FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
JavaRes/src/atp/StreamTokenizer_s.java at master · eprover/JavaRes · GitHub
Uh oh!
There was an error while loading.
Please reload this page
.
eprover
/
JavaRes
Public
Notifications
You must be signed in to change notification settings
Fork
1
Star
1
Code
Issues
0
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
JavaRes
/
src
/
atp
/
StreamTokenizer_s.java
Copy path
More file actions
More file actions
Latest commit
History
History
History
819 lines (765 loc) · 27.1 KB
Breadcrumbs
JavaRes
/
src
/
atp
/
StreamTokenizer_s.java
Copy path
File metadata and controls
819 lines (765 loc) · 27.1 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
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
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
package
atp
;
/** This code is copyright Articulate Software (c) 2003. Some portions
copyright Teknowledge (c) 2003 and reused under the terms of the GNU license.
This software is released under the GNU Public License <http://www.gnu.org/copyleft/gpl.html>.
Users of this code also consent, by use of this code, to credit Articulate Software
and Teknowledge in any writings, briefings, publications, presentations, or
other representations of any software which incorporates, builds on, or uses this
code. Please cite the following article in any publication with references:
Pease, A., (2003). The Sigma Ontology Development Environment,
in Working Notes of the IJCAI-2003 Workshop on Ontology and Distributed Systems,
August 9, Acapulco, Mexico. See also http://sigmakee.sourceforge.net
Note that this is a copy of the com.articulate.sigma.StreamTokenizer_s class
and should not be modified. Is is included in ATP just to simplify
configuration and compilation.
*/
import
java
.
io
.*;
/**
* The <code>StreamTokenizer_s</code> class takes an input stream and
* parses it into "tokens", allowing the tokens to be
* read one at a time. The parsing process is controlled by a table
* and a number of flags that can be set to various states. The
* stream tokenizer can recognize identifiers, numbers, quoted
* strings, and various comment styles.
* <p>
* Each byte read from the input stream is regarded as a character
* in the range <code>'\u0000'</code> through <code>'\u00FF'</code>.
* The character value is used to look up five possible attributes of
* the character: <i>white space</i>, <i>alphabetic</i>,
* <i>numeric</i>, <i>string quote</i>, and <i>comment character</i>.
* Each character can have zero or more of these attributes.
* <p>
* In addition, an instance has four flags. These flags indicate:
* <ul>
* <li>Whether line terminators are to be returned as tokens or treated
* as white space that merely separates tokens.
* <li>Whether C-style comments are to be recognized and skipped.
* <li>Whether C++-style comments are to be recognized and skipped.
* <li>Whether the characters of identifiers are converted to lowercase.
* </ul>
* <p>
* A typical application first constructs an instance of this class,
* sets up the syntax tables, and then repeatedly loops calling the
* <code>nextToken</code> method in each iteration of the loop until
* it returns the value <code>TT_EOF</code>.
*
* @author James Gosling
* @version 1.37, 12/03/01
* @see java.io.StreamTokenizer_s#nextToken()
* @see java.io.StreamTokenizer_s#TT_EOF
* @since JDK1.0
*/
/**
* A modified StreamTokenizer that handles multi-line
* quoted strings.
*/
public
class
StreamTokenizer_s
{
/* Only one of these will be non-null */
private
Reader
reader
=
null
;
private
InputStream
input
=
null
;
private
char
buf
[] =
new
char
[
20
];
/**
* The next character to be considered by the nextToken method. May also
* be NEED_CHAR to indicate that a new character should be read, or SKIP_LF
* to indicate that a new character should be read and, if it is a '\n'
* character, it should be discarded and a second new character should be
* read.
*/
private
int
peekc
=
NEED_CHAR
;
private
static
final
int
NEED_CHAR
=
Integer
.
MAX_VALUE
;
private
static
final
int
SKIP_LF
=
Integer
.
