Menu

[r4509]: / trunk / drjava / src / edu / rice / cs / util / StringOps.java  Maximize  Restore  History

Download this file

922 lines (836 with data), 33.7 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
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
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
/*BEGIN_COPYRIGHT_BLOCK
*
* Copyright (c) 2001-2008, JavaPLT group at Rice University (drjava@rice.edu)
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the names of DrJava, the JavaPLT group, Rice University, nor the
* names of its contributors may be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* This software is Open Source Initiative approved Open Source Software.
* Open Source Initative Approved is a trademark of the Open Source Initiative.
*
* This file is part of DrJava. Download the current version of this project
* from http://www.drjava.org/ or http://sourceforge.net/projects/drjava/
*
* END_COPYRIGHT_BLOCK*/
package edu.rice.cs.util;
import edu.rice.cs.plt.tuple.Pair;
import edu.rice.cs.drjava.config.*;
import java.io.StringWriter;
import java.io.PrintWriter;
import java.text.DecimalFormat;
import java.io.StreamTokenizer;
import java.io.StringReader;
import java.util.Map;
import java.util.Enumeration;
import java.util.Properties;
import java.util.ArrayList;
import java.util.List;
import java.util.HashMap;
import java.io.IOException;
/**
* A class to provide some convenient String operations as static methods.
* It's abstract to prevent (useless) instantiation, though it can be subclassed
* to provide convenient namespace importation of its methods.
* @version $Id$
*/
public abstract class StringOps {
public static final String EOL = System.getProperty("line.separator");
/** Takes theString fullString and replaces all instances of toReplace with replacement.
* TODO: deprecate and used corresponding String method added in Java 5.0.
*/
public static String replace (String fullString, String toReplace, String replacement) {
int index = 0;
int pos;
int fullStringLength = fullString.length();
int toReplaceLength = toReplace.length();
if (toReplaceLength > 0) {
int replacementLength = replacement.length();
StringBuilder buff;
while (index < fullStringLength &&
((pos = fullString.indexOf(toReplace, index)) >= 0)) {
buff = new StringBuilder(fullString.substring(0, pos));
buff.append(replacement);
buff.append(fullString.substring(pos + toReplaceLength, fullStringLength));
index = pos + replacementLength;
fullString = buff.toString();
fullStringLength = fullString.length();
}
}
return fullString;
}
/** Converts the given string to a valid Java string literal.
* All back slashes, quotes, new-lines, and tabs are converted
* to their escap character form, and the sourounding quotes
* are added.
* @param s the normal string to turn into a string literal
* @return the valid Java string literal
*/
public static String convertToLiteral(String s) {
String output = s;
output = replace(output, "\\", "\\\\"); // convert \ to \\
output = replace(output, "\"", "\\\""); // convert " to \"
output = replace(output, "\t", "\\t"); // convert [tab] to \t
output = replace(output, "\n", "\\n"); // convert [newline] to \n
return "\"" + output + "\"";
}
/** Verifies that (startRow, startCol) occurs before (endRow, endCol).
* @throws IllegalArgumentException if end is before start
*/
private static void _ensureStartBeforeEnd(int startRow, int startCol,
int endRow, int endCol) {
if (startRow > endRow) {
throw new IllegalArgumentException("end row before start row: " +
startRow + " > " + endRow);
}
else if (startRow == endRow && startCol > endCol) {
throw new IllegalArgumentException("end before start: (" +
startRow + ", " + startCol +
") > (" + endRow + ", " + endCol + ")");
}
}
/** Verifies that the given column position is within the row at rowStartIndex
* in the given String.
* @param fullString the string in which to check the column
* @param col the column index that should be within the row
* @param rowStartIndex the first index of the row within fullString that col should be in
* @throws IllegalArgumentException if col is after the end of the given row
*/
private static void _ensureColInRow(String fullString, int col, int rowStartIndex) {
int endOfLine = fullString.indexOf("\n",rowStartIndex);
if (endOfLine == -1) {
endOfLine = fullString.length();
}
if (col > (endOfLine - rowStartIndex)) {
throw new IllegalArgumentException("the given column is past the end of its row");
}
}
/** Gets the offset and length equivalent to the given pairs start and end row-col.
