Repository navigation
Expand file tree
/
Copy pathDataInput.java
More file actions
602 lines (586 loc) · 22.6 KB
/
Copy pathDataInput.java
File metadata and controls
602 lines (586 loc) · 22.6 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
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
/*
* Copyright (c) 1995, 2022, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
package java.io;
/**
* The {@code DataInput} interface provides
* for reading bytes from a binary stream and
* reconstructing from them data in any of
* the Java primitive types. There is also
* a
* facility for reconstructing a {@code String}
* from data in
* <a href="#modified-utf-8">modified UTF-8</a>
* format.
* <p>
* It is generally true of all the reading
* routines in this interface that if end of
* file is reached before the desired number
* of bytes has been read, an {@code EOFException}
* (which is a kind of {@code IOException})
* is thrown. If any byte cannot be read for
* any reason other than end of file, an {@code IOException}
* other than {@code EOFException} is
* thrown. In particular, an {@code IOException}
* may be thrown if the input stream has been
* closed.
*
* <h2><a id="modified-utf-8">Modified UTF-8</a></h2>
* <p>
* Implementations of the DataInput and DataOutput interfaces represent
* Unicode strings in a format that is a slight modification of UTF-8.
* (For information regarding the standard UTF-8 format, see section
* <i>3.9 Unicode Encoding Forms</i> of <i>The Unicode Standard, Version
* 4.0</i>)
*
* <ul>
* <li>Characters in the range {@code '\u005Cu0001'} to
* {@code '\u005Cu007F'} are represented by a single byte.
* <li>The null character {@code '\u005Cu0000'} and characters
* in the range {@code '\u005Cu0080'} to {@code '\u005Cu07FF'} are
* represented by a pair of bytes.
* <li>Characters in the range {@code '\u005Cu0800'}
* to {@code '\u005CuFFFF'} are represented by three bytes.
* </ul>
*
* <table class="plain" style="margin-left:2em;">
* <caption>Encoding of UTF-8 values</caption>
* <thead>
* <tr>
* <th scope="col" rowspan="2">Value</th>
* <th scope="col" rowspan="2">Byte</th>
* <th scope="col" colspan="8" id="bit_a">Bit Values</th>
* </tr>
* <tr>
* <!-- Value -->
* <!-- Byte -->
* <th scope="col" style="width:3em"> 7 </th>
* <th scope="col" style="width:3em"> 6 </th>
* <th scope="col" style="width:3em"> 5 </th>
* <th scope="col" style="width:3em"> 4 </th>
* <th scope="col" style="width:3em"> 3 </th>
* <th scope="col" style="width:3em"> 2 </th>
* <th scope="col" style="width:3em"> 1 </th>
* <th scope="col" style="width:3em"> 0 </th>
* </thead>
* <tbody>
* <tr>
* <th scope="row" style="text-align:left; font-weight:normal">
* {@code \u005Cu0001} to {@code \u005Cu007F} </th>
* <th scope="row" style="font-weight:normal; text-align:center"> 1 </th>
* <td style="text-align:center">0
* <td colspan="7" style="text-align:right; padding-right:6em">bits 6-0
* </tr>
* <tr>
* <th scope="row" rowspan="2" style="text-align:left; font-weight:normal">
* {@code \u005Cu0000},<br>
* {@code \u005Cu0080} to {@code \u005Cu07FF} </th>
* <th scope="row" style="font-weight:normal; text-align:center"> 1 </th>
* <td style="text-align:center">1
* <td style="text-align:center">1
* <td style="text-align:center">0
* <td colspan="5" style="text-align:right; padding-right:6em">bits 10-6
* </tr>
* <tr>
* <!-- (value) -->
* <th scope="row" style="font-weight:normal; text-align:center"> 2 </th>
* <td style="text-align:center">1
* <td style="text-align:center">0
* <td colspan="6" style="text-align:right; padding-right:6em">bits 5-0
* </tr>
* <tr>
* <th scope="row" rowspan="3" style="text-align:left; font-weight:normal">
* {@code \u005Cu0800} to {@code \u005CuFFFF} </th>
* <th scope="row" style="font-weight:normal; text-align:center"> 1 </th>
* <td style="text-align:center">1
* <td style="text-align:center">1
* <td style="text-align:center">1
* <td style="text-align:center">0
* <td colspan="4" style="text-align:right; padding-right:6em">bits 15-12
* </tr>
* <tr>
* <!-- (value) -->
* <th scope="row" style="font-weight:normal; text-align:center"> 2 </th>
* <td style="text-align:center">1
* <td style="text-align:center">0
* <td colspan="6" style="text-align:right; padding-right:6em">bits 11-6
* </tr>
* <tr>
* <!-- (value) -->
* <th scope="row" style="font-weight:normal; text-align:center"> 3 </th>
* <td style="text-align:center">1
* <td style="text-align:center">0
* <td colspan="6" style="text-align:right; padding-right:6em">bits 5-0
* </tr>
* </tbody>
* </table>
*
* <p>
* The differences between this format and the
* standard UTF-8 format are the following:
* <ul>
* <li>The null byte {@code '\u005Cu0000'} is encoded in 2-byte format
* rather than 1-byte, so that the encoded strings never have
* embedded nulls.
