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
|
/* Copyright (C) 2000 MySQL AB
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 */
#include "mysys_priv.h"
#include "mysys_err.h"
#include <m_ctype.h>
#include <m_string.h>
#include <my_dir.h>
#include <my_sys.h>
#include <my_xml.h>
namespace mysql_parser
{
/*
The code below implements this functionality:
- Initializing charset related structures
- Loading dynamic charsets
- Searching for a proper CHARSET_INFO
using charset name, collation name or collation ID
- Setting server default character set
*/
my_bool my_charset_same(CHARSET_INFO *cs1, CHARSET_INFO *cs2)
{
return ((cs1 == cs2) || !strcmp(cs1->csname,cs2->csname));
}
static uint
get_collation_number_internal(const char *name)
{
CHARSET_INFO **cs;
for (cs= all_charsets;
cs < all_charsets+array_elements(all_charsets)-1 ;
cs++)
{
if ( cs[0] && cs[0]->name &&
!my_strcasecmp(&my_charset_latin1, cs[0]->name, name))
return cs[0]->number;
}
return 0;
}
static my_bool init_state_maps(CHARSET_INFO *cs)
{
uint i;
uchar *state_map;
uchar *ident_map;
if (!(cs->state_map= (uchar*) my_once_alloc(256, MYF(MY_WME))))
return 1;
if (!(cs->ident_map= (uchar*) my_once_alloc(256, MYF(MY_WME))))
return 1;
state_map= cs->state_map;
ident_map= cs->ident_map;
/* Fill state_map with states to get a faster parser */
for (i=0; i < 256 ; i++)
{
if (my_isalpha(cs,i))
state_map[i]=(uchar) MY_LEX_IDENT;
else if (my_isdigit(cs,i))
state_map[i]=(uchar) MY_LEX_NUMBER_IDENT;
#if defined(USE_MB) && defined(USE_MB_IDENT)
else if (my_mbcharlen(cs, i)>1)
state_map[i]=(uchar) MY_LEX_IDENT;
#endif
else if (my_isspace(cs,i))
state_map[i]=(uchar) MY_LEX_SKIP;
else
state_map[i]=(uchar) MY_LEX_CHAR;
}
state_map[(uchar)'_']=state_map[(uchar)'$']=(uchar) MY_LEX_IDENT;
state_map[(uchar)'\'']=(uchar) MY_LEX_STRING;
state_map[(uchar)'.']=(uchar) MY_LEX_REAL_OR_POINT;
state_map[(uchar)'>']=state_map[(uchar)'=']=state_map[(uchar)'!']= (uchar) MY_LEX_CMP_OP;
state_map[(uchar)'<']= (uchar) MY_LEX_LONG_CMP_OP;
state_map[(uchar)'&']=state_map[(uchar)'|']=(uchar) MY_LEX_BOOL;
state_map[(uchar)'#']=(uchar) MY_LEX_COMMENT;
state_map[(uchar)';']=(uchar) MY_LEX_SEMICOLON;
state_map[(uchar)':']=(uchar) MY_LEX_SET_VAR;
state_map[0]=(uchar) MY_LEX_EOL;
state_map[(uchar)'\\']= (uchar) MY_LEX_ESCAPE;
state_map[(uchar)'/']= (uchar) MY_LEX_LONG_COMMENT;
state_map[(uchar)'*']= (uchar) MY_LEX_END_LONG_COMMENT;
state_map[(uchar)'@']= (uchar) MY_LEX_USER_END;
state_map[(uchar) '`']= (uchar) MY_LEX_USER_VARIABLE_DELIMITER;
state_map[(uchar)'"']= (uchar) MY_LEX_STRING_OR_DELIMITER;
/*
Create a second map to make it faster to find identifiers
*/
for (i=0; i < 256 ; i++)
{
ident_map[i]= (uchar) (state_map[i] == MY_LEX_IDENT ||
state_map[i] == MY_LEX_NUMBER_IDENT);
}
/* Special handling of hex and binary strings */
state_map[(uchar)'x']= state_map[(uchar)'X']= (uchar) MY_LEX_IDENT_OR_HEX;
state_map[(uchar)'b']= state_map[(uchar)'B']= (uchar) MY_LEX_IDENT_OR_BIN;
state_map[(uchar)'n']= state_map[(uchar)'N']= (uchar) MY_LEX_IDENT_OR_NCHAR;
return 0;
}
static void simple_cs_init_functions(CHARSET_INFO *cs)
{
if (cs->state & MY_CS_BINSORT)