* @param fullString the string in which to compute the offset/length
* @param startRow the row on which the error starts, starting at one for the first row
* @param startCol the col on which the error starts, starting at one for the first column
* @param endRow the row on which the error ends. Equals the startRow for one-line errors
* @param endCol the character position on which the error ends. Equals the startCol for one-character errors.
* @return a Pair of which the first is the offset, the second is the length
*/
public static Pair<Integer,Integer> getOffsetAndLength(String fullString, int startRow,
int startCol, int endRow, int endCol) {
_ensureStartBeforeEnd(startRow, startCol, endRow, endCol);
// find the offset
int currentChar = 0;
int linesSeen = 1;
while (startRow > linesSeen) {
currentChar = fullString.indexOf("\n",currentChar);
if (currentChar == -1) {
throw new IllegalArgumentException("startRow is beyond the end of the string");
}
// Must move past the newline
currentChar++;
linesSeen++;
}
_ensureColInRow(fullString, startCol, currentChar);
int offset = currentChar + startCol - 1; // offset is zero-based
// find the length
while (endRow > linesSeen) {
currentChar = fullString.indexOf("\n",currentChar);
if (currentChar == -1) {
throw new IllegalArgumentException("endRow is beyond the end of the string");
}
currentChar++;
linesSeen++;
}
_ensureColInRow(fullString, endCol, currentChar);
int length = currentChar + endCol - offset;
// ensure the length is in bounds
if (offset + length > fullString.length()) {
throw new IllegalArgumentException("Given positions beyond the end of the string");
}
return new Pair<Integer,Integer>(Integer.valueOf(offset), Integer.valueOf(length));
}
/** Gets the stack trace of the given Throwable as a String.
* @param t the throwable object for which to get the stack trace
* @return the stack trace of the given Throwable
*/
public static String getStackTrace(Throwable t) {
StringWriter sw = new StringWriter();
PrintWriter pw = new PrintWriter(sw);
t.printStackTrace(pw);
return sw.toString();
}
/** Gets the stack trace of the current code. Does not include this method.
* @return the stack trace for the current code
*/
public static String getStackTrace() {
try { throw new Exception(); } // Thread.getStackTrace() might be more efficient, but is new in Java 5.0
catch (Exception e) {
StringWriter sw = new StringWriter();
PrintWriter pw = new PrintWriter(sw);
StackTraceElement[] stes = e.getStackTrace();
int skip = 1;
for(StackTraceElement ste: stes) {
if (skip>0) { --skip; } else { pw.print("at "); pw.println(ste); }
}
return sw.toString();
}
}
/** Character.isDigit answers <tt>true</tt> to some non-ascii
* digits. This one does not.
*/
public static boolean isAsciiDigit(char c) {
return '0' <= c && c <= '9';
}
/** Returns true if the class is an anonymous inner class.
* This works just like Class.isAnonymousClass() in Java 5.0 but is not version-specific.
* @param c class to check
* @return true if anonymous inner class
*/
public static boolean isAnonymousClass(Class c) {
String simpleName = c.getName();
int idx = simpleName.lastIndexOf('$');
if (idx >= 0) {
// see if we have just numbers after the $
for (int pos=idx+1; pos < simpleName.length(); ++pos) {
if (!isAsciiDigit(simpleName.charAt(pos))) {
return false;
}
}
return true;
}
return false;
}
/** Returns true if the class is a member class.
* This works just like Class.isMemberClass() in Java 5.0 but is not version-specific.
* @param c class to check
* @return true if member class
*/
public static boolean isMemberClass(Class c) {
String simpleName = c.getName();
int idx = simpleName.lastIndexOf('$');
if (idx == -1) {
return false;
}
return !isAnonymousClass(c);
}
/** Returns the simple class name.
* This works just like Class.getSimpleName() in Java 5.0 but is not version-specific.
* @param c class for which to get the simple name
* @return simple name
*/
public static String getSimpleName(Class c) {
if (c.isArray())
return getSimpleName(c.getComponentType())+"[]";
if (isAnonymousClass(c)) {
return "";
}
String simpleName = c.getName();
int idx = Math.max(simpleName.lastIndexOf('.'),
simpleName.lastIndexOf('$'));
return simpleName.substring(idx + 1); // strip the package name
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(long[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(int[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(short[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(char[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(byte[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(boolean[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(float[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(double[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
buf.append('[');
buf.append(a[0]);
for (int i = 1; i < a.length; i++) {
buf.append(", ");
buf.append(a[i]);
}
buf.append("]");
return buf.toString();
}
/** This works just like java.util.Arrays.toString in Java 5.0 but is not version-specific.