MAX_VALUE
-
1
;
private
boolean
pushedBack
;
private
boolean
forceLower
;
/** The line number of the last token read */
private
int
LINENO
=
1
;
private
boolean
eolIsSignificantP
=
false
;
private
boolean
slashSlashCommentsP
=
false
;
private
boolean
slashStarCommentsP
=
false
;
private
byte
ctype
[] =
new
byte
[
256
];
private
static
final
byte
CT_WHITESPACE
=
1
;
private
static
final
byte
CT_DIGIT
=
2
;
private
static
final
byte
CT_ALPHA
=
4
;
private
static
final
byte
CT_QUOTE
=
8
;
private
static
final
byte
CT_COMMENT
=
16
;
/**
* After a call to the <code>nextToken</code> method, this field
* contains the type of the token just read. For a single character
* token, its value is the single character, converted to an integer.
* For a quoted string token (see , its value is the quote character.
* Otherwise, its value is one of the following:
* <ul>
* <li><code>TT_WORD</code> indicates that the token is a word.
* <li><code>TT_NUMBER</code> indicates that the token is a number.
* <li><code>TT_EOL</code> indicates that the end of line has been read.
* The field can only have this value if the
* <code>eolIsSignificant</code> method has been called with the
* argument <code>true</code>.
* <li><code>TT_EOF</code> indicates that the end of the input stream
* has been reached.
* </ul>
* <p>
* The initial value of this field is -4.
*
* @see java.io.StreamTokenizer_s#eolIsSignificant(boolean)
* @see java.io.StreamTokenizer_s#nextToken()
* @see java.io.StreamTokenizer_s#quoteChar(int)
* @see java.io.StreamTokenizer_s#TT_EOF
* @see java.io.StreamTokenizer_s#TT_EOL
* @see java.io.StreamTokenizer_s#TT_NUMBER
* @see java.io.StreamTokenizer_s#TT_WORD
*/
public
int
ttype
=
TT_NOTHING
;
/**
* A constant indicating that the end of the stream has been read.
*/
public
static
final
int
TT_EOF
= -
1
;
/**
* A constant indicating that the end of the line has been read.
*/
public
static
final
int
TT_EOL
=
'\n'
;
/**
* A constant indicating that a number token has been read.
*/
public
static
final
int
TT_NUMBER
= -
2
;
/**
* A constant indicating that a word token has been read.
*/
public
static
final
int
TT_WORD
= -
3
;
/* A constant indicating that no token has been read, used for
* initializing ttype. FIXME This could be made public and
* made available as the part of the API in a future release.
*/
private
static
final
int
TT_NOTHING
= -
4
;
/**
* If the current token is a word token, this field contains a
* string giving the characters of the word token. When the current
* token is a quoted string token, this field contains the body of
* the string.
* <p>
* The current token is a word when the value of the
* <code>ttype</code> field is <code>TT_WORD</code>. The current token is
* a quoted string token when the value of the <code>ttype</code> field is
* a quote character.
* <p>
* The initial value of this field is null.
*
* @see java.io.StreamTokenizer_s#quoteChar(int)
* @see java.io.StreamTokenizer_s#TT_WORD
* @see java.io.StreamTokenizer_s#ttype
*/
public
String
sval
;
/**
* If the current token is a number, this field contains the value
* of that number. The current token is a number when the value of
* the <code>ttype</code> field is <code>TT_NUMBER</code>.
* <p>
* The initial value of this field is 0.0.
*
* @see java.io.StreamTokenizer_s#TT_NUMBER
* @see java.io.StreamTokenizer_s#ttype
*/
public
double
nval
;
/** Private constructor that initializes everything except the streams. */
private
StreamTokenizer_s
() {
wordChars
(
'a'
,
'z'
);
wordChars
(
'A'
,
'Z'
);
wordChars
(
128
+
32
,
255
);
whitespaceChars
(
0
,
' '
);
commentChar
(
'/'
);
quoteChar
(
'"'
);
quoteChar
(
'\''
);
// parseNumbers();
}
/**
* Creates a stream tokenizer that parses the specified input
* stream. The stream tokenizer is initialized to the following
* default state:
* <ul>
* <li>All byte values <code>'A'</code> through <code>'Z'</code>,
* <code>'a'</code> through <code>'z'</code>, and
* <code>'\u00A0'</code> through <code>'\u00FF'</code> are
* considered to be alphabetic.
