xref: /PHP-7.2/ext/mysqlnd/mysqlnd_charset.c (revision 7a7ec01a)
1 /*
2   +----------------------------------------------------------------------+
3   | PHP Version 7                                                        |
4   +----------------------------------------------------------------------+
5   | Copyright (c) 2006-2018 The PHP Group                                |
6   +----------------------------------------------------------------------+
7   | This source file is subject to version 3.01 of the PHP license,      |
8   | that is bundled with this package in the file LICENSE, and is        |
9   | available through the world-wide-web at the following url:           |
10   | http://www.php.net/license/3_01.txt                                  |
11   | If you did not receive a copy of the PHP license and are unable to   |
12   | obtain it through the world-wide-web, please send a note to          |
13   | license@php.net so we can mail you a copy immediately.               |
14   +----------------------------------------------------------------------+
15   | Authors: Andrey Hristov <andrey@php.net>                             |
16   |          Ulf Wendel <uw@php.net>                                     |
17   |          Georg Richter <georg@php.net>                               |
18   +----------------------------------------------------------------------+
19 */
20 
21 #include "php.h"
22 #include "mysqlnd.h"
23 #include "mysqlnd_priv.h"
24 #include "mysqlnd_debug.h"
25 #include "mysqlnd_charset.h"
26 
27 /* {{{ utf8 functions */
check_mb_utf8mb3_sequence(const char * start,const char * end)28 static unsigned int check_mb_utf8mb3_sequence(const char *start, const char *end)
29 {
30 	zend_uchar	c;
31 
32 	if (start >= end) {
33 		return 0;
34 	}
35 
36 	c = (zend_uchar) start[0];
37 
38 	if (c < 0x80) {
39 		return 1;		/* single byte character */
40 	}
41 	if (c < 0xC2) {
42 		return 0;		/* invalid mb character */
43 	}
44 	if (c < 0xE0) {
45 		if (start + 2 > end) {
46 			return 0;	/* too small */
47 		}
48 		if (!(((zend_uchar)start[1] ^ 0x80) < 0x40)) {
49 			return 0;
50 		}
51 		return 2;
52 	}
53 	if (c < 0xF0) {
54 		if (start + 3 > end) {
55 			return 0;	/* too small */
56 		}
57 		if (!(((zend_uchar)start[1] ^ 0x80) < 0x40 && ((zend_uchar)start[2] ^ 0x80) < 0x40 &&
58 			(c >= 0xE1 || (zend_uchar)start[1] >= 0xA0))) {
59 			return 0;	/* invalid utf8 character */
60 		}
61 		return 3;
62 	}
63 	return 0;
64 }
65 
66 
check_mb_utf8_sequence(const char * start,const char * end)67 static unsigned int check_mb_utf8_sequence(const char *start, const char *end)
68 {
69 	zend_uchar	c;
70 
71 	if (start >= end) {
72 		return 0;
73 	}
74 
75 	c = (zend_uchar) start[0];
76 
77 	if (c < 0x80) {
78 		return 1;		/* single byte character */
79 	}
80 	if (c < 0xC2) {
81 		return 0;		/* invalid mb character */
82 	}
83 	if (c < 0xE0) {
84 		if (start + 2 > end) {
85 			return 0;	/* too small */
86 		}
87 		if (!(((zend_uchar)start[1] ^ 0x80) < 0x40)) {
88 			return 0;
89 		}
90 		return 2;
91 	}
92 	if (c < 0xF0) {
93 		if (start + 3 > end) {
94 			return 0;	/* too small */
95 		}
96 		if (!(((zend_uchar)start[1] ^ 0x80) < 0x40 && ((zend_uchar)start[2] ^ 0x80) < 0x40 &&
97 			(c >= 0xE1 || (zend_uchar)start[1] >= 0xA0))) {
98 			return 0;	/* invalid utf8 character */
99 		}
100 		return 3;
101 	}
102 	if (c < 0xF5) {
103 		if (start + 4 > end) { /* We need 4 characters */
104 			return 0;	/* too small */
105 		}
106 
107 		/*
108 		  UTF-8 quick four-byte mask:
109 		  11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
110 		  Encoding allows to encode U+00010000..U+001FFFFF
111 
112 		  The maximum character defined in the Unicode standard is U+0010FFFF.
113 		  Higher characters U+00110000..U+001FFFFF are not used.
114 
115 		  11110000.10010000.10xxxxxx.10xxxxxx == F0.90.80.80 == U+00010000 (min)
116 		  11110100.10001111.10111111.10111111 == F4.8F.BF.BF == U+0010FFFF (max)
117 
118 		  Valid codes:
119 		  [F0][90..BF][80..BF][80..BF]
120 		  [F1][80..BF][80..BF][80..BF]
121 		  [F2][80..BF][80..BF][80..BF]
122 		  [F3][80..BF][80..BF][80..BF]
123 		  [F4][80..8F][80..BF][80..BF]
124 		*/
125 
126 		if (!(((zend_uchar)start[1] ^ 0x80) < 0x40 &&
127 			((zend_uchar)start[2] ^ 0x80) < 0x40 &&
128 			((zend_uchar)start[3] ^ 0x80) < 0x40 &&
129 				(c >= 0xf1 || (zend_uchar)start[1] >= 0x90) &&
130 				(c <= 0xf3 || (zend_uchar)start[1] <= 0x8F)))
131 		{
132 			return 0;	/* invalid utf8 character */
133 		}
134 		return 4;
135 	}
136 	return 0;
137 }
138 
check_mb_utf8mb3_valid(const char * start,const char * end)139 static unsigned int check_mb_utf8mb3_valid(const char *start, const char *end)
140 {
141 	unsigned int len = check_mb_utf8mb3_sequence(start, end);
142 	return (len > 1)? len:0;
143 }
144 
check_mb_utf8_valid(const char * start,const char * end)145 static unsigned int check_mb_utf8_valid(const char *start, const char *end)
146 {
147 	unsigned int len = check_mb_utf8_sequence(start, end);
148 	return (len > 1)? len:0;
149 }
150 
151 
mysqlnd_mbcharlen_utf8mb3(unsigned int utf8)152 static unsigned int mysqlnd_mbcharlen_utf8mb3(unsigned int utf8)
153 {
154 	if (utf8 < 0x80) {
155 		return 1;		/* single byte character */
156 	}
157 	if (utf8 < 0xC2) {
