strfunc.cc 8.43 KB
Newer Older
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
/* Copyright (C) 2003 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 */

/* Some useful string utility functions used by the MySQL server */

#include "mysql_priv.h"

/*
  Return bitmap for strings used in a set

  SYNOPSIS
  find_set()
  lib			Strings in set
  str			Strings of set-strings separated by ','
  err_pos		If error, set to point to start of wrong set string
  err_len		If error, set to the length of wrong set string
  set_warning		Set to 1 if some string in set couldn't be used

  NOTE
    We delete all end space from str before comparison

  RETURN
    bitmap of all sets found in x.
    set_warning is set to 1 if there was any sets that couldn't be set
*/

static const char field_separator=',';

42 43
ulonglong find_set(TYPELIB *lib, const char *str, uint length, CHARSET_INFO *cs,
                   char **err_pos, uint *err_len, bool *set_warning)
44
{
45 46
  CHARSET_INFO *strip= cs ? cs : &my_charset_latin1;
  const char *end= str + strip->cset->lengthsp(strip, str, length);
47
  ulonglong found= 0;
48
  *err_pos= 0;                  // No error yet
49 50 51 52 53 54 55
  if (str != end)
  {
    const char *start= str;    
    for (;;)
    {
      const char *pos= start;
      uint var_len;
56
      int mblen= 1;
57

58 59 60 61 62 63 64 65 66 67 68 69 70 71
      if (cs && cs->mbminlen > 1)
      {
        for ( ; pos < end; pos+= mblen)
        {
          my_wc_t wc;
          if ((mblen= cs->cset->mb_wc(cs, &wc, (const uchar *) pos, 
                                               (const uchar *) end)) < 1)
            mblen= 1; // Not to hang on a wrong multibyte sequence
          if (wc == (my_wc_t) field_separator)
            break;
        }
      }
      else
        for (; pos != end && *pos != field_separator; pos++) ;
72
      var_len= (uint) (pos - start);
73 74
      uint find= cs ? find_type2(lib, start, var_len, cs) :
                      find_type(lib, start, var_len, (bool) 0);
75 76 77 78 79 80 81 82
      if (!find)
      {
        *err_pos= (char*) start;
        *err_len= var_len;
        *set_warning= 1;
      }
      else
        found|= ((longlong) 1 << (find - 1));
83
      if (pos >= end)
84
        break;
85
      start= pos + mblen;
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
    }
  }
  return found;
}


/*
  Function to find a string in a TYPELIB
  (Same format as mysys/typelib.c)

  SYNOPSIS
   find_type()
   lib			TYPELIB (struct of pointer to values + count)
   find			String to find
   length		Length of string to find
   part_match		Allow part matching of value

 RETURN
  0 error
  > 0 position in TYPELIB->type_names +1
*/

uint find_type(TYPELIB *lib, const char *find, uint length, bool part_match)
{
  uint found_count=0, found_pos=0;
  const char *end= find+length;
  const char *i;
  const char *j;
  for (uint pos=0 ; (j=lib->type_names[pos++]) ; )
  {
    for (i=find ; i != end && 
	   my_toupper(system_charset_info,*i) == 
	   my_toupper(system_charset_info,*j) ; i++, j++) ;
    if (i == end)
    {
      if (! *j)
	return(pos);
      found_count++;
      found_pos= pos;
    }
  }
unknown's avatar
unknown committed
127
  return(found_count == 1 && part_match ? found_pos : 0);
128 129 130
}


131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
/*
  Find a string in a list of strings according to collation

  SYNOPSIS
   find_type2()
   lib			TYPELIB (struct of pointer to values + count)
   x			String to find
   length               String length
   cs			Character set + collation to use for comparison

  NOTES

  RETURN
    0	No matching value
    >0  Offset+1 in typelib for matched string
*/

uint find_type2(TYPELIB *typelib, const char *x, uint length, CHARSET_INFO *cs)
{
150
  int pos;
151 152
  const char *j;
  DBUG_ENTER("find_type2");
153
  DBUG_PRINT("enter",("x: '%.*s'  lib: 0x%lx", length, x, typelib));
154 155 156 157 158 159

  if (!typelib->count)
  {
    DBUG_PRINT("exit",("no count"));
    DBUG_RETURN(0);
  }
160

161
  for (pos=0 ; (j=typelib->type_names[pos]) ; pos++)
162 163 164 165 166 167 168 169 170 171
  {
    if (!my_strnncoll(cs, (const uchar*) x, length,
                          (const uchar*) j, typelib->type_lengths[pos]))
      DBUG_RETURN(pos+1);
  }
  DBUG_PRINT("exit",("Couldn't find type"));
  DBUG_RETURN(0);
} /* find_type */