cs->coll= &my_collation_8bit_bin_handler;
else
cs->coll= &my_collation_8bit_simple_ci_handler;
cs->cset= &my_charset_8bit_handler;
}
static int cs_copy_data(CHARSET_INFO *to, CHARSET_INFO *from)
{
to->number= from->number ? from->number : to->number;
if (from->csname)
if (!(to->csname= my_once_strdup(from->csname,MYF(MY_WME))))
goto err;
if (from->name)
if (!(to->name= my_once_strdup(from->name,MYF(MY_WME))))
goto err;
if (from->comment)
if (!(to->comment= my_once_strdup(from->comment,MYF(MY_WME))))
goto err;
if (from->ctype)
{
if (!(to->ctype= (uchar*) my_once_memdup((char*) from->ctype,
MY_CS_CTYPE_TABLE_SIZE,
MYF(MY_WME))))
goto err;
if (init_state_maps(to))
goto err;
}
if (from->to_lower)
if (!(to->to_lower= (uchar*) my_once_memdup((char*) from->to_lower,
MY_CS_TO_LOWER_TABLE_SIZE,
MYF(MY_WME))))
goto err;
if (from->to_upper)
if (!(to->to_upper= (uchar*) my_once_memdup((char*) from->to_upper,
MY_CS_TO_UPPER_TABLE_SIZE,
MYF(MY_WME))))
goto err;
if (from->sort_order)
{
if (!(to->sort_order= (uchar*) my_once_memdup((char*) from->sort_order,
MY_CS_SORT_ORDER_TABLE_SIZE,
MYF(MY_WME))))
goto err;
}
if (from->tab_to_uni)
{
uint sz= MY_CS_TO_UNI_TABLE_SIZE*sizeof(uint16);
if (!(to->tab_to_uni= (uint16*) my_once_memdup((char*)from->tab_to_uni,
sz, MYF(MY_WME))))
goto err;
}
if (from->tailoring)
if (!(to->tailoring= my_once_strdup(from->tailoring,MYF(MY_WME))))
goto err;
return 0;
err:
return 1;
}
static my_bool simple_cs_is_full(CHARSET_INFO *cs)
{
return ((cs->csname && cs->tab_to_uni && cs->ctype && cs->to_upper &&
cs->to_lower) &&
(cs->number && cs->name &&
(cs->sort_order || (cs->state & MY_CS_BINSORT) )));
}
static int add_collation(CHARSET_INFO *cs)
{
if (cs->name && (cs->number ||
(cs->number=get_collation_number_internal(cs->name))))
{
if (!all_charsets[cs->number])
{
if (!(all_charsets[cs->number]=
(CHARSET_INFO*) my_once_alloc(sizeof(CHARSET_INFO),MYF(0))))
return MY_XML_ERROR;
bzero((void*)all_charsets[cs->number],sizeof(CHARSET_INFO));
}
if (cs->primary_number == cs->number)
cs->state |= MY_CS_PRIMARY;
if (cs->binary_number == cs->number)
cs->state |= MY_CS_BINSORT;
all_charsets[cs->number]->state|= cs->state;
if (!(all_charsets[cs->number]->state & MY_CS_COMPILED))
{
CHARSET_INFO *new_= all_charsets[cs->number];
if (cs_copy_data(all_charsets[cs->number],cs))
return MY_XML_ERROR;
if (!strcmp(cs->csname,"ucs2") )
{
#if defined(HAVE_CHARSET_ucs2) && defined(HAVE_UCA_COLLATIONS)
new_->cset= my_charset_ucs2_general_uca.cset;
new_->coll= my_charset_ucs2_general_uca.coll;
new_->strxfrm_multiply= my_charset_ucs2_general_uca.strxfrm_multiply;
new_->min_sort_char= my_charset_ucs2_general_uca.min_sort_char;
new_->max_sort_char= my_charset_ucs2_general_uca.max_sort_char;
new_->mbminlen= 2;
new_->mbmaxlen= 2;
new_->state |= MY_CS_AVAILABLE | MY_CS_LOADED;
#endif
}
else
{
uchar *sort_order= all_charsets[cs->number]->sort_order;
simple_cs_init_functions(all_charsets[cs->number]);
new_->mbminlen= 1;
new_->mbmaxlen= 1;
if (simple_cs_is_full(all_charsets[cs->number]))
{
all_charsets[cs->number]->state |= MY_CS_LOADED;
}
all_charsets[cs->number]->state|= MY_CS_AVAILABLE;
/*
Check if case sensitive sort order: A < a < B.