* <li>Only the 1-byte, 2-byte, and 3-byte formats are used.
* <li><a href="../lang/Character.html#unicode">Supplementary characters</a>
* are represented in the form of surrogate pairs.
* </ul>
* @author Frank Yellin
* @see java.io.DataInputStream
* @see java.io.DataOutput
* @since 1.0
*/
public interface DataInput {
/**
* Reads some bytes from an input
* stream and stores them into the buffer
* array {@code b}. The number of bytes
* read is equal
* to the length of {@code b}.
* <p>
* This method blocks until one of the
* following conditions occurs:
* <ul>
* <li>{@code b.length}
* bytes of input data are available, in which
* case a normal return is made.
*
* <li>End of
* file is detected, in which case an {@code EOFException}
* is thrown.
*
* <li>An I/O error occurs, in
* which case an {@code IOException} other
* than {@code EOFException} is thrown.
* </ul>
* <p>
* If {@code b} is {@code null},
* a {@code NullPointerException} is thrown.
* If {@code b.length} is zero, then
* no bytes are read. Otherwise, the first
* byte read is stored into element {@code b[0]},
* the next one into {@code b[1]}, and
* so on.
* If an exception is thrown from
* this method, then it may be that some but
* not all bytes of {@code b} have been
* updated with data from the input stream.
*
* @param b the buffer into which the data is read.
* @throws NullPointerException if {@code b} is {@code null}.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
void readFully(byte[] b) throws IOException;
/**
*
* Reads {@code len}
* bytes from
* an input stream.
* <p>
* This method
* blocks until one of the following conditions
* occurs:
* <ul>
* <li>{@code len} bytes
* of input data are available, in which case
* a normal return is made.
*
* <li>End of file
* is detected, in which case an {@code EOFException}
* is thrown.
*
* <li>An I/O error occurs, in
* which case an {@code IOException} other
* than {@code EOFException} is thrown.
* </ul>
* <p>
* If {@code b} is {@code null},
* a {@code NullPointerException} is thrown.
* If {@code off} is negative, or {@code len}
* is negative, or {@code off+len} is
* greater than the length of the array {@code b},
* then an {@code IndexOutOfBoundsException}
* is thrown.
* If {@code len} is zero,
* then no bytes are read. Otherwise, the first
* byte read is stored into element {@code b[off]},
* the next one into {@code b[off+1]},
* and so on. The number of bytes read is,
* at most, equal to {@code len}.
*
* @param b the buffer into which the data is read.
* @param off an int specifying the offset in the data array {@code b}.
* @param len an int specifying the number of bytes to read.
* @throws NullPointerException if {@code b} is {@code null}.
* @throws IndexOutOfBoundsException if {@code off} is negative,
* {@code len} is negative, or {@code len} is greater than
* {@code b.length - off}.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
void readFully(byte[] b, int off, int len) throws IOException;
/**
* Makes an attempt to skip over
* {@code n} bytes
* of data from the input
* stream, discarding the skipped bytes. However,
* it may skip
* over some smaller number of
* bytes, possibly zero. This may result from
* any of a
* number of conditions; reaching
* end of file before {@code n} bytes
* have been skipped is
* only one possibility.
* This method never throws an {@code EOFException}.
* The actual
* number of bytes skipped is returned.
*
* @param n the number of bytes to be skipped.
* @return the number of bytes actually skipped.
* @throws IOException if an I/O error occurs.
*/
int skipBytes(int n) throws IOException;
/**
* Reads one input byte and returns
* {@code true} if that byte is nonzero,
* {@code false} if that byte is zero.
* This method is suitable for reading
* the byte written by the {@code writeBoolean}
* method of interface {@code DataOutput}.
