summaryrefslogtreecommitdiff
path: root/java/io/DataInputStream.java
blob: acd8cbc80ed7590b51f2517310b0169b878ac6f5 (plain)
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
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
/*************************************************************************
/* DataInputStream.java -- Class for reading Java data from a stream
/*
/* Copyright (c) 1998 by Aaron M. Renn (arenn@urbanophile.com)
/*
/* This program is free software; you can redistribute it and/or modify
/* it under the terms of the GNU Library General Public License as published 
/* by the Free Software Foundation, version 2. (see COPYING.LIB)
/*
/* This program 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 for more details.
/*
/* You should have received a copy of the GNU Library General Public License
/* along with this program; if not, write to the Free Software Foundation
/* Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307 USA
/*************************************************************************/

package java.io;

/**
  * This subclass of @code{FilteredInputStream} implements the
  * @code{DataInput} interface that provides method for reading primitive
  * Java data types from a stream.
  *
  * @see DataInput
  *
  * @version 0.0
  *
  * @author Aaron M. Renn (arenn@urbanophile.com)
  */
public class DataInputStream extends FilterInputStream implements DataInput
{

/*************************************************************************/

/*
 * Class Methods
 */

/**
  * This method reads a String encoded in UTF-8 format from the 
  * specified <code>DataInput</code> source.
  *
  * @param in The <code>DataInput</code> source to read from
  *
  * @return The String read from the source
  *
  * @exception IOException If an error occurs
  */
public static final String
readUTF(DataInput in) throws IOException
{
  return(in.readUTF());
}

/*************************************************************************/

/*
 * Constructors
 */

/**
  * This method initializes a new @code{DataInputStream} to read from
  * the specified subordinate stream.
  *
  * @param in The subordinate @code{InputStream} to read from
  */
public
DataInputStream(InputStream in)
{
  super(in);

  this.in = new PushbackInputStream(in);
}

/*************************************************************************/

/*
 * Instance Methods
 */

/**
  * This method reads a Java boolean value from an input stream.  It does
  * so by reading a single byte of data.  If that byte is zero, then the
  * value returned is @code{false}.  If the byte is non-zero, then
  * the value returned is @code{true}.
  *
  * This method can read a @code{boolean} written by an object implementing the
  * @code{writeBoolean()} method in the @code{DataOutput} interface.
  *
  * @return The @code{boolean} value read
  *
  * @exception EOFException If end of file is reached before reading the boolean
  * @exception IOException If any other error occurs
  */
public final boolean
readBoolean() throws EOFException, IOException
{
  int byte_read = in.read();

  if (byte_read == -1)
    throw new EOFException("Unexpected end of stream");

  if (byte_read == 0)
    return(false);
  else
    return(true);
}

/*************************************************************************/

/**
  * This method reads a Java byte value from an input stream.  The value
  * is in the range of -128 to 127.
  *
  * This method can read a @code{byte} written by an object implementing the 
  * @code{writeByte()} method in the @code{DataOutput} interface.
  *
  * @return The @code{byte} value read
  *
  * @exception EOFException If end of file is reached before reading the byte
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final byte
readByte() throws EOFException, IOException
{
  int byte_read = in.read();

  if (byte_read == -1)
    throw new EOFException("Unexpected end of stream");

  return((byte)byte_read); 
}

/*************************************************************************/

/**
  * This method reads 8 unsigned bits into a Java @code{int} value from the 
  * stream. The value returned is in the range of 0 to 255.
  *
  * This method can read an unsigned byte written by an object implementing the
  * @code{writeUnsignedByte()} method in the @code{DataOutput} interface.
  *
  * @return The unsigned bytes value read as a Java @code{int}.
  *
  * @exception EOFException If end of file is reached before reading the value
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final int
readUnsignedByte() throws EOFException, IOException
{
  int byte_read = in.read();

  if (byte_read == -1)
    throw new EOFException("Unexpected end of stream");

