| 1 | # iconv_open-utf.m4 serial 1 |
| 2 | dnl Copyright (C) 2007-2014 Free Software Foundation, Inc. |
| 3 | dnl This file is free software; the Free Software Foundation |
| 4 | dnl gives unlimited permission to copy and/or distribute it, |
| 5 | dnl with or without modifications, as long as this notice is preserved. |
| 6 | |
| 7 | # A placeholder to ensure that this m4 file gets included by aclocal. |
| 8 | AC_DEFUN([gl_FUNC_ICONV_OPEN_UTF], []) |
| 9 | |
| 10 | AC_DEFUN([gl_FUNC_ICONV_OPEN_UTF_SUPPORT], |
| 11 | [ |
| 12 | dnl This macro relies on am_cv_func_iconv and gl_func_iconv_gnu from |
| 13 | dnl gl_FUNC_ICONV_OPEN, but is called from within gl_FUNC_ICONV_OPEN. |
| 14 | dnl *Not* AC_REQUIRE([gl_FUNC_ICONV_OPEN]). |
| 15 | AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles |
| 16 | AC_REQUIRE([gl_ICONV_H_DEFAULTS]) |
| 17 | if test "$am_cv_func_iconv" = yes; then |
| 18 | AC_CACHE_CHECK([whether iconv supports conversion between UTF-8 and UTF-{16,32}{BE,LE}], |
| 19 | [gl_cv_func_iconv_supports_utf], |
| 20 | [ |
| 21 | save_LIBS="$LIBS" |
| 22 | LIBS="$LIBS $LIBICONV" |
| 23 | AC_RUN_IFELSE( |
| 24 | [AC_LANG_SOURCE([[ |
| 25 | #include <iconv.h> |
| 26 | #include <errno.h> |
| 27 | #include <stdio.h> |
| 28 | #include <stdlib.h> |
| 29 | #include <string.h> |
| 30 | int main () |
| 31 | { |
| 32 | int result = 0; |
| 33 | /* Test conversion from UTF-8 to UTF-16BE with no errors. */ |
| 34 | { |
| 35 | static const char input[] = |
| 36 | "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; |
| 37 | static const char expected[] = |
| 38 | "\000J\000a\000p\000a\000n\000e\000s\000e\000 \000(\145\345\147\054\212\236\000)\000 \000[\330\065\335\015\330\065\335\036\330\065\335\055\000]"; |
| 39 | iconv_t cd; |
| 40 | cd = iconv_open ("UTF-16BE", "UTF-8"); |
| 41 | if (cd == (iconv_t)(-1)) |
| 42 | result |= 1; |
| 43 | else |
| 44 | { |
| 45 | char buf[100]; |
| 46 | const char *inptr; |
| 47 | size_t inbytesleft; |
| 48 | char *outptr; |
| 49 | size_t outbytesleft; |
| 50 | size_t res; |
| 51 | inptr = input; |
| 52 | inbytesleft = sizeof (input) - 1; |
| 53 | outptr = buf; |
| 54 | outbytesleft = sizeof (buf); |
| 55 | res = iconv (cd, |
| 56 | (ICONV_CONST char **) &inptr, &inbytesleft, |
| 57 | &outptr, &outbytesleft); |
| 58 | if (!(res == 0 && inbytesleft == 0)) |
| 59 | result |= 1; |
| 60 | else if (!(outptr == buf + (sizeof (expected) - 1))) |
| 61 | result |= 1; |
| 62 | else if (!(memcmp (buf, expected, sizeof (expected) - 1) == 0)) |
| 63 | result |= 1; |
| 64 | else if (!(iconv_close (cd) == 0)) |
| 65 | result |= 1; |
| 66 | } |
| 67 | } |
| 68 | /* Test conversion from UTF-8 to UTF-16LE with no errors. */ |
| 69 | { |
| 70 | static const char input[] = |
| 71 | "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; |
| 72 | static const char expected[] = |
| 73 | "J\000a\000p\000a\000n\000e\000s\000e\000 \000(\000\345\145\054\147\236\212)\000 \000[\000\065\330\015\335\065\330\036\335\065\330\055\335]\000"; |