*
* @return the {@code boolean} value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
boolean readBoolean() throws IOException;
/**
* Reads and returns one input byte.
* The byte is treated as a signed value in
* the range {@code -128} through {@code 127},
* inclusive.
* This method is suitable for
* reading the byte written by the {@code writeByte}
* method of interface {@code DataOutput}.
*
* @return the 8-bit value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
byte readByte() throws IOException;
/**
* Reads one input byte, zero-extends
* it to type {@code int}, and returns
* the result, which is therefore in the range
* {@code 0}
* through {@code 255}.
* This method is suitable for reading
* the byte written by the {@code writeByte}
* method of interface {@code DataOutput}
* if the argument to {@code writeByte}
* was intended to be a value in the range
* {@code 0} through {@code 255}.
*
* @return the unsigned 8-bit value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
int readUnsignedByte() throws IOException;
/**
* Reads two input bytes and returns
* a {@code short} value. Let {@code a}
* be the first byte read and {@code b}
* be the second byte. The value
* returned
* is:
* <pre>{@code (short)((a << 8) | (b & 0xff))
* }</pre>
* This method
* is suitable for reading the bytes written
* by the {@code writeShort} method of
* interface {@code DataOutput}.
*
* @return the 16-bit value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
short readShort() throws IOException;
/**
* Reads two input bytes and returns
* an {@code int} value in the range {@code 0}
* through {@code 65535}. Let {@code a}
* be the first byte read and
* {@code b}
* be the second byte. The value returned is:
* <pre>{@code (((a & 0xff) << 8) | (b & 0xff))
* }</pre>
* This method is suitable for reading the bytes
* written by the {@code writeShort} method
* of interface {@code DataOutput} if
* the argument to {@code writeShort}
* was intended to be a value in the range
* {@code 0} through {@code 65535}.
*
* @return the unsigned 16-bit value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
int readUnsignedShort() throws IOException;
/**
* Reads two input bytes and returns a {@code char} value.
* Let {@code a}
* be the first byte read and {@code b}
* be the second byte. The value
* returned is:
* <pre>{@code (char)((a << 8) | (b & 0xff))
* }</pre>
* This method
* is suitable for reading bytes written by
* the {@code writeChar} method of interface
* {@code DataOutput}.
*
* @return the {@code char} value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
char readChar() throws IOException;
/**
* Reads four input bytes and returns an
* {@code int} value. Let {@code a-d}
* be the first through fourth bytes read. The value returned is:
* <pre>{@code
* (((a & 0xff) << 24) | ((b & 0xff) << 16) |
* ((c & 0xff) << 8) | (d & 0xff))
* }</pre>
* This method is suitable
* for reading bytes written by the {@code writeInt}
* method of interface {@code DataOutput}.
*
* @return the {@code int} value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
int readInt() throws IOException;
/**
* Reads eight input bytes and returns
* a {@code long} value. Let {@code a-h}
* be the first through eighth bytes read.
* The value returned is:
* <pre>{@code
* (((long)(a & 0xff) << 56) |
* ((long)(b & 0xff) << 48) |
* ((long)(c & 0xff) << 40) |
* ((long)(d & 0xff) << 32) |
* ((long)(e & 0xff) << 24) |
* ((long)(f & 0xff) << 16) |
* ((long)(g & 0xff) << 8) |
* ((long)(h & 0xff)))
* }</pre>
* <p>
* This method is suitable
* for reading bytes written by the {@code writeLong}
* method of interface {@code DataOutput}.
*
* @return the {@code long} value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
long readLong() throws IOException;
/**
* Reads four input bytes and returns
* a {@code float} value. It does this
* by first constructing an {@code int}
* value in exactly the manner
* of the {@code readInt}
* method, then converting this {@code int}
* value to a {@code float} in
* exactly the manner of the method {@code Float.intBitsToFloat}.
* This method is suitable for reading
* bytes written by the {@code writeFloat}
* method of interface {@code DataOutput}.
*
* @return the {@code float} value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
float readFloat() throws IOException;
/**
* Reads eight input bytes and returns
* a {@code double} value. It does this
* by first constructing a {@code long}
* value in exactly the manner
* of the {@code readLong}
* method, then converting this {@code long}
* value to a {@code double} in exactly
* the manner of the method {@code Double.longBitsToDouble}.
* This method is suitable for reading
* bytes written by the {@code writeDouble}
* method of interface {@code DataOutput}.
*
* @return the {@code double} value read.