  return(byte_read);
}

/*************************************************************************/

/**
  * This method reads a Java @code{char} value from an input stream.  
  * It operates by reading two bytes from the stream and converting them to 
  * a single 16-bit Java @code{char}.  The two bytes are stored most
  * significant byte first (i.e., "big endian") regardless of the native
  * host byte ordering. 
  *
  * As an example, if @code{byte1} and code{byte2} represent the first
  * and second byte read from the stream respectively, they will be
  * transformed to a @code{char} in the following manner:
  *
  * @code{(char)(((byte1 & 0xFF) << 8) | (byte2 & 0xFF)}
  *
  * This method can read a @code{char} written by an object implementing the
  * @code{writeChar()} method in the @code{DataOutput} interface.
  *
  * @return The @code{char} value read 
  *
  * @exception EOFException If end of file is reached before reading the char
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final char
readChar() throws EOFException, IOException
{
  byte[] buf = new byte[2];

  readFully(buf);

  char retval = (char)(((buf[0] & 0xFF) << 8) | (buf[1] & 0xFF));

  return(retval);
}

/*************************************************************************/

/**
  * This method reads a signed 16-bit value into a Java in from the stream.
  * It operates by reading two bytes from the stream and converting them to 
  * a single 16-bit Java @code{short}.  The two bytes are stored most
  * significant byte first (i.e., "big endian") regardless of the native
  * host byte ordering. 
  *
  * As an example, if @code{byte1} and code{byte2} represent the first
  * and second byte read from the stream respectively, they will be
  * transformed to a @code{short} in the following manner:
  *
  * @code{(short)(((byte1 & 0xFF) << 8) | (byte2 & 0xFF)}
  *
  * The value returned is in the range of -32768 to 32767.
  *
  * This method can read a @code{short} written by an object implementing the
  * @code{writeShort()} method in the @code{DataOutput} interface.
  *
  * @return The @code{short} value read
  *
  * @exception EOFException If end of file is reached before reading the value
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final short
readShort() throws EOFException, IOException
{
  byte[] buf = new byte[2];

  readFully(buf);

  short retval = (short)(((buf[0] & 0xFF) << 8) | (buf[1] & 0xFF));

  return(retval);
}

/*************************************************************************/

/**
  * This method reads 16 unsigned bits into a Java int value from the stream.
  * It operates by reading two bytes from the stream and converting them to 
  * a single Java @code{int}.  The two bytes are stored most
  * significant byte first (i.e., "big endian") regardless of the native
  * host byte ordering. 
  *
  * As an example, if @code{byte1} and code{byte2} represent the first
  * and second byte read from the stream respectively, they will be
  * transformed to an @code{int} in the following manner:
  *
  * @code{(int)(((byte1 & 0xFF) << 8) + (byte2 & 0xFF))}
  *
  * The value returned is in the range of 0 to 65535.
  *
  * This method can read an unsigned short written by an object implementing
  * the @code{writeUnsignedShort()} method in the @code{DataOutput} interface.
  *
  * @return The unsigned short value read as a Java @code{int}.
  *
  * @exception EOFException If end of file is reached before reading the value
  * @exception IOException If any other error occurs
  */
public final int
readUnsignedShort() throws EOFException, IOException
{
  byte[] buf = new byte[2];

  readFully(buf);

  int retval = ((buf[0] & 0xFF) << 8) | (buf[1] & 0xFF);

  return(retval);
}

/*************************************************************************/

/**
  * This method reads a Java @code{int} value from an input stream
  * It operates by reading four bytes from the stream and converting them to 
  * a single Java @code{int}.  The bytes are stored most
  * significant byte first (i.e., "big endian") regardless of the native
  * host byte ordering. 
  *
  * As an example, if @code{byte1} through @code{byte4} represent the first
  * four bytes read from the stream, they will be
  * transformed to an @code{int} in the following manner:
  *
  * @code{(int)(((byte1 & 0xFF) << 24) + ((byte2 & 0xFF) << 16) + 
  * ((byte3 & 0xFF) << 8) + (byte4 & 0xFF)))}
  *
  * The value returned is in the range of 0 to 65535.
  *
  * This method can read an @code{int} written by an object implementing the
  * @code{writeInt()} method in the @code{DataOutput} interface.
  *
  * @return The @code{int} value read
  *
  * @exception EOFException If end of file is reached before reading the int
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final int
readInt() throws EOFException, IOException
{
  byte[] buf = new byte[4];