| 74 | iconv_t cd; |
| 75 | cd = iconv_open ("UTF-16LE", "UTF-8"); |
| 76 | if (cd == (iconv_t)(-1)) |
| 77 | result |= 2; |
| 78 | else |
| 79 | { |
| 80 | char buf[100]; |
| 81 | const char *inptr; |
| 82 | size_t inbytesleft; |
| 83 | char *outptr; |
| 84 | size_t outbytesleft; |
| 85 | size_t res; |
| 86 | inptr = input; |
| 87 | inbytesleft = sizeof (input) - 1; |
| 88 | outptr = buf; |
| 89 | outbytesleft = sizeof (buf); |
| 90 | res = iconv (cd, |
| 91 | (ICONV_CONST char **) &inptr, &inbytesleft, |
| 92 | &outptr, &outbytesleft); |
| 93 | if (!(res == 0 && inbytesleft == 0)) |
| 94 | result |= 2; |
| 95 | else if (!(outptr == buf + (sizeof (expected) - 1))) |
| 96 | result |= 2; |
| 97 | else if (!(memcmp (buf, expected, sizeof (expected) - 1) == 0)) |
| 98 | result |= 2; |
| 99 | else if (!(iconv_close (cd) == 0)) |
| 100 | result |= 2; |
| 101 | } |
| 102 | } |
| 103 | /* Test conversion from UTF-8 to UTF-32BE with no errors. */ |
| 104 | { |
| 105 | static const char input[] = |
| 106 | "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; |
| 107 | static const char expected[] = |
| 108 | "\000\000\000J\000\000\000a\000\000\000p\000\000\000a\000\000\000n\000\000\000e\000\000\000s\000\000\000e\000\000\000 \000\000\000(\000\000\145\345\000\000\147\054\000\000\212\236\000\000\000)\000\000\000 \000\000\000[\000\001\325\015\000\001\325\036\000\001\325\055\000\000\000]"; |
| 109 | iconv_t cd; |
| 110 | cd = iconv_open ("UTF-32BE", "UTF-8"); |
| 111 | if (cd == (iconv_t)(-1)) |
| 112 | result |= 4; |
| 113 | else |
| 114 | { |
| 115 | char buf[100]; |
| 116 | const char *inptr; |
| 117 | size_t inbytesleft; |
| 118 | char *outptr; |
| 119 | size_t outbytesleft; |
| 120 | size_t res; |
| 121 | inptr = input; |
| 122 | inbytesleft = sizeof (input) - 1; |
| 123 | outptr = buf; |
| 124 | outbytesleft = sizeof (buf); |
| 125 | res = iconv (cd, |
| 126 | (ICONV_CONST char **) &inptr, &inbytesleft, |
| 127 | &outptr, &outbytesleft); |
| 128 | if (!(res == 0 && inbytesleft == 0)) |
| 129 | result |= 4; |
| 130 | else if (!(outptr == buf + (sizeof (expected) - 1))) |
| 131 | result |= 4; |
| 132 | else if (!(memcmp (buf, expected, sizeof (expected) - 1) == 0)) |
| 133 | result |= 4; |
| 134 | else if (!(iconv_close (cd) == 0)) |
| 135 | result |= 4; |
| 136 | } |
| 137 | } |
| 138 | /* Test conversion from UTF-8 to UTF-32LE with no errors. */ |
| 139 | { |
| 140 | static const char input[] = |
| 141 | "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; |
| 142 | static const char expected[] = |
| 143 | "J\000\000\000a\000\000\000p\000\000\000a\000\000\000n\000\000\000e\000\000\000s\000\000\000e\000\000\000 \000\000\000(\000\000\000\345\145\000\000\054\147\000\000\236\212\000\000)\000\000\000 \000\000\000[\000\000\000\015\325\001\000\036\325\001\000\055\325\001\000]\000\000\000"; |
| 144 | iconv_t cd; |
| 145 | cd = iconv_open ("UTF-32LE", "UTF-8"); |
