Repository navigation
Expand file tree
/
Copy pathStringCoding.java
More file actions
402 lines (371 loc) · 14.5 KB
/
Copy pathStringCoding.java
File metadata and controls
402 lines (371 loc) · 14.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
/*
* Copyright 2000-2009 Sun Microsystems, Inc. All rights reserved.
* SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*/
package java.lang;
import java.io.UnsupportedEncodingException;
import java.lang.ref.SoftReference;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.CoderResult;
import java.nio.charset.CodingErrorAction;
import java.nio.charset.IllegalCharsetNameException;
import java.nio.charset.UnsupportedCharsetException;
import java.util.Arrays;
import sun.misc.MessageUtils;
import sun.nio.cs.HistoricallyNamedCharset;
import sun.nio.cs.ArrayDecoder;
import sun.nio.cs.ArrayEncoder;
/**
* Utility class for string encoding and decoding.
*/
class StringCoding {
private StringCoding() { }
/** The cached coders for each thread */
private final static ThreadLocal<SoftReference<StringDecoder>> decoder =
new ThreadLocal<SoftReference<StringDecoder>>();
private final static ThreadLocal<SoftReference<StringEncoder>> encoder =
new ThreadLocal<SoftReference<StringEncoder>>();
private static boolean warnUnsupportedCharset = true;
private static <T> T deref(ThreadLocal<SoftReference<T>> tl) {
SoftReference<T> sr = tl.get();
if (sr == null)
return null;
return sr.get();
}
private static <T> void set(ThreadLocal<SoftReference<T>> tl, T ob) {
tl.set(new SoftReference<T>(ob));
}
// Trim the given byte array to the given length
//
private static byte[] safeTrim(byte[] ba, int len, Charset cs, boolean isTrusted) {
if (len == ba.length && (isTrusted || System.getSecurityManager() == null))
return ba;
else
return Arrays.copyOf(ba, len);
}
// Trim the given char array to the given length
//
private static char[] safeTrim(char[] ca, int len,
Charset cs, boolean isTrusted) {
if (len == ca.length && (isTrusted || System.getSecurityManager() == null))
return ca;
else
return Arrays.copyOf(ca, len);
}
private static int scale(int len, float expansionFactor) {
// We need to perform double, not float, arithmetic; otherwise
// we lose low order bits when len is larger than 2**24.
return (int)(len * (double)expansionFactor);
}
private static Charset lookupCharset(String csn) {
if (Charset.isSupported(csn)) {
try {
return Charset.forName(csn);
} catch (UnsupportedCharsetException x) {
throw new Error(x);
}
}
return null;
}
private static void warnUnsupportedCharset(String csn) {
if (warnUnsupportedCharset) {
// Use sun.misc.MessageUtils rather than the Logging API or
// System.err since this method may be called during VM
// initialization before either is available.
MessageUtils.err("WARNING: Default charset " + csn +
" not supported, using ISO-8859-1 instead");
warnUnsupportedCharset = false;
}
}
// -- Decoding --
private static class StringDecoder {
private final String requestedCharsetName;
private final Charset cs;
private final CharsetDecoder cd;
private final boolean isTrusted;
private StringDecoder(Charset cs, String rcn) {
this.requestedCharsetName = rcn;
this.cs = cs;
this.cd = cs.newDecoder()
.onMalformedInput(CodingErrorAction.REPLACE)
.onUnmappableCharacter(CodingErrorAction.REPLACE);
this.isTrusted = (cs.getClass().getClassLoader0() == null);
}
String charsetName() {
if (cs instanceof HistoricallyNamedCharset)
return ((HistoricallyNamedCharset)cs).historicalName();
return cs.name();
}
final String requestedCharsetName() {
return requestedCharsetName;
}
char[] decode(byte[] ba, int off, int len) {
int en = scale(len, cd.maxCharsPerByte());
char[] ca = new char[en];
if (len == 0)
return ca;
if (cd instanceof ArrayDecoder) {
int clen = ((ArrayDecoder)cd).decode(ba, off, len, ca);