* <li>All byte values <code>'\u0000'</code> through
* <code>'\u0020'</code> are considered to be white space.
* <li><code>'/'</code> is a comment character.
* <li>Single quote <code>'\''</code> and double quote <code>'"'</code>
* are string quote characters.
* <li>Numbers are parsed.
* <li>Ends of lines are treated as white space, not as separate tokens.
* <li>C-style and C++-style comments are not recognized.
* </ul>
*
* @deprecated As of JDK version 1.1, the preferred way to tokenize an
* input stream is to convert it into a character stream, for example:
* <blockquote><pre>
* Reader r = new BufferedReader(new InputStreamReader(is));
* StreamTokenizer_s st = new StreamTokenizer_s(r);
* </pre></blockquote>
*
* @param is an input stream.
* @see java.io.BufferedReader
* @see java.io.InputStreamReader
* @see java.io.StreamTokenizer_s#StreamTokenizer_s(java.io.Reader)
*/
public
StreamTokenizer_s
(
InputStream
is
) {
this
();
if
(
is
==
null
) {
throw
new
NullPointerException
();
}
input
=
is
;
}
/**
* Create a tokenizer that parses the given character stream.
*
* @param r a Reader object providing the input stream.
* @since JDK1.1
*/
public
StreamTokenizer_s
(
Reader
r
) {
this
();
if
(
r
==
null
) {
throw
new
NullPointerException
();
}
reader
=
r
;
}
/**
* Resets this tokenizer's syntax table so that all characters are
* "ordinary." See the <code>ordinaryChar</code> method
* for more information on a character being ordinary.
*
* @see java.io.StreamTokenizer_s#ordinaryChar(int)
*/
public
void
resetSyntax
() {
for
(
int
i
=
ctype
.
length
; --
i
>=
0
;)
ctype
[
i
] =
0
;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are word constituents. A word token consists of a word constituent
* followed by zero or more word constituents or number constituents.
*
* @param low the low end of the range.
* @param hi the high end of the range.
*/
public
void
wordChars
(
int
low
,
int
hi
) {
if
(
low
<
0
)
low
=
0
;
if
(
hi
>=
ctype
.
length
)
hi
=
ctype
.
length
-
1
;
while
(
low
<=
hi
)
ctype
[
low
++] |=
CT_ALPHA
;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are white space characters. White space characters serve only to
* separate tokens in the input stream.
*
* @param low the low end of the range.
* @param hi the high end of the range.
*/
public
void
whitespaceChars
(
int
low
,
int
hi
) {
if
(
low
<
0
)
low
=
0
;
if
(
hi
>=
ctype
.
length
)
hi
=
ctype
.
length
-
1
;
while
(
low
<=
hi
)
ctype
[
low
++] =
CT_WHITESPACE
;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are "ordinary" in this tokenizer. See the
* <code>ordinaryChar</code> method for more information on a
* character being ordinary.
*
* @param low the low end of the range.
* @param hi the high end of the range.
* @see java.io.StreamTokenizer_s#ordinaryChar(int)
*/
public
void
ordinaryChars
(
int
low
,
int
hi
) {
if
(
low
<
0
)
low
=
0
;
if
(
hi
>=
ctype
.
length
)
hi
=
ctype
.
length
-
1
;
while
(
low
<=
hi
)
ctype
[
low
++] =
0
;
}
/**
* Specifies that the character argument is "ordinary"
* in this tokenizer. It removes any special significance the
* character has as a comment character, word component, string
* delimiter, white space, or number character. When such a character
* is encountered by the parser, the parser treates it as a
* single-character token and sets <code>ttype</code> field to the
* character value.
*
* @param ch the character.
* @see java.io.StreamTokenizer_s#ttype
*/
public
void
ordinaryChar
(
int
ch
) {
if
(
ch
>=
0
&&
ch
<
ctype
.
length
)
ctype
[
ch
] =
0
;
}
/**
* Specified that the character argument starts a single-line
* comment. All characters from the comment character to the end of
* the line are ignored by this stream tokenizer.
*
* @param ch the character.
*/
public
void
commentChar
(
int
ch
) {
if
(
ch
>=
0
&&
ch
<
ctype
.
length
)
ctype
[
ch
] =
CT_COMMENT
;
}
/**
* Specifies that matching pairs of this character delimit string
* constants in this tokenizer.
* <p>
* When the <code>nextToken</code> method encounters a string
* constant, the <code>ttype</code> field is set to the string
* delimiter and the <code>sval</code> field is set to the body of
* the string.
* <p>
* If a string quote character is encountered, then a string is
* recognized, consisting of all characters after (but not including)
* the string quote character, up to (but not including) the next
* occurrence of that same string quote character, or a line
* terminator, or end of file. The usual escape sequences such as
* <code>"\n"</code> and <code>"\t"</code> are recognized and
* converted to single characters as the string is parsed.
*
* @param ch the character.
* @see java.io.StreamTokenizer_s#nextToken()
* @see java.io.StreamTokenizer_s#sval
* @see java.io.StreamTokenizer_s#ttype
*/
public
void
quoteChar
(
int
ch
) {
if
(
ch
>=
0
&&
ch
<
ctype
.
length
)
ctype
[
ch
] =
CT_QUOTE
;
}
/**
* Specifies that numbers should be parsed by this tokenizer. The
* syntax table of this tokenizer is modified so that each of the twelve
* characters:
* <blockquote><pre>
* 0 1 2 3 4 5 6 7 8 9 . -
* </pre></blockquote>
* <p>
* has the "numeric" attribute.
* <p>
* When the parser encounters a word token that has the format of a
* double precision floating-point number, it treats the token as a
* number rather than a word, by setting the the <code>ttype</code>
* field to the value <code>TT_NUMBER</code> and putting the numeric
* value of the token into the <code>nval</code> field.
*
* @see java.io.StreamTokenizer_s#nval
* @see java.io.StreamTokenizer_s#TT_NUMBER
* @see java.io.StreamTokenizer_s#ttype
*/
public
void
parseNumbers
() {
for
(
int
i
=
'0'
;
i
<=
'9'
;
i
++)
ctype
[
i
] |=
CT_DIGIT
;
ctype
[
'.'
] |=
CT_DIGIT
;
ctype
[
'-'
] |=
CT_DIGIT
;
}
/**
* Determines whether or not ends of line are treated as tokens.
* If the flag argument is true, this tokenizer treats end of lines
* as tokens; the <code>nextToken</code> method returns
* <code>TT_EOL</code> and also sets the <code>ttype</code> field to
* this value when an end of line is read.
* <p>
* A line is a sequence of characters ending with either a
* carriage-return character (<code>'\r'</code>) or a newline
* character (<code>'\n'</code>). In addition, a carriage-return
* character followed immediately by a newline character is treated
* as a single end-of-line token.
* <p>
* If the <code>flag</code> is false, end-of-line characters are
* treated as white space and serve only to separate tokens.
*
* @param flag <code>true</code> indicates that end-of-line characters
* are separate tokens; <code>false</code> indicates that
* end-of-line characters are white space.
* @see java.io.StreamTokenizer_s#nextToken()
* @see java.io.StreamTokenizer_s#ttype
* @see java.io.StreamTokenizer_s#TT_EOL
*/
public
void
eolIsSignificant
(
boolean
flag
) {
eolIsSignificantP
=
flag
;
}
/**
* Determines whether or not the tokenizer recognizes C-style comments.
* If the flag argument is <code>true</code>, this stream tokenizer
* recognizes C-style comments. All text between successive
* occurrences of <code>/*</code> and <code>*/</code> are discarded.
* <p>
* If the flag argument is <code>false</code>, then C-style comments
* are not treated specially.
*
* @param flag <code>true</code> indicates to recognize and ignore
* C-style comments.
*/
public
void
slashStarComments
(
boolean
flag
) {
slashStarCommentsP
=
flag
;
}
/**
* Determines whether or not the tokenizer recognizes C++-style comments.
* If the flag argument is <code>true</code>, this stream tokenizer
* recognizes C++-style comments. Any occurrence of two consecutive
* slash characters (<code>'/'</code>) is treated as the beginning of
* a comment that extends to the end of the line.
* <p>
* If the flag argument is <code>false</code>, then C++-style
* comments are not treated specially.
*
* @param flag <code>true</code> indicates to recognize and ignore
* C++-style comments.
*/
public
void
slashSlashComments
(
boolean
flag
) {
slashSlashCommentsP
=
flag
;
}
/**
* Determines whether or not word token are automatically lowercased.
* If the flag argument is <code>true</code>, then the value in the
* <code>sval</code> field is lowercased whenever a word token is
* returned (the <code>ttype</code> field has the
* value <code>TT_WORD</code> by the <code>nextToken</code> method
* of this tokenizer.
* <p>
* If the flag argument is <code>false</code>, then the
* <code>sval</code> field is not modified.
*
* @param fl <code>true</code> indicates that all word tokens should
* be lowercased.
* @see java.io.StreamTokenizer_s#nextToken()
* @see java.io.StreamTokenizer_s#ttype
* @see java.io.StreamTokenizer_s#TT_WORD
*/
public
void
lowerCaseMode
(
boolean
fl
) {
forceLower
=
fl
;
}
/** Read the next character */
private
int
read
()
throws
IOException
{
if
(
reader
!=
null
)
return
reader
.
read
();
else
if
(
input
!=
null
)
return
input
.
read
();
else
throw
new
IllegalStateException
();
}
/**
* Parses the next token from the input stream of this tokenizer.
* The type of the next token is returned in the <code>ttype</code>
* field. Additional information about the token may be in the
* <code>nval</code> field or the <code>sval</code> field of this
* tokenizer.
* <p>
* Typical clients of this
* class first set up the syntax tables and then sit in a loop
* calling nextToken to parse successive tokens until TT_EOF
* is returned.
*
* @return the value of the <code>ttype</code> field.
* @exception IOException if an I/O error occurs.
* @see java.io.StreamTokenizer_s#nval
* @see java.io.StreamTokenizer_s#sval
* @see java.io.StreamTokenizer_s#ttype
*/
public
int
nextToken
()
throws
IOException
{
if
(
pushedBack
) {
pushedBack
=
false
;
return
ttype
;
}
byte
ct
[] =
ctype
;
sval
=
null
;
int
c
=
peekc
;
if
(
c
<
0
)
c
=
NEED_CHAR
;
if
(
c
==
SKIP_LF
) {
c
=
read
();
if
(
c
<
0
)
return
ttype
=
TT_EOF
;
if
(
c
==
'\n'
)
c
=
NEED_CHAR
;
}
if
(
c
==
NEED_CHAR
) {
c
=
read
();
if
(
c
<
0
)
return
ttype
=
TT_EOF
;
}
ttype
=
c
;
/* Just to be safe */
/* Set peekc so that the next invocation of nextToken will read
* another character unless peekc is reset in this invocation
*/
peekc
=
NEED_CHAR
;
int
ctype
=
c
<
256
?
ct
[
c
] :
CT_ALPHA
;
while
((
ctype
&
CT_WHITESPACE
) !=
0
) {
if
(
c
==
'\r'
) {
LINENO
++;
if
(
eolIsSignificantP
) {
peekc
=
SKIP_LF
;
return
ttype
=
TT_EOL
;
}
c
=
read
();
if
(
c
==
'\n'
)
c
=
read
();
}
else
{
if
(
c
==
'\n'
) {
LINENO
++;
if
(
eolIsSignificantP
) {
return
ttype
=
TT_EOL
;
}
}
c
=
read
();
}
if
(
c
<
0
)
return
ttype
=
TT_EOF
;
ctype
=
c
<
256
?
ct
[
c
] :
CT_ALPHA
;
}
if
((
ctype
&
CT_DIGIT
) !=
0
) {
boolean
neg
=
false
;
if
(
c
==
'-'
) {
c
=
read
();
if
(
c
!=
'.'
