man3/mbstowcs.3

   1 '\" t
   2 .\" Copyright (c) Bruno Haible <haible@clisp.cons.org>
   3 .\" and Copyright 2014 Michael Kerrisk <mtk.manpages@gmail.com>
   4 .\"
   5 .\" SPDX-License-Identifier: GPL-2.0-or-later
   6 .\"
   7 .\" References consulted:
   8 .\"   GNU glibc-2 source code and manual
   9 .\"   Dinkumware C library reference http://www.dinkumware.com/
  10 .\"   OpenGroup's Single UNIX specification http://www.UNIX-systems.org/online.html
  11 .\"   ISO/IEC 9899:1999
  12 .\"
  13 .TH mbstowcs 3 (date) "Linux man-pages (unreleased)"
  14 .SH NAME
  15 mbstowcs \- convert a multibyte string to a wide-character string
  16 .SH LIBRARY
  17 Standard C library
  18 .RI ( libc ", " \-lc )
  19 .SH SYNOPSIS
  20 .nf
  21 .B #include <stdlib.h>
  22 .PP
  23 .BI "size_t mbstowcs(wchar_t " dest "[restrict ." n "], \
  24 const char *restrict " src ,
  25 .BI "                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 \[bu] 3
  47 An invalid multibyte sequence has been encountered.
  48 In this case,
  49 .I (size_t)\ \-1
  50 is returned.
  51 .IP \[bu]
  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 \[bu]
  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 .I 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 .ad l
  99 .nh
 100 .TS
 101 allbox;
 102 lbx lb lb
 103 l l l.
 104 Interface       Attribute       Value
 105 T{
 106 .BR mbstowcs ()
 107 T}      Thread safety   MT-Safe
 108 .TE
 109 .hy
 110 .ad
 111 .sp 1
 112 .SH VERSIONS
 113 The function
 114 .BR mbsrtowcs (3)
 115 provides a better interface to the same
 116 functionality.
 117 .SH STANDARDS
 118 C11, POSIX.1-2008.
 119 .SH HISTORY
 120 POSIX.1-2001, C99.
 121 .SH NOTES
 122 The behavior of
 123 .BR mbstowcs ()
 124 depends on the
 125 .B LC_CTYPE
 126 category of the
 127 current locale.
 128 .SH EXAMPLES
 129 The program below illustrates the use of
 130 .BR mbstowcs (),
 131 as well as some of the wide character classification functions.
 132 An example run is the following:
 133 .PP
 134 .in +4n
 135 .EX
 136 $ ./t_mbstowcs de_DE.UTF\-8 Grüße!
 137 Length of source string (excluding terminator):
 138     8 bytes
 139     6 multibyte characters
 140 \&
 141 Wide character string is: Grüße! (6 characters)
 142     G alpha upper
 143     r alpha lower
 144     ü alpha lower
 145     ß alpha lower
 146     e alpha lower
 147     ! !alpha
 148 .EE
 149 .in
 150 .SS Program source
 151 \&
 152 .\" SRC BEGIN (mbstowcs.c)
 153 .EX
 154 #include <locale.h>
 155 #include <stdio.h>
 156 #include <stdlib.h>
 157 #include <string.h>
 158 #include <wchar.h>
 159 #include <wctype.h>
 160 \&
 161 int
 162 main(int argc, char *argv[])
 163 {
 164     size_t mbslen;      /* Number of multibyte characters in source */
 165     wchar_t *wcs;       /* Pointer to converted wide character string */
 166 \&
 167     if (argc < 3) {
 168         fprintf(stderr, "Usage: %s <locale> <string>\en", argv[0]);
 169         exit(EXIT_FAILURE);
 170     }
 171 \&
 172     /* Apply the specified locale. */
 173 \&
 174     if (setlocale(LC_ALL, argv[1]) == NULL) {
 175         perror("setlocale");
 176         exit(EXIT_FAILURE);
 177     }
 178 \&
 179     /* Calculate the length required to hold argv[2] converted to
 180        a wide character string. */
 181 \&
 182     mbslen = mbstowcs(NULL, argv[2], 0);
 183     if (mbslen == (size_t) \-1) {
 184         perror("mbstowcs");
 185         exit(EXIT_FAILURE);
 186     }
 187 \&
 188     /* Describe the source string to the user. */
 189 \&
 190     printf("Length of source string (excluding terminator):\en");
 191     printf("    %zu bytes\en", strlen(argv[2]));
 192     printf("    %zu multibyte characters\en\en", mbslen);
 193 \&
 194     /* Allocate wide character string of the desired size.  Add 1
 195        to allow for terminating null wide character (L\[aq]\e0\[aq]). */
 196 \&
 197     wcs = calloc(mbslen + 1, sizeof(*wcs));
 198     if (wcs == NULL) {
 199         perror("calloc");
 200         exit(EXIT_FAILURE);
 201     }
 202 \&
 203     /* Convert the multibyte character string in argv[2] to a
 204        wide character string. */
 205 \&
 206     if (mbstowcs(wcs, argv[2], mbslen + 1) == (size_t) \-1) {
 207         perror("mbstowcs");
 208         exit(EXIT_FAILURE);
 209     }
 210 \&
 211     printf("Wide character string is: %ls (%zu characters)\en",
 212            wcs, mbslen);
 213 \&
 214     /* Now do some inspection of the classes of the characters in
 215        the wide character string. */
 216 \&
 217     for (wchar_t *wp = wcs; *wp != 0; wp++) {
 218         printf("    %lc ", (wint_t) *wp);
 219 \&
 220         if (!iswalpha(*wp))
 221             printf("!");
 222         printf("alpha ");
 223 \&
 224         if (iswalpha(*wp)) {
 225             if (iswupper(*wp))
 226                 printf("upper ");
 227 \&
 228             if (iswlower(*wp))
 229                 printf("lower ");
 230         }
 231 \&
 232         putchar(\[aq]\en\[aq]);
 233     }
 234 \&
 235     exit(EXIT_SUCCESS);
 236 }
 237 .EE
 238 .\" SRC END
 239 .SH SEE ALSO
 240 .BR mblen (3),
 241 .BR mbsrtowcs (3),
 242 .BR mbtowc (3),
 243 .BR wcstombs (3),
 244 .BR wctomb (3)