lib/mbscasecmp.c

   1 /* Case-insensitive string comparison function.
   2    Copyright (C) 1998-1999, 2005-2024 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2005,
   4    based on earlier glibc code.
   5
   6    This file is free software: you can redistribute it and/or modify
   7    it under the terms of the GNU Lesser General Public License as
   8    published by the Free Software Foundation, either version 3 of the
   9    License, or (at your option) any later version.
  10
  11    This file is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14    GNU Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public License
  17    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  18
  19 #include <config.h>
  20
  21 /* Specification.  */
  22 #include <string.h>
  23
  24 #include <ctype.h>
  25 #include <limits.h>
  26 #include <stdlib.h>
  27 #include <uchar.h>
  28
  29 #if GNULIB_MCEL_PREFER
  30 # include "mcel.h"
  31 #else
  32 # include "mbuiterf.h"
  33 #endif
  34
  35 /* Compare the character strings S1 and S2, ignoring case, returning less than,
  36    equal to or greater than zero if S1 is lexicographically less than, equal to
  37    or greater than S2.
  38    Note: This function may, in multibyte locales, return 0 for strings of
  39    different lengths!  */
  40 int
  41 mbscasecmp (const char *s1, const char *s2)
  42 {
  43   if (s1 == s2)
  44     return 0;
  45
  46   const char *iter1 = s1;
  47   const char *iter2 = s2;
  48
  49   /* Be careful not to look at the entire extent of s1 or s2 until needed.
  50      This is useful because when two strings differ, the difference is
  51      most often already in the very few first characters.  */
  52   if (MB_CUR_MAX > 1)
  53     {
  54 #if GNULIB_MCEL_PREFER
  55       while (true)
  56         {
  57           mcel_t g1 = mcel_scanz (iter1); iter1 += g1.len;
  58           mcel_t g2 = mcel_scanz (iter2); iter2 += g2.len;
  59           int cmp = mcel_tocmp (c32tolower, g1, g2);
  60           if (cmp | !g1.ch)
  61             return cmp;
  62         }
  63 #else
  64       mbuif_state_t state1;
  65       mbuif_init (state1);
  66
  67       mbuif_state_t state2;
  68       mbuif_init (state2);
  69
  70       while (mbuif_avail (state1, iter1) && mbuif_avail (state2, iter2))
  71         {
  72           mbchar_t cur1 = mbuif_next (state1, iter1);
  73           mbchar_t cur2 = mbuif_next (state2, iter2);
  74           int cmp = mb_casecmp (cur1, cur2);
  75
  76           if (cmp != 0)
  77             return cmp;
  78
  79           iter1 += mb_len (cur1);
  80           iter2 += mb_len (cur2);
  81         }
  82       if (mbuif_avail (state1, iter1))
  83         /* s2 terminated before s1.  */
  84         return 1;
  85       if (mbuif_avail (state2, iter2))
  86         /* s1 terminated before s2.  */
  87         return -1;
  88       return 0;
  89 #endif
  90     }
  91   else
  92     for (;;)
  93       {
  94         unsigned char c1 = *iter1++;
  95         unsigned char c2 = *iter2++;
  96         /* On machines where 'char' and 'int' are types of the same size, the
  97            difference of two 'unsigned char' values - including the sign bit -
  98            doesn't fit in an 'int'.  */
  99         int cmp = UCHAR_MAX <= INT_MAX ? c1 - c2 : _GL_CMP (c1, c2);
 100         if (cmp != 0)
 101           {
 102             c1 = tolower (c1);
 103             if (c1 == c2)
 104               cmp = 0;
 105             else
 106               {
 107                 c2 = tolower (c2);
 108                 cmp = UCHAR_MAX <= INT_MAX ? c1 - c2 : _GL_CMP (c1, c2);
 109               }
 110           }
 111         if (cmp | !c1)
 112           return cmp;
 113       }
 114 }