1 /* |
|
2 * Copyright (c) 1996, 2004, 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 java.io.*; |
|
29 |
|
30 |
|
31 /** |
|
32 * An abstract base class for subclasses which convert character data |
|
33 * in an external encoding into Unicode characters. |
|
34 * |
|
35 * @author Asmus Freytag |
|
36 * @author Lloyd Honomichl |
|
37 * |
|
38 * @deprecated Replaced by {@link java.nio.charset}. THIS API WILL BE |
|
39 * REMOVED IN J2SE 1.6. |
|
40 */ |
|
41 @Deprecated |
|
42 public abstract class ByteToCharConverter { |
|
43 |
|
44 /* |
|
45 * Substitution mode flag. |
|
46 */ |
|
47 protected boolean subMode = true; |
|
48 |
|
49 /* |
|
50 * Characters to use for automatic substitution. |
|
51 */ |
|
52 protected char[] subChars = { '\uFFFD' }; |
|
53 |
|
54 /* |
|
55 * Offset of next character to be output |
|
56 */ |
|
57 protected int charOff; |
|
58 |
|
59 /* |
|
60 * Offset of next byte to be converted |
|
61 */ |
|
62 protected int byteOff; |
|
63 |
|
64 /* |
|
65 * Length of bad input that caused a MalformedInputException. |
|
66 */ |
|
67 protected int badInputLength; |
|
68 |
|
69 /** |
|
70 * Create an instance of the default ByteToCharConverter subclass. |
|
71 */ |
|
72 public static ByteToCharConverter getDefault() { |
|
73 Object cvt; |
|
74 cvt = Converters.newDefaultConverter(Converters.BYTE_TO_CHAR); |
|
75 return (ByteToCharConverter)cvt; |
|
76 } |
|
77 |
|
78 /** |
|
79 * Returns appropriate ByteToCharConverter subclass instance. |
|
80 * @param string represents encoding |
|
81 */ |
|
82 public static ByteToCharConverter getConverter(String encoding) |
|
83 throws UnsupportedEncodingException |
|
84 { |
|
85 Object cvt; |
|
86 cvt = Converters.newConverter(Converters.BYTE_TO_CHAR, encoding); |
|
87 return (ByteToCharConverter)cvt; |
|
88 } |
|
89 |
|
90 /** |
|
91 * Returns the character set id for the conversion |
|
92 */ |
|
93 public abstract String getCharacterEncoding(); |
|
94 |
|
95 /** |
|
96 * Converts an array of bytes containing characters in an external |
|
97 * encoding into an array of Unicode characters. This method allows |
|
98 * a buffer by buffer conversion of a data stream. The state of the |
|
99 * conversion is saved between calls to convert. Among other things, |
|
100 * this means multibyte input sequences can be split between calls. |
|
101 * If a call to convert results in an exception, the conversion may be |
|
102 * continued by calling convert again with suitably modified parameters. |
|
103 * All conversions should be finished with a call to the flush method. |
|
104 * |
|
105 * @return the number of bytes written to output. |
|
106 * @param input byte array containing text to be converted. |
|
107 * @param inStart begin conversion at this offset in input array. |
|
108 * @param inEnd stop conversion at this offset in input array (exclusive). |
|
109 * @param output character array to receive conversion result. |
|
110 * @param outStart start writing to output array at this offset. |
|
111 * @param outEnd stop writing to output array at this offset (exclusive). |
|
112 * @exception MalformedInputException if the input buffer contains any |
|
113 * sequence of bytes that is illegal for the input character set. |
|
114 * @exception UnknownCharacterException for any character that |
|
115 * that cannot be converted to Unicode. Thrown only when converter |
|
116 * is not in substitution mode. |
|
117 * @exception ConversionBufferFullException if output array is filled prior |
|
118 * to converting all the input. |
|
119 */ |
|
120 public abstract int convert(byte[] input, int inStart, int inEnd, |
|
121 char[] output, int outStart, int outEnd) |
|
122 throws MalformedInputException, |
|
123 UnknownCharacterException, |
|
124 ConversionBufferFullException; |
|
125 |
|
126 /** |
|
127 * Converts an array of bytes containing characters in an external |
|
128 * encoding into an array of Unicode characters. Unlike convert, |
|
129 * this method does not do incremental conversion. It assumes that |
|
130 * the given input array contains all the characters to be |
|
131 * converted. The state of the converter is reset at the beginning |
|
132 * of this method and is left in the reset state on successful |
|
133 * termination. The converter is not reset if an exception is |
|
134 * thrown. This allows the caller to determine where the bad input |
|
135 * was encountered by calling nextByteIndex. |
|
136 * <p> |
|
137 * This method uses substitution mode when performing the |
|
138 * conversion. The method setSubstitutionChars may be used to |
|
139 * determine what characters are substituted. Even though substitution |
|
140 * mode is used, the state of the converter's substitution mode is |
|
141 * not changed at the end of this method. |
|
142 * |
|
143 * @return an array of chars containing the converted characters. |
|
144 * @param input array containing Unicode characters to be converted. |
|
145 * @exception MalformedInputException if the input buffer contains any |
|
146 * sequence of chars that is illegal in the input character encoding. |
|
147 * After this exception is thrown, |
|
148 * the method nextByteIndex can be called to obtain the index of the |
|
149 * first invalid input byte and getBadInputLength can be called |
|
150 * to determine the length of the invalid input. |
|
151 * |
|
152 * @see #nextByteIndex |
|
153 * @see #setSubstitutionMode |