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
/*
  Un-hex all elements in a typelib

  SYNOPSIS
   unhex_type2()
   interval       TYPELIB (struct of pointer to values + lengths + count)

  NOTES

  RETURN
    N/A
*/

void unhex_type2(TYPELIB *interval)
{
  for (uint pos= 0; pos < interval->count; pos++)
  {
    char *from, *to;
    for (from= to= (char*) interval->type_names[pos]; *from; )
    {
      /*
        Note, hexchar_to_int(*from++) doesn't work
        one some compilers, e.g. IRIX. Looks like a compiler
        bug in inline functions in combination with arguments
        that have a side effect. So, let's use from[0] and from[1]
        and increment 'from' by two later.
      */

      *to++= (char) (hexchar_to_int(from[0]) << 4) +
                     hexchar_to_int(from[1]);
      from+= 2;
    }
    interval->type_lengths[pos] /= 2;
  }
}


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
/*
  Check if the first word in a string is one of the ones in TYPELIB

  SYNOPSIS
    check_word()
    lib		TYPELIB
    val		String to check
    end		End of input
    end_of_word	Store value of last used byte here if we found word

  RETURN
    0	 No matching value
    > 1  lib->type_names[#-1] matched
	 end_of_word will point to separator character/end in 'val'
*/

uint check_word(TYPELIB *lib, const char *val, const char *end,
		const char **end_of_word)
{
  int res;
  const char *ptr;

  /* Fiend end of word */
  for (ptr= val ; ptr < end && my_isalpha(&my_charset_latin1, *ptr) ; ptr++)
    ;
  if ((res=find_type(lib, val, (uint) (ptr - val), 1)) > 0)
    *end_of_word= ptr;
  return res;
}
238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260


/*
  Converts a string between character sets

  SYNOPSIS
    strconvert()
    from_cs       source character set
    from          source, a null terminated string
    to            destination buffer
    to_length     destination buffer length

  NOTES
    'to' is always terminated with a '\0' character.
    If there is no enough space to convert whole string,
    only prefix is converted, and terminated with '\0'.

  RETURN VALUES
    result string length
*/


uint strconvert(CHARSET_INFO *from_cs, const char *from,
261
                CHARSET_INFO *to_cs, char *to, uint to_length, uint *errors)
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
{
  int cnvres;
  my_wc_t wc;
  char *to_start= to;
  uchar *to_end= (uchar*) to + to_length - 1;
  int (*mb_wc)(struct charset_info_st *, my_wc_t *, const uchar *,
	       const uchar *)= from_cs->cset->mb_wc;
  int (*wc_mb)(struct charset_info_st *, my_wc_t, uchar *s, uchar *e)=
    to_cs->cset->wc_mb;
  uint error_count= 0;

  while (1)
  {
    /*
      Using 'from + 10' is safe:
      - it is enough to scan a single character in any character set.
      - if remaining string is shorter than 10, then mb_wc will return
        with error because of unexpected '\0' character.
    */
    if ((cnvres= (*mb_wc)(from_cs, &wc,
                          (uchar*) from, (uchar*) from + 10)) > 0)
    {
      if (!wc)
        break;
      from+= cnvres;
    }
    else if (cnvres == MY_CS_ILSEQ)
    {
      error_count++;
      from++;
      wc= '?';
    }
    else
      break; // Impossible char.

outp:

    if ((cnvres= (*wc_mb)(to_cs, wc, (uchar*) to, to_end)) > 0)
      to+= cnvres;
    else if (cnvres == MY_CS_ILUNI && wc != '?')
    {
      error_count++;
      wc= '?';
      goto outp;
    }
    else
      break;
  }
  *to= '\0';
311
  *errors= error_count;
312 313 314
  return (uint32) (to - to_start);

}
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


/*
  Searches for a LEX_STRING in an LEX_STRING array.

  SYNOPSIS
    find_string_in_array()
      heap    The array
      needle  The string to search for

  NOTE
    The last LEX_STRING in the array should have str member set to NULL

  RETURN VALUES
    -1   Not found
    >=0  Ordinal position
*/

int find_string_in_array(LEX_STRING * const haystack, LEX_STRING * const needle,
                         CHARSET_INFO * const cs)
{
  const LEX_STRING *pos;
  for (pos= haystack; pos->str; pos++)
    if (!cs->coll->strnncollsp(cs, (uchar *) pos->str, pos->length,
                               (uchar *) needle->str, needle->length, 0))
    {
      return (pos - haystack);
    }
  return -1;
}