| 146 | if (cd == (iconv_t)(-1)) |
| 147 | result |= 8; |
| 148 | else |
| 149 | { |
| 150 | char buf[100]; |
| 151 | const char *inptr; |
| 152 | size_t inbytesleft; |
| 153 | char *outptr; |
| 154 | size_t outbytesleft; |
| 155 | size_t res; |
| 156 | inptr = input; |
| 157 | inbytesleft = sizeof (input) - 1; |
| 158 | outptr = buf; |
| 159 | outbytesleft = sizeof (buf); |
| 160 | res = iconv (cd, |
| 161 | (ICONV_CONST char **) &inptr, &inbytesleft, |
| 162 | &outptr, &outbytesleft); |
| 163 | if (!(res == 0 && inbytesleft == 0)) |
| 164 | result |= 8; |
| 165 | else if (!(outptr == buf + (sizeof (expected) - 1))) |
| 166 | result |= 8; |
| 167 | else if (!(memcmp (buf, expected, sizeof (expected) - 1) == 0)) |
| 168 | result |= 8; |
| 169 | else if (!(iconv_close (cd) == 0)) |
| 170 | result |= 8; |
| 171 | } |
| 172 | } |
| 173 | /* Test conversion from UTF-16BE to UTF-8 with no errors. |
| 174 | This test fails on NetBSD 3.0. */ |
| 175 | { |
| 176 | static const char input[] = |
| 177 | "\000J\000a\000p\000a\000n\000e\000s\000e\000 \000(\145\345\147\054\212\236\000)\000 \000[\330\065\335\015\330\065\335\036\330\065\335\055\000]"; |
| 178 | static const char expected[] = |
| 179 | "Japanese (\346\227\245\346\234\254\350\252\236) [\360\235\224\215\360\235\224\236\360\235\224\255]"; |
| 180 | iconv_t cd; |
| 181 | cd = iconv_open ("UTF-8", "UTF-16BE"); |
| 182 | if (cd == (iconv_t)(-1)) |
| 183 | result |= 16; |
| 184 | else |
| 185 | { |
| 186 | char buf[100]; |
| 187 | const char *inptr; |
| 188 | size_t inbytesleft; |
| 189 | char *outptr; |
| 190 | size_t outbytesleft; |
| 191 | size_t res; |
| 192 | inptr = input; |
| 193 | inbytesleft = sizeof (input) - 1; |
| 194 | outptr = buf; |
| 195 | outbytesleft = sizeof (buf); |
| 196 | res = iconv (cd, |
| 197 | (ICONV_CONST char **) &inptr, &inbytesleft, |
| 198 | &outptr, &outbytesleft); |
| 199 | if (!(res == 0 && inbytesleft == 0)) |
| 200 | result |= 16; |
| 201 | else if (!(outptr == buf + (sizeof (expected) - 1))) |
| 202 | result |= 16; |
| 203 | else if (!(memcmp (buf, expected, sizeof (expected) - 1) == 0)) |
| 204 | result |= 16; |
| 205 | else if (!(iconv_close (cd) == 0)) |
| 206 | result |= 16; |
| 207 | } |
| 208 | } |
| 209 | return result; |
| 210 | }]])], |
| 211 | [gl_cv_func_iconv_supports_utf=yes], |
| 212 | [gl_cv_func_iconv_supports_utf=no], |
| 213 | [ |
| 214 | dnl We know that GNU libiconv, GNU libc, and Solaris >= 9 do. |
| 215 | dnl OSF/1 5.1 has these encodings, but inserts a BOM in the "to" |
| 216 | dnl direction. |
| 217 | gl_cv_func_iconv_supports_utf=no |
| 218 | if test $gl_func_iconv_gnu = yes; then |
| 219 | gl_cv_func_iconv_supports_utf=yes |
| 220 | else |
| 221 | changequote(,)dnl |
| 222 | case "$host_os" in |
| 223 | solaris2.9 | solaris2.1[0-9]) gl_cv_func_iconv_supports_utf=yes ;; |
| 224 | esac |
| 225 | changequote([,])dnl |
| 226 | fi |
| 227 | ]) |
| 228 | LIBS="$save_LIBS" |
| 229 | ]) |
| 230 | fi |
| 231 | ]) |