1 /* |
|
2 * Copyright (c) 1999, 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 sun.io; |
|
27 |
|
28 import sun.nio.cs.ext.ISCII91; |
|
29 |
|
30 /* |
|
31 * Copyright (c) 1998 International Business Machines. |
|
32 * All Rights Reserved. |
|
33 * |
|
34 * Author : Sunanda Bera, C. Thirumalesh |
|
35 * Last Modified : 23,November,1998 |
|
36 * |
|
37 * Purpose : Defines class ByteToCharISCII91. |
|
38 * |
|
39 * |
|
40 * Revision History |
|
41 * ======== ======= |
|
42 * |
|
43 * Date By Description |
|
44 * ---- -- ----------- |
|
45 * |
|
46 * |
|
47 */ |
|
48 |
|
49 /** |
|
50 * Converter class. Converts between Unicode encoding and ISCII91 encoding. |
|
51 * ISCII91 is the character encoding as defined in Indian Standard document |
|
52 * IS 13194:1991 ( Indian Script Code for Information Interchange ). |
|
53 * |
|
54 * @see sun.io.ByteToCharConverter |
|
55 */ |
|
56 public class ByteToCharISCII91 extends ByteToCharConverter { |
|
57 |
|
58 private static final char[] directMapTable = ISCII91.getDirectMapTable(); |
|
59 |
|
60 private static final char NUKTA_CHAR = '\u093c'; |
|
61 private static final char HALANT_CHAR = '\u094d'; |
|
62 private static final char ZWNJ_CHAR = '\u200c'; |
|
63 private static final char ZWJ_CHAR = '\u200d'; |
|
64 private static final char INVALID_CHAR = '\uffff'; |
|
65 |
|
66 private char contextChar = INVALID_CHAR; |
|
67 private boolean needFlushing = false; |
|
68 |
|
69 /** |
|
70 * Converts ISCII91 characters to Unicode. |
|
71 * @see sun.io.ByteToCharConverter#convert |
|
72 */ |
|
73 public int convert(byte input[], int inStart, int inEnd, |
|
74 char output[], int outStart, int outEnd) |
|
75 throws ConversionBufferFullException, UnknownCharacterException { |
|
76 /*Rules: |
|
77 * 1)ATR,EXT,following character to be replaced with '\ufffd' |
|
78 * 2)Halant + Halant => '\u094d' (Virama) + '\u200c'(ZWNJ) |
|
79 * 3)Halant + Nukta => '\u094d' (Virama) + '\u200d'(ZWJ) |
|
80 */ |
|
81 charOff = outStart; |
|
82 byteOff = inStart; |
|
83 while (byteOff < inEnd) { |
|
84 if (charOff >= outEnd) { |
|
85 throw new ConversionBufferFullException(); |
|
86 } |
|
87 int index = input[byteOff++]; |
|
88 index = ( index < 0 )? ( index + 255 ):index; |
|
89 char currentChar = directMapTable[index]; |
|
90 |
|
91 // if the contextChar is either ATR || EXT set the output to '\ufffd' |
|
92 if(contextChar == '\ufffd') { |
|
93 output[charOff++] = '\ufffd'; |
|
94 contextChar = INVALID_CHAR; |
|
95 needFlushing = false; |
|
96 continue; |
|
97 } |
|
98 |
|
99 switch(currentChar) { |
|
100 case '\u0901': |
|
101 case '\u0907': |
|
102 case '\u0908': |
|
103 case '\u090b': |
|
104 case '\u093f': |
|
105 case '\u0940': |
|
106 case '\u0943': |
|
107 case '\u0964': |
|
108 if(needFlushing) { |
|
109 output[charOff++] = contextChar; |
|
110 contextChar = currentChar; |
|
111 continue; |
|
112 } |
|
113 contextChar = currentChar; |
|
114 needFlushing = true; |
|
115 continue; |
|
116 case NUKTA_CHAR: |
|
117 switch(contextChar) { |
|
