-
Notifications
You must be signed in to change notification settings - Fork 7
/
str.c
537 lines (464 loc) · 15.1 KB
/
str.c
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
/***************************************************************************
* Copyright (C) 2019 by John D. Robertson *
* john@rrci.com *
* *
* 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 3 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 *
* *
* 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. *
***************************************************************************/
#include <assert.h>
#include <ctype.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "str.h"
#include "util.h"
int
STR_sinit(STR *self, size_t sz_hint)
/**********************************************************************************
* Initialization to be called for static instances of STR each use, but
* actual initialization only occurs once.
*/
{
int rtn= 1;
if(!self->buf) {
if(!STR_constructor(self, sz_hint)) goto abort;
} else {
STR_reset(self);
}
rtn= 0;
abort:
return rtn;
}
STR*
STR_constructor(STR *self, size_t sz_hint)
/**********************************************************************************
* Prepare a STR for use with initial size of sz_hint.
*/
{
STR *rtn= NULL;
assert(sz_hint);
self->sz= sz_hint;
if(!(self->buf= malloc(self->sz))) goto abort;
STR_reset(self);
rtn= self;
abort:
return rtn;
}
void*
STR_destructor(STR *self)
/**********************************************************************************
* Free resources associated with STR.
*/
{
if(self->buf) free(self->buf);
return self;
}
static int
growbuf(STR *self)
/**********************************************************************************
* Attempt to increase the size buffer initially trying to double it, then
* backing off 10% at a time.
* Returns non-zero for error.
*/
{
int rtn= 1;
size_t i;
/* Initially try do double memory. If that fails, back off 10% at a time */
for(i= 20; i > 10; i--) {
char *p;
size_t new_sz= self->sz * i / 10;
/* Try to reallocate the memory */
if(!(p= realloc(self->buf, new_sz))) continue;
/* Try vsnprintf() again */
self->buf= p;
self->sz = new_sz;
break;
}
if(i != 10) rtn= 0; /* Not success if we grew the buffer */
abort:
return rtn;
}
int
STR_sprintf(STR *self, const char *fmt, ...)
/**********************************************************************************
* Same as sprintf, except you don't have to worry about buffer overflows.
* Returns non-zero for error.
*/
{
int is_done, rtn= -1;
va_list arglist;
/* Catch empty strings */
if(!strlen(fmt)) return 0;
/* vsprintf the fmt string */
for(is_done= 0; !is_done;) {
int rc;
va_start (arglist, fmt);
rc= vsnprintf(self->buf+self->len, self->sz - self->len, fmt, arglist);
if(rc >= (self->sz - self->len)) { /* Buffer isn't large enough */
if(growbuf(self)) is_done= 1;
} else {
if(rc != -1) { /* Successful return */
rtn= rc;
self->len += rc;
}
is_done= 1;
}
va_end (arglist);
}
return rtn;
}
int
STR_vsprintf(STR *self, const char *fmt, va_list ap)
/**********************************************************************************
* Same as vsprintf, except you don't have to worry about buffer overflows.
* Returns non-zero for error.
*/
{
int is_done, rtn= -1;
/* Catch empty strings */
if(!strlen(fmt)) return 0;
/* vsprintf the fmt string */
for(is_done= 0; !is_done;) {
int rc;
va_list arglist;
#if __GNUC__ == 2
arglist= ap;
#else
va_copy(arglist, ap);
#endif
rc= vsnprintf(self->buf+self->len, self->sz - self->len, fmt, arglist);
if(rc >= (self->sz - self->len)) { /* Buffer isn't large enough */
if(growbuf(self)) is_done= 1;
} else {
if(rc != -1) { /* Successful return */
rtn= rc;
self->len += rc;
}
is_done= 1;
}
va_end (arglist);
}
return rtn;
}
int
STR_append(STR *self, const char *str, size_t str_len)
/**********************************************************************************
* Append string str to the end of the current buffer.
* Returns -1 for error.
*/
{
if(str_len == -1) str_len= strlen(str);
/* Make sure there is enough space to store the string */
while(self->len + str_len + 1 >= self->sz) {
if(growbuf(self)) return 1;
}
/* Copy the string into place */
memcpy(self->buf + self->len, str, str_len);
/* Update length */
self->len += str_len;
/* Null terminate string */
self->buf[self->len] = '\0';
return 0;
}
int
STR_putc(STR *self, int c)
/**********************************************************************************
* Append a single character to the end of the current buffer.
* Returns -1 for error.
*/
{
/* Make sure there is enough space to store the string */
while(self->len + 1 >= self->sz) {
if(growbuf(self)) return 1;
}
/* Copy the character into place */
self->buf[self->len]= c;
/* Update length */
++self->len;
/* Null terminate string */
self->buf[self->len] = '\0';
return 0;
}
const char*
STR_tolower(STR *self)
/**********************************************************************************
* Convert all characters in buffer to lower case.
*/
{
char *c;
for(c= self->buf; *c; ++c) {
*c= tolower(*c);
}
return self->buf;
}
const char*
STR_XMLencode(STR *self, const char *src)
/**************************************************************
* encode the src string for XML into self. Return self's buffer.
* NOTE: self does not get reset!
*/
{
const char *c;
if(!src) return "";
for(c= src; *c; ++c) {
const char *str= NULL;
unsigned len= 0;
switch(*c) {
#define doit(litstr) \
len= strlen(litstr); str= litstr
case '"': doit("""); break;
case '\'': doit("'"); break;
case '<': doit("<"); break;
case '>': doit(">"); break;
case '&': doit("&"); break;
#undef doit
}
if(str) { // Special string was assigned
STR_append(self, str, len);
} else {
STR_putc(self, *c);
}
}
return STR_str(self);
}
const char*
STR_URLencode(STR *self, const char *src)
/**************************************************************
* encode the src string for URL into self. Return self's buffer.
* NOTE: self does not get reset!
*/
{
const char *c;
if(!src) return "";
for(c= src; *c; ++c) {
const char *str= NULL;
switch(*c) {
case '!': str= "%21"; break;
case '#': str= "%23"; break;
case '$': str= "%24"; break;
case '&': str= "%26"; break;
case '\'': str= "%27"; break;
case '(': str= "%28"; break;
case ')': str= "%29"; break;
case '*': str= "%2A"; break;
case '+': str= "%2B"; break;
case ',': str= "%2C"; break;
// case '/': str= "%2F"; break;
case ':': str= "%3A"; break;
case ';': str= "%3B"; break;
case '=': str= "%3D"; break;
case '?': str= "%3F"; break;
case '@': str= "%40"; break;
case '[': str= "%5B"; break;
case ']': str= "%5D"; break;
}
if(str) { // Special string was assigned
STR_append(self, str, 3);
} else {
STR_putc(self, *c);
}
}
return STR_str(self);
}
const char*
STR_utf8toHTML(STR *self, const char *src)
/**************************************************************
* place the HTML representation of the utf-8 src string into self.
* Return self's buffer.
* NOTE: self does not get reset!
*/
{
const unsigned char *c;
unsigned code= '?';
if(!src) return "";
for(c= (const unsigned char*)src; *c; ++c) {
/******* Map UTF-8 to a code point **********/
if(0xF0 == (*c & 0xF8)) { // first of four bytes
/* Make sure the string doesn't end too soon */
assert(c[1] && c[2] && c[3]);
code= (*c & ~0xF8) << 18;
++c;
code |= (*c & ~0xC0) << 12;
++c;
code |= (*c & ~0xC0) << 6;
++c;
code |= (*c & ~0xC0);
} else if(0xE0 == (*c & 0xF0)) { // first of three bytes
/* Make sure the string doesn't end too soon */
assert(c[1] && c[2]);
code= (*c & ~0xF0) << 12;
++c;
code |= (*c & ~0xC0) << 6;
++c;
code |= (*c & ~0xC0);
} else if(0xC0 == (*c & 0xE0)) { // first of two bytes
/* Make sure the string doesn't end too soon */
assert(c[1]);
code= (*c & ~0xE0) << 6;
++c;
code |= (*c & ~0xC0);
} else if(0 == (*c & 0x80)) {// first of one byte
code= *c;
}
/************** Assign HTML special string if one is defined **********/
const char *str= NULL;
unsigned len= 0;
switch(code) {
#define doit(litstr) \
len= strlen(litstr); str= litstr
case '"': doit("""); break;
case '<': doit("<"); break;
case '>': doit(">"); break;
case '&': doit("&"); break;
case 160: doit(" "); break;