&& (
c
<
'0'
||
c
>
'9'
)) {
peekc
=
c
;
return
ttype
=
'-'
;
}
neg
=
true
;
}
double
v
=
0
;
int
decexp
=
0
;
int
seendot
=
0
;
while
(
true
) {
if
(
c
==
'.'
&&
seendot
==
0
)
seendot
=
1
;
else
if
(
'0'
<=
c
&&
c
<=
'9'
) {
v
=
v
*
10
+ (
c
-
'0'
);
decexp
+=
seendot
;
}
else
break
;
c
=
read
();
}
peekc
=
c
;
if
(
decexp
!=
0
) {
double
denom
=
10
;
decexp
--;
while
(
decexp
>
0
) {
denom
*=
10
;
decexp
--;
}
/* Do one division of a likely-to-be-more-accurate number */
v
=
v
/
denom
;
}
nval
=
neg
? -
v
:
v
;
return
ttype
=
TT_NUMBER
;
}
if
((
ctype
&
CT_ALPHA
) !=
0
) {
int
i
=
0
;
do
{
if
(
i
>=
buf
.
length
) {
char
nb
[] =
new
char
[
buf
.
length
*
2
];
System
.
arraycopy
(
buf
,
0
,
nb
,
0
,
buf
.
length
);
buf
=
nb
;
}
buf
[
i
++] = (
char
)
c
;
c
=
read
();
ctype
=
c
<
0
?
CT_WHITESPACE
:
c
<
256
?
ct
[
c
] :
CT_ALPHA
;
}
while
((
ctype
& (
CT_ALPHA
|
CT_DIGIT
)) !=
0
);
peekc
=
c
;
sval
=
String
.
copyValueOf
(
buf
,
0
,
i
);
if
(
forceLower
)
sval
=
sval
.
toLowerCase
();
return
ttype
=
TT_WORD
;
}
if
((
ctype
&
CT_QUOTE
) !=
0
) {
ttype
=
c
;
int
i
=
0
;
/* Invariants (because \Octal needs a lookahead):
* (i) c contains char value
* (ii) d contains the lookahead
*/
int
d
=
read
();
// while (d >= 0 && d != ttype && d != '\n' && d != '\r') {
while
(
d
>=
0
&&
d
!=
ttype
) {
if
(
d
==
'\\'
) {
c
=
read
();
int
first
=
c
;
/* To allow \377, but not \477 */
if
(
c
>=
'0'
&&
c
<=
'7'
) {
c
=
c
-
'0'
;
int
c2
=
read
();
if
(
'0'
<=
c2
&&
c2
<=
'7'
) {
c
= (
c
<<
3
) + (
c2
-
'0'
);
c2
=
read
();
if
(
'0'
<=
c2
&&
c2
<=
'7'
&&
first
<=
'3'
) {
c
= (
c
<<
3
) + (
c2
-
'0'
);
d
=
read
();
}
else
d
=
c2
;
}
else
d
=
c2
;
}
else
{
switch
(
c
) {
case
'a'
:
c
=
0x7
;
break
;
case
'b'
:
c
=
'\b'
;
break
;
case
'f'
:
c
=
0xC
;
break
;
case
'n'
:
c
=
'\n'
;
break
;
case
'r'
:
c
=
'\r'
;
break
;
case
't'
:
c
=
'\t'
;
break
;
case
'v'
:
c
=
0xB
;
break
;
}
d
=
read
();
}
}
else
{
c
=
d
;
d
=
read
();
}
if
(
i
>=
buf
.
length
) {
char
nb
[] =
new
char
[
buf
.
length
*
2
];
System
.
arraycopy
(
buf
,
0
,
nb
,
0
,
buf
.
length
);
buf
=
nb
;
}
buf
[
i
++] = (
char
)
c
;
}
/* If we broke out of the loop because we found a matching quote
* character then arrange to read a new character next time
* around; otherwise, save the character.