  readFully(buf);

  int retval = ((buf[0] & 0xFF) << 24) | ((buf[1] & 0xFF) << 16) | 
               ((buf[2] & 0xFF) << 8) | (buf[3] & 0xFF);

  return(retval);
}

/*************************************************************************/

/**
  * This method reads a Java long value from an input stream
  * It operates by reading eight bytes from the stream and converting them to 
  * a single Java @code{long}.  The bytes are stored most
  * significant byte first (i.e., "big endian") regardless of the native
  * host byte ordering. 
  *
  * As an example, if @code{byte1} through @code{byte8} represent the first
  * eight bytes read from the stream, they will be
  * transformed to an @code{long} in the following manner:
  *
  * @code{(long)((((long)byte1 & 0xFF) << 56) + (((long)byte2 & 0xFF) << 48) + 
  * (((long)byte3 & 0xFF) << 40) + (((long)byte4 & 0xFF) << 32) + 
  * (((long)byte5 & 0xFF) << 24) + (((long)byte6 & 0xFF) << 16) + 
  * (((long)byte7 & 0xFF) << 8) + ((long)byte9 & 0xFF)))}
  *
  * The value returned is in the range of 0 to 65535.
  *
  * This method can read an @code{long} written by an object implementing the
  * @code{writeLong()} method in the @code{DataOutput} interface.
  *
  * @return The @code{long} value read
  *
  * @exception EOFException If end of file is reached before reading the long
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final long
readLong() throws EOFException, IOException
{
  byte[] buf = new byte[8];

  readFully(buf);

  long retval = (((long)buf[0] & 0xFF) << 56) | (((long)buf[1] & 0xFF) << 48) | 
                (((long)buf[2] & 0xFF) << 40) | (((long)buf[3] & 0xFF) << 32) | 
                (((long)buf[4] & 0xFF) << 24) | (((long)buf[5] & 0xFF) << 16) |
                (((long)buf[6] & 0xFF) << 8) | ((long)buf[7] & 0xFF);

  return(retval);
}

/*************************************************************************/

/**
  * This method reads a Java float value from an input stream.  It operates
  * by first reading an @code{int} value from the stream by calling the
  * @code{readInt()} method in this interface, then converts that @code{int}
  * to a @code{float} using the @code{intBitsToFloat} method in 
  * the class @{java.lang.Float}.
  *
  * This method can read a @code{float} written by an object implementing the
  * @code{writeFloat()} method in the @code{DataOutput} interface.
  *
  * @return The @code{float} value read
  *
  * @exception EOFException If end of file is reached before reading the float
  * @exception IOException If any other error occurs
  *
  * @see java.lang.Float
  * @see DataOutput
  */
public final float
readFloat() throws EOFException, IOException
{
  int val = readInt();

  return(Float.intBitsToFloat(val));
}

/*************************************************************************/

/**
  * This method reads a Java double value from an input stream.  It operates
  * by first reading a @code{logn} value from the stream by calling the
  * @code{readLong()} method in this interface, then converts that @code{long}
  * to a @code{double} using the @code{longBitsToDouble} method in 
  * the class @{java.lang.Double}.
  *
  * This method can read a @code{double} written by an object implementing the
  * @code{writeDouble()} method in the @code{DataOutput} interface.
  *
  * @return The @code{double} value read
  *
  * @exception EOFException If end of file is reached before reading the double
  * @exception IOException If any other error occurs
  *
  * @see java.lang.Double
  * @see DataOutput
  */
public final double
readDouble() throws EOFException, IOException
{
  long val = readLong();