case 161: doit("¡"); break;
case 162: doit("¢"); break;
case 163: doit("£"); break;
case 164: doit("¤"); break;
case 165: doit("¥"); break;
case 166: doit("¦"); break;
case 167: doit("§"); break;
case 168: doit("¨"); break;
case 169: doit("©"); break;
case 170: doit("ª"); break;
case 171: doit("«"); break;
case 172: doit("¬"); break;
case 173: doit("­"); break;
case 174: doit("®"); break;
case 175: doit("¯"); break;
case 176: doit("°"); break;
case 177: doit("±"); break;
case 178: doit("²"); break;
case 179: doit("³"); break;
case 180: doit("´"); break;
case 181: doit("µ"); break;
case 182: doit("¶"); break;
case 183: doit("·"); break;
case 184: doit("¸"); break;
case 185: doit("¹"); break;
case 186: doit("º"); break;
case 187: doit("»"); break;
case 188: doit("¼"); break;
case 189: doit("½"); break;
case 190: doit("¾"); break;
case 191: doit("¿"); break;
case 192: doit("À"); break;
case 193: doit("Á"); break;
case 194: doit("Â"); break;
case 195: doit("Ã"); break;
case 196: doit("Ä"); break;
case 197: doit("Å"); break;
case 198: doit("Æ"); break;
case 199: doit("Ç"); break;
case 200: doit("È"); break;
case 201: doit("É"); break;
case 202: doit("Ê"); break;
case 203: doit("Ë"); break;
case 204: doit("Ì"); break;
case 205: doit("Í"); break;
case 206: doit("Î"); break;
case 207: doit("Ï"); break;
case 208: doit("Ð"); break;
case 209: doit("Ñ"); break;
case 210: doit("Ò"); break;
case 211: doit("Ó"); break;
case 212: doit("Ô"); break;
case 213: doit("Õ"); break;
case 214: doit("Ö"); break;
case 215: doit("×"); break;
case 216: doit("Ø"); break;
case 217: doit("Ù"); break;
case 218: doit("Ú"); break;
case 219: doit("Û"); break;
case 220: doit("Ü"); break;
case 221: doit("Ý"); break;
case 222: doit("Þ"); break;
case 223: doit("ß"); break;
case 224: doit("à"); break;
case 225: doit("á"); break;
case 226: doit("â"); break;
case 227: doit("ã"); break;
case 228: doit("ä"); break;
case 229: doit("å"); break;
case 230: doit("æ"); break;
case 231: doit("ç"); break;
case 232: doit("è"); break;
case 233: doit("é"); break;
case 234: doit("ê"); break;
case 235: doit("ë"); break;
case 236: doit("ì"); break;
case 237: doit("í"); break;
case 238: doit("î"); break;
case 239: doit("ï"); break;
case 240: doit("ð"); break;
case 241: doit("ñ"); break;
case 242: doit("ò"); break;
case 243: doit("ó"); break;
case 244: doit("ô"); break;
case 245: doit("õ"); break;
case 246: doit("ö"); break;
case 247: doit("÷"); break;
case 248: doit("ø"); break;
case 249: doit("ù"); break;
case 250: doit("ú"); break;
case 251: doit("û"); break;
case 252: doit("ü"); break;
case 253: doit("ý"); break;
case 254: doit("þ"); break;
case 255: doit("ÿ"); break;
case 8364: doit("€"); break;
#undef doit
}
/****** Place final representation into our string buffer ******/
if(str) { // Special string was assigned
STR_append(self, str, len);
} else if(code < 128 && isprint(code)) { // Normal ASCII character
STR_putc(self, code);
} else if(65533 == code) {
// This is the placeholder for unrecognized characters
} else { // All others
STR_sprintf(self, "&#%u;", code);
}
}
return STR_str(self);
}
const char*
STR_escapeJSONstr(STR *self, const char *src)
/**************************************************************
* Escape any characters such the src can be used in a JSON
* string.
* Return self's buffer.
* NOTE: self does not get reset!
*/
{
const char *pc;
for(pc= src; *pc; ++pc) {
switch(*pc) {
case '\\':
STR_sprintf(self, "\\\\");
break;
case '"':
STR_sprintf(self, "\\\"");
break;
default:
if(iscntrl(*pc)) {
STR_sprintf(self, "\\u%4X", (int)(*pc));
} else {
STR_putc(self, *pc);
}
}
}
return STR_str(self);
}