Parent: [dc7c31] (diff)

Child: [0ccf8f] (diff)

Download this file

smallut.cpp    795 lines (738 with data), 18.5 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
#ifndef lint
static char rcsid[] = "@(#$Id: smallut.cpp,v 1.35 2008-11-19 10:06:49 dockes Exp $ (C) 2004 J.F.Dockes";
#endif
/*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* 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 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.
*/
#ifndef TEST_SMALLUT
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <ctype.h>
#include <unistd.h>
#include <errno.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <string>
#include "smallut.h"
#include "utf8iter.h"
#ifndef NO_NAMESPACES
using namespace std;
#endif /* NO_NAMESPACES */
#define MIN(A,B) ((A)<(B)?(A):(B))
int stringicmp(const string & s1, const string& s2)
{
string::const_iterator it1 = s1.begin();
string::const_iterator it2 = s2.begin();
int size1 = s1.length(), size2 = s2.length();
char c1, c2;
if (size1 > size2) {
while (it1 != s1.end()) {
c1 = ::toupper(*it1);
c2 = ::toupper(*it2);
if (c1 != c2) {
return c1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : 1;
} else {
while (it2 != s2.end()) {
c1 = ::toupper(*it1);
c2 = ::toupper(*it2);
if (c1 != c2) {
return c1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : -1;
}
}
void stringtolower(string& io)
{
string::iterator it = io.begin();
string::iterator ite = io.end();
while (it != ite) {
*it = ::tolower(*it);
it++;
}
}
string stringtolower(const string& i)
{
string o = i;
stringtolower(o);
return o;
}
extern int stringisuffcmp(const string& s1, const string& s2)
{
string::const_reverse_iterator r1 = s1.rbegin(), re1 = s1.rend(),
r2 = s2.rbegin(), re2 = s2.rend();
while (r1 != re1 && r2 != re2) {
char c1 = ::toupper(*r1);
char c2 = ::toupper(*r2);
if (c1 != c2) {
return c1 > c2 ? 1 : -1;
}
++r1; ++r2;
}
return 0;
}
// s1 is already lowercase
int stringlowercmp(const string & s1, const string& s2)
{
string::const_iterator it1 = s1.begin();
string::const_iterator it2 = s2.begin();
int size1 = s1.length(), size2 = s2.length();
char c2;
if (size1 > size2) {
while (it1 != s1.end()) {
c2 = ::tolower(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : 1;
} else {
while (it2 != s2.end()) {
c2 = ::tolower(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : -1;
}
}
// s1 is already uppercase
int stringuppercmp(const string & s1, const string& s2)
{
string::const_iterator it1 = s1.begin();
string::const_iterator it2 = s2.begin();
int size1 = s1.length(), size2 = s2.length();
char c2;
if (size1 > size2) {
while (it1 != s1.end()) {
c2 = ::toupper(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : 1;
} else {
while (it2 != s2.end()) {
c2 = ::toupper(*it2);
if (*it1 != c2) {
return *it1 > c2 ? 1 : -1;
}
++it1; ++it2;
}
return size1 == size2 ? 0 : -1;
}
}
// Compare charset names, removing the more common spelling variations
bool samecharset(const string &cs1, const string &cs2)
{
string mcs1, mcs2;
// Remove all - and _, turn to lowecase
for (unsigned int i = 0; i < cs1.length();i++) {
if (cs1[i] != '_' && cs1[i] != '-') {
mcs1 += ::tolower(cs1[i]);
}
}
for (unsigned int i = 0; i < cs2.length();i++) {
if (cs2[i] != '_' && cs2[i] != '-') {
mcs2 += ::tolower(cs2[i]);
}
}
return mcs1 == mcs2;
}
template <class T> bool stringToStrings(const string &s, T &tokens)
{
string current;
tokens.clear();
enum states {SPACE, TOKEN, INQUOTE, ESCAPE};
states state = SPACE;
for (unsigned int i = 0; i < s.length(); i++) {
switch (s[i]) {
case '"':
switch(state) {
case SPACE:
state=INQUOTE; continue;
case TOKEN:
current += '"';
continue;
case INQUOTE:
tokens.push_back(current);
current.clear();
state = SPACE;
continue;
case ESCAPE:
current += '"';
state = INQUOTE;
continue;
}
break;
case '\\':
switch(state) {
case SPACE:
case TOKEN:
current += '\\';
state=TOKEN;
continue;
case INQUOTE:
state = ESCAPE;
continue;
case ESCAPE:
current += '\\';
state = INQUOTE;
continue;
}
break;
case ' ':
case '\t':
case '\n':
case '\r':
switch(state) {
case SPACE:
continue;