*/
peekc
= (
d
==
ttype
) ?
NEED_CHAR
:
d
;
sval
=
String
.
copyValueOf
(
buf
,
0
,
i
);
return
ttype
;
}
if
(
c
==
'/'
&& (
slashSlashCommentsP
||
slashStarCommentsP
)) {
c
=
read
();
if
(
c
==
'*'
&&
slashStarCommentsP
) {
int
prevc
=
0
;
while
((
c
=
read
()) !=
'/'
||
prevc
!=
'*'
) {
if
(
c
==
'\r'
) {
LINENO
++;
c
=
read
();
if
(
c
==
'\n'
) {
c
=
read
();
}
}
else
{
if
(
c
==
'\n'
) {
LINENO
++;
c
=
read
();
}
}
if
(
c
<
0
)
return
ttype
=
TT_EOF
;
prevc
=
c
;
}
return
nextToken
();
}
else
if
(
c
==
'/'
&&
slashSlashCommentsP
) {
while
((
c
=
read
()) !=
'\n'
&&
c
!=
'\r'
&&
c
>=
0
);
peekc
=
c
;
return
nextToken
();
}
else
{
/* Now see if it is still a single line comment */
if
((
ct
[
'/'
] &
CT_COMMENT
) !=
0
) {
while
((
c
=
read
()) !=
'\n'
&&
c
!=
'\r'
&&
c
>=
0
);
peekc
=
c
;
return
nextToken
();
}
else
{
peekc
=
c
;
return
ttype
=
'/'
;
}
}
}
if
((
ctype
&
CT_COMMENT
) !=
0
) {
while
((
c
=
read
()) !=
'\n'
&&
c
!=
'\r'
&&
c
>=
0
);
peekc
=
c
;
return
nextToken
();
}
return
ttype
=
c
;
}
/**
* Causes the next call to the <code>nextToken</code> method of this
* tokenizer to return the current value in the <code>ttype</code>
* field, and not to modify the value in the <code>nval</code> or
* <code>sval</code> field.
*
* @see java.io.StreamTokenizer_s#nextToken()
* @see java.io.StreamTokenizer_s#nval
* @see java.io.StreamTokenizer_s#sval
* @see java.io.StreamTokenizer_s#ttype
*/
public
void
pushBack
() {
if
(
ttype
!=
TT_NOTHING
)
/* No-op if nextToken() not called */
pushedBack
=
true
;
}
/**
* Return the current line number.
*
* @return the current line number of this stream tokenizer.
*/
public
int
lineno
() {
return
LINENO
;
}
/**
* Returns the string representation of the current stream token.
*
* @return a string representation of the token specified by the
* <code>ttype</code>, <code>nval</code>, and <code>sval</code>
* fields.
* @see java.io.StreamTokenizer_s#nval
* @see java.io.StreamTokenizer_s#sval
* @see java.io.StreamTokenizer_s#ttype
*/
public
String
toString
() {
String
ret
;
switch
(
ttype
) {
case
TT_EOF
:
ret
=
"EOF"
;
break
;
case
TT_EOL
:
ret
=
"EOL"
;
break
;
case
TT_WORD
:
ret
=
sval
;
break
;
case
TT_NUMBER
:
ret
=
"n="
+
nval
;
break
;
case
TT_NOTHING
:
ret
=
"NOTHING"
;
break
;
default
: {
/*
* ttype is the first character of either a quoted string or
* is an ordinary character. ttype can definitely not be less
* than 0, since those are reserved values used in the previous
* case statements
*/
if
(
ttype
<
256
&&
((
ctype
[
ttype
] &
CT_QUOTE
) !=
0
)) {
ret
=
sval
;
break
;
}
char
s
[] =
new
char
[
3
];
s
[
0
] =
s
[
2
] =
'\''
;
s
[
1
] = (
char
)
ttype
;
ret
=
new
String
(
s
);
break
;
}
}
return
"Token["
+
ret
+
"], line "
+
LINENO
;
}
}
Back
|
FazBrowse Home
|
New Git URL