return safeTrim(ca, clen, cs, isTrusted);
} else {
cd.reset();
ByteBuffer bb = ByteBuffer.wrap(ba, off, len);
CharBuffer cb = CharBuffer.wrap(ca);
try {
CoderResult cr = cd.decode(bb, cb, true);
if (!cr.isUnderflow())
cr.throwException();
cr = cd.flush(cb);
if (!cr.isUnderflow())
cr.throwException();
} catch (CharacterCodingException x) {
// Substitution is always enabled,
// so this shouldn't happen
throw new Error(x);
}
return safeTrim(ca, cb.position(), cs, isTrusted);
}
}
}
static char[] decode(String charsetName, byte[] ba, int off, int len)
throws UnsupportedEncodingException
{
StringDecoder sd = deref(decoder);
String csn = (charsetName == null) ? "ISO-8859-1" : charsetName;
if ((sd == null) || !(csn.equals(sd.requestedCharsetName())
|| csn.equals(sd.charsetName()))) {
sd = null;
try {
Charset cs = lookupCharset(csn);
if (cs != null)
sd = new StringDecoder(cs, csn);
} catch (IllegalCharsetNameException x) {}
if (sd == null)
throw new UnsupportedEncodingException(csn);
set(decoder, sd);
}
return sd.decode(ba, off, len);
}
static char[] decode(Charset cs, byte[] ba, int off, int len) {
// (1)We never cache the "external" cs, the only benefit of creating
// an additional StringDe/Encoder object to wrap it is to share the
// de/encode() method. These SD/E objects are short-lifed, the young-gen
// gc should be able to take care of them well. But the best approash
// is still not to generate them if not really necessary.
// (2)The defensive copy of the input byte/char[] has a big performance
// impact, as well as the outgoing result byte/char[]. Need to do the
// optimization check of (sm==null && classLoader0==null) for both.
// (3)getClass().getClassLoader0() is expensive
// (4)There might be a timing gap in isTrusted setting. getClassLoader0()
// is only chcked (and then isTrusted gets set) when (SM==null). It is
// possible that the SM==null for now but then SM is NOT null later
// when safeTrim() is invoked...the "safe" way to do is to redundant
// check (... && (isTrusted || SM == null || getClassLoader0())) in trim
// but it then can be argued that the SM is null when the opertaion
// is started...
CharsetDecoder cd = cs.newDecoder();
int en = scale(len, cd.maxCharsPerByte());
char[] ca = new char[en];
if (len == 0)
return ca;
boolean isTrusted = false;
if (System.getSecurityManager() != null) {
if (!(isTrusted = (cs.getClass().getClassLoader0() == null))) {
ba = Arrays.copyOfRange(ba, off, off + len);
off = 0;
}
}
if (cd instanceof ArrayDecoder) {
int clen = ((ArrayDecoder)cd).decode(ba, off, len, ca);
return safeTrim(ca, clen, cs, isTrusted);
} else {
cd.onMalformedInput(CodingErrorAction.REPLACE)
.onUnmappableCharacter(CodingErrorAction.REPLACE)
.reset();
ByteBuffer bb = ByteBuffer.wrap(ba, off, len);
CharBuffer cb = CharBuffer.wrap(ca);
try {
CoderResult cr = cd.decode(bb, cb, true);
if (!cr.isUnderflow())
cr.throwException();
cr = cd.flush(cb);
if (!cr.isUnderflow())
cr.throwException();
} catch (CharacterCodingException x) {
// Substitution is always enabled,
// so this shouldn't happen
throw new Error(x);
}
return safeTrim(ca, cb.position(), cs, isTrusted);
}
}
static char[] decode(byte[] ba, int off, int len) {
String csn = Charset.defaultCharset().name();
try {
return decode(csn, ba, off, len);
} catch (UnsupportedEncodingException x) {
warnUnsupportedCharset(csn);
}
try {
return decode("ISO-8859-1", ba, off, len);
} catch (UnsupportedEncodingException x) {
// If this code is hit during VM initialization, MessageUtils is
// the only way we will be able to get any kind of error message.
MessageUtils.err("ISO-8859-1 charset not available: "
+ x.toString());
// If we can not find ISO-8859-1 (a required encoding) then things
// are seriously wrong with the installation.