case TOKEN:
tokens.push_back(current);
current.clear();
state = SPACE;
continue;
case INQUOTE:
case ESCAPE:
current += s[i];
continue;
}
break;
default:
switch(state) {
case ESCAPE:
state = INQUOTE;
break;
case SPACE:
state = TOKEN;
break;
case TOKEN:
case INQUOTE:
break;
}
current += s[i];
}
}
switch(state) {
case SPACE:
break;
case TOKEN:
tokens.push_back(current);
break;
case INQUOTE:
case ESCAPE:
return false;
}
return true;
}
bool stringToStrings(const string &s, list<string> &tokens)
{
return stringToStrings<list<string> >(s, tokens);
}
bool stringToStrings(const string &s, vector<string> &tokens)
{
return stringToStrings<vector<string> >(s, tokens);
}
template <class T> void stringsToString(const T &tokens, string &s)
{
for (typename T::const_iterator it = tokens.begin();
it != tokens.end(); it++) {
bool hasblanks = false;
if (it->find_first_of(" \t\n") != string::npos)
hasblanks = true;
if (it != tokens.begin())
s.append(1, ' ');
if (hasblanks)
s.append(1, '"');
for (unsigned int i = 0; i < it->length(); i++) {
char car = it->at(i);
if (car == '"') {
s.append(1, '\\');
s.append(1, car);
} else {
s.append(1, car);
}
}
if (hasblanks)
s.append(1, '"');
}
}
void stringsToString(const list<string> &tokens, string &s)
{
stringsToString<list<string> >(tokens, s);
}
void stringsToString(const vector<string> &tokens, string &s)
{
stringsToString<vector<string> >(tokens, s);
}
void stringsToString(const set<string> &tokens, string &s)
{
stringsToString<set<string> >(tokens, s);
}
void stringToTokens(const string& str, list<string>& tokens,
const string& delims, bool skipinit)
{
string::size_type startPos = 0, pos;
for (pos = 0;;) {
// Skip initial delims, break if this eats all.
if (skipinit &&
(startPos = str.find_first_not_of(delims, pos)) == string::npos)
break;
// Find next delimiter or end of string (end of token)
pos = str.find_first_of(delims, startPos);
// Add token to the vector. Note: token cant be empty here
if (pos == string::npos)
tokens.push_back(str.substr(startPos));
else
tokens.push_back(str.substr(startPos, pos - startPos));
}
}
bool stringToBool(const string &s)
{
if (s.empty())
return false;
if (isdigit(s[0])) {
int val = atoi(s.c_str());
return val ? true : false;
}
if (s.find_first_of("yYtT") == 0)
return true;
return false;
}
void trimstring(string &s, const char *ws)
{
string::size_type pos = s.find_first_not_of(ws);
if (pos == string::npos) {
s.clear();
return;
}
s.replace(0, pos, string());
pos = s.find_last_not_of(ws);
if (pos != string::npos && pos != s.length()-1)
s.replace(pos+1, string::npos, string());
}
// Remove some chars and replace them with spaces
string neutchars(const string &str, const string &chars)
{
string out;
neutchars(str, out, chars);
return out;
}
void neutchars(const string &str, string &out, const string& chars)
{
string::size_type startPos, pos;
for (pos = 0;;) {
// Skip initial chars, break if this eats all.
if ((startPos = str.find_first_not_of(chars, pos)) == string::npos)
break;
// Find next delimiter or end of string (end of token)
pos = str.find_first_of(chars, startPos);
// Add token to the output. Note: token cant be empty here
if (pos == string::npos) {
out += str.substr(startPos);
} else {
out += str.substr(startPos, pos - startPos) + " ";
}
}
}
/* Truncate a string to a given maxlength, avoiding cutting off midword
* if reasonably possible. Note: we could also use textsplit, stopping when
* we have enough, this would be cleanly utf8-aware but would remove
* punctuation */
static const string SEPAR = " \t\n\r-:.;,/[]{}";
string truncate_to_word(const string &input, string::size_type maxlen)
{
string output;
if (input.length() <= maxlen) {
output = input;
} else {
output = input.substr(0, maxlen);
string::size_type space = output.find_last_of(SEPAR);
// Original version only truncated at space if space was found after
// maxlen/2. But we HAVE to truncate at space, else we'd need to do
// utf8 stuff to avoid truncating at multibyte char. In any case,
// not finding space means that the text probably has no value.
