test/testiconv.c
author Sam Lantinga <slouken@libsdl.org>
Tue, 14 Mar 2006 07:45:15 +0000
changeset 1528 ff3322d66771
parent 1516 4d241ea8a1cd
child 1662 782fd950bd46
child 1895 c121d94672cb
child 3997 6a4f3a32c2e6
permissions -rw-r--r--
The check for UTF-* isn't needed anymore since UTF-8 has the same code range.
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
1501
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     1
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     2
#include <stdio.h>
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     3
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     4
#include "SDL.h"
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     5
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     6
static size_t widelen(char *data)
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     7
{
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     8
	size_t len = 0;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
     9
	Uint32 *p = (Uint32 *)data;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    10
	while(*p++) {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    11
		++len;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    12
	}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    13
	return len;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    14
}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    15
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    16
int main(int argc, char *argv[])
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    17
{
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    18
	const char * formats[] = {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    19
		"UTF8",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    20
		"UTF-8",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    21
		"UTF16BE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    22
		"UTF-16BE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    23
		"UTF16LE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    24
		"UTF-16LE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    25
		"UTF32BE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    26
		"UTF-32BE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    27
		"UTF32LE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    28
		"UTF-32LE",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    29
		"UCS4",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    30
		"UCS-4",
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    31
	};
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    32
	char buffer[BUFSIZ];
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    33
	char *ucs4;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    34
	char *test[2];
1516
4d241ea8a1cd Updated MacOS Classic build
Sam Lantinga <slouken@libsdl.org>
parents: 1502
diff changeset
    35
	int i, index = 0;
1501
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    36
	FILE *file;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    37
	int errors = 0;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    38
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    39
	if ( !argv[1] ) {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    40
		argv[1] = "utf8.txt";
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    41
	}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    42
	file = fopen(argv[1], "rb");
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    43
	if ( !file ) {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    44
		fprintf(stderr, "Unable to open %s\n", argv[1]);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    45
		return (1);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    46
	}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    47
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    48
	while ( fgets(buffer, sizeof(buffer), file) ) {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    49
		/* Convert to UCS-4 */
1516
4d241ea8a1cd Updated MacOS Classic build
Sam Lantinga <slouken@libsdl.org>
parents: 1502
diff changeset
    50
		size_t len;
1501
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    51
		ucs4 = SDL_iconv_string("UCS-4", "UTF-8", buffer, SDL_strlen(buffer)+1);
1516
4d241ea8a1cd Updated MacOS Classic build
Sam Lantinga <slouken@libsdl.org>
parents: 1502
diff changeset
    52
		len = (widelen(ucs4)+1)*4;
1501
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    53
		for ( i = 0; i < SDL_arraysize(formats); ++i ) {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    54
			test[0] = SDL_iconv_string(formats[i], "UCS-4", ucs4, len);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    55
			test[1] = SDL_iconv_string("UCS-4", formats[i], test[0], len);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    56
			if ( SDL_memcmp(test[1], ucs4, len) != 0 ) {
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    57
				fprintf(stderr, "FAIL: %s\n", formats[i]);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    58
				++errors;
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    59
			}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    60
			SDL_free(test[0]);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    61
			SDL_free(test[1]);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    62
		}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    63
		test[0] = SDL_iconv_string("UTF-8", "UCS-4", ucs4, len);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    64
		SDL_free(ucs4);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    65
		fputs(test[0], stdout);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    66
		SDL_free(test[0]);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    67
	}
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    68
	return (errors ? errors + 1 : 0);
73dc5d39bbf8 Added UTF-8 <-> UTF-16 <-> UTF-32 <-> UCS-2 <-> UCS-4 conversion capability
Sam Lantinga <slouken@libsdl.org>
parents:
diff changeset
    69
}