#include #include #include #include #include #include #include #include #include locale_t c_utf8_locale = NULL; void unicode_to_utf8(unsigned long int c, unsigned char *utf8string) { if (c <= 0x7F) { utf8string[0] = c; } else if (c <= 0x7FF) { utf8string[0] = 0xC0 | ((c >> 6) & 0x1F); utf8string[1] = 0x80 | (c & 0x3F); } else if (c <= 0xFFFF) { utf8string[0] = 0xE0 | ((c >> 12) & 0x0F); utf8string[1] = 0x80 | ((c >> 6) & 0x3F); utf8string[2] = 0x80 | (c & 0x3F); } else { utf8string[0] = 0xF0 | ((c >> 18) & 0x07); utf8string[1] = 0x80 | ((c >> 12) & 0x3F); utf8string[2] = 0x80 | ((c >> 6) & 0x3F); utf8string[3] = 0x80 | (c & 0x3F); } } size_t mbstowcs_l(wchar_t *dest, const char *src, size_t n, locale_t loc) { locale_t save_locale = uselocale(loc); size_t result; result = mbstowcs(dest, src, n); uselocale(save_locale); return result; } wchar_t unicode_to_wchar_l(int codepoint, locale_t locale) { unsigned char utf8_string[5] = {0}; wchar_t wc[3] = {0}; size_t n; if (codepoint == 0x000000) return 0x00; if (!c_utf8_locale) { c_utf8_locale = newlocale(LC_CTYPE_MASK, "C.UTF-8", NULL); if (!c_utf8_locale) { printf("locale \"C.UTF-8\" not available\n"); exit(1); } } memset(utf8_string, 0, 5); unicode_to_utf8(codepoint, utf8_string); n = mbstowcs_l(NULL, utf8_string, 0, c_utf8_locale); if (n == -1) { printf("could not convert 0x%06x to wchar_t: invalid byte sequence\n", codepoint); printf("utf8_string: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x\n", utf8_string[0], utf8_string[1], utf8_string[2], utf8_string[3], utf8_string[4]); exit(1); } mbstowcs_l(wc, utf8_string, 2, c_utf8_locale); return wc[0]; } int main(int argc, char *argv[]) { char *base_locale_string, *test_locale_string; locale_t base_locale, test_locale; if (argc < 2) { printf("Usage: ctype_test BASE_LOCALE TEST_LOCALE\n"); exit(1); } base_locale_string = argv[1]; test_locale_string = argv[2]; base_locale = newlocale(LC_CTYPE_MASK, base_locale_string, NULL); if (!base_locale) { printf("base locale \"%s\" not available\n", base_locale_string); exit(1); } test_locale = newlocale(LC_CTYPE_MASK, test_locale_string, NULL); if (!test_locale) { printf("test locale \"%s\" not available\n", test_locale_string); exit(1); } /* test plain char variants */ for (int i = -1; i <= 0x7f; i++) { bool base_isalpha = isalpha_l(i, base_locale); bool base_islower = islower_l(i, base_locale); bool base_isupper = isupper_l(i, base_locale); bool base_isdigit = isdigit_l(i, base_locale); bool base_isxdigit = isxdigit_l(i, base_locale); bool base_isalnum = isalnum_l(i, base_locale); bool base_isspace = isspace_l(i, base_locale); bool base_ispunct = ispunct_l(i, base_locale); bool base_isblank = isblank_l(i, base_locale); bool base_isprint = isprint_l(i, base_locale); bool base_isgraph = isgraph_l(i, base_locale); bool base_iscntrl = iscntrl_l(i, base_locale); bool test_isalpha = isalpha_l(i, test_locale); bool test_islower = islower_l(i, test_locale); bool test_isupper = isupper_l(i, test_locale); bool test_isdigit = isdigit_l(i, test_locale); bool test_isxdigit = isxdigit_l(i, test_locale); bool test_isalnum = isalnum_l(i, test_locale); bool test_isspace = isspace_l(i, test_locale); bool test_ispunct = ispunct_l(i, test_locale); bool test_isblank = isblank_l(i, test_locale); bool test_isprint = isprint_l(i, test_locale); bool test_isgraph = isgraph_l(i, test_locale); bool test_iscntrl = iscntrl_l(i, test_locale); if (base_isalpha != test_isalpha || base_islower != test_islower || base_isupper != test_isupper || base_isdigit != test_isdigit || base_isxdigit != test_isxdigit || base_isalnum != test_isalnum || base_isspace != test_isspace || base_ispunct != test_ispunct || base_isblank != test_isblank || base_isprint != test_isprint || base_isgraph != test_isgraph || base_iscntrl != test_iscntrl) { printf("FAILURE (%s,%s) for plain char 0x%02x\n", base_locale_string, test_locale_string, i); exit(1); } } /* test wide variants */ for (wchar_t unicode = 0; unicode < 0x10ffff; unicode++) { /* skip surrogates */ if (unicode >= 0xd800 && unicode < 0xE000) continue; wchar_t wc1 = unicode_to_wchar_l(unicode, base_locale); wchar_t wc2 = unicode_to_wchar_l(unicode, test_locale); bool base_isalpha = iswalpha_l(wc1, base_locale); bool base_islower = iswlower_l(wc1, base_locale); bool base_isupper = iswupper_l(wc1, base_locale); bool base_isdigit = iswdigit_l(wc1, base_locale); bool base_isxdigit = iswxdigit_l(wc1, base_locale); bool base_isalnum = iswalnum_l(wc1, base_locale); bool base_isspace = iswspace_l(wc1, base_locale); bool base_ispunct = iswpunct_l(wc1, base_locale); bool base_isblank = iswblank_l(wc1, base_locale); bool base_isprint = iswprint_l(wc1, base_locale); bool base_isgraph = iswgraph_l(wc1, base_locale); bool base_iscntrl = iswcntrl_l(wc1, base_locale); bool test_isalpha = iswalpha_l(wc2, test_locale); bool test_islower = iswlower_l(wc2, test_locale); bool test_isupper = iswupper_l(wc2, test_locale); bool test_isdigit = iswdigit_l(wc2, test_locale); bool test_isxdigit = iswxdigit_l(wc2, test_locale); bool test_isalnum = iswalnum_l(wc2, test_locale); bool test_isspace = iswspace_l(wc2, test_locale); bool test_ispunct = iswpunct_l(wc2, test_locale); bool test_isblank = iswblank_l(wc2, test_locale); bool test_isprint = iswprint_l(wc2, test_locale); bool test_isgraph = iswgraph_l(wc2, test_locale); bool test_iscntrl = iswcntrl_l(wc2, test_locale); /* just a sanity check that works on some platforms, but not guaranteed */ if (unicode != wc1 || unicode != wc2) printf("codepoint 0x%06x: 0x%06x 0x%06x\n", unicode, wc1, wc2); if (base_isalpha != test_isalpha || base_islower != test_islower || base_isupper != test_isupper || base_isdigit != test_isdigit || base_isxdigit != test_isxdigit || base_isalnum != test_isalnum || base_isspace != test_isspace || base_ispunct != test_ispunct || base_isblank != test_isblank || base_isprint != test_isprint || base_isgraph != test_isgraph || base_iscntrl != test_iscntrl) { printf("FAILURE (%s,%s) for unicode char 0x%06x\n", base_locale_string, test_locale_string, unicode); exit(1); } } freelocale(base_locale); freelocale(test_locale); }