// Except probably for Asian languages, so we may want to fix this
// one day
if (space == string::npos) {
output.erase();
} else {
output.erase(space);
}
output += " ...";
}
return output;
}
void utf8truncate(string &s, int maxlen)
{
if (s.size() <= string::size_type(maxlen))
return;
Utf8Iter iter(s);
int pos = 0;
while (iter++ != string::npos)
if (iter.getBpos() < string::size_type(maxlen))
pos = iter.getBpos();
s.erase(pos);
}
// Escape things that would look like markup
string escapeHtml(const string &in)
{
string out;
for (string::size_type pos = 0; pos < in.length(); pos++) {
switch(in.at(pos)) {
case '<':
out += "&lt;";
break;
case '&':
out += "&amp;";
break;
default:
out += in.at(pos);
}
}
return out;
}
string escapeShell(const string &in)
{
string out;
out += "\"";
for (string::size_type pos = 0; pos < in.length(); pos++) {
switch(in.at(pos)) {
case '$':
out += "\\$";
break;
case '`':
out += "\\`";
break;
case '"':
out += "\\\"";
break;
case '\n':
out += "\\\n";
break;
case '\\':
out += "\\\\";
break;
default:
out += in.at(pos);
}
}
out += "\"";
return out;
}
// Small utility to substitute printf-like percents cmds in a string
bool pcSubst(const string& in, string& out, map<char, string>& subs)
{
string::const_iterator it;
for (it = in.begin(); it != in.end();it++) {
if (*it == '%') {
if (++it == in.end()) {
out += '%';
break;
}
if (*it == '%') {
out += '%';
continue;
}
map<char,string>::iterator tr;
if ((tr = subs.find(*it)) != subs.end()) {
out += tr->second;
} else {
// We used to do "out += *it;" here but this does not make
// sense
}
} else {
out += *it;
}
}
return true;
}
bool pcSubst(const string& in, string& out, map<string, string>& subs)
{
out.erase();
string::size_type i;
for (i = 0; i < in.size(); i++) {
if (in[i] == '%') {
if (++i == in.size()) {
out += '%';
break;
}
if (in[i] == '%') {
out += '%';
continue;
}
string key = "";
if (in[i] == '(') {
if (++i == in.size()) {
out += string("%(");
break;
}
string::size_type j = in.find_first_of(")", i);
if (j == string::npos) {
// ??concatenate remaining part and stop
out += in.substr(i-2);
break;
}
key = in.substr(i, j-i);
i = j;
} else {
key = in[i];
}
map<string,string>::iterator tr;
if ((tr = subs.find(key)) != subs.end()) {
out += tr->second;
} else {
// Substitute to nothing, that's the reasonable thing to do
// instead of keeping the %(key)
// out += key.size()==1? key : string("(") + key + string(")");
}
} else {
out += in[i];
}
}
return true;
}
// Convert byte count into unit (KB/MB...) appropriate for display
string displayableBytes(long size)
{
char sizebuf[30];
const char * unit = " B ";
if (size > 1024 && size < 1024*1024) {
unit = " KB ";
size /= 1024;
} else if (size >= 1024*1204) {
unit = " MB ";
size /= (1024*1024);
}
sprintf(sizebuf, "%ld%s", size, unit);
return string(sizebuf);
}
string breakIntoLines(const string& in, unsigned int ll,
unsigned int maxlines)
{
string query = in;
string oq;
unsigned int nlines = 0;
while (query.length() > 0) {
string ss = query.substr(0, ll);
if (ss.length() == ll) {
string::size_type pos = ss.find_last_of(" ");
if (pos == string::npos) {
pos = query.find_first_of(" ");
if (pos != string::npos)
ss = query.substr(0, pos+1);
else
ss = query;
} else {
ss = ss.substr(0, pos+1);
}
}
// This cant happen, but anyway. Be very sure to avoid an infinite loop
if (ss.length() == 0) {
oq = query;
break;
}
oq += ss + "\n";
if (nlines++ >= maxlines) {
oq += " ... \n";
break;
}
query= query.substr(ss.length());
}
return oq;
}
////////////////////
// Internal redefinition of system time interface to help with dependancies
struct m_timespec {
time_t tv_sec;
long tv_nsec;
};
#ifndef CLOCK_REALTIME
#define CLOCK_REALTIME 1
#endif
#define MILLIS(TV) ( (long)(((TV).tv_sec - m_secs) * 1000 + \