We need MY_CS_FLAG for regex library, and for
case sensitivity flag for 5.0 client protocol,
to support isCaseSensitive() method in JDBC driver
*/
if (sort_order && sort_order[(uchar)'A'] < sort_order[(uchar)'a'] &&
sort_order[(uchar)'a'] < sort_order[(uchar)'B'])
all_charsets[cs->number]->state|= MY_CS_CSSORT;
}
}
else
{
/*
We need the below to make get_charset_name()
and get_charset_number() working even if a
character set has not been really incompiled.
The above functions are used for example
in error message compiler extra/comp_err.c.
If a character set was compiled, this information
will get lost and overwritten in add_compiled_collation().
*/
CHARSET_INFO *dst= all_charsets[cs->number];
dst->number= cs->number;
if (cs->comment)
if (!(dst->comment= my_once_strdup(cs->comment,MYF(MY_WME))))
return MY_XML_ERROR;
if (cs->csname)
if (!(dst->csname= my_once_strdup(cs->csname,MYF(MY_WME))))
return MY_XML_ERROR;
if (cs->name)
if (!(dst->name= my_once_strdup(cs->name,MYF(MY_WME))))
return MY_XML_ERROR;
}
cs->number= 0;
cs->primary_number= 0;
cs->binary_number= 0;
cs->name= NULL;
cs->state= 0;
cs->sort_order= NULL;
cs->state= 0;
}
return MY_XML_OK;
}
#define MY_MAX_ALLOWED_BUF 1024*1024
#define MY_CHARSET_INDEX "Index.xml"
const char *charsets_dir= NULL;
static int charset_initialized=0;
static my_bool my_read_charset_file(const char *filename, myf myflags)
{
char *buf;
int fd;
uint len;
MY_STAT stat_info;
if (!my_stat(filename, &stat_info, MYF(myflags)) ||
((len= (uint)stat_info.st_size) > MY_MAX_ALLOWED_BUF) ||
!(buf= (char *)my_malloc(len,myflags)))
return TRUE;
if ((fd=my_open(filename,O_RDONLY,myflags)) < 0)
{
my_free(buf,myflags);
return TRUE;
}
#ifdef _MSC_VER
#pragma warning(push)
#pragma warning(disable:4996)
#endif
len=read(fd,buf,len);
#ifdef _MSC_VER
#pragma warning(pop)
#endif
my_close(fd,myflags);
if (my_parse_charset_xml(buf,len,add_collation))
{
#ifdef NOT_YET
printf("ERROR at line %d pos %d '%s'\n",
my_xml_error_lineno(&p)+1,
my_xml_error_pos(&p),
my_xml_error_string(&p));
#endif
}
my_free(buf, myflags);
return FALSE;
}
char *get_charsets_dir(char *buf)
{
return strxmov(buf, "./", CHARSET_DIR, NullS);
#if 0
const char *sharedir= SHAREDIR;
char *res;
DBUG_ENTER("get_charsets_dir");
if (charsets_dir != NULL)
strmake(buf, charsets_dir, FN_REFLEN-1);
else
{
if (test_if_hard_path(sharedir) ||
is_prefix(sharedir, DEFAULT_CHARSET_HOME))
strxmov(buf, sharedir, "/", CHARSET_DIR, NullS);
else
strxmov(buf, DEFAULT_CHARSET_HOME, "/", sharedir, "/", CHARSET_DIR,
NullS);
}
res= convert_dirname(buf,buf,NullS);
DBUG_PRINT("info",("charsets dir: '%s'", buf));
DBUG_RETURN(res);
#endif
}
CHARSET_INFO *all_charsets[256];
CHARSET_INFO *default_charset_info = &my_charset_latin1;
void add_compiled_collation(CHARSET_INFO *cs)
{
all_charsets[cs->number]= cs;
cs->state|= MY_CS_AVAILABLE;
}
static void *cs_alloc(uint size)
{
return my_once_alloc(size, MYF(MY_WME));
}
#ifdef __NETWARE__
my_bool STDCALL init_available_charsets(myf myflags)
#else
static my_bool init_available_charsets(myf myflags)
#endif
{
// char fname[FN_REFLEN];
my_bool error=FALSE;
/*
We have to use charset_initialized to not lock on THR_LOCK_charset
inside get_internal_charset...
*/
if (!charset_initialized)
{
CHARSET_INFO **cs;
/*
To make things thread safe we are not allowing other threads to interfere
while we may changing the cs_info_table
*/
//xxx pthread_mutex_lock(&THR_LOCK_charset);
if (!charset_initialized)
{
bzero(&all_charsets,sizeof(all_charsets));
init_compiled_charsets(myflags);
/* Copy compiled charsets */
for (cs=all_charsets;
cs < all_charsets+array_elements(all_charsets)-1 ;
cs++)
{
if (*cs)
{
if (cs[0]->ctype)
if (init_state_maps(*cs))
*cs= NULL;
}
}
// absent charsets dir in linux causes crash. compiled charsets should be enough.
////strmov(get_charsets_dir(fname), MY_CHARSET_INDEX);
//strcpy(get_charsets_dir(fname), MY_CHARSET_INDEX);
//error= my_read_charset_file(fname,myflags);
charset_initialized=1;
}
//xxx pthread_mutex_unlock(&THR_LOCK_charset);
}
return error;
}
void free_charsets(void)
{
charset_initialized=0;
}
uint get_collation_number(const char *name)
{
init_available_charsets(MYF(0));
return get_collation_number_internal(name);
}
uint get_charset_number(const char *charset_name, uint cs_flags)
{
CHARSET_INFO **cs;
init_available_charsets(MYF(0));
for (cs= all_charsets;
cs < all_charsets+array_elements(all_charsets)-1 ;
cs++)
{
if ( cs[0] && cs[0]->csname && (cs[0]->state & cs_flags) &&
!my_strcasecmp(&my_charset_latin1, cs[0]->csname, charset_name))
return cs[0]->number;
}
return 0;
}
const char *get_charset_name(uint charset_number)
{
CHARSET_INFO *cs;
init_available_charsets(MYF(0));
cs=all_charsets[charset_number];
if (cs && (cs->number == charset_number) && cs->name )
return (char*) cs->name;
return (char*) "?"; /* this mimics find_type() */
}
static CHARSET_INFO *get_internal_charset(uint cs_number, myf flags)
{
char buf[FN_REFLEN];
CHARSET_INFO *cs;
/*
To make things thread safe we are not allowing other threads to interfere
while we may changing the cs_info_table
*/
//xxx pthread_mutex_lock(&THR_LOCK_charset);
if ((cs= all_charsets[cs_number]))
{
if (!(cs->state & MY_CS_COMPILED) && !(cs->state & MY_CS_LOADED))
{
strxmov(get_charsets_dir(buf), cs->csname, ".xml", NullS);
my_read_charset_file(buf,flags);
}
cs= (cs->state & MY_CS_AVAILABLE) ? cs : NULL;
}
if (cs && !(cs->state & MY_CS_READY))
{
if ((cs->cset->init && cs->cset->init(cs, cs_alloc)) ||
(cs->coll->init && cs->coll->init(cs, cs_alloc)))
cs= NULL;
else
cs->state|= MY_CS_READY;
}
//xxx pthread_mutex_unlock(&THR_LOCK_charset);
return cs;
}
CHARSET_INFO *get_charset(uint cs_number, myf flags)
{
CHARSET_INFO *cs;
if (cs_number == default_charset_info->number)
return default_charset_info;
(void) init_available_charsets(MYF(0)); /* If it isn't initialized */
if (!cs_number || cs_number >= array_elements(all_charsets)-1)
return NULL;
cs=get_internal_charset(cs_number, flags);
if (!cs && (flags & MY_WME))
{
char index_file[FN_REFLEN], cs_string[23];
//strmov(get_charsets_dir(index_file),MY_CHARSET_INDEX);