158 		return 0;		/* invalid multibyte header */
159 	}
160 	if (utf8 < 0xE0) {
161 		return 2;		/* double byte character */
162 	}
163 	if (utf8 < 0xF0) {
164 		return 3;		/* triple byte character */
165 	}
166 	return 0;
167 }
168 
169 
mysqlnd_mbcharlen_utf8(unsigned int utf8)170 static unsigned int mysqlnd_mbcharlen_utf8(unsigned int utf8)
171 {
172 	if (utf8 < 0x80) {
173 		return 1;		/* single byte character */
174 	}
175 	if (utf8 < 0xC2) {
176 		return 0;		/* invalid multibyte header */
177 	}
178 	if (utf8 < 0xE0) {
179 		return 2;		/* double byte character */
180 	}
181 	if (utf8 < 0xF0) {
182 		return 3;		/* triple byte character */
183 	}
184 	if (utf8 < 0xF8) {
185 		return 4;		/* four byte character */
186 	}
187 	return 0;
188 }
189 /* }}} */
190 
191 
192 /* {{{ big5 functions */
193 #define valid_big5head(c)	(0xA1 <= (unsigned int)(c) && (unsigned int)(c) <= 0xF9)
194 #define valid_big5tail(c)	((0x40 <= (unsigned int)(c) && (unsigned int)(c) <= 0x7E) || \
195 							(0xA1 <= (unsigned int)(c) && (unsigned int)(c) <= 0xFE))
196 
197 #define isbig5code(c,d) (isbig5head(c) && isbig5tail(d))
198 
check_mb_big5(const char * start,const char * end)199 static unsigned int check_mb_big5(const char *start, const char *end)
200 {
201 	return (valid_big5head(*(start)) && (end - start) > 1 && valid_big5tail(*(start + 1)) ? 2 : 0);
202 }
203 
204 
mysqlnd_mbcharlen_big5(unsigned int big5)205 static unsigned int mysqlnd_mbcharlen_big5(unsigned int big5)
206 {
207 	return (valid_big5head(big5)) ? 2 : 1;
208 }
209 /* }}} */
210 
211 
212 /* {{{ cp932 functions */
213 #define valid_cp932head(c) ((0x81 <= (c) && (c) <= 0x9F) || (0xE0 <= (c) && c <= 0xFC))
214 #define valid_cp932tail(c) ((0x40 <= (c) && (c) <= 0x7E) || (0x80 <= (c) && c <= 0xFC))
215 
216 
check_mb_cp932(const char * start,const char * end)217 static unsigned int check_mb_cp932(const char *start, const char *end)
218 {
219 	return (valid_cp932head((zend_uchar)start[0]) && (end - start >  1) &&
220 			valid_cp932tail((zend_uchar)start[1])) ? 2 : 0;
221 }
222 
223 
mysqlnd_mbcharlen_cp932(unsigned int cp932)224 static unsigned int mysqlnd_mbcharlen_cp932(unsigned int cp932)
225 {
226 	return (valid_cp932head((zend_uchar)cp932)) ? 2 : 1;
227 }
228 /* }}} */
229 
230 
231 /* {{{ euckr functions */
232 #define valid_euckr(c)	((0xA1 <= (zend_uchar)(c) && (zend_uchar)(c) <= 0xFE))
233 
check_mb_euckr(const char * start,const char * end)234 static unsigned int check_mb_euckr(const char *start, const char *end)
235 {
236 	if (end - start <= 1) {
237 		return 0;	/* invalid length */
238 	}
239 	if (*(zend_uchar *)start < 0x80) {
240 		return 0;	/* invalid euckr character */
241 	}
242 	if (valid_euckr(start[1])) {
243 		return 2;
244 	}
245 	return 0;
246 }
247 
248 
mysqlnd_mbcharlen_euckr(unsigned int kr)249 static unsigned int mysqlnd_mbcharlen_euckr(unsigned int kr)
250 {
251 	return (valid_euckr(kr)) ? 2 : 1;
252 }
253 /* }}} */
254 
255 
256 /* {{{ eucjpms functions */
257 #define valid_eucjpms(c) 		(((c) & 0xFF) >= 0xA1 && ((c) & 0xFF) <= 0xFE)
258 #define valid_eucjpms_kata(c)	(((c) & 0xFF) >= 0xA1 && ((c) & 0xFF) <= 0xDF)
259 #define valid_eucjpms_ss2(c)	(((c) & 0xFF) == 0x8E)
260 #define valid_eucjpms_ss3(c)	(((c) & 0xFF) == 0x8F)
261 
check_mb_eucjpms(const char * start,const char * end)262 static unsigned int check_mb_eucjpms(const char *start, const char *end)
263 {
264 	if (*((zend_uchar *)start) < 0x80) {
265 		return 0;	/* invalid eucjpms character */
266 	}
267 	if (valid_eucjpms(start[0]) && (end - start) > 1 && valid_eucjpms(start[1])) {
268 		return 2;
269 	}
270 	if (valid_eucjpms_ss2(start[0]) && (end - start) > 1 && valid_eucjpms_kata(start[1])) {
271 		return 2;
272 	}
273 	if (valid_eucjpms_ss3(start[0]) && (end - start) > 2 && valid_eucjpms(start[1]) &&
274 		valid_eucjpms(start[2])) {
275 		return 2;
276 	}
277 	return 0;
278 }
279 
280 
mysqlnd_mbcharlen_eucjpms(unsigned int jpms)281 static unsigned int mysqlnd_mbcharlen_eucjpms(unsigned int jpms)
282 {
283 	if (valid_eucjpms(jpms) || valid_eucjpms_ss2(jpms)) {
284 		return 2;
285 	}
286 	if (valid_eucjpms_ss3(jpms)) {
287 		return 3;
288 	}
289 	return 1;
290 }
291 /* }}} */
292 
293 
294 /* {{{ gb2312 functions */
295 #define valid_gb2312_head(c)	(0xA1 <= (zend_uchar)(c) && (zend_uchar)(c) <= 0xF7)
296 #define valid_gb2312_tail(c)	(0xA1 <= (zend_uchar)(c) && (zend_uchar)(c) <= 0xFE)
297 
298 
check_mb_gb2312(const char * start,const char * end)299 static unsigned int check_mb_gb2312(const char *start, const char *end)
300 {
301 	return (valid_gb2312_head((unsigned int)start[0]) && end - start > 1 &&
302 			valid_gb2312_tail((unsigned int)start[1])) ? 2 : 0;
303 }
304 
305 
mysqlnd_mbcharlen_gb2312(unsigned int gb)306 static unsigned int mysqlnd_mbcharlen_gb2312(unsigned int gb)
307 {
308 	return (valid_gb2312_head(gb)) ? 2 : 1;
309 }
310 /* }}} */
311 
312 
313 /* {{{ gbk functions */
314 #define valid_gbk_head(c)	(0x81<=(zend_uchar)(c) && (zend_uchar)(c)<=0xFE)
315 #define valid_gbk_tail(c)	((0x40<=(zend_uchar)(c) && (zend_uchar)(c)<=0x7E) || (0x80<=(zend_uchar)(c) && (zend_uchar)(c)<=0xFE))
316 
check_mb_gbk(const char * start,const char * end)317 static unsigned int check_mb_gbk(const char *start, const char *end)
318 {
319 	return (valid_gbk_head(start[0]) && (end) - (start) > 1 && valid_gbk_tail(start[1])) ? 2 : 0;
320 }
321 
mysqlnd_mbcharlen_gbk(unsigned int gbk)322 static unsigned int mysqlnd_mbcharlen_gbk(unsigned int gbk)
323 {
324 	return (valid_gbk_head(gbk) ? 2 : 1);
325 }
326 /* }}} */
327 
328 
329 /* {{{ sjis functions */
330 #define valid_sjis_head(c)	((0x81 <= (c) && (c) <= 0x9F) || (0xE0 <= (c) && (c) <= 0xFC))
331 #define valid_sjis_tail(c)	((0x40 <= (c) && (c) <= 0x7E) || (0x80 <= (c) && (c) <= 0xFC))
332 
333 
check_mb_sjis(const char * start,const char * end)334 static unsigned int check_mb_sjis(const char *start, const char *end)
335 {
336 	return (valid_sjis_head((zend_uchar)start[0]) && (end - start) > 1 && valid_sjis_tail((zend_uchar)start[1])) ? 2 : 0;
337 }
338 
339 
mysqlnd_mbcharlen_sjis(unsigned int sjis)340 static unsigned int mysqlnd_mbcharlen_sjis(unsigned int sjis)
341 {
342 	return (valid_sjis_head((zend_uchar)sjis)) ? 2 : 1;
343 }
344 /* }}} */
345 
346 
347 /* {{{ ucs2 functions */
check_mb_ucs2(const char * start __attribute ((unused)),const char * end __attribute ((unused)))348 static unsigned int check_mb_ucs2(const char *start __attribute((unused)), const char *end __attribute((unused)))
349 {
350 	return 2; /* always 2 */
351 }
352 
mysqlnd_mbcharlen_ucs2(unsigned int ucs2 __attribute ((unused)))353 static unsigned int mysqlnd_mbcharlen_ucs2(unsigned int ucs2 __attribute((unused)))
354 {
355 	return 2; /* always 2 */
356 }
357 /* }}} */
358 
359 
360 /* {{{ ujis functions */
361 #define valid_ujis(c)     	((0xA1 <= ((c)&0xFF) && ((c)&0xFF) <= 0xFE))
362 #define valid_ujis_kata(c)  ((0xA1 <= ((c)&0xFF) && ((c)&0xFF) <= 0xDF))
363 #define valid_ujis_ss2(c) 	(((c)&0xFF) == 0x8E)
364 #define valid_ujis_ss3(c) 	(((c)&0xFF) == 0x8F)
365 
check_mb_ujis(const char * start,const char * end)366 static unsigned int check_mb_ujis(const char *start, const char *end)
367 {
368 	if (*(zend_uchar*)start < 0x80) {
369 		return 0;	/* invalid ujis character */
370 	}
371 	if (valid_ujis(*(start)) && valid_ujis(*((start)+1))) {
372 		return 2;
373 	}
374 	if (valid_ujis_ss2(*(start)) && valid_ujis_kata(*((start)+1))) {
375 		return 2;
376 	}
377 	if (valid_ujis_ss3(*(start)) && (end-start) > 2 && valid_ujis(*((start)+1)) && valid_ujis(*((start)+2))) {
378 		return 3;
379 	}
380 	return 0;
381 }
382 
383 
mysqlnd_mbcharlen_ujis(unsigned int ujis)384 static unsigned int mysqlnd_mbcharlen_ujis(unsigned int ujis)
385 {
386 	return (valid_ujis(ujis)? 2: valid_ujis_ss2(ujis)? 2: valid_ujis_ss3(ujis)? 3: 1);
387 }
388 /* }}} */
389 
390 
391 
392 /* {{{ utf16 functions */
393 #define UTF16_HIGH_HEAD(x)  ((((zend_uchar) (x)) & 0xFC) == 0xD8)
394 #define UTF16_LOW_HEAD(x)   ((((zend_uchar) (x)) & 0xFC) == 0xDC)
395 
check_mb_utf16(const char * start,const char * end)396 static unsigned int check_mb_utf16(const char *start, const char *end)
397 {
398 	if (start + 2 > end) {
399 		return 0;
400 	}
401 
402 	if (UTF16_HIGH_HEAD(*start)) {
403 		return (start + 4 <= end) && UTF16_LOW_HEAD(start[2]) ? 4 : 0;
404 	}
405 
406 	if (UTF16_LOW_HEAD(*start)) {
407 		return 0;
408 	}
409 	return 2;
410 }
411 
412 
mysqlnd_mbcharlen_utf16(unsigned int utf16)413 static uint32_t mysqlnd_mbcharlen_utf16(unsigned int utf16)
414 {
415   return UTF16_HIGH_HEAD(utf16) ? 4 : 2;
416 }
417 /* }}} */
418 
419 
420 /* {{{ utf32 functions */
check_mb_utf32(const char * start __attribute ((unused)),const char * end __attribute ((unused)))421 static unsigned int check_mb_utf32(const char *start __attribute((unused)), const char *end __attribute((unused)))
422 {
423 	return 4;
424 }
425 
426 
mysqlnd_mbcharlen_utf32(unsigned int utf32 __attribute ((unused)))427 static unsigned int mysqlnd_mbcharlen_utf32(unsigned int utf32 __attribute((unused)))
428 {
429 	return 4;
430 }
431 /* }}} */
432 
433 
434 /* {{{ gb18030 functions */
435 #define is_gb18030_odd(c)          (0x81 <= (zend_uchar) (c) && (zend_uchar) (c) <= 0xFE)
436 #define is_gb18030_even_2(c)       ((0x40 <= (zend_uchar) (c) && (zend_uchar) (c) <= 0x7E) || (0x80 <= (zend_uchar) (c) && (zend_uchar) (c) <= 0xFE))
437 #define is_gb18030_even_4(c)       (0x30 <= (zend_uchar) (c) && (zend_uchar) (c) <= 0x39)
438 
439 
mysqlnd_mbcharlen_gb18030(unsigned int c)440 static unsigned int mysqlnd_mbcharlen_gb18030(unsigned int c)
441 {
442 	if (c <= 0xFF) {
443 		return !is_gb18030_odd(c);
444 	}
445 	if (c > 0xFFFF || !is_gb18030_odd((c >> 8) & 0xFF)) {
446 		return 0;
447 	}
448 	if (is_gb18030_even_2((c & 0xFF))) {
449 	    return 2;
450 	}
451 	if (is_gb18030_even_4((c & 0xFF))) {
452 		return 4;
453 	}
454 
455 	return 0;
456 }
457 
458 
my_ismbchar_gb18030(const char * start,const char * end)459 static unsigned int my_ismbchar_gb18030(const char * start, const char * end)
460 {
461 	if (end - start <= 1 || !is_gb18030_odd(start[0])) {
462 		return 0;
463 	}
464 
465 	if (is_gb18030_even_2(start[1])) {
466 		return 2;
467 	} else if (end - start > 3 && is_gb18030_even_4(start[1]) && is_gb18030_odd(start[2]) && is_gb18030_even_4(start[3])) {
468 		return 4;
469 	}
470 
471 	return 0;
472 }
473 /* }}} */
474 
475 /*
476   The server compiles sometimes the full utf-8 (the mb4) as utf8m4, and the old as utf8,
477   for BC reasons. Sometimes, utf8mb4 is just utf8 but the old charsets are utf8mb3.