*/
public static String toString(Object[] a) {
if (a == null)
return "null";
if (a.length == 0)
return "[]";
final StringBuilder buf = new StringBuilder();
for (int i = 0; i < a.length; i++) {
if (i == 0)
buf.append('[');
else
buf.append(", ");
buf.append(String.valueOf(a[i]));
}
buf.append("]");
return buf.toString();
}
/** Encode &, <, > and newlines as HTML entities.
* @param s string to encode
* @return encoded string
*/
public static String encodeHTML(String s) {
s = StringOps.replace(s, "&", "&amp;");
s = StringOps.replace(s, "<", "&lt;");
s = StringOps.replace(s, ">", "&gt;");
s = StringOps.replace(s, EOL,"<br>");
s = StringOps.replace(s, "\n","<br>");
return s;
}
/** Return a string representing the approximate amount of memory specified in bytes.
* @param l memory in bytes
* @return string approximating the amount of memory
*/
public static String memSizeToString(long l) {
String[] sizes = new String[] { "byte", "kilobyte", "megabyte", "gigabyte" };
double d = l;
int i = 0;
while((d >= 1024) && (i < sizes.length)) {
++i;
d /= 1024;
}
if (i >= sizes.length) { i = sizes.length - 1; }
StringBuilder sb = new StringBuilder();
long whole = (long)d;
if (whole == d) {
if (whole == 1) {
sb.append(whole);
sb.append(' ');
sb.append(sizes[i]);
}
else {
sb.append(whole);
sb.append(' ');
sb.append(sizes[i]);
sb.append('s');
}
}
else {
// two decimal digits
DecimalFormat df = new DecimalFormat("#.00");
sb.append(df.format(d));
sb.append(' ');
sb.append(sizes[i]);
sb.append('s');
}
return sb.toString();
}
// public static edu.rice.cs.util.Log LOG = new edu.rice.cs.util.Log("stringops.txt", true);
/** Escapes spaces ' ' with the sequence "\u001b ", and a single '\u001b' with a double.
* '\u001b' was picked because its ASCII meaning is 'escape', and it should be platform-independent.
* @param s string to encode
* @return encoded string */
public static String escapeSpacesWith1bHex(String s) {
StringBuilder sb = new StringBuilder();
for (int i=0; i<s.length(); ++i) {
if (s.charAt(i)=='\u001b') {
sb.append("\u001b\u001b");
}
else if (s.charAt(i)==' ') {
sb.append("\u001b ");
}
else {
sb.append(""+s.charAt(i));
}
}
return sb.toString();
}
/** Unescapes spaces the sequence "\u001b " to a space ' ', and a double '\u001b' to a single.
* '\u001b' was picked because its ASCII meaning is 'escape', and it should be platform-independent.
* @param s string to encode
* @return encoded string */
public static String unescapeSpacesWith1bHex(String s) {
StringBuilder sb = new StringBuilder();
for (int i=0; i<s.length(); ++i) {
if (s.charAt(i)=='\u001b') {
if (i+1<s.length()) {
char next = s.charAt(i+1);
if (next=='\u001b') { sb.append("\u001b"); ++i; }
else if (next==' ') { sb.append(" "); ++i; }
else { throw new IllegalArgumentException("1b hex followed by neither space nor another 1b hex"); }
}
else { throw new IllegalArgumentException("1b hex followed by neither space nor another 1b hex"); }
}
else {
sb.append(""+s.charAt(i));
}
}
return sb.toString();
}
/** Convert a command line into a list of individual arguments.
* This keeps quoted parts together using ", ' and `.
* It also keeps treats a '\u001b' followed by a space as non-breaking space.
* And a double '\u001b' becomes a single '\u001b'.
* It does not allow escaping of the quote characters. */
public static List<String> commandLineToList(String cmdline) {
StreamTokenizer tok = new StreamTokenizer(new StringReader(cmdline));
tok.resetSyntax();
tok.ordinaryChars(0,255);
tok.quoteChar('\'');
tok.quoteChar('"');
tok.quoteChar('`');
tok.slashSlashComments(false);
tok.slashStarComments(false);
ArrayList<String> cmds = new ArrayList<String>();
boolean justEscape = false;
StringBuilder sb = new StringBuilder();
int next;
try {
while(((next=tok.nextToken())!=StreamTokenizer.TT_EOF) &&
(next!=StreamTokenizer.TT_EOL)) {
switch(next) {
case '\u001b':
if (justEscape) {
sb.append('\u001b');
justEscape = false;
}
else {
justEscape = true;
}
break;
case ' ':
if (justEscape) {
sb.append(' ');
}
else {
cmds.add(sb.toString());
sb = new StringBuilder();
}
justEscape = false;
break;
case '\'':
case '"':
case '`':
sb.append(""+((char)next)+tok.sval+((char)next));
justEscape = false;
break;
default:
sb.append(""+((char)next));
break;
}
}
if (sb.length()>0) { cmds.add(sb.toString()); }
}
catch(IOException ioe) {
return new ArrayList<String>();
}
return cmds;
}
/** Convert a command line into a list of list of lists of individual
* arguments. The outermost list is a list of list of lists of arguments
* for processes separated by ProcessChain.PROCESS_SEPARATOR (either ';'
* or ':', depending on which is NOT File.pathSeparatorChar).
* The lists contained in the outermost list are lists of lists of
* arguments for processes in the same piping chain, i.e. processes
* separated by '|'.
* The innermost lists are lists of arguments for the individual
* processes.
* This method keeps quoted parts together using ", ' and `.
* It also keeps treats a '\u001b' followed by a space as non-breaking space.
* And a double '\u001b' becomes a single '\u001b'.
* It does not allow escaping of the quote characters. */
public static List<List<List<String>>> commandLineToLists(String cmdline) {
BalancingStreamTokenizer tok = new BalancingStreamTokenizer(new StringReader(cmdline));
tok.wordRange(0,255);
tok.addQuotes("${", "}");
tok.addQuotes("\"", "\"");
tok.addQuotes("'", "'");
tok.addQuotes("`", "`");
tok.addKeyword(ProcessChain.PROCESS_SEPARATOR);
tok.addKeyword(ProcessChain.PIPE_SEPARATOR);
// add whitespace characters as keyword, as per Character.isWhitespace
tok.addKeyword(" ");
tok.addKeyword(new Character((char)0x09).toString()); // horizontal tab
tok.addKeyword(new Character((char)0x0A).toString()); // line feed
tok.addKeyword(new Character((char)0x0B).toString()); // vertical tab
tok.addKeyword(new Character((char)0x0C).toString()); // form feed / Character.SPACE_SEPARATOR
tok.addKeyword(new Character((char)0x0D).toString()); // carriage return / Character.LINE_SEPARATOR
tok.addKeyword(new Character((char)0x0E).toString()); // carriage return / Character.PARAGRAPH_SEPARATOR
tok.addKeyword(new Character((char)0x1C).toString()); // file separator
tok.addKeyword(new Character((char)0x1D).toString()); // group separator
tok.addKeyword(new Character((char)0x1E).toString()); // record separator
tok.addKeyword(new Character((char)0x1F).toString()); // unit separator
// read tokens; concatenate tokens until keyword is found
String n = null, p = null;
BalancingStreamTokenizer.Token pTok = BalancingStreamTokenizer.Token.NONE;
StringBuilder sb = new StringBuilder();
List<List<List<String>>> lll = new ArrayList<List<List<String>>>();
List<List<String>> ll = new ArrayList<List<String>>();
List<String> l = new ArrayList<String>();
try {
while((n=tok.getNextToken())!=null) {
if (tok.token()==BalancingStreamTokenizer.Token.KEYWORD) {
if (n.equals(ProcessChain.PROCESS_SEPARATOR)) {
// add the current string to the argument list and start a new argument
String arg = sb.toString();
sb.setLength(0);
if (arg.length()>0) { l.add(arg); }
// add the current list of arguments to the list of list and start a new
// argument list
ll.add(l);
l = new ArrayList<String>();
// add the current list of list to the outermost list and start a new
// list of lists
lll.add(ll);
ll = new ArrayList<List<String>>();
}
else if (n.equals(ProcessChain.PIPE_SEPARATOR)) {
// add the current string to the argument list and start a new argument
String arg = sb.toString();
sb.setLength(0);
if (arg.length()>0) { l.add(arg); }
// add the current list of arguments to the list of list and start a new
// argument list
ll.add(l);
l = new ArrayList<String>();
}
else { // must be whitespace
// add the current string to the argument list and start a new argument
String arg = sb.toString();
sb.setLength(0);
if (arg.length()>0) { l.add(arg); }
}
}
else {
sb.append(n);
}
p = n;
}
}
catch(IOException e) { /* ignore, return what we have */ }
// add the current string to the argument list and start a new argument
String arg = sb.toString();
sb.setLength(0);
if (arg.length()>0) { l.add(arg); }
// add the current list of arguments to the list of list and start a new
// argument list
ll.add(l);
l = new ArrayList<String>();
// add the current list of list to the outermost list and start a new
// list of lists
lll.add(ll);
ll = new ArrayList<List<String>>();
return lll;
}
/** Replace variables of the form "${variable}" with the value associated with the string "variable" in the
* provided hash table.
* To give the "$" character its literal meaning, it needs to be escaped as "\$" (backslash dollar).
* To make the "\" character not escaping, escape it as "\\"(double backslash).
* @param str input string
* @param props map with maps of variable-value pairs
* @param getter lambda from a DrJavaProperty to String
* @return string with variables replaced by values
*/
public static String replaceVariables(String str, final PropertyMaps props, final Lambda<String,DrJavaProperty> getter) {
BalancingStreamTokenizer tok = new BalancingStreamTokenizer(new StringReader(str), '$');
tok.wordRange(0,255);
tok.addQuotes("${", "}");
tok.addQuotes("\"", "\"");
// LOG.log("---------");
// LOG.log("Replacing: "+str);
StringBuilder sb = new StringBuilder();
String next = null;
try {
while((next=tok.getNextToken())!=null) {
// LOG.log("Token: "+next);
if ((tok.token()==BalancingStreamTokenizer.Token.QUOTED) &&
(next.startsWith("${")) &&
(next.endsWith("}"))) {
// LOG.log("Found property: "+next);
String key;
String attrList = "";
int firstCurly = next.indexOf('}');
int firstSemi = next.indexOf(';');
if (firstSemi<0) {
// format: ${property.name}
// for key, cut off ${ and }
key = next.substring(2,firstCurly);
}
else {
// format: {$property.name;...}
// for key, cut off ${ and ;...}
key = next.substring(2,firstSemi);
// for attribute list, cut off ${propertyname; and }
attrList = next.substring(firstSemi+1,next.length()-1).trim();
}
// LOG.log("\tKey = '"+key+"'");
// LOG.log("\tAttrList = '"+attrList+"'");
DrJavaProperty p = props.getProperty(key);
if (p!=null) {
// found property name
p.resetAttributes();
// if we have a list of attributes
try {
if (attrList.length()>0) {
BalancingStreamTokenizer atok = new BalancingStreamTokenizer(new StringReader(attrList), '$');
atok.wordRange(0,255);
atok.whitespaceRange(0,32);
atok.addQuotes("\"", "\"");
atok.addQuotes("${", "}");
atok.addKeyword(";");
atok.addKeyword("=");
// LOG.log("\tProcessing AttrList");
String n = null;
HashMap<String,String> attrs = new HashMap<String,String>();
while((n=atok.getNextToken())!=null) {
if ((n==null) || (atok.token()!=BalancingStreamTokenizer.Token.NORMAL) ||
n.equals(";") || n.equals("=") || n.startsWith("\"")) {
throw new IllegalArgumentException("Unknown attribute list format for property "+key+"; expected name, but was "+n);
}
String name = n;
// LOG.log("\t\tname = '"+name+"'");
n = atok.getNextToken();
if ((n==null) || (atok.token()!=BalancingStreamTokenizer.Token.KEYWORD) || (!n.equals("="))) {
throw new IllegalArgumentException("Unknown attribute list format for property "+key+"; expected =, but was "+n);
}
// LOG.log("\t\tread '='");
n = atok.getNextToken();
if ((n==null) || (atok.token()!=BalancingStreamTokenizer.Token.QUOTED) || (!n.startsWith("\""))) {
throw new IllegalArgumentException("Unknown attribute list format for property "+key+"; expected \", but was "+n);
}
String value = "";
if (n.length()>1) {
value = n.substring(1,n.length()-1);
// LOG.log("\t\tvalue = '"+value+"'");
}
n = atok.getNextToken();
if (((n!=null) && ((atok.token()!=BalancingStreamTokenizer.Token.KEYWORD) || (!n.equals(";")))) ||
((n==null) && (atok.token()!=BalancingStreamTokenizer.Token.END))) {
throw new IllegalArgumentException("Unknown attribute list format for property "+key);
}
// LOG.log("\t\tread ';' or EOF");
// processed correctly
// LOG.log("\t\treplacing variables in '"+value+"'...");
// String replacedValue = replaceVariables(value, props, getter);
// LOG.log("\t\treplaced value is '"+replacedValue+"'");
attrs.put(name,value);
// p.setAttribute(name, replacedValue);
if (n==null) { break; }
}
p.setAttributes(attrs, new Lambda<String,String>() {
public String apply(String param) {
return replaceVariables(param, props, getter);
}
});
}
// append the value of the property, e.g. /home/user instead of "${property.name}"
String finalValue = getter.apply(p);
// LOG.log("\tfinal value: '"+finalValue+"'");
sb.append(finalValue);
}
catch(IllegalArgumentException e) {
sb.append("<-- Error: "+e.getMessage()+" -->");
}
}
else {
// unknown property
sb.append(next);
}
}
else {
sb.append(next);
}
}
}
catch(IllegalArgumentException e) {
return "<-- Error: "+e.getMessage()+" -->";
}
catch(IOException e) {
return "<-- Error: "+e.getMessage()+" -->";
}
// LOG.log("Returning '"+sb.toString()+"'");
// LOG.log("---------");
return sb.toString();
}
/** Split a string into lines at a certain width, at word boundaries.
* @param s string to split
* @param widthInChars approximate width of the new lines
* @param lineBreak string to be inserted at line breaks
* @param wordSepChars string of characters that can serve as word separators
*/
public static String splitStringAtWordBoundaries(String s, int widthInChars,
String lineBreak,
String wordSepChars) {
StringBuilder sb = new StringBuilder();
// remove word separators at the beginning of the string
while(s.length()>0) {
if (wordSepChars.indexOf(String.valueOf(s.charAt(0)))>=0) {
// System.out.println("Removing leading separator...");
s = s.substring(1);
}
else { break; /* first character that is not a separator */ }
}
// remove word separators at the end of the string
while(s.length()>0) {
if (wordSepChars.indexOf(String.valueOf(s.charAt(s.length()-1)))>=0) {
// System.out.println("Removing trailing separator...");
s = s.substring(0, s.length()-1);
}
else { break; /* first character that is not a separator */ }
}
// System.out.println("Removed all leading and trailing separator chars");
// System.out.println("String: "+s);
java.util.StringTokenizer tok = new java.util.StringTokenizer(s, wordSepChars);
StringBuilder sbl = new StringBuilder(); // current line
// System.out.println("hasMoreElements? "+tok.hasMoreElements());
while(tok.hasMoreElements()) {
String token = tok.nextToken();
// System.out.println("\ttoken: "+token);
sbl.append(token);
// System.out.println("\tline (length="+sbl.length()+"): "+sbl.toString());
if (sbl.length()>=widthInChars) {
// System.out.println("\tnewline");
// System.out.println("\t\thasMoreElements? "+tok.hasMoreElements());
if (tok.hasMoreElements()) {
// System.out.println("\t\tinserting line break");
sbl.append(lineBreak);
}
// System.out.println("\t\tFinal line: "+sbl.toString());
sb.append(sbl.toString());
// System.out.println("\t\tEntire buffer: "+sb.toString());
sbl.setLength(0);
}
else { sbl.append(" "); }
}
// System.out.println("No more tokens. Last line: "+sbl.toString());
if (sbl.length()>0) { sb.append(sbl.toString()); }
// System.out.println("Final entire buffer: "+sb.toString());
return sb.toString();
}
}
MongoDB Logo MongoDB