strcpy(get_charsets_dir(index_file),MY_CHARSET_INDEX);
cs_string[0]='#';
int10_to_str(cs_number, cs_string+1, 10);
my_error(EE_UNKNOWN_CHARSET, MYF(ME_BELL), cs_string, index_file);
}
return cs;
}
CHARSET_INFO *get_charset_by_name(const char *cs_name, myf flags)
{
uint cs_number;
CHARSET_INFO *cs;
(void) init_available_charsets(MYF(0)); /* If it isn't initialized */
cs_number=get_collation_number(cs_name);
cs= cs_number ? get_internal_charset(cs_number,flags) : NULL;
if (!cs && (flags & MY_WME))
{
char index_file[FN_REFLEN];
//strmov(get_charsets_dir(index_file),MY_CHARSET_INDEX);
strcpy(get_charsets_dir(index_file),MY_CHARSET_INDEX);
my_error(EE_UNKNOWN_COLLATION, MYF(ME_BELL), cs_name, index_file);
}
return cs;
}
CHARSET_INFO *get_charset_by_csname(const char *cs_name,
uint cs_flags,
myf flags)
{
uint cs_number;
CHARSET_INFO *cs;
DBUG_ENTER("get_charset_by_csname");
DBUG_PRINT("enter",("name: '%s'", cs_name));
(void) init_available_charsets(MYF(0)); /* If it isn't initialized */
cs_number= get_charset_number(cs_name, cs_flags);
cs= cs_number ? get_internal_charset(cs_number, flags) : NULL;
if (!cs && (flags & MY_WME))
{
char index_file[FN_REFLEN];
//strmov(get_charsets_dir(index_file),MY_CHARSET_INDEX);
strcpy(get_charsets_dir(index_file),MY_CHARSET_INDEX);
my_error(EE_UNKNOWN_CHARSET, MYF(ME_BELL), cs_name, index_file);
}
DBUG_RETURN(cs);
}
/*
Escape string with backslashes (\)
SYNOPSIS
escape_string_for_mysql()
charset_info Charset of the strings
to Buffer for escaped string
to_length Length of destination buffer, or 0
from The string to escape
length The length of the string to escape
DESCRIPTION
This escapes the contents of a string by adding backslashes before special
characters, and turning others into specific escape sequences, such as
turning newlines into \n and null bytes into \0.
NOTE
To maintain compatibility with the old C API, to_length may be 0 to mean
"big enough"
RETURN VALUES
~0 The escaped string did not fit in the to buffer
>=0 The length of the escaped string
*/
ulong escape_string_for_mysql(CHARSET_INFO *charset_info,
char *to, ulong to_length,
const char *from, ulong length)
{
const char *to_start= to;
const char *end, *to_end=to_start + (to_length ? to_length-1 : 2*length);
my_bool overflow= FALSE;
#ifdef USE_MB
my_bool use_mb_flag= use_mb(charset_info);
#endif
for (end= from + length; from < end; from++)
{
char escape= 0;
#ifdef USE_MB
int tmp_length;
if (use_mb_flag && (tmp_length= my_ismbchar(charset_info, from, end)))
{
if (to + tmp_length > to_end)
{
overflow= TRUE;
break;
}
while (tmp_length--)
*to++= *from++;
from--;
continue;
}
/*
If the next character appears to begin a multi-byte character, we
escape that first byte of that apparent multi-byte character. (The
character just looks like a multi-byte character -- if it were actually
a multi-byte character, it would have been passed through in the test
above.)