478   Change easily now, with a macro, could be made compilastion dependable.
479 */
480 
481 #define UTF8_MB4 "utf8mb4"
482 #define UTF8_MB3 "utf8"
483 
484 /* {{{ mysqlnd_charsets */
485 const MYSQLND_CHARSET mysqlnd_charsets[] =
486 {
487 	{   1, "big5","big5_chinese_ci", 1, 2, "", mysqlnd_mbcharlen_big5, check_mb_big5},
488 	{   3, "dec8", "dec8_swedish_ci", 1, 1, "", NULL, NULL},
489 	{   4, "cp850", "cp850_general_ci", 1, 1, "", NULL, NULL},
490 	{   6, "hp8", "hp8_english_ci", 1, 1, "", NULL, NULL},
491 	{   7, "koi8r", "koi8r_general_ci", 1, 1, "", NULL, NULL},
492 	{   8, "latin1", "latin1_swedish_ci", 1, 1, "", NULL, NULL},
493 	{   5, "latin1", "latin1_german1_ci", 1, 1, "", NULL, NULL}, /* should be after 0x8 because swedish_ci is the default collation */
494 	{   9, "latin2", "latin2_general_ci", 1, 1, "", NULL, NULL},
495 	{   2, "latin2", "latin2_czech_cs", 1, 1, "", NULL, NULL}, /* should be after 0x9 because general_ci is the default collation */
496 	{  10, "swe7", "swe7_swedish_ci", 1, 1, "", NULL, NULL},
497 	{  11, "ascii", "ascii_general_ci", 1, 1, "", NULL, NULL},
498 	{  12, "ujis", "ujis_japanese_ci", 1, 3, "", mysqlnd_mbcharlen_ujis, check_mb_ujis},
499 	{  13, "sjis", "sjis_japanese_ci", 1, 2, "", mysqlnd_mbcharlen_sjis, check_mb_sjis},
500 	{  16, "hebrew", "hebrew_general_ci", 1, 1, "", NULL, NULL},
501 	{  17, "filename", "filename", 1, 5, "", NULL, NULL},
502 	{  18, "tis620", "tis620_thai_ci", 1, 1, "", NULL, NULL},
503 	{  19, "euckr", "euckr_korean_ci", 1, 2, "", mysqlnd_mbcharlen_euckr, check_mb_euckr},
504 	{  21, "latin2", "latin2_hungarian_ci", 1, 1, "", NULL, NULL},
505 	{  27, "latin2", "latin2_croatian_ci", 1, 1, "", NULL, NULL},
506 	{  22, "koi8u", "koi8u_general_ci", 1, 1, "", NULL, NULL},
507 	{  24, "gb2312", "gb2312_chinese_ci", 1, 2, "", mysqlnd_mbcharlen_gb2312, check_mb_gb2312},
508 	{  25, "greek", "greek_general_ci", 1, 1, "", NULL, NULL},
509 	{  26, "cp1250", "cp1250_general_ci", 1, 1, "", NULL, NULL},
510 	{  28, "gbk", "gbk_chinese_ci", 1, 2, "", mysqlnd_mbcharlen_gbk, check_mb_gbk},
511 	{  30, "latin5", "latin5_turkish_ci", 1, 1, "", NULL, NULL},
512 	{  31, "latin1", "latin1_german2_ci", 1, 1, "", NULL, NULL},
513 	{  15, "latin1", "latin1_danish_ci", 1, 1, "", NULL, NULL},
514 	{  32, "armscii8", "armscii8_general_ci", 1, 1, "", NULL, NULL},
515 	{  33, UTF8_MB3, UTF8_MB3"_general_ci", 1, 3, "UTF-8 Unicode", mysqlnd_mbcharlen_utf8mb3,  check_mb_utf8mb3_valid},
516 	{  35, "ucs2", "ucs2_general_ci", 2, 2, "UCS-2 Unicode", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
517 	{  36, "cp866", "cp866_general_ci", 1, 1, "", NULL, NULL},
518 	{  37, "keybcs2", "keybcs2_general_ci", 1, 1, "", NULL, NULL},
519 	{  38, "macce", "macce_general_ci", 1, 1, "", NULL, NULL},
520 	{  39, "macroman", "macroman_general_ci", 1, 1, "", NULL, NULL},
521 	{  40, "cp852", "cp852_general_ci", 1, 1, "", NULL, NULL},
522 	{  41, "latin7", "latin7_general_ci", 1, 1, "", NULL, NULL},
523 	{  20, "latin7", "latin7_estonian_cs", 1, 1, "", NULL, NULL},
524 	{  57, "cp1256", "cp1256_general_ci", 1, 1, "", NULL, NULL},
525 	{  59, "cp1257", "cp1257_general_ci", 1, 1, "", NULL, NULL},
526 	{  63, "binary", "binary", 1, 1, "", NULL, NULL},
527 	{  97, "eucjpms", "eucjpms_japanese_ci", 1, 3, "", mysqlnd_mbcharlen_eucjpms, check_mb_eucjpms},
528 	{  29, "cp1257", "cp1257_lithuanian_ci", 1, 1, "", NULL, NULL},
529 	{  31, "latin1", "latin1_german2_ci", 1, 1, "", NULL, NULL},
530 	{  34, "cp1250", "cp1250_czech_cs", 1, 1, "", NULL, NULL},
531 	{  42, "latin7", "latin7_general_cs", 1, 1, "", NULL, NULL},
532 	{  43, "macce", "macce_bin", 1, 1, "", NULL, NULL},
533 	{  44, "cp1250", "cp1250_croatian_ci", 1, 1, "", NULL, NULL},
534 	{  45, UTF8_MB4, UTF8_MB4"_general_ci", 1, 4, "UTF-8 Unicode", mysqlnd_mbcharlen_utf8,  check_mb_utf8_valid},
535 	{  46, UTF8_MB4, UTF8_MB4"_bin", 1, 4, "UTF-8 Unicode", mysqlnd_mbcharlen_utf8,  check_mb_utf8_valid},
536 	{  47, "latin1", "latin1_bin", 1, 1, "", NULL, NULL},
537 	{  48, "latin1", "latin1_general_ci", 1, 1, "", NULL, NULL},
538 	{  49, "latin1", "latin1_general_cs", 1, 1, "", NULL, NULL},
539 	{  51, "cp1251", "cp1251_general_ci", 1, 1, "", NULL, NULL},
540 	{  14, "cp1251", "cp1251_bulgarian_ci", 1, 1, "", NULL, NULL},
541 	{  23, "cp1251", "cp1251_ukrainian_ci", 1, 1, "", NULL, NULL},
542 	{  50, "cp1251", "cp1251_bin", 1, 1, "", NULL, NULL},
543 	{  52, "cp1251", "cp1251_general_cs", 1, 1, "", NULL, NULL},
544 	{  53, "macroman", "macroman_bin", 1, 1, "", NULL, NULL},
545 	{  54, "utf16", "utf16_general_ci", 2, 4, "UTF-16 Unicode", mysqlnd_mbcharlen_utf16, check_mb_utf16},
546 	{  55, "utf16", "utf16_bin", 2, 4, "UTF-16 Unicode", mysqlnd_mbcharlen_utf16, check_mb_utf16},
547 	{  56, "utf16le", "utf16le_general_ci", 2, 4, "UTF-16LE Unicode", mysqlnd_mbcharlen_utf16, check_mb_utf16},
548 	{  58, "cp1257", "cp1257_bin", 1, 1, "", NULL, NULL},
549 /*55*/{  60, "utf32", "utf32_general_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
550 /*55*/{  61, "utf32", "utf32_bin", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
551 	{  62, "utf16le", "utf16le_bin", 2, 4, "UTF-16LE Unicode", mysqlnd_mbcharlen_utf16, check_mb_utf16},
552 	{  64, "armscii8", "armscii8_bin", 1, 1, "", NULL, NULL},
553 	{  65, "ascii", "ascii_bin", 1, 1, "", NULL, NULL},
554 	{  66, "cp1250", "cp1250_bin", 1, 1, "", NULL, NULL},