118 case '\u0901': |
|
119 output[charOff] = '\u0950'; |
|
120 break; |
|
121 case '\u0907': |
|
122 output[charOff] = '\u090c'; |
|
123 break; |
|
124 case '\u0908': |
|
125 output[charOff] = '\u0961'; |
|
126 break; |
|
127 case '\u090b': |
|
128 output[charOff] = '\u0960'; |
|
129 break; |
|
130 case '\u093f': |
|
131 output[charOff] = '\u0962'; |
|
132 break; |
|
133 case '\u0940': |
|
134 output[charOff] = '\u0963'; |
|
135 break; |
|
136 case '\u0943': |
|
137 output[charOff] = '\u0944'; |
|
138 break; |
|
139 case '\u0964': |
|
140 output[charOff] = '\u093d'; |
|
141 break; |
|
142 case HALANT_CHAR: |
|
143 if(needFlushing) { |
|
144 output[charOff++] = contextChar; |
|
145 contextChar = currentChar; |
|
146 continue; |
|
147 } |
|
148 output[charOff] = ZWJ_CHAR; |
|
149 break; |
|
150 default: |
|
151 if(needFlushing) { |
|
152 output[charOff++] = contextChar; |
|
153 contextChar = currentChar; |
|
154 continue; |
|
155 } |
|
156 output[charOff] = NUKTA_CHAR; |
|
157 } |
|
158 break; |
|
159 case HALANT_CHAR: |
|
160 if(needFlushing) { |
|
161 output[charOff++] = contextChar; |
|
162 contextChar = currentChar; |
|
163 continue; |
|
164 } |
|
165 if(contextChar == HALANT_CHAR) { |
|
166 output[charOff] = ZWNJ_CHAR; |
|
167 break; |
|
168 } |
|
169 output[charOff] = HALANT_CHAR; |
|
170 break; |
|
171 case INVALID_CHAR: |
|
172 if(needFlushing) { |
|
173 output[charOff++] = contextChar; |
|
174 contextChar = currentChar; |
|
175 continue; |
|
176 } |
|
177 if(subMode) { |
|
178 output[charOff] = subChars[0]; |
|
179 break; |
|
180 } else { |
|
181 contextChar = INVALID_CHAR; |
|
182 throw new UnknownCharacterException(); |
|
183 } |
|
184 default: |
|
185 if(needFlushing) { |
|
186 output[charOff++] = contextChar; |
|
187 contextChar = currentChar; |
|
188 continue; |
|
189 } |
|
190 output[charOff] = currentChar; |
|
191 break; |
|
192 }//end switch |
|
193 |
|
194 contextChar = currentChar; |
|
195 needFlushing = false; |
|
196 charOff++; |
|
197 }//end while |
|
198 return charOff - outStart; |
|
199 } //convert() |
|
200 |
|
201 /** |
|
202 * @see sun.io.ByteToCharConverter#flush |
|
203 */ |
|
204 public int flush( char[] output, int outStart, int outEnd ) |
|
205 throws MalformedInputException, ConversionBufferFullException |
|
206 { |
|
207 int charsWritten = 0; |
|
208 //if the last char was not flushed, flush it! |
|
209 if(needFlushing) { |
|
210 output[outStart] = contextChar; |
|
211 charsWritten = 1; |
|
212 } |
|
213 contextChar = INVALID_CHAR; |
|
214 needFlushing = false; |
|
215 byteOff = charOff = 0; |
|
216 return charsWritten; |
|
217 }//flush() |
|
218 /** |
|
219 * Returns the character set id for the conversion. |
|
220 */ |
|
221 public String getCharacterEncoding() |
|
222 { |
|
223 return "ISCII91"; |
|
224 }//getCharacterEncoding() |
|
225 /** |
|
226 * @see sun.io.ByteToCharConverter#reset |
|
227 */ |
|
228 public void reset() |
|
229 { |
|
230 byteOff = charOff = 0; |
|
231 }//reset() |
|
232 |
|
233 }//end of class definition |
|