Without this check, we can create a problem by converting an invalid
multi-byte character into a valid one. For example, 0xbf27 is not
a valid GBK character, but 0xbf5c is. (0x27 = ', 0x5c = \)
*/
if (use_mb_flag && (tmp_length= my_mbcharlen(charset_info, *from)) > 1)
escape= *from;
else
#endif
switch (*from) {
case 0: /* Must be escaped for 'mysql' */
escape= '0';
break;
case '\n': /* Must be escaped for logs */
escape= 'n';
break;
case '\r':
escape= 'r';
break;
case '\\':
escape= '\\';
break;
case '\'':
escape= '\'';
break;
case '"': /* Better safe than sorry */
escape= '"';
break;
case '\032': /* This gives problems on Win32 */
escape= 'Z';
break;
}
if (escape)
{
if (to + 2 > to_end)
{
overflow= TRUE;
break;
}
*to++= '\\';
*to++= escape;
}
else
{
if (to + 1 > to_end)
{
overflow= TRUE;
break;
}
*to++= *from;
}
}
*to= 0;
return overflow ? (ulong)~0 : (ulong) (to - to_start);
}
#ifdef BACKSLASH_MBTAIL
static CHARSET_INFO *fs_cset_cache= NULL;
CHARSET_INFO *fs_character_set()
{
if (!fs_cset_cache)
{
char buf[10]= "cp";
GetLocaleInfoA(LOCALE_SYSTEM_DEFAULT, LOCALE_IDEFAULTANSICODEPAGE,
buf+2, sizeof(buf)-3);
/*
We cannot call get_charset_by_name here
because fs_character_set() is executed before
LOCK_THD_charset mutex initialization, which
is used inside get_charset_by_name.
As we're now interested in cp932 only,
let's just detect it using strcmp().
*/
fs_cset_cache= !strcmp(buf, "cp932") ?
&my_charset_cp932_japanese_ci : &my_charset_bin;
}
return fs_cset_cache;
}
#endif
/*
Escape apostrophes by doubling them up
SYNOPSIS
escape_quotes_for_mysql()
charset_info Charset of the strings
to Buffer for escaped string
to_length Length of destination buffer, or 0
from The string to escape
length The length of the string to escape
DESCRIPTION
This escapes the contents of a string by doubling up any apostrophes that
it contains. This is used when the NO_BACKSLASH_ESCAPES SQL_MODE is in
effect on the server.
NOTE
To be consistent with escape_string_for_mysql(), to_length may be 0 to
mean "big enough"
RETURN VALUES
~0 The escaped string did not fit in the to buffer
>=0 The length of the escaped string
*/
ulong escape_quotes_for_mysql(CHARSET_INFO *charset_info,
char *to, ulong to_length,
const char *from, ulong length)
{
const char *to_start= to;
const char *end, *to_end=to_start + (to_length ? to_length-1 : 2*length);
my_bool overflow= FALSE;
#ifdef USE_MB
my_bool use_mb_flag= use_mb(charset_info);
#endif
for (end= from + length; from < end; from++)
{
#ifdef USE_MB
int tmp_length;
if (use_mb_flag && (tmp_length= my_ismbchar(charset_info, from, end)))
{
if (to + tmp_length > to_end)
{
overflow= TRUE;
break;
}
while (tmp_length--)
*to++= *from++;
from--;
continue;
}
/*
We don't have the same issue here with a non-multi-byte character being
turned into a multi-byte character by the addition of an escaping
character, because we are only escaping the ' character with itself.
*/
#endif
if (*from == '\'')
{
if (to + 2 > to_end)
{
overflow= TRUE;
break;
}
*to++= '\'';
*to++= '\'';
}
else
{
if (to + 1 > to_end)
{
overflow= TRUE;
break;
}
*to++= *from;
}
}
*to= 0;
return overflow ? (ulong)~0 : (ulong) (to - to_start);
}
} // namespace mysql_parser
|