555 	{  67, "cp1256", "cp1256_bin", 1, 1, "", NULL, NULL},
556 	{  68, "cp866", "cp866_bin", 1, 1, "", NULL, NULL},
557 	{  69, "dec8", "dec8_bin", 1, 1, "", NULL, NULL},
558 	{  70, "greek", "greek_bin", 1, 1, "", NULL, NULL},
559 	{  71, "hebrew", "hebrew_bin", 1, 1, "", NULL, NULL},
560 	{  72, "hp8", "hp8_bin", 1, 1, "", NULL, NULL},
561 	{  73, "keybcs2", "keybcs2_bin", 1, 1, "", NULL, NULL},
562 	{  74, "koi8r", "koi8r_bin", 1, 1, "", NULL, NULL},
563 	{  75, "koi8u", "koi8u_bin", 1, 1, "", NULL, NULL},
564 	{  77, "latin2", "latin2_bin", 1, 1, "", NULL, NULL},
565 	{  78, "latin5", "latin5_bin", 1, 1, "", NULL, NULL},
566 	{  79, "latin7", "latin7_bin", 1, 1, "", NULL, NULL},
567 	{  80, "cp850", "cp850_bin", 1, 1, "", NULL, NULL},
568 	{  81, "cp852", "cp852_bin", 1, 1, "", NULL, NULL},
569 	{  82, "swe7", "swe7_bin", 1, 1, "", NULL, NULL},
570 	{  83, UTF8_MB3, UTF8_MB3"_bin", 1, 3, "UTF-8 Unicode", mysqlnd_mbcharlen_utf8mb3,  check_mb_utf8mb3_valid},
571 	{  84, "big5", "big5_bin", 1, 2, "", mysqlnd_mbcharlen_big5, check_mb_big5},
572 	{  85, "euckr", "euckr_bin", 1, 2, "", mysqlnd_mbcharlen_euckr, check_mb_euckr},
573 	{  86, "gb2312", "gb2312_bin", 1, 2, "", mysqlnd_mbcharlen_gb2312, check_mb_gb2312},
574 	{  87, "gbk", "gbk_bin", 1, 2, "", mysqlnd_mbcharlen_gbk, check_mb_gbk},
575 	{  88, "sjis", "sjis_bin", 1, 2, "", mysqlnd_mbcharlen_sjis, check_mb_sjis},
576 	{  89, "tis620", "tis620_bin", 1, 1, "", NULL, NULL},
577 	{  90, "ucs2", "ucs2_bin", 2, 2, "UCS-2 Unicode", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
578 	{  91, "ujis", "ujis_bin", 1, 3, "", mysqlnd_mbcharlen_ujis, check_mb_ujis},
579 	{  92, "geostd8", "geostd8_general_ci", 1, 1, "", NULL, NULL},
580 	{  93, "geostd8", "geostd8_bin", 1, 1, "", NULL, NULL},
581 	{  94, "latin1", "latin1_spanish_ci", 1, 1, "", NULL, NULL},
582 	{  95, "cp932", "cp932_japanese_ci", 1, 2, "", mysqlnd_mbcharlen_cp932, check_mb_cp932},
583 	{  96, "cp932", "cp932_bin", 1, 2, "", mysqlnd_mbcharlen_cp932, check_mb_cp932},
584 	{  97, "eucjpms", "eucjpms_japanese_ci", 1, 3, "", mysqlnd_mbcharlen_eucjpms, check_mb_eucjpms},
585 	{  98, "eucjpms", "eucjpms_bin", 1, 3, "", mysqlnd_mbcharlen_eucjpms, check_mb_eucjpms},
586 	{  99, "cp1250", "cp1250_polish_ci", 1, 1, "", NULL, NULL},
587 	{ 128, "ucs2", "ucs2_unicode_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
588 	{ 129, "ucs2", "ucs2_icelandic_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
589 	{ 130, "ucs2", "ucs2_latvian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
590 	{ 131, "ucs2", "ucs2_romanian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
591 	{ 132, "ucs2", "ucs2_slovenian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
592 	{ 133, "ucs2", "ucs2_polish_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
593 	{ 134, "ucs2", "ucs2_estonian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
594 	{ 135, "ucs2", "ucs2_spanish_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
595 	{ 136, "ucs2", "ucs2_swedish_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
596 	{ 137, "ucs2", "ucs2_turkish_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
597 	{ 138, "ucs2", "ucs2_czech_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
598 	{ 139, "ucs2", "ucs2_danish_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
599 	{ 140, "ucs2", "ucs2_lithuanian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
600 	{ 141, "ucs2", "ucs2_slovak_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
601 	{ 142, "ucs2", "ucs2_spanish2_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
602 	{ 143, "ucs2", "ucs2_roman_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
603 	{ 144, "ucs2", "ucs2_persian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
604 	{ 145, "ucs2", "ucs2_esperanto_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
605 	{ 146, "ucs2", "ucs2_hungarian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
606 	{ 147, "ucs2", "ucs2_sinhala_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
607 	{ 148, "ucs2", "ucs2_german2_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
608 	{ 149, "ucs2", "ucs2_croatian_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
609 	{ 150, "ucs2", "ucs2_unicode_520_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
610 	{ 151, "ucs2", "ucs2_vietnamese_ci", 2, 2, "", mysqlnd_mbcharlen_ucs2, check_mb_ucs2},
611 
612 /*56*/{160, "utf32", "utf32_unicode_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
613 /*56*/{161, "utf32", "utf32_icelandic_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
614 /*56*/{162, "utf32", "utf32_latvian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
615 /*56*/{163, "utf32", "utf32_romanian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
616 /*56*/{164, "utf32", "utf32_slovenian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
617 /*56*/{165, "utf32", "utf32_polish_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
618 /*56*/{166, "utf32", "utf32_estonian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
619 /*56*/{167, "utf32", "utf32_spanish_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
620 /*56*/{168, "utf32", "utf32_swedish_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
621 /*56*/{169, "utf32", "utf32_turkish_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
622 /*56*/{170, "utf32", "utf32_czech_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
623 /*56*/{171, "utf32", "utf32_danish_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
624 /*56*/{172, "utf32", "utf32_lithuanian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
625 /*56*/{173, "utf32", "utf32_slovak_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
626 /*56*/{174, "utf32", "utf32_spanish2_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
627 /*56*/{175, "utf32", "utf32_roman_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
628 /*56*/{176, "utf32", "utf32_persian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
629 /*56*/{177, "utf32", "utf32_esperanto_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
630 /*56*/{178, "utf32", "utf32_hungarian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
631 /*56*/{179, "utf32", "utf32_sinhala_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
632 /*56*/{180, "utf32", "utf32_german2_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
633 /*56*/{181, "utf32", "utf32_croatian_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
634 /*56*/{182, "utf32", "utf32_unicode_520_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
635 /*56*/{183, "utf32", "utf32_vietnamese_ci", 4, 4, "UTF-32 Unicode", mysqlnd_mbcharlen_utf32, check_mb_utf32},
636 
637 	{ 192, UTF8_MB3, UTF8_MB3"_unicode_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
638 	{ 193, UTF8_MB3, UTF8_MB3"_icelandic_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
639 	{ 194, UTF8_MB3, UTF8_MB3"_latvian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3,  check_mb_utf8mb3_valid},
640 	{ 195, UTF8_MB3, UTF8_MB3"_romanian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
641 	{ 196, UTF8_MB3, UTF8_MB3"_slovenian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
642 	{ 197, UTF8_MB3, UTF8_MB3"_polish_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
643 	{ 198, UTF8_MB3, UTF8_MB3"_estonian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
644 	{ 199, UTF8_MB3, UTF8_MB3"_spanish_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
645 	{ 200, UTF8_MB3, UTF8_MB3"_swedish_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
646 	{ 201, UTF8_MB3, UTF8_MB3"_turkish_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
647 	{ 202, UTF8_MB3, UTF8_MB3"_czech_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
648 	{ 203, UTF8_MB3, UTF8_MB3"_danish_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid },
649 	{ 204, UTF8_MB3, UTF8_MB3"_lithuanian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid },
650 	{ 205, UTF8_MB3, UTF8_MB3"_slovak_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
651 	{ 206, UTF8_MB3, UTF8_MB3"_spanish2_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
652 	{ 207, UTF8_MB3, UTF8_MB3"_roman_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
653 	{ 208, UTF8_MB3, UTF8_MB3"_persian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
654 	{ 209, UTF8_MB3, UTF8_MB3"_esperanto_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
655 	{ 210, UTF8_MB3, UTF8_MB3"_hungarian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
656 	{ 211, UTF8_MB3, UTF8_MB3"_sinhala_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
657 	{ 212, UTF8_MB3, UTF8_MB3"_german2_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
658 	{ 213, UTF8_MB3, UTF8_MB3"_croatian_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
659 	{ 214, UTF8_MB3, UTF8_MB3"_unicode_520_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
660 	{ 215, UTF8_MB3, UTF8_MB3"_vietnamese_ci", 1, 3, "", mysqlnd_mbcharlen_utf8mb3, check_mb_utf8mb3_valid},
661 
662 	{ 224, UTF8_MB4, UTF8_MB4"_unicode_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
663 	{ 225, UTF8_MB4, UTF8_MB4"_icelandic_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
664 	{ 226, UTF8_MB4, UTF8_MB4"_latvian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
665 	{ 227, UTF8_MB4, UTF8_MB4"_romanian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
666 	{ 228, UTF8_MB4, UTF8_MB4"_slovenian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
667 	{ 229, UTF8_MB4, UTF8_MB4"_polish_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
668 	{ 230, UTF8_MB4, UTF8_MB4"_estonian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
669 	{ 231, UTF8_MB4, UTF8_MB4"_spanish_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
670 	{ 232, UTF8_MB4, UTF8_MB4"_swedish_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
671 	{ 233, UTF8_MB4, UTF8_MB4"_turkish_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
672 	{ 234, UTF8_MB4, UTF8_MB4"_czech_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
673 	{ 235, UTF8_MB4, UTF8_MB4"_danish_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
674 	{ 236, UTF8_MB4, UTF8_MB4"_lithuanian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
675 	{ 237, UTF8_MB4, UTF8_MB4"_slovak_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
676 	{ 238, UTF8_MB4, UTF8_MB4"_spanish2_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
677 	{ 239, UTF8_MB4, UTF8_MB4"_roman_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
678 	{ 240, UTF8_MB4, UTF8_MB4"_persian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
679 	{ 241, UTF8_MB4, UTF8_MB4"_esperanto_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
680 	{ 242, UTF8_MB4, UTF8_MB4"_hungarian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
