int mbsToC16s( const char *mbStr, char16_t *c16Str, size_t len)
{
if( mbStr == NULL || c16Str == NULL || len == 0) // Sanity checks.
return -1;
mbstate_t mbstate = {0};
char16_t c16;
int count = 0, i = 0, rv = 0,
nBytes = (int)strlen(mbStr)+1;
do {
rv = (int)mbrtoc16( &c16, mbStr+i, nBytes-i, &mbstate);
switch( rv)
{
case 0: c16Str[count] = 0; i = nBytes; // End of string.
break;
case -1: // Encoding error.
case -2: count = -1;
break;
default:
if( count < (int)len-1 )
{
c16Str[count++] = c16;
if( rv > 0) i += rv; // rv != -3
}
else count = -1;
}
} while( count > 0 && i < nBytes);
return count;
}
int _RTL_FUNC mbtoc16(char16_t *pc16, const char *s, size_t n)
{
size_t rv ;
if (!s || !*s)
return 0 ;
if (n ==0)
return -1 ;
rv = mbrtoc16(pc16,s,n,&__getRtlData()->mbtowc_st);
if (rv == (size_t)-2)
rv = (size_t)-1;
return (int)rv ;
}
int
main(int argc, char *argv[])
{
mbstate_t s;
size_t len;
char16_t c16;
/*
* C/POSIX locale.
*/
printf("1..1\n");
/* Null wide character, internal state. */
assert(mbrtoc16(&c16, "", 1, NULL) == 0);
assert(c16 == 0);
/* Null wide character. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "", 1, &s) == 0);
assert(c16 == 0);
/* Latin letter A, internal state. */
assert(mbrtoc16(NULL, 0, 0, NULL) == 0);
assert(mbrtoc16(&c16, "A", 1, NULL) == 1);
assert(c16 == L'A');
/* Latin letter A. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "A", 1, &s) == 1);
assert(c16 == L'A');
/* Incomplete character sequence. */
c16 = L'z';
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "", 0, &s) == (size_t)-2);
assert(c16 == L'z');
/* Check that mbrtoc16() doesn't access the buffer when n == 0. */
c16 = L'z';
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "", 0, &s) == (size_t)-2);
assert(c16 == L'z');
/* Check that mbrtoc16() doesn't read ahead too aggressively. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "AB", 2, &s) == 1);
assert(c16 == L'A');
assert(mbrtoc16(&c16, "C", 1, &s) == 1);
assert(c16 == L'C');
/*
* ISO-8859-1.
*/
assert(strcmp(setlocale(LC_CTYPE, "en_US.ISO8859-1"),
"en_US.ISO8859-1") == 0);
/* Currency sign. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "\xa4", 1, &s) == 1);
assert(c16 == 0xa4);
/*
* ISO-8859-15.
*/
assert(strcmp(setlocale(LC_CTYPE, "en_US.ISO8859-15"),
"en_US.ISO8859-15") == 0);
/* Euro sign. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "\xa4", 1, &s) == 1);
assert(c16 == 0x20ac);
/*
* UTF-8.
*/
assert(strcmp(setlocale(LC_CTYPE, "en_US.UTF-8"), "en_US.UTF-8") == 0);
/* Null wide character, internal state. */
assert(mbrtoc16(NULL, 0, 0, NULL) == 0);
assert(mbrtoc16(&c16, "", 1, NULL) == 0);
assert(c16 == 0);
/* Null wide character. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "", 1, &s) == 0);
assert(c16 == 0);
/* Latin letter A, internal state. */
assert(mbrtoc16(NULL, 0, 0, NULL) == 0);
assert(mbrtoc16(&c16, "A", 1, NULL) == 1);
assert(c16 == L'A');
/* Latin letter A. */
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "A", 1, &s) == 1);
assert(c16 == L'A');
/* Incomplete character sequence (zero length). */
c16 = L'z';
memset(&s, 0, sizeof(s));
assert(mbrtoc16(&c16, "", 0, &s) == (size_t)-2);
assert(c16 == L'z');
/* Incomplete character sequence (truncated double-byte). */
memset(&s, 0, sizeof(s));
c16 = 0;
assert(mbrtoc16(&c16, "\xc3", 1, &s) == (size_t)-2);
/* Same as above, but complete. */
memset(&s, 0, sizeof(s));
c16 = 0;
assert(mbrtoc16(&c16, "\xc3\x84", 2, &s) == 2);
assert(c16 == 0xc4);
/* Test restarting behaviour. */
memset(&s, 0, sizeof(s));
c16 = 0;
assert(mbrtoc16(&c16, "\xc3", 1, &s) == (size_t)-2);
assert(c16 == 0);
assert(mbrtoc16(&c16, "\xb7", 1, &s) == 1);
assert(c16 == 0xf7);
/* Surrogate pair. */
memset(&s, 0, sizeof(s));
c16 = 0;
assert(mbrtoc16(&c16, "\xf0\x9f\x92\xa9", 4, &s) == 4);
assert(c16 == 0xd83d);
assert(mbrtoc16(&c16, "", 0, &s) == (size_t)-3);
assert(c16 == 0xdca9);
/* Letter e with acute, precomposed. */
memset(&s, 0, sizeof(s));
c16 = 0;
assert(mbrtoc16(&c16, "\xc3\xa9", 2, &s) == 2);
assert(c16 == 0xe9);
/* Letter e with acute, combined. */
memset(&s, 0, sizeof(s));
c16 = 0;
assert(mbrtoc16(&c16, "\x65\xcc\x81", 3, &s) == 1);
assert(c16 == 0x65);
assert(mbrtoc16(&c16, "\xcc\x81", 2, &s) == 2);
assert(c16 == 0x301);
printf("ok 1 - mbrtoc16()\n");
return (0);
}
static int
do_test (void)
{
if (setlocale (LC_ALL, "de_DE.UTF-8") == NULL)
{
puts ("cannot set locale");
return 1;
}
int result = 0;
char32_t c32 = 48;
do
{
if (c32 >= 0xd800 && c32 <= 0xe000)
continue;
char buf[20];
size_t n1 = c32rtomb (buf, c32, NULL);
if (n1 <= 0)
{
printf ("c32rtomb for U'\\x%" PRIx32 "' failed\n", (uint32_t) c32);
result = 1;
continue;
}
char32_t c32out;
size_t n2 = mbrtoc32 (&c32out, buf, n1, NULL);
if ((ssize_t) n2 < 0)
{
printf ("mbrtoc32 for U'\\x%" PRIx32 "' failed\n", (uint32_t) c32);
result = 1;
continue;
}
if (n2 != n1)
{
printf ("mbrtoc32 for U'\\x%" PRIx32 "' consumed %zu bytes, not %zu\n",
(uint32_t) c32, n2, n1);
result = 1;
}
else if (c32out != c32)
{
printf ("mbrtoc32 for U'\\x%" PRIx32 "' produced U'\\x%" PRIx32 "\n",
(uint32_t) c32, (uint32_t) c32out);
result = 1;
}
char16_t c16;
size_t n3 = mbrtoc16 (&c16, buf, n1, NULL);
if (n3 != n1)
{
printf ("mbrtoc16 for U'\\x%" PRIx32 "' did not consume all bytes\n",
(uint32_t) c32);
result = 1;
continue;
}
if (c32 < 0x10000)
{
if (c16 != c32)
{
printf ("mbrtoc16 for U'\\x%" PRIx32 "' produce u'\\x%" PRIx16 "'\n",
(uint32_t) c32, (uint16_t) c16);
result = 1;
continue;
}
}
else
{
buf[0] = '1';
char16_t c16_2;
size_t n4 = mbrtoc16 (&c16_2, buf, 1, NULL);
if (n4 != (size_t) -3)
{
printf ("second mbrtoc16 for U'\\x%" PRIx32 "' did not return -3\n",
(uint32_t) c32);
result = 1;
continue;
}
if (c32 != (((uint32_t) (c16 - 0xd7c0)) << 10) + (c16_2 - 0xdc00))
{
printf ("mbrtoc16 for U'\\x%" PRIx32 "' returns U'\\x%" PRIx32 "\n",
(uint32_t) c32,
(((uint32_t) (c16 - 0xd7c0)) << 10) + (c16_2 - 0xdc00));
result = 1;
continue;
}
}
buf[0] = '\0';
char16_t c16_nul;
n3 = mbrtoc16 (&c16_nul, buf, n1, NULL);
if (n3 != 0)
{
printf ("mbrtoc16 for '\\0' returns %zd\n", n3);
result = 1;
continue;
}
if (c32 < 0x10000)
{
size_t n5 = c16rtomb (buf, c16, NULL);
if ((ssize_t) n5 < 0)
{
printf ("c16rtomb for U'\\x%" PRIx32 "' failed with %zd\n",
(uint32_t) c32, n5);
result = 1;
continue;
}
if (n5 != n1)
{
printf ("c16rtomb for U'\\x%" PRIx32 "' produced %zu bytes instead of %zu bytes\n",
(uint32_t) c32, n5, n1);
result = 1;
continue;
}
}
}
while ((c32 += 0x1111) <= U'\x12000');
return result;
}
