man3/mbstowcs.3

   1 '\" t -*- coding: UTF-8 -*-
   2 .\" Copyright (c) Bruno Haible <haible@clisp.cons.org>
   3 .\" and Copyright 2014 Michael Kerrisk <mtk.manpages@gmail.com>
   4 .\"
   5 .\" %%%LICENSE_START(GPLv2+_DOC_ONEPARA)
   6 .\" This is free documentation; you can redistribute it and/or
   7 .\" modify it under the terms of the GNU General Public License as
   8 .\" published by the Free Software Foundation; either version 2 of
   9 .\" the License, or (at your option) any later version.
  10 .\" %%%LICENSE_END
  11 .\"
  12 .\" References consulted:
  13 .\"   GNU glibc-2 source code and manual
  14 .\"   Dinkumware C library reference http://www.dinkumware.com/
  15 .\"   OpenGroup's Single UNIX specification http://www.UNIX-systems.org/online.html
  16 .\"   ISO/IEC 9899:1999
  17 .\"
  18 .TH MBSTOWCS 3  2020-06-09 "GNU" "Linux Programmer's Manual"
  19 .SH NAME
  20 mbstowcs \- convert a multibyte string to a wide-character string
  21 .SH SYNOPSIS
  22 .nf
  23 .B #include <stdlib.h>
  24 .PP
  25 .BI "size_t mbstowcs(wchar_t *" dest ", const char *" src ", size_t " n );
  26 .fi
  27 .SH DESCRIPTION
  28 If
  29 .I dest
  30 is not NULL,
  31 the
  32 .BR mbstowcs ()
  33 function converts the
  34 multibyte string
  35 .I src
  36 to a wide-character string starting at
  37 .IR dest .
  38 At most
  39 .I n
  40 wide characters are written to
  41 .IR dest .
  42 The sequence of characters in the string
  43 .I src
  44 shall begin in the initial shift state.
  45 The conversion can stop for three reasons:
  46 .IP 1. 3
  47 An invalid multibyte sequence has been encountered.
  48 In this case,
  49 .I (size_t)\ \-1
  50 is returned.
  51 .IP 2.
  52 .I n
  53 non-L\(aq\e0\(aq wide characters have been stored at
  54 .IR dest .
  55 In this case, the number of wide characters written to
  56 .I dest
  57 is returned, but the
  58 shift state at this point is lost.
  59 .IP 3.
  60 The multibyte string has been completely converted, including the
  61 terminating null character (\(aq\e0\(aq).
  62 In this case, the number of wide characters written to
  63 .IR dest ,
  64 excluding the terminating null wide character, is returned.
  65 .PP
  66 The programmer must ensure that there is room for at least
  67 .I n
  68 wide
  69 characters at
  70 .IR dest .
  71 .PP
  72 If
  73 .IR dest
  74 is NULL,
  75 .I n
  76 is ignored, and the conversion proceeds as
  77 above, except that the converted wide characters are not written out to memory,
  78 and that no length limit exists.
  79 .PP
  80 In order to avoid the case 2 above, the programmer should make sure
  81 .I n
  82 is
  83 greater than or equal to
  84 .IR "mbstowcs(NULL,src,0)+1" .
  85 .SH RETURN VALUE
  86 The
  87 .BR mbstowcs ()
  88 function returns the number of wide characters that make
  89 up the converted part of the wide-character string, not including the
  90 terminating null wide character.
  91 If an invalid multibyte sequence was
  92 encountered,
  93 .I (size_t)\ \-1
  94 is returned.
  95 .SH ATTRIBUTES
  96 For an explanation of the terms used in this section, see
  97 .BR attributes (7).
  98 .TS
  99 allbox;
 100 lb lb lb
 101 l l l.
 102 Interface       Attribute       Value
 103 T{
 104 .BR mbstowcs ()
 105 T}      Thread safety   MT-Safe
 106 .TE
 107 .SH CONFORMING TO
 108 POSIX.1-2001, POSIX.1-2008, C99.
 109 .SH NOTES
 110 The behavior of
 111 .BR mbstowcs ()
 112 depends on the
 113 .B LC_CTYPE
 114 category of the
 115 current locale.