681 	{ 243, UTF8_MB4, UTF8_MB4"_sinhala_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
682 	{ 244, UTF8_MB4, UTF8_MB4"_german2_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
683 	{ 245, UTF8_MB4, UTF8_MB4"_croatian_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
684 	{ 246, UTF8_MB4, UTF8_MB4"_unicode_520_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
685 	{ 247, UTF8_MB4, UTF8_MB4"_vietnamese_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
686 	{ 248, "gb18030", "gb18030_chinese_ci", 1, 4, "", mysqlnd_mbcharlen_gb18030, my_ismbchar_gb18030},
687 	{ 249, "gb18030", "gb18030_bin", 1, 4, "", mysqlnd_mbcharlen_gb18030, my_ismbchar_gb18030},
688 
689 	{ 254, UTF8_MB3, UTF8_MB3"_general_cs", 1, 3, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
690 	{ 255, UTF8_MB4, UTF8_MB4"_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
691 	{ 256, UTF8_MB4, UTF8_MB4"_de_pb_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
692 	{ 257, UTF8_MB4, UTF8_MB4"_is_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
693 	{ 258, UTF8_MB4, UTF8_MB4"_lv_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
694 	{ 259, UTF8_MB4, UTF8_MB4"_ro_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
695 	{ 260, UTF8_MB4, UTF8_MB4"_sl_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
696 	{ 261, UTF8_MB4, UTF8_MB4"_pl_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
697 	{ 262, UTF8_MB4, UTF8_MB4"_et_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
698 	{ 263, UTF8_MB4, UTF8_MB4"_es_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
699 	{ 264, UTF8_MB4, UTF8_MB4"_sv_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
700 	{ 265, UTF8_MB4, UTF8_MB4"_tr_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
701 	{ 266, UTF8_MB4, UTF8_MB4"_cs_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
702 	{ 267, UTF8_MB4, UTF8_MB4"_da_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
703 	{ 268, UTF8_MB4, UTF8_MB4"_lt_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
704 	{ 269, UTF8_MB4, UTF8_MB4"_sk_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
705 	{ 270, UTF8_MB4, UTF8_MB4"_es_trad_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
706 	{ 271, UTF8_MB4, UTF8_MB4"_la_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
707 	{ 272, UTF8_MB4, UTF8_MB4"_fa_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
708 	{ 273, UTF8_MB4, UTF8_MB4"_eo_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
709 	{ 274, UTF8_MB4, UTF8_MB4"_hu_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
710 	{ 275, UTF8_MB4, UTF8_MB4"_hr_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
711 	{ 276, UTF8_MB4, UTF8_MB4"_si_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
712 	{ 277, UTF8_MB4, UTF8_MB4"_vi_0900_ai_ci", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
713 	{ 278, UTF8_MB4, UTF8_MB4"_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
714 	{ 279, UTF8_MB4, UTF8_MB4"_de_pb_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
715 	{ 280, UTF8_MB4, UTF8_MB4"_is_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
716 	{ 281, UTF8_MB4, UTF8_MB4"_lv_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
717 	{ 282, UTF8_MB4, UTF8_MB4"_ro_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
718 	{ 283, UTF8_MB4, UTF8_MB4"_sl_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
719 	{ 284, UTF8_MB4, UTF8_MB4"_pl_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
720 	{ 285, UTF8_MB4, UTF8_MB4"_et_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
721 	{ 286, UTF8_MB4, UTF8_MB4"_es_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
722 	{ 287, UTF8_MB4, UTF8_MB4"_sv_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
723 	{ 288, UTF8_MB4, UTF8_MB4"_tr_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
724 	{ 289, UTF8_MB4, UTF8_MB4"_cs_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
725 	{ 290, UTF8_MB4, UTF8_MB4"_da_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
726 	{ 291, UTF8_MB4, UTF8_MB4"_lt_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
727 	{ 292, UTF8_MB4, UTF8_MB4"_sk_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
728 	{ 293, UTF8_MB4, UTF8_MB4"_es_trad_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
729 	{ 294, UTF8_MB4, UTF8_MB4"_la_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
730 	{ 295, UTF8_MB4, UTF8_MB4"_fa_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
731 	{ 296, UTF8_MB4, UTF8_MB4"_eo_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
732 	{ 297, UTF8_MB4, UTF8_MB4"_hu_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
733 	{ 298, UTF8_MB4, UTF8_MB4"_hr_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
734 	{ 299, UTF8_MB4, UTF8_MB4"_si_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
735 	{ 300, UTF8_MB4, UTF8_MB4"_vi_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
736 	{ 303, UTF8_MB4, UTF8_MB4"_ja_0900_as_cs", 1, 4, "", mysqlnd_mbcharlen_utf8, check_mb_utf8_valid},
737 	{   0, NULL, NULL, 0, 0, NULL, NULL, NULL}
738 };
739 /* }}} */
740 
741 
742 /* {{{ mysqlnd_find_charset_nr */
mysqlnd_find_charset_nr(unsigned int charsetnr)743 PHPAPI const MYSQLND_CHARSET * mysqlnd_find_charset_nr(unsigned int charsetnr)
744 {
745 	const MYSQLND_CHARSET * c = mysqlnd_charsets;
746 
747 	do {
