michael@0: /*
michael@0: Copyright (c) 2007, Adobe Systems, Incorporated
michael@0: All rights reserved.
michael@0: 
michael@0: Redistribution and use in source and binary forms, with or without
michael@0: modification, are permitted provided that the following conditions are
michael@0: met:
michael@0: 
michael@0: * Redistributions of source code must retain the above copyright
michael@0:   notice, this list of conditions and the following disclaimer.
michael@0: 
michael@0: * Redistributions in binary form must reproduce the above copyright
michael@0:   notice, this list of conditions and the following disclaimer in the
michael@0:   documentation and/or other materials provided with the distribution.
michael@0: 
michael@0: * Neither the name of Adobe Systems, Network Resonance nor the names of its
michael@0:   contributors may be used to endorse or promote products derived from
michael@0:   this software without specific prior written permission.
michael@0: 
michael@0: THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
michael@0: "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
michael@0: LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
michael@0: A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
michael@0: OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
michael@0: SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
michael@0: LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
michael@0: DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
michael@0: THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
michael@0: (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
michael@0: OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
michael@0: */
michael@0: 
michael@0: 
michael@0: #ifdef LINUX
michael@0: #define _GNU_SOURCE 1
michael@0: #endif
michael@0: #include <string.h>
michael@0: 
michael@0: #include <errno.h>
michael@0: #include <csi_platform.h>
michael@0: 
michael@0: #include <assert.h>
michael@0: #include <locale.h>
michael@0: #include <stdlib.h>
michael@0: #include <wchar.h>
michael@0: #ifdef DARWIN
michael@0: #define HAVE_XLOCALE
michael@0: #endif
michael@0: 
michael@0: #ifdef __FreeBSD__
michael@0: #include <osreldate.h>
michael@0: # if __FreeBSD_version > 900505
michael@0: #  define HAVE_XLOCALE
michael@0: # endif
michael@0: #endif
michael@0: 
michael@0: #ifdef HAVE_XLOCALE
michael@0: #include <xlocale.h>
michael@0: #endif /* HAVE_XLOCALE */
michael@0: 
michael@0: #include "nr_api.h"
michael@0: #include "mbslen.h"
michael@0: 
michael@0: /* get number of characters in a mult-byte character string */
michael@0: int
michael@0: mbslen(const char *s, size_t *ncharsp)
michael@0: {
michael@0: #ifdef HAVE_XLOCALE
michael@0:     static locale_t loc = 0;
michael@0:     static int initialized = 0;
michael@0: #endif /* HAVE_XLOCALE */
michael@0: #ifdef WIN32
michael@0:     char *my_locale=0;
michael@0:     unsigned int i;
michael@0: #endif  /* WIN32 */
michael@0:     int _status;
michael@0:     size_t nbytes;
michael@0:     int nchars;
michael@0:     mbstate_t mbs;
michael@0: 
michael@0: #ifdef HAVE_XLOCALE
michael@0:     if (! initialized) {
michael@0:         initialized = 1;
michael@0:         loc = newlocale(LC_CTYPE_MASK, "UTF-8", LC_GLOBAL_LOCALE);
michael@0:     }
michael@0: 
michael@0:     if (loc == 0) {
michael@0:         /* unable to create the UTF-8 locale */
michael@0:         assert(loc != 0);  /* should never happen */
michael@0: #endif /* HAVE_XLOCALE */
michael@0: 
michael@0: #ifdef WIN32
michael@0:     if (!setlocale(LC_CTYPE, 0))
michael@0:         ABORT(R_INTERNAL);
michael@0: 
michael@0:     if (!(my_locale = r_strdup(setlocale(LC_CTYPE, 0))))
michael@0:         ABORT(R_NO_MEMORY);
michael@0: 
michael@0:     for (i=0; i<strlen(my_locale); i++)
michael@0:         my_locale[i] = toupper(my_locale[i]);
michael@0: 
michael@0:     if (!strstr(my_locale, "UTF-8") && !strstr(my_locale, "UTF8"))
michael@0:         ABORT(R_NOT_FOUND);
michael@0: #else
michael@0:     /* can't count UTF-8 characters with mbrlen if the locale isn't UTF-8 */
michael@0:     /* null-checking setlocale is required because Android */
michael@0:     char *locale = setlocale(LC_CTYPE, 0);
michael@0:     /* some systems use "utf8" instead of "UTF-8" like Fedora 17 */
michael@0:     if (!locale || (!strcasestr(locale, "UTF-8") && !strcasestr(locale, "UTF8")))
michael@0:         ABORT(R_NOT_FOUND);
michael@0: #endif
michael@0: 
michael@0: #ifdef HAVE_XLOCALE
michael@0:     }
michael@0: #endif /* HAVE_XLOCALE */
michael@0: 
michael@0:     memset(&mbs, 0, sizeof(mbs));
michael@0:     nchars = 0;
michael@0: 
michael@0: #ifdef HAVE_XLOCALE
michael@0:     while (*s != '\0' && (nbytes = mbrlen_l(s, strlen(s), &mbs, loc)) != 0)
michael@0: #else
michael@0:     while (*s != '\0' && (nbytes = mbrlen(s, strlen(s), &mbs)) != 0)
michael@0: #endif /* HAVE_XLOCALE */
michael@0:     {
michael@0:         if (nbytes == (size_t)-1)   /* should never happen */ {
michael@0:             ABORT(R_INTERNAL);
michael@0:         }
michael@0:         if (nbytes == (size_t)-2)   /* encoding error */ {
michael@0:             ABORT(R_BAD_DATA);
michael@0:         }
michael@0: 
michael@0:         s += nbytes;
michael@0:         ++nchars;
michael@0:     }
michael@0: 
michael@0:     *ncharsp = nchars;
michael@0: 
michael@0:     _status = 0;
michael@0:   abort:
michael@0: #ifdef WIN32
michael@0:     RFREE(my_locale);
michael@0: #endif
michael@0:     return _status;
michael@0: }
michael@0: