summaryrefslogtreecommitdiff
path: root/indra/llcommon/llstring.cpp
blob: 0d50919e26ec5af7fe4cc783f0e24c5b53b1a0d7 (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
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
/** 
 * @file llstring.cpp
 * @brief String utility functions and the std::string class.
 *
 * $LicenseInfo:firstyear=2001&license=viewergpl$
 * 
 * Copyright (c) 2001-2007, Linden Research, Inc.
 * 
 * Second Life Viewer Source Code
 * The source code in this file ("Source Code") is provided by Linden Lab
 * to you under the terms of the GNU General Public License, version 2.0
 * ("GPL"), unless you have obtained a separate licensing agreement
 * ("Other License"), formally executed by you and Linden Lab.  Terms of
 * the GPL can be found in doc/GPL-license.txt in this distribution, or
 * online at http://secondlife.com/developers/opensource/gplv2
 * 
 * There are special exceptions to the terms and conditions of the GPL as
 * it is applied to this Source Code. View the full text of the exception
 * in the file doc/FLOSS-exception.txt in this software distribution, or
 * online at http://secondlife.com/developers/opensource/flossexception
 * 
 * By copying, modifying or distributing this software, you acknowledge
 * that you have read and understood your obligations described above,
 * and agree to abide by those obligations.
 * 
 * ALL LINDEN LAB SOURCE CODE IS PROVIDED "AS IS." LINDEN LAB MAKES NO
 * WARRANTIES, EXPRESS, IMPLIED OR OTHERWISE, REGARDING ITS ACCURACY,
 * COMPLETENESS OR PERFORMANCE.
 * $/LicenseInfo$
 */

#include "linden_common.h"

#include "llstring.h"
#include "llerror.h"

#if LL_WINDOWS
#define WIN32_LEAN_AND_MEAN
#include <winsock2.h>
#include <windows.h>
#include <winnls.h> // for WideCharToMultiByte
#endif

std::string ll_safe_string(const char* in)
{
	if(in) return std::string(in);
	return std::string();
}

std::string ll_safe_string(const char* in, S32 maxlen)
{
	if(in) return std::string(in, maxlen);
	return std::string();
}

U8 hex_as_nybble(char hex)
{
	if((hex >= '0') && (hex <= '9'))
	{
		return (U8)(hex - '0');
	}
	else if((hex >= 'a') && (hex <='f'))
	{
		return (U8)(10 + hex - 'a');
	}
	else if((hex >= 'A') && (hex <='F'))
	{
		return (U8)(10 + hex - 'A');
	}
	return 0; // uh - oh, not hex any more...
}


bool _read_file_into_string(std::string& str, const std::string& filename)
{
	llifstream ifs(filename, llifstream::binary);
	if (!ifs.is_open())
	{
		llinfos << "Unable to open file " << filename << llendl;
		return false;
	}

	std::ostringstream oss;

	oss << ifs.rdbuf();
	str = oss.str();
	ifs.close();
	return true;
}




// See http://www.unicode.org/Public/BETA/CVTUTF-1-2/ConvertUTF.c
// for the Unicode implementation - this doesn't match because it was written before finding
// it.


std::ostream& operator<<(std::ostream &s, const LLWString &wstr)
{
	std::string utf8_str = wstring_to_utf8str(wstr);
	s << utf8_str;
	return s;
}

std::string rawstr_to_utf8(const std::string& raw)
{
	LLWString wstr(utf8str_to_wstring(raw));
	return wstring_to_utf8str(wstr);
}

S32 wchar_to_utf8chars(llwchar in_char, char* outchars)
{
	U32 cur_char = (U32)in_char;
	char* base = outchars;
	if (cur_char < 0x80)
	{
		*outchars++ = (U8)cur_char;
	}
	else if (cur_char < 0x800)
	{
		*outchars++ = 0xC0 | (cur_char >> 6);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else if (cur_char < 0x10000)
	{
		*outchars++ = 0xE0 | (cur_char >> 12);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | (cur_char & 0x3F);
	}
	else if (cur_char < 0x200000)
	{
		*outchars++ = 0xF0 | (cur_char >> 18);
		*outchars++ = 0x80 | ((cur_char >> 12) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | cur_char & 0x3F;
	}
	else if (cur_char < 0x4000000)
	{
		*outchars++ = 0xF8 | (cur_char >> 24);
		*outchars++ = 0x80 | ((cur_char >> 18) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 12) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | cur_char & 0x3F;
	}
	else if (cur_char < 0x80000000)
	{
		*outchars++ = 0xFC | (cur_char >> 30);
		*outchars++ = 0x80 | ((cur_char >> 24) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 18) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 12) & 0x3F);
		*outchars++ = 0x80 | ((cur_char >> 6) & 0x3F);
		*outchars++ = 0x80 | cur_char & 0x3F;
	}
	else
	{
		llwarns << "Invalid Unicode character " << cur_char << "!" << llendl;
		*outchars++ = LL_UNKNOWN_CHAR;
	}
	return outchars - base;
}	

S32 utf16chars_to_wchar(const U16* inchars, llwchar* outchar)
{
	const U16* base = inchars;
	U16 cur_char = *inchars++;
	llwchar char32 = cur_char;
	if ((cur_char >= 0xD800) && (cur_char <= 0xDFFF))
	{
		// Surrogates
		char32 = ((llwchar)(cur_char - 0xD800)) << 10;
		cur_char = *inchars++;
		char32 += (llwchar)(cur_char - 0xDC00) + 0x0010000UL;
	}
	else
	{
		char32 = (llwchar)cur_char;
	}
	*outchar = char32;
	return inchars - base;
}

llutf16string wstring_to_utf16str(const LLWString &utf32str, S32 len)
{
	llutf16string out;

	S32 i = 0;
	while (i < len)
	{
		U32 cur_char = utf32str[i];
		if (cur_char > 0xFFFF)
		{
			out += (0xD7C0 + (cur_char >> 10));
			out += (0xDC00 | (cur_char & 0x3FF));
		}
		else
		{
			out += cur_char;
		}
		i++;
	}
	return out;
}

llutf16string wstring_to_utf16str(const LLWString &utf32str)
{
	const S32 len = (S32)utf32str.length();
	return wstring_to_utf16str(utf32str, len);
}

llutf16string utf8str_to_utf16str ( const std::string& utf8str )
{
	LLWString wstr = utf8str_to_wstring ( utf8str );
	return wstring_to_utf16str ( wstr );
}


LLWString utf16str_to_wstring(const llutf16string &utf16str, S32 len)
{
	LLWString wout;
	if((len <= 0) || utf16str.empty()) return wout;

	S32 i = 0;
	// craziness to make gcc happy (llutf16string.c_str() is tweaked on linux):
	const U16* chars16 = &(*(utf16str.begin()));
	while (i < len)
	{
		llwchar cur_char;
		i += utf16chars_to_wchar(chars16+i, &cur_char);
		wout += cur_char;
	}
	return wout;
}

LLWString utf16str_to_wstring(const llutf16string &utf16str)
{
	const S32 len = (S32)utf16str.length();
	return utf16str_to_wstring(utf16str, len);
}

// Length in llwchar (UTF-32) of the first len units (16 bits) of the given UTF-16 string.
S32 utf16str_wstring_length(const llutf16string &utf16str, const S32 utf16_len)
{
	S32 surrogate_pairs = 0;
	// ... craziness to make gcc happy (llutf16string.c_str() is tweaked on linux):
	const U16 *const utf16_chars = &(*(utf16str.begin()));
	S32 i = 0;
	while (i < utf16_len)
	{
		const U16 c = utf16_chars[i++];
		if (c >= 0xD800 && c <= 0xDBFF)		// See http://en.wikipedia.org/wiki/UTF-16
		{   // Have first byte of a surrogate pair
			if (i >= utf16_len)
			{
				break;
			}
			const U16 d = utf16_chars[i];
			if (d >= 0xDC00 && d <= 0xDFFF)
			{   // Have valid second byte of a surrogate pair
				surrogate_pairs++;
				i++;
			}
		}
	}
	return utf16_len - surrogate_pairs;
}

// Length in utf16string (UTF-16) of wlen wchars beginning at woffset.
S32 wstring_utf16_length(const LLWString &wstr, const S32 woffset, const S32 wlen)
{
	const S32 end = llmin((S32)wstr.length(), woffset + wlen);
	if (end < woffset)
	{
		return 0;
	}
	else
	{
		S32 length = end - woffset;
		for (S32 i = woffset; i < end; i++)
		{
			if (wstr[i] >= 0x10000)
			{
				length++;
			}
		}
		return length;
	}
}

// Given a wstring and an offset in it, returns the length as wstring (i.e.,
// number of llwchars) of the longest substring that starts at the offset
// and whose equivalent utf-16 string does not exceeds the given utf16_length.
S32 wstring_wstring_length_from_utf16_length(const LLWString & wstr, const S32 woffset, const S32 utf16_length, BOOL *unaligned)
{
	const S32 end = wstr.length();
	BOOL u = FALSE;
	S32 n = woffset + utf16_length;
	S32 i = woffset;
	while (i < end)
	{
		if (wstr[i] >= 0x10000)
		{
			--n;
		}
		if (i >= n)
		{
			u = (i > n);
			break;
		}
		i++;
	}
	if (unaligned)
	{
		*unaligned = u;
	}
	return i - woffset;
}

S32 wchar_utf8_length(const llwchar wc)
{
	if (wc < 0x80)
	{
		// This case will also catch negative values which are
		// technically invalid.
		return 1;
	}
	else if (wc < 0x800)
	{
		return 2;
	}
	else if (wc < 0x10000)
	{
		return 3;
	}
	else if (wc < 0x200000)
	{
		return 4;
	}
	else if (wc < 0x4000000)
	{
		return 5;
	}
	else
	{
		return 6;
	}
}


S32 wstring_utf8_length(const LLWString& wstr)
{
	S32 len = 0;
	for (S32 i = 0; i < (S32)wstr.length(); i++)
	{
		len += wchar_utf8_length(wstr[i]);
	}
	return len;
}


LLWString utf8str_to_wstring(const std::string& utf8str, S32 len)
{
	LLWString wout;

	S32 i = 0;
	while (i < len)
	{
		llwchar unichar;
		U8 cur_char = utf8str[i];

		if (cur_char < 0x80)
		{
			// Ascii character, just add it
			unichar = cur_char;
		}
		else
		{
			S32 cont_bytes = 0;
			if ((cur_char >> 5) == 0x6)			// Two byte UTF8 -> 1 UTF32
			{
				unichar = (0x1F&cur_char);
				cont_bytes = 1;
			}
			else if ((cur_char >> 4) == 0xe)	// Three byte UTF8 -> 1 UTF32
			{
				unichar = (0x0F&cur_char);
				cont_bytes = 2;
			}
			else if ((cur_char >> 3) == 0x1e)	// Four byte UTF8 -> 1 UTF32
			{
				unichar = (0x07&cur_char);
				cont_bytes = 3;
			}
			else if ((cur_char >> 2) == 0x3e)	// Five byte UTF8 -> 1 UTF32
			{
				unichar = (0x03&cur_char);
				cont_bytes = 4;
			}
			else if ((cur_char >> 1) == 0x7e)	// Six byte UTF8 -> 1 UTF32
			{
				unichar = (0x01&cur_char);
				cont_bytes = 5;
			}
			else
			{
				wout += LL_UNKNOWN_CHAR;
				++i;
				continue;
			}

			// Check that this character doesn't go past the end of the string
			S32 end = (len < (i + cont_bytes)) ? len : (i + cont_bytes);
			do
			{
				++i;

				cur_char = utf8str[i];
				if ( (cur_char >> 6) == 0x2 )
				{
					unichar <<= 6;
					unichar += (0x3F&cur_char);
				}
				else
				{
					// Malformed sequence - roll back to look at this as a new char
					unichar = LL_UNKNOWN_CHAR;
					--i;
					break;
				}
			} while(i < end);

			// Handle overlong characters and NULL characters
			if ( ((cont_bytes == 1) && (unichar < 0x80))
				|| ((cont_bytes == 2) && (unichar < 0x800))
				|| ((cont_bytes == 3) && (unichar < 0x10000))
				|| ((cont_bytes == 4) && (unichar < 0x200000))
				|| ((cont_bytes == 5) && (unichar < 0x4000000)) )
			{
				unichar = LL_UNKNOWN_CHAR;
			}
		}

		wout += unichar;
		++i;
	}
	return wout;
}

LLWString utf8str_to_wstring(const std::string& utf8str)
{
	const S32 len = (S32)utf8str.length();
	return utf8str_to_wstring(utf8str, len);
}

std::string wstring_to_utf8str(const LLWString& utf32str, S32 len)
{
	std::string out;

	S32 i = 0;
	while (i < len)
	{
		char tchars[8];		/* Flawfinder: ignore */
		S32 n = wchar_to_utf8chars(utf32str[i], tchars);
		tchars[n] = 0;
		out += tchars;
		i++;
	}
	return out;
}

std::string wstring_to_utf8str(const LLWString& utf32str)
{
	const S32 len = (S32)utf32str.length();
	return wstring_to_utf8str(utf32str, len);
}

std::string utf16str_to_utf8str(const llutf16string& utf16str)
{
	return wstring_to_utf8str(utf16str_to_wstring(utf16str));
}

std::string utf16str_to_utf8str(const llutf16string& utf16str, S32 len)
{
	return wstring_to_utf8str(utf16str_to_wstring(utf16str, len), len);
}

std::string utf8str_trim(const std::string& utf8str)
{
	LLWString wstr = utf8str_to_wstring(utf8str);
	LLWStringUtil::trim(wstr);
	return wstring_to_utf8str(wstr);
}


std::string utf8str_tolower(const std::string& utf8str)
{
	LLWString out_str = utf8str_to_wstring(utf8str);
	LLWStringUtil::toLower(out_str);
	return wstring_to_utf8str(out_str);
}


S32 utf8str_compare_insensitive(const std::string& lhs, const std::string& rhs)
{
	LLWString wlhs = utf8str_to_wstring(lhs);
	LLWString wrhs = utf8str_to_wstring(rhs);
	return LLWStringUtil::compareInsensitive(wlhs, wrhs);
}

std::string utf8str_truncate(const std::string& utf8str, const S32 max_len)
{
	if (0 == max_len)
	{
		return std::string();
	}
	if ((S32)utf8str.length() <= max_len)
	{
		return utf8str;
	}
	else
	{
		S32 cur_char = max_len;

		// If we're ASCII, we don't need to do anything
		if ((U8)utf8str[cur_char] > 0x7f)
		{
			// If first two bits are (10), it's the tail end of a multibyte char.  We need to shift back
			// to the first character
			while (0x80 == (0xc0 & utf8str[cur_char]))
			{
				cur_char--;
				// Keep moving forward until we hit the first char;
				if (cur_char == 0)
				{
					// Make sure we don't trash memory if we've got a bogus string.
					break;
				}
			}
		}
		// The byte index we're on is one we want to get rid of, so we only want to copy up to (cur_char-1) chars
		return utf8str.substr(0, cur_char);
	}
}

std::string utf8str_substChar(
	const std::string& utf8str,
	const llwchar target_char,
	const llwchar replace_char)
{
	LLWString wstr = utf8str_to_wstring(utf8str);
	LLWStringUtil::replaceChar(wstr, target_char, replace_char);
	//wstr = wstring_substChar(wstr, target_char, replace_char);
	return wstring_to_utf8str(wstr);
}

std::string utf8str_makeASCII(const std::string& utf8str)
{
	LLWString wstr = utf8str_to_wstring(utf8str);
	LLWStringUtil::_makeASCII(wstr);
	return wstring_to_utf8str(wstr);
}

std::string mbcsstring_makeASCII(const std::string& wstr)
{
	// Replace non-ASCII chars with replace_char
	std::string out_str = wstr;
	for (S32 i = 0; i < (S32)out_str.length(); i++)
	{
		if ((U8)out_str[i] > 0x7f)
		{
			out_str[i] = LL_UNKNOWN_CHAR;
		}
	}
	return out_str;
}
std::string utf8str_removeCRLF(const std::string& utf8str)
{
	if (0 == utf8str.length())
	{
		return std::string();
	}
	const char CR = 13;

	std::string out;
	out.reserve(utf8str.length());
	const S32 len = (S32)utf8str.length();
	for( S32 i = 0; i < len; i++ )
	{
		if( utf8str[i] != CR )
		{
			out.push_back(utf8str[i]);
		}
	}
	return out;
}

#if LL_WINDOWS
// documentation moved to header. Phoenix 2007-11-27
namespace snprintf_hack
{
	int snprintf(char *str, size_t size, const char *format, ...)
	{
		va_list args;
		va_start(args, format);

		int num_written = _vsnprintf(str, size, format, args); /* Flawfinder: ignore */
		va_end(args);
		
		str[size-1] = '\0'; // always null terminate
		return num_written;
	}
}

std::string ll_convert_wide_to_string(const wchar_t* in)
{
	std::string out;
	if(in)
	{
		int len_in = wcslen(in);
		int len_out = WideCharToMultiByte(
			CP_ACP,
			0,
			in,
			len_in,
			NULL,
			0,
			0,
			0);
		// We will need two more bytes for the double NULL ending
		// created in WideCharToMultiByte().
		char* pout = new char [len_out + 2];
		memset(pout, 0, len_out + 2);
		if(pout)
		{
			WideCharToMultiByte(
				CP_ACP,
				0,
				in,
				len_in,
				pout,
				len_out,
				0,
				0);
			out.assign(pout);
			delete[] pout;
		}
	}
	return out;
}
#endif // LL_WINDOWS

S32	LLStringOps::collate(const llwchar* a, const llwchar* b)
{ 
	#if LL_WINDOWS
		// in Windows, wide string functions operator on 16-bit strings, 
		// not the proper 32 bit wide string
		return strcmp(wstring_to_utf8str(LLWString(a)).c_str(), wstring_to_utf8str(LLWString(b)).c_str());
	#else
		return wcscoll(a, b);
	#endif
}

namespace LLStringFn
{
	void replace_nonprintable(std::basic_string<char>& string, char replacement)
	{
		const char MIN = 0x20;
		std::basic_string<char>::size_type len = string.size();
		for(std::basic_string<char>::size_type ii = 0; ii < len; ++ii)
		{
			if(string[ii] < MIN)
			{
				string[ii] = replacement;
			}
		}
	}

	void replace_nonprintable(
		std::basic_string<llwchar>& string,
		llwchar replacement)
	{
		const llwchar MIN = 0x20;
		const llwchar MAX = 0x7f;
		std::basic_string<llwchar>::size_type len = string.size();
		for(std::basic_string<llwchar>::size_type ii = 0; ii < len; ++ii)
		{
			if((string[ii] < MIN) || (string[ii] > MAX))
			{
				string[ii] = replacement;
			}
		}
	}

	void replace_nonprintable_and_pipe(std::basic_string<char>& str,
									   char replacement)
	{
		const char MIN  = 0x20;
		const char PIPE = 0x7c;
		std::basic_string<char>::size_type len = str.size();
		for(std::basic_string<char>::size_type ii = 0; ii < len; ++ii)
		{
			if( (str[ii] < MIN) || (str[ii] == PIPE) )
			{
				str[ii] = replacement;
			}
		}
	}

	void replace_nonprintable_and_pipe(std::basic_string<llwchar>& str,
									   llwchar replacement)
	{
		const llwchar MIN  = 0x20;
		const llwchar MAX  = 0x7f;
		const llwchar PIPE = 0x7c;
		std::basic_string<llwchar>::size_type len = str.size();
		for(std::basic_string<llwchar>::size_type ii = 0; ii < len; ++ii)
		{
			if( (str[ii] < MIN) || (str[ii] > MAX) || (str[ii] == PIPE) )
			{
				str[ii] = replacement;
			}
		}
	}

	// https://wiki.lindenlab.com/wiki/Unicode_Guidelines has details on
	// allowable code points for XML. Specifically, they are:
	// 0x09, 0x0a, 0x0d, and 0x20 on up.  JC
	std::string strip_invalid_xml(const std::string& input)
	{
		std::string output;
		output.reserve( input.size() );
		std::string::const_iterator it = input.begin();
		while (it != input.end())
		{
			// Must compare as unsigned for >=
			// Test most likely match first
			const unsigned char c = (unsigned char)*it;
			if (   c >= (unsigned char)0x20   // SPACE
				|| c == (unsigned char)0x09   // TAB
				|| c == (unsigned char)0x0a   // LINE_FEED
				|| c == (unsigned char)0x0d ) // CARRIAGE_RETURN
			{
				output.push_back(c);
			}
			++it;
		}
		return output;
	}

}


////////////////////////////////////////////////////////////
// Testing

#ifdef _DEBUG

template<class T> 
void LLStringUtilBase<T>::testHarness()
{
	std::string s1;
	
	llassert( s1.c_str() == NULL );
	llassert( s1.size() == 0 );
	llassert( s1.empty() );
	
	std::string s2( "hello");
	llassert( !strcmp( s2.c_str(), "hello" ) );
	llassert( s2.size() == 5 ); 
	llassert( !s2.empty() );
	std::string s3( s2 );

	llassert( "hello" == s2 );
	llassert( s2 == "hello" );
	llassert( s2 > "gello" );
	llassert( "gello" < s2 );
	llassert( "gello" != s2 );
	llassert( s2 != "gello" );

	std::string s4 = s2;
	llassert( !s4.empty() );
	s4.empty();
	llassert( s4.empty() );
	
	std::string s5("");
	llassert( s5.empty() );
	
	llassert( isValidIndex(s5, 0) );
	llassert( !isValidIndex(s5, 1) );
	
	s3 = s2;
	s4 = "hello again";
	
	s4 += "!";
	s4 += s4;
	llassert( s4 == "hello again!hello again!" );
	
	
	std::string s6 = s2 + " " + s2;
	std::string s7 = s6;
	llassert( s6 == s7 );
	llassert( !( s6 != s7) );
	llassert( !(s6 < s7) );
	llassert( !(s6 > s7) );
	
	llassert( !(s6 == "hi"));
	llassert( s6 == "hello hello");
	llassert( s6 < "hi");
	
	llassert( s6[1] == 'e' );
	s6[1] = 'f';
	llassert( s6[1] == 'f' );
	
	s2.erase( 4, 1 );
	llassert( s2 == "hell");
	s2.insert( 0, 'y' );
	llassert( s2 == "yhell");
	s2.erase( 1, 3 );
	llassert( s2 == "yl");
	s2.insert( 1, "awn, don't yel");
	llassert( s2 == "yawn, don't yell");
	
	std::string s8 = s2.substr( 6, 5 );
	llassert( s8 == "don't"  );
	
	std::string s9 = "   \t\ntest  \t\t\n  ";
	trim(s9);
	llassert( s9 == "test"  );

	s8 = "abc123&*(ABC";

	s9 = s8;
	toUpper(s9);
	llassert( s9 == "ABC123&*(ABC"  );

	s9 = s8;
	toLower(s9);
	llassert( s9 == "abc123&*(abc"  );


	std::string s10( 10, 'x' );
	llassert( s10 == "xxxxxxxxxx" );

	std::string s11( "monkey in the middle", 7, 2 );
	llassert( s11 == "in" );

	std::string s12;  //empty
	s12 += "foo";
	llassert( s12 == "foo" );

	std::string s13;  //empty
	s13 += 'f';
	llassert( s13 == "f" );
}


#endif  // _DEBUG