 116 .PP
 117 The function
 118 .BR mbsrtowcs (3)
 119 provides a better interface to the same
 120 functionality.
 121 .SH EXAMPLES
 122 The program below illustrates the use of
 123 .BR mbstowcs (),
 124 as well as some of the wide character classification functions.
 125 An example run is the following:
 126 .PP
 127 .in +4n
 128 .EX
 129 $ ./t_mbstowcs de_DE.UTF\-8 Grüße!
 130 Length of source string (excluding terminator):
 131     8 bytes
 132     6 multibyte characters
 133
 134 Wide character string is: Grüße! (6 characters)
 135     G alpha upper
 136     r alpha lower
 137     ü alpha lower
 138     ß alpha lower
 139     e alpha lower
 140     ! !alpha
 141 .EE
 142 .in
 143 .SS Program source
 144 \&
 145 .EX
 146 #include <wctype.h>
 147 #include <locale.h>
 148 #include <wchar.h>
 149 #include <stdio.h>
 150 #include <string.h>
 151 #include <stdlib.h>
 152
 153 int
 154 main(int argc, char *argv[])
 155 {
 156     size_t mbslen;      /* Number of multibyte characters in source */
 157     wchar_t *wcs;       /* Pointer to converted wide character string */
 158     wchar_t *wp;
 159
 160     if (argc < 3) {
 161         fprintf(stderr, "Usage: %s <locale> <string>\en", argv[0]);
 162         exit(EXIT_FAILURE);
 163     }
 164
 165     /* Apply the specified locale */
 166
 167     if (setlocale(LC_ALL, argv[1]) == NULL) {
 168         perror("setlocale");
 169         exit(EXIT_FAILURE);
 170     }
 171
 172     /* Calculate the length required to hold argv[2] converted to
 173        a wide character string */
 174
 175     mbslen = mbstowcs(NULL, argv[2], 0);
 176     if (mbslen == (size_t) \-1) {
 177         perror("mbstowcs");
 178         exit(EXIT_FAILURE);
 179     }
 180
 181     /* Describe the source string to the user */
 182
 183     printf("Length of source string (excluding terminator):\en");
 184     printf("    %zu bytes\en", strlen(argv[2]));
 185     printf("    %zu multibyte characters\en\en", mbslen);
 186
 187     /* Allocate wide character string of the desired size.  Add 1
 188        to allow for terminating null wide character (L\(aq\e0\(aq). */
 189
 190     wcs = calloc(mbslen + 1, sizeof(wchar_t));
 191     if (wcs == NULL) {
 192         perror("calloc");
 193         exit(EXIT_FAILURE);
 194     }
 195
 196     /* Convert the multibyte character string in argv[2] to a
 197        wide character string */
 198
 199     if (mbstowcs(wcs, argv[2], mbslen + 1) == (size_t) \-1) {
 200         perror("mbstowcs");
 201         exit(EXIT_FAILURE);
 202     }
 203
 204     printf("Wide character string is: %ls (%zu characters)\en",
 205             wcs, mbslen);
 206
 207     /* Now do some inspection of the classes of the characters in
 208        the wide character string */
 209
 210     for (wp = wcs; *wp != 0; wp++) {
 211         printf("    %lc ", (wint_t) *wp);
 212
 213         if (!iswalpha(*wp))
 214             printf("!");
 215         printf("alpha ");
 216
 217         if (iswalpha(*wp)) {
 218             if (iswupper(*wp))
 219                 printf("upper ");
 220
 221             if (iswlower(*wp))
 222                 printf("lower ");
 223         }
 224
 225         putchar(\(aq\en\(aq);
 226     }
 227
 228     exit(EXIT_SUCCESS);
 229 }
 230 .EE
 231 .SH SEE ALSO
 232 .BR mblen (3),
 233 .BR mbsrtowcs (3),
 234 .BR mbtowc (3),
 235 .BR wcstombs (3),
 236 .BR wctomb (3)