System.exit(1);
return null;
}
}
// -- Encoding --
private static class StringEncoder {
private Charset cs;
private CharsetEncoder ce;
private final String requestedCharsetName;
private final boolean isTrusted;
private StringEncoder(Charset cs, String rcn) {
this.requestedCharsetName = rcn;
this.cs = cs;
this.ce = cs.newEncoder()
.onMalformedInput(CodingErrorAction.REPLACE)
.onUnmappableCharacter(CodingErrorAction.REPLACE);
this.isTrusted = (cs.getClass().getClassLoader0() == null);
}
String charsetName() {
if (cs instanceof HistoricallyNamedCharset)
return ((HistoricallyNamedCharset)cs).historicalName();
return cs.name();
}
final String requestedCharsetName() {
return requestedCharsetName;
}
byte[] encode(char[] ca, int off, int len) {
int en = scale(len, ce.maxBytesPerChar());
byte[] ba = new byte[en];
if (len == 0)
return ba;
if (ce instanceof ArrayEncoder) {
int blen = ((ArrayEncoder)ce).encode(ca, off, len, ba);
return safeTrim(ba, blen, cs, isTrusted);
} else {
ce.reset();
ByteBuffer bb = ByteBuffer.wrap(ba);
CharBuffer cb = CharBuffer.wrap(ca, off, len);
try {
CoderResult cr = ce.encode(cb, bb, true);
if (!cr.isUnderflow())
cr.throwException();
cr = ce.flush(bb);
if (!cr.isUnderflow())
cr.throwException();
} catch (CharacterCodingException x) {
// Substitution is always enabled,
// so this shouldn't happen
throw new Error(x);
}
return safeTrim(ba, bb.position(), cs, isTrusted);
}
}
}
static byte[] encode(String charsetName, char[] ca, int off, int len)
throws UnsupportedEncodingException
{
StringEncoder se = deref(encoder);
String csn = (charsetName == null) ? "ISO-8859-1" : charsetName;
if ((se == null) || !(csn.equals(se.requestedCharsetName())
|| csn.equals(se.charsetName()))) {
se = null;
try {
Charset cs = lookupCharset(csn);
if (cs != null)
se = new StringEncoder(cs, csn);
} catch (IllegalCharsetNameException x) {}
if (se == null)
throw new UnsupportedEncodingException (csn);
set(encoder, se);
}
return se.encode(ca, off, len);
}
static byte[] encode(Charset cs, char[] ca, int off, int len) {
CharsetEncoder ce = cs.newEncoder();
int en = scale(len, ce.maxBytesPerChar());
byte[] ba = new byte[en];
if (len == 0)
return ba;
boolean isTrusted = false;
if (System.getSecurityManager() != null) {
if (!(isTrusted = (cs.getClass().getClassLoader0() == null))) {
ca = Arrays.copyOfRange(ca, off, off + len);
off = 0;
}
}
if (ce instanceof ArrayEncoder) {
int blen = ((ArrayEncoder)ce).encode(ca, off, len, ba);
return safeTrim(ba, blen, cs, isTrusted);
} else {
ce.onMalformedInput(CodingErrorAction.REPLACE)
.onUnmappableCharacter(CodingErrorAction.REPLACE)
.reset();
ByteBuffer bb = ByteBuffer.wrap(ba);
CharBuffer cb = CharBuffer.wrap(ca, off, len);
try {
CoderResult cr = ce.encode(cb, bb, true);
if (!cr.isUnderflow())
cr.throwException();
cr = ce.flush(bb);
if (!cr.isUnderflow())
cr.throwException();
} catch (CharacterCodingException x) {
throw new Error(x);
}
return safeTrim(ba, bb.position(), cs, isTrusted);
}
}
static byte[] encode(char[] ca, int off, int len) {
String csn = Charset.defaultCharset().name();
try {
return encode(csn, ca, off, len);
} catch (UnsupportedEncodingException x) {
warnUnsupportedCharset(csn);
}
try {
return encode("ISO-8859-1", ca, off, len);
} catch (UnsupportedEncodingException x) {
// If this code is hit during VM initialization, MessageUtils is
// the only way we will be able to get any kind of error message.
MessageUtils.err("ISO-8859-1 charset not available: "
+ x.toString());
// If we can not find ISO-8859-1 (a required encoding) then things
// are seriously wrong with the installation.
System.exit(1);
return null;
}
}
}