get the bytes for it |
|
150 theBytes = encodeChar(inputChar); |
|
151 if (theBytes == UNMAPPABLE_ENCODING) { |
|
152 // if there was no mapping - look for substitution characters |
|
153 if (subMode) { |
|
154 if (subBytes.length == 1) { |
|
155 outputByte[0] = 0x00; |
|
156 outputByte[1] = subBytes[0]; |
|
157 } else { |
|
158 outputByte[0] = subBytes[0]; |
|
159 outputByte[1] = subBytes[1]; |
|
160 } |
|
161 } else { |
|
162 badInputLength = 1; |
|
163 throw new UnknownCharacterException(); |
|
164 } |
|
165 } else { |
|
166 outputByte[0] = (byte)((theBytes & 0x0000ff00)>>8); |
|
167 outputByte[1] = (byte)(theBytes & 0x000000ff); |
|
168 } |
|
169 } |
|
170 |
|
171 //Set the output buffer into the correct state |
|
172 |
|
173 if (currentState == DBCS && outputByte[0] == 0x00) { |
|
174 if (byteOff >= outEnd) |
|
175 throw new ConversionBufferFullException(); |
|
176 currentState = SBCS; |
|
177 output[byteOff++] = SI; |
|
178 } else |
|
179 if (currentState == SBCS && outputByte[0] != 0x00) { |
|
180 if (byteOff >= outEnd) { |
|
181 throw new ConversionBufferFullException(); |
|
182 } |
|
183 currentState = DBCS; |
|
184 output[byteOff++] = SO; |
|
185 } |
|
186 |
|
187 if (currentState == DBCS) |
|
188 spaceNeeded = 2; |
|
189 else |
|
190 spaceNeeded = 1; |
|
191 |
|
192 if (byteOff + spaceNeeded > outEnd) { |
|
193 throw new ConversionBufferFullException(); |
|
194 } |
|
195 |
|
196 if (currentState == SBCS) |
|
197 output[byteOff++] = outputByte[1]; |
|
198 else { |
|
199 output[byteOff++] = outputByte[0]; |
|
200 output[byteOff++] = outputByte[1]; |
|
201 } |
|
202 |
|
203 charOff += inputSize; |
|
204 } |
|
205 return byteOff - outOff; |
|
206 } |
|
207 |
|
208 |
|
209 |
|
210 /** |
|
211 * Resets converter to its initial state. |
|
212 */ |
|
213 public void reset() { |
|
214 charOff = byteOff = 0; |
|
215 highHalfZoneCode = 0; |
|
216 currentState = SBCS; |
|
217 } |
|
218 |
|
219 |
|
220 /** |
|
221 * Returns the maximum number of bytes needed to convert a char. |
|
222 */ |
|
223 public int getMaxBytesPerChar() { |
|
224 return 4; //Fixed with bug 4199599 so tests would pass. |
|
225 } |
|
226 |
|
227 |
|
228 /** |
|
229 * Sets the substitution bytes to use when the converter is in |
|
230 * substitution mode. The given bytes should represent a valid |
|
231 * character in the target character encoding. |
|
232 */ |
|
233 |
|
234 public void setSubstitutionBytes( byte[] newSubBytes ) |
|
235 throws IllegalArgumentException |
|
236 { |
|
237 if( newSubBytes.length > 2 || newSubBytes.length == 0) { |
|
238 throw new IllegalArgumentException(); |
|
239 } |
|
240 |
|
241 subBytes = new byte[ newSubBytes.length ]; |
|
242 System.arraycopy( newSubBytes, 0, subBytes, 0, newSubBytes.length ); |
|
243 |
|
244 } |
|
245 |
|
246 /** |
|
247 * Returns true if the given character can be converted to the |
|
248 * target character encoding. |
|
249 */ |
|
250 public boolean canConvert(char c) { |
|
251 return encodeChar(c) != UNMAPPABLE_ENCODING; |
|
252 } |
|
253 } |
|