  return(Double.longBitsToDouble(val));
}

/*************************************************************************/

/**
  * This method reads the next line of text data from an input stream.
  * It operates by reading bytes and converting those bytes to @{char}
  * values by treating the byte read as the low eight bits of the @{char}
  * and using @code{0} as the high eight bits.  Because of this, it does
  * not support the full 16-bit Unicode character set.
  *
  * The reading of bytes ends when either the end of file or a line terminator
  * is encountered.  The bytes read are then returned as a @code{String}.
  * A line terminator is a byte sequence consisting of either 
  * @samp{\r}, @samp{\n} or @samp{\r\n}.  These termination charaters are
  * discarded and are not returned as part of the string.
  *
  * This method can read data that was written by an object implementing the
  * @code{writeLine()} method in @code{DataOutput}.
  *
  * @return The line read as a @code{String}
  *
  * @exception IOException If an error occurs
  *
  * @see DataOutput
  *
  * @deprecated
  */
public final String
readLine() throws IOException
{
  StringBuffer sb = new StringBuffer("");

  for (;;)
    {
      int byte_read = in.read();
 
      if (byte_read == -1)
        return(sb.toString());

      char c = (char)byte_read;

      if (c == '\r')
        {
          byte_read = in.read();
          if (((char)byte_read) != '\n')
            ((PushbackInputStream)in).unread(byte_read);

          return(sb.toString());
        }

      if (c == '\n')
        return(sb.toString());

      sb.append(c);
    }
}

/*************************************************************************/

/**
  * This method reads a @code{String} from an input stream that is encoded in
  * a modified UTF-8 format.  This format has a leading two byte sequence
  * that contains the remaining number of bytes to read.  This two byte
  * sequence is read using the @code{readUnsignedShort()} method of this
  * interface.
  *
  * After the number of remaining bytes have been determined, these bytes
  * are read an transformed into @{char} values.  These @code{char} values
  * are encoded in the stream using either a one, two, or three byte format.
  * The particular format in use can be determined by examining the first
  * byte read.  
  *
  * If the first byte has a high order bit of @samp{0}, then
  * that character consists on only one byte.  This character value consists
  * of seven bits that are at positions 0 through 6 of the byte.  As an
  * example, if @code{byte1} is the byte read from the stream, it would
  * be converted to a @code{char} like so:
  *
  * @code{(char)byte1}
  *
  * If the first byte has @code{110} as its high order bits, then the 
  * character consists of two bytes.  The bits that make up the character
  * value are in positions 0 through 4 of the first byte and bit positions
  * 0 through 5 of the second byte.  (The second byte should have 
  * @samp{10} as its high order bits).  These values are in most significant
  * byte first (i.e., "big endian") order.
  *
  * As an example, if @code{byte1} and @code{byte2} are the first two bytes
  * read respectively, and the high order bits of them match the patterns
  * which indicate a two byte character encoding, then they would be
  * converted to a Java @code{char} like so:
  *
  * @code{(char)(((byte1 & 0x1F) << 6) | (byte2 & 0x3F))}
  *
  * If the first byte has a @code{1110} as its high order bits, then the
  * character consists of three bytes.  The bits that make up the character
  * value are in positions 0 through 3 of the first byte and bit positions
  * 0 through 5 of the other two bytes.  (The second and third bytes should
  * have @code{10} as their high order bits).  These values are in most
  * significant byte first (i.e., "big endian") order.
  *
  * As an example, if @code{byte1}, @code{byte2}, and @code{byte3} are the
  * three bytes read, and the high order bits of them match the patterns
  * which indicate a three byte character encoding, then they would be
  * converted to a Java @code{char} like so:
  *
  * @code{(char)(((byte1 & 0x0F) << 12) | ((byte2 & 0x3F) << 6) | (byte3 & 0x3F))}
  *
  * Note that all characters are encoded in the method that requires the
  * fewest number of bytes with the exception of the character with the
  * value of @samp{\u0000} which is encoded as two bytes.  This is a 
  * modification of the UTF standard used to prevent C language style
  * @samp{NUL} values from appearing in the byte stream.
  *
  * This method can read data that was written by an object implementing the
  * @code{writeUTF()} method in @code{DataOutput}.
  * 
  * @returns The @code{String} read
  *
  * @exception EOFException If end of file is reached before reading the String
  * @exception UTFDataFormatException If the data is not in UTF-8 format
  * @exception IOException If any other error occurs
  *
  * @see DataOutput
  */
public final String
readUTF() throws EOFException, UTFDataFormatException, IOException
{
  StringBuffer sb = new StringBuffer("");

  int num_bytes = readUnsignedShort();

  for (int i = 0; i < num_bytes; i++)
    {
      int byte_read = in.read();

      if (byte_read == -1)
        throw new EOFException("Unexpected end of stream");

      // Three byte encoding case
      if ((byte_read & 0xE0) == 0xE0) // 224
        {
          int val = (byte_read & 0x0F) << 12;

          byte_read = in.read();
          if (byte_read == -1)
            throw new EOFException("Unexpected end of stream");

          if ((byte_read & 0x80) != 0x80)
            throw new UTFDataFormatException("Bad byte in input: " + byte_read);

          val |= (byte_read & 0x3F) << 6;

          byte_read = in.read();
          if (byte_read == -1)
            throw new EOFException("Unexpected end of stream");

          if ((byte_read & 0x80) != 0x80)
            throw new UTFDataFormatException("Bad byte in input: " + byte_read);

          val |= (byte_read & 0x3F);

          sb.append((char)val);

          i += 2;
        }
      // Two byte encoding case
      else if ((byte_read & 0xC0) == 0xC0) // 192
        {
          int val = (byte_read & 0x1F) << 6;

          byte_read = in.read();
          if (byte_read == -1)
            throw new EOFException("Unexpected end of stream");

          if ((byte_read & 0x80) != 0x80)
            throw new UTFDataFormatException("Bad byte in input: " + byte_read);

          val |= (byte_read & 0x3F);

          sb.append((char)val);
          
          ++i;
        }
      // One byte encoding case
      else if (byte_read < 128)
        {
          sb.append((char)byte_read);
        }
      else
        {
          throw new UTFDataFormatException("Bad byte in input: " + byte_read);
        }
    }
  return(sb.toString()); 
}

/*************************************************************************/

/**
  * This method reads raw bytes into the passed array until the array is
  * full.  Note that this method blocks until the data is available and
  * throws an exception if there is not enough data left in the stream to
  * fill the buffer
  *
  * @param buf The buffer into which to read the data
  *
  * @exception EOFException If end of file is reached before filling the buffer
  * @exception IOException If any other error occurs
  */
public final void
readFully(byte[] buf) throws EOFException, IOException
{
  readFully(buf, 0, buf.length);
}

/*************************************************************************/

/**
  * This method reads raw bytes into the passed array @code{buf} starting
  * @code{offset} bytes into the buffer.  The number of bytes read will be
  * exactly @code{len}.  Note that this method blocks until the data is 
  * available and * throws an exception if there is not enough data left in 
  * the stream to read @code{len} bytes.
  *
  * @param buf The buffer into which to read the data
  * @param offset The offset into the buffer to start storing data
  * @param len The number of bytes to read into the buffer
  *
  * @exception EOFException If end of file is reached before filling the buffer
  * @exception IOException If any other error occurs
  */
public final void
readFully(byte[] buf, int offset, int len) throws EOFException, IOException
{
  int total_read = 0;

  while (total_read < len)
   {
     int bytes_read = in.read(buf, offset + total_read, len - total_read);
     if (bytes_read == -1)
       throw new EOFException("Unexpected end of stream");

     total_read += bytes_read;
   }
}

/*************************************************************************/

/**
  * This method attempts to skip and discard the specified number of bytes 
  * in the input stream.  It may actually skip fewer bytes than requested. 
  * The actual number of bytes skipped is returned.  This method will not
  * skip any bytes if passed a negative number of bytes to skip.
  *
  * @param num_bytes The requested number of bytes to skip.
  *
  * @return The number of bytes actually skipped.
  *
  * @exception IOException If an error occurs.
  */
public final int
skipBytes(int n) throws EOFException, IOException
{
  long total_skipped = in.skip(n);

  return((int)n);
}

} // interface DataInput