((TV).tv_nsec - m_nsecs) / 1000000))
#define MICROS(TV) ( (long)(((TV).tv_sec - m_secs) * 1000000 + \
((TV).tv_nsec - m_nsecs) / 1000))
// We use gettimeofday instead of clock_gettime for now and get only
// uS resolution, because clock_gettime is more configuration trouble
// than it's worth
static void gettime(int, struct m_timespec *ts)
{
struct timeval tv;
gettimeofday(&tv, 0);
ts->tv_sec = tv.tv_sec;
ts->tv_nsec = tv.tv_usec * 1000;
}
///// End system interface
static m_timespec frozen_tv;
void Chrono::refnow()
{
gettime(CLOCK_REALTIME, &frozen_tv);
}
Chrono::Chrono()
{
restart();
}
// Reset and return value before rest in milliseconds
long Chrono::restart()
{
struct m_timespec tv;
gettime(CLOCK_REALTIME, &tv);
long ret = MILLIS(tv);
m_secs = tv.tv_sec;
m_nsecs = tv.tv_nsec;
return ret;
}
// Get current timer value, milliseconds
long Chrono::millis(int frozen)
{
if (frozen) {
return MILLIS(frozen_tv);
} else {
struct m_timespec tv;
gettime(CLOCK_REALTIME, &tv);
return MILLIS(tv);
}
}
//
long Chrono::micros(int frozen)
{
if (frozen) {
return MICROS(frozen_tv);
} else {
struct m_timespec tv;
gettime(CLOCK_REALTIME, &tv);
return MICROS(tv);
}
}
float Chrono::secs(int frozen)
{
struct m_timespec tv;
gettime(CLOCK_REALTIME, &tv);
float secs = (float)(frozen?frozen_tv.tv_sec:tv.tv_sec - m_secs);
float nsecs = (float)(frozen?frozen_tv.tv_nsec:tv.tv_nsec - m_nsecs);
//fprintf(stderr, "secs %.2f nsecs %.2f\n", secs, nsecs);
return secs + nsecs * 1e-9;
}
#else
#include <string>
using namespace std;
#include <iostream>
#include "smallut.h"
struct spair {
const char *s1;
const char *s2;
};
struct spair pairs[] = {
{"", ""},
{"", "a"},
{"a", ""},
{"a", "a"},
{"A", "a"},
{"a", "A"},
{"A", "A"},
{"12", "12"},
{"a", "ab"},
{"ab", "a"},
{"A", "Ab"},
{"a", "Ab"},
};
int npairs = sizeof(pairs) / sizeof(struct spair);
struct spair suffpairs[] = {
{"", ""},
{"", "a"},
{"a", ""},
{"a", "a"},
{"toto.txt", ".txt"},
{"TXT", "toto.txt"},
{"toto.txt", ".txt1"},
{"toto.txt1", ".txt"},
};
int nsuffpairs = sizeof(suffpairs) / sizeof(struct spair);
int main(int argc, char **argv)
{
#if 0
for (int i = 0; i < npairs; i++) {
{
int c = stringicmp(pairs[i].s1, pairs[i].s2);
printf("'%s' %s '%s' ", pairs[i].s1,
c == 0 ? "==" : c < 0 ? "<" : ">", pairs[i].s2);
}
{
int cl = stringlowercmp(pairs[i].s1, pairs[i].s2);
printf("L '%s' %s '%s' ", pairs[i].s1,
cl == 0 ? "==" : cl < 0 ? "<" : ">", pairs[i].s2);
}
{
int cu = stringuppercmp(pairs[i].s1, pairs[i].s2);
printf("U '%s' %s '%s' ", pairs[i].s1,
cu == 0 ? "==" : cu < 0 ? "<" : ">", pairs[i].s2);
}
printf("\n");
}
#elif 0
for (int i = 0; i < nsuffpairs; i++) {
int c = stringisuffcmp(suffpairs[i].s1, suffpairs[i].s2);
printf("[%s] %s [%s] \n", suffpairs[i].s1,
c == 0 ? "matches" : c < 0 ? "<" : ">", suffpairs[i].s2);
}
#elif 0
std::string testit("\303\251l\303\251gant");
for (int sz = 10; sz >= 0; sz--) {
utf8truncate(testit, sz);
cout << testit << endl;
}
#elif 0
std::string testit("ligne\ndeuxieme ligne\r3eme ligne\r\n");
cout << "[" << neutchars(testit, "\r\n") << "]" << endl;
string i, o;
cout << "neutchars(null) is [" << neutchars(i, "\r\n") << "]" << endl;
#elif 1
map<string, string> substs;
substs["a"] = "A_SUBST";
substs["title"] = "TITLE_SUBST";
string in = "a: %a title: %(title) pcpc: %% %";
string out;
pcSubst(in, out, substs);
cout << in << " => " << out << endl;
in = "unfinished: %(unfinished";
pcSubst(in, out, substs);
cout << in << " => " << out << endl;
in = "unfinished: %(";
pcSubst(in, out, substs);
cout << in << " => " << out << endl;
in = "empty: %()";
pcSubst(in, out, substs);
cout << in << " => " << out << endl;
substs.clear();
in = "a: %a title: %(title) pcpc: %% %";
pcSubst(in, out, substs);
cout << "After map clear: " << in << " => " << out << endl;
#endif
}
#endif