* @throws EOFException if this stream reaches the end before reading
* all the bytes.
* @throws IOException if an I/O error occurs.
*/
double readDouble() throws IOException;
/**
* Reads the next line of text from the input stream.
* It reads successive bytes, converting
* each byte separately into a character,
* until it encounters a line terminator or
* end of
* file; the characters read are then
* returned as a {@code String}. Note
* that because this
* method processes bytes,
* it does not support input of the full Unicode
* character set.
* <p>
* If end of file is encountered
* before even one byte can be read, then {@code null}
* is returned. Otherwise, each byte that is
* read is converted to type {@code char}
* by zero-extension. If the character {@code '\n'}
* is encountered, it is discarded and reading
* ceases. If the character {@code '\r'}
* is encountered, it is discarded and, if
* the following byte converts to the
* character {@code '\n'}, then that is
* discarded also; reading then ceases. If
* end of file is encountered before either
* of the characters {@code '\n'} and
* {@code '\r'} is encountered, reading
* ceases. Once reading has ceased, a {@code String}
* is returned that contains all the characters
* read and not discarded, taken in order.
* Note that every character in this string
* will have a value less than {@code \u005Cu0100},
* that is, {@code (char)256}.
*
* @return the next line of text from the input stream,
* or {@code null} if the end of file is
* encountered before a byte can be read.
* @throws IOException if an I/O error occurs.
*/
String readLine() throws IOException;
/**
* Reads in a string that has been encoded using a
* <a href="#modified-utf-8">modified UTF-8</a>
* format.
* The general contract of {@code readUTF}
* is that it reads a representation of a Unicode
* character string encoded in modified
* UTF-8 format; this string of characters
* is then returned as a {@code String}.
* <p>
* First, two bytes are read and used to
* construct an unsigned 16-bit integer in
* exactly the manner of the {@code readUnsignedShort}
* method . This integer value is called the
* <i>UTF length</i> and specifies the number
* of additional bytes to be read. These bytes
* are then converted to characters by considering
* them in groups. The length of each group
* is computed from the value of the first
* byte of the group. The byte following a
* group, if any, is the first byte of the
* next group.
* <p>
* If the first byte of a group
* matches the bit pattern {@code 0xxxxxxx}
* (where {@code x} means "may be {@code 0}
* or {@code 1}"), then the group consists
* of just that byte. The byte is zero-extended
* to form a character.
* <p>
* If the first byte
* of a group matches the bit pattern {@code 110xxxxx},
* then the group consists of that byte {@code a}
* and a second byte {@code b}. If there
* is no byte {@code b} (because byte
* {@code a} was the last of the bytes
* to be read), or if byte {@code b} does
* not match the bit pattern {@code 10xxxxxx},
* then a {@code UTFDataFormatException}
* is thrown. Otherwise, the group is converted
* to the character:
* <pre>{@code (char)(((a & 0x1F) << 6) | (b & 0x3F))
* }</pre>
* If the first byte of a group
* matches the bit pattern {@code 1110xxxx},
* then the group consists of that byte {@code a}
* and two more bytes {@code b} and {@code c}.
* If there is no byte {@code c} (because
* byte {@code a} was one of the last
* two of the bytes to be read), or either
* byte {@code b} or byte {@code c}
* does not match the bit pattern {@code 10xxxxxx},
* then a {@code UTFDataFormatException}
* is thrown. Otherwise, the group is converted
* to the character:
* <pre>{@code
* (char)(((a & 0x0F) << 12) | ((b & 0x3F) << 6) | (c & 0x3F))
* }</pre>
* If the first byte of a group matches the
* pattern {@code 1111xxxx} or the pattern
* {@code 10xxxxxx}, then a {@code UTFDataFormatException}
* is thrown.
* <p>
* If end of file is encountered
* at any time during this entire process,
* then an {@code EOFException} is thrown.
* <p>
* After every group has been converted to
* a character by this process, the characters
* are gathered, in the same order in which
* their corresponding groups were read from
* the input stream, to form a {@code String},
* which is returned.
* <p>
* The {@code writeUTF}
* method of interface {@code DataOutput}
* may be used to write data that is suitable
* for reading by this method.
* @return a Unicode string.
* @throws EOFException if this stream reaches the end
* before reading all the bytes.
* @throws IOException if an I/O error occurs.
* @throws UTFDataFormatException if the bytes do not represent a
* valid modified UTF-8 encoding of a string.
*/
String readUTF() throws IOException;
}