748 		if (c->nr == charsetnr) {
749 			return c;
750 		}
751 		++c;
752 	} while (c[0].nr != 0);
753 	return NULL;
754 }
755 /* }}} */
756 
757 
758 /* {{{ mysqlnd_find_charset_name */
mysqlnd_find_charset_name(const char * const name)759 PHPAPI const MYSQLND_CHARSET * mysqlnd_find_charset_name(const char * const name)
760 {
761 	if (name) {
762 		const MYSQLND_CHARSET * c = mysqlnd_charsets;
763 		do {
764 			if (!strcasecmp(c->name, name)) {
765 				return c;
766 			}
767 			++c;
768 		} while (c[0].nr != 0);
769 	}
770 	return NULL;
771 }
772 /* }}} */
773 
774 
775 /* {{{ mysqlnd_cset_escape_quotes */
mysqlnd_cset_escape_quotes(const MYSQLND_CHARSET * const cset,char * newstr,const char * escapestr,size_t escapestr_len)776 PHPAPI zend_ulong mysqlnd_cset_escape_quotes(const MYSQLND_CHARSET * const cset, char *newstr,
777 										const char * escapestr, size_t escapestr_len)
778 {
779 	const char 	*newstr_s = newstr;
780 	const char 	*newstr_e = newstr + 2 * escapestr_len;
781 	const char 	*end = escapestr + escapestr_len;
782 	zend_bool	escape_overflow = FALSE;
783 
784 	DBG_ENTER("mysqlnd_cset_escape_quotes");
785 
786 	for (;escapestr < end; escapestr++) {
787 		unsigned int len = 0;
788 		/* check unicode characters */
789 
790 		if (cset->char_maxlen > 1 && (len = cset->mb_valid(escapestr, end))) {
791 
792 			/* check possible overflow */
793 			if ((newstr + len) > newstr_e) {
794 				escape_overflow = TRUE;
795 				break;
796 			}
797 			/* copy mb char without escaping it */
798 			while (len--) {
799 				*newstr++ = *escapestr++;
800 			}
801 			escapestr--;
802 			continue;
803 		}
804 		if (*escapestr == '\'') {
805 			if (newstr + 2 > newstr_e) {
806 				escape_overflow = TRUE;
807 				break;
808 			}
809 			*newstr++ = '\'';
810 			*newstr++ = '\'';
811 		} else {
812 			if (newstr + 1 > newstr_e) {
813 				escape_overflow = TRUE;
814 				break;
815 			}
816 			*newstr++ = *escapestr;
817 		}
818 	}
819 	*newstr = '\0';
820 
821 	if (escape_overflow) {
822 		DBG_RETURN((ulong)~0);
823 	}
824 	DBG_RETURN((ulong)(newstr - newstr_s));
825 }
826 /* }}} */
827 
828 
829 /* {{{ mysqlnd_cset_escape_slashes */
mysqlnd_cset_escape_slashes(const MYSQLND_CHARSET * const cset,char * newstr,const char * escapestr,size_t escapestr_len)830 PHPAPI zend_ulong mysqlnd_cset_escape_slashes(const MYSQLND_CHARSET * const cset, char *newstr,
831 										 const char * escapestr, size_t escapestr_len)
832 {
833 	const char 	*newstr_s = newstr;
834 	const char 	*newstr_e = newstr + 2 * escapestr_len;
835 	const char 	*end = escapestr + escapestr_len;
836 	zend_bool	escape_overflow = FALSE;
837 
838 	DBG_ENTER("mysqlnd_cset_escape_slashes");
839 	DBG_INF_FMT("charset=%s", cset->name);
840 
841 	for (;escapestr < end; escapestr++) {
842 		char esc = '\0';
843 		unsigned int len = 0;
844 
845 		/* check unicode characters */
846 		if (cset->char_maxlen > 1 && (len = cset->mb_valid(escapestr, end))) {
847 			/* check possible overflow */
848 			if ((newstr + len) > newstr_e) {
849 				escape_overflow = TRUE;
850 				break;
851 			}
852 			/* copy mb char without escaping it */
853 			while (len--) {
854 				*newstr++ = *escapestr++;
855 			}
856 			escapestr--;
857 			continue;
858 		}
859 		if (cset->char_maxlen > 1 && cset->mb_charlen(*escapestr) > 1) {
860 			esc = *escapestr;
861 		} else {
862 			switch (*escapestr) {
863 				case 0:
864 					esc = '0';
865 					break;
866 				case '\n':
867 					esc = 'n';
868 					break;
869 				case '\r':
870 					esc = 'r';
871 					break;
872 				case '\\':
873 				case '\'':
874 				case '"':
875 					esc = *escapestr;
876 					break;
877 				case '\032':
878 					esc = 'Z';
879 					break;
880 			}
881 		}
882 		if (esc) {
883 			if (newstr + 2 > newstr_e) {
884 				escape_overflow = TRUE;
885 				break;
886 			}
887 			/* copy escaped character */
888 			*newstr++ = '\\';
889 			*newstr++ = esc;
890 		} else {
891 			if (newstr + 1 > newstr_e) {
892 				escape_overflow = TRUE;
893 				break;
894 			}
895 			/* copy non escaped character */
896 			*newstr++ = *escapestr;
897 		}
898 	}
899 	*newstr = '\0';
900 
901 	if (escape_overflow) {
902 		DBG_RETURN((ulong)~0);
903 	}
904 	DBG_RETURN((ulong)(newstr - newstr_s));
905 }
906 /* }}} */
907 
908 
909 static struct st_mysqlnd_plugin_charsets mysqlnd_plugin_charsets_plugin =
910 {
911 	{
912 		MYSQLND_PLUGIN_API_VERSION,
913 		"charsets",
914 		MYSQLND_VERSION_ID,
915 		PHP_MYSQLND_VERSION,
916 		"PHP License 3.01",
917 		"Andrey Hristov <andrey@php.net>,  Ulf Wendel <uw@php.net>, Georg Richter <georg@php.net>",
918 		{
919 			NULL, /* no statistics , will be filled later if there are some */
920 			NULL, /* no statistics */
921 		},
922 		{
923 			NULL /* plugin shutdown */
924 		}
925 	},
926 	{/* methods */
927 		mysqlnd_find_charset_nr,
928 		mysqlnd_find_charset_name,
929 		mysqlnd_cset_escape_quotes,
930 		mysqlnd_cset_escape_slashes
931 	}
932 };
933 
934 
935 /* {{{ mysqlnd_charsets_plugin_register */
936 void
mysqlnd_charsets_plugin_register(void)937 mysqlnd_charsets_plugin_register(void)
938 {
939 	mysqlnd_plugin_register_ex((struct st_mysqlnd_plugin_header *) &mysqlnd_plugin_charsets_plugin);
940 }
941 /* }}} */
942 
943 
944 /*
945  * Local variables:
946  * tab-width: 4
947  * c-basic-offset: 4
948  * End:
949  * vim600: noet sw=4 ts=4 fdm=marker
950  * vim<600: noet sw=4 ts=4
951  */
952