|
154 * @see sun.io.CharToByteConverter#setSubstitutionBytes(byte[]) |
|
155 * @see #getBadInputLength |
|
156 */ |
|
157 public char[] convertAll( byte input[] ) throws MalformedInputException { |
|
158 reset(); |
|
159 boolean savedSubMode = subMode; |
|
160 subMode = true; |
|
161 |
|
162 char[] output = new char[ getMaxCharsPerByte() * input.length ]; |
|
163 |
|
164 try { |
|
165 int outputLength = convert( input, 0, input.length, |
|
166 output, 0, output.length ); |
|
167 outputLength += flush( output, outputLength, output.length ); |
|
168 |
|
169 char [] returnedOutput = new char[ outputLength ]; |
|
170 System.arraycopy( output, 0, returnedOutput, 0, outputLength ); |
|
171 return returnedOutput; |
|
172 } |
|
173 catch( ConversionBufferFullException e ) { |
|
174 //Not supposed to happen. If it does, getMaxCharsPerByte() lied. |
|
175 throw new |
|
176 InternalError("this.getMaxCharsBerByte returned bad value"); |
|
177 } |
|
178 catch( UnknownCharacterException e ) { |
|
179 // Not supposed to happen since we're in substitution mode. |
|
180 throw new InternalError(); |
|
181 } |
|
182 finally { |
|
183 subMode = savedSubMode; |
|
184 } |
|
185 } |
|
186 |
|
187 /** |
|
188 * Writes any remaining output to the output buffer and resets the |
|
189 * converter to its initial state. |
|
190 * |
|
191 * @param output char array to receive flushed output. |
|
192 * @param outStart start writing to output array at this offset. |
|
193 * @param outEnd stop writing to output array at this offset (exclusive). |
|
194 * @exception MalformedInputException if the output to be flushed contained |
|
195 * a partial or invalid multibyte character sequence. flush will |
|
196 * write what it can to the output buffer and reset the converter before |
|
197 * throwing this exception. An additional call to flush is not required. |
|
198 * @exception ConversionBufferFullException if output array is filled |
|
199 * before all the output can be flushed. flush will write what it can |
|
200 * to the output buffer and remember its state. An additional call to |
|
201 * flush with a new output buffer will conclude the operation. |
|
202 */ |
|
203 public abstract int flush( char[] output, int outStart, int outEnd ) |
|
204 throws MalformedInputException, ConversionBufferFullException; |
|
205 |
|
206 /** |
|
207 * Resets converter to its initial state. |
|
208 */ |
|
209 public abstract void reset(); |
|
210 |
|
211 /** |
|
212 * Returns the maximum number of characters needed to convert a byte. Useful |
|
213 * for calculating the maximum output buffer size needed for a particular |
|
214 * input buffer. |
|
215 */ |
|
216 public int getMaxCharsPerByte() { |
|
217 // Until UTF-16, this will do for every encoding |
|
218 return 1; |
|
219 } |
|
220 |
|
221 /** |
|
222 * Returns the length, in bytes, of the input which caused a |
|
223 * MalformedInputException. Always refers to the last |
|
224 * MalformedInputException thrown by the converter. If none have |
|
225 * ever been thrown, returns 0. |
|
226 */ |
|
227 public int getBadInputLength() { |
|
228 return badInputLength; |
|
229 } |
|
230 |
|
231 /** |
|
232 * Returns the index of the character just past the last character |
|
233 * written by the previous call to convert. |
|
234 */ |
|
235 public int nextCharIndex() { |
|
236 return charOff; |
|
237 } |
|
238 |
|
239 /** |
|
240 * Returns the index of the byte just past the last byte successfully |
|
241 * converted by the previous call to convert. |
|
242 */ |
|
243 public int nextByteIndex() { |
|
244 return byteOff; |
|
245 } |
|
246 |
|
247 /** |
|
248 * Sets converter into substitution mode. In substitution mode, |
|
249 * the converter will replace untranslatable characters in the source |
|
250 * encoding with the substitution character set by setSubstitionChars. |
|
251 * When not in substitution mode, the converter will throw an |
|
252 * UnknownCharacterException when it encounters untranslatable input. |
|
253 * |
|
254 * @param doSub if true, enable substitution mode. |
|
255 * @see #setSubstitutionChars |
|
256 */ |
|
257 public void setSubstitutionMode(boolean doSub) { |
|
258 subMode = doSub; |
|
259 } |
|
260 |
|
261 /** |
|
262 * Sets the substitution characters to use when the converter is in |
|
263 * substitution mode. The given chars must not be |
|
264 * longer than the value returned by getMaxCharsPerByte for this |
|
265 * converter. |
|
266 * |
|
267 * @param newSubBytes the substitution bytes |
|
268 * @exception IllegalArgumentException if given byte array is longer than |
|
269 * the value returned by the method getMaxBytesPerChar. |
|
270 * @see #setSubstitutionMode |
|
271 * @see #getMaxBytesPerChar |
|
272 */ |
|
273 /** |
|
274 * sets the substitution character to use |
|
275 * @param c the substitution character |
|
276 */ |
|
277 public void setSubstitutionChars(char[] c) |
|
278 throws IllegalArgumentException |
|
279 { |
|
280 if( c.length > getMaxCharsPerByte() ) { |
|
281 throw new IllegalArgumentException(); |
|
282 } |
|
283 |
|
284 subChars = new char[ c.length ]; |
|
285 System.arraycopy( c, 0, subChars, 0, c.length ); |
|
286 } |
|
287 |
|
288 /** |
|
289 * returns a string representation of the character conversion |
|
290 */ |
|
291 public String toString() { |
|
292 return "ByteToCharConverter: " + getCharacterEncoding(); |
|
293 } |
|
294 } |
|