Last active
September 6, 2019 18:30
-
-
Save silvioprog/1d05876811e8b57c05860ddc7f0d8d55 to your computer and use it in GitHub Desktop.
Convert encoding of given string from CP1252 to UTF-8 in C using iconv(3).
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* Public domain */ | |
/* Author: silvioprog */ | |
/* | |
Build and test: | |
$ gcc cp1252_to_utf8.c | |
$ ./a.out | |
A função atou() é incrível! | |
Valgrind dump: | |
$ valgrind --show-error-list=yes --tool=memcheck --gen-suppressions=all --leak-check=full --leak-resolution=med --track-origins=yes --vgdb=no ./a.out | |
==22979== Memcheck, a memory error detector | |
==22979== Copyright (C) 2002-2017, and GNU GPL'd, by Julian Seward et al. | |
==22979== Using Valgrind-3.15.0 and LibVEX; rerun with -h for copyright info | |
==22979== Command: ./a.out | |
==22979== | |
A função atou() é incrível! | |
==22979== | |
==22979== HEAP SUMMARY: | |
==22979== in use at exit: 0 bytes in 0 blocks | |
==22979== total heap usage: 14 allocs, 14 frees, 35,631 bytes allocated | |
==22979== | |
==22979== All heap blocks were freed -- no leaks are possible | |
==22979== | |
==22979== ERROR SUMMARY: 0 errors from 0 contexts (suppressed: 0 from 0) | |
Feel free to use or improve it and have a lot of fun! (: | |
*/ | |
#include <stdio.h> | |
#include <stdlib.h> | |
#include <string.h> | |
#include <errno.h> | |
#include <iconv.h> | |
static char *atou(const char *str) { | |
char *res, *out, *tmp; | |
size_t len, obl, ibl, diff; | |
iconv_t ic; | |
len = strlen(str); | |
if (len < 1) | |
return NULL; | |
res = NULL; | |
obl = len; | |
ibl = len; | |
ic = iconv_open("UTF-8", "CP1252"); | |
if (ic != (iconv_t) -1) { | |
res = malloc(len + 1); | |
if (!res) { | |
iconv_close(ic); | |
return NULL; | |
} | |
out = res; | |
while (ibl > 0) | |
if (iconv(ic, (char **) &str, &ibl, &out, &obl) == -1) { | |
if (errno == E2BIG) { | |
diff = out - res; | |
len += ibl; | |
obl += ibl; | |
tmp = realloc(res, len + 1); | |
if (tmp) { | |
res = tmp; | |
out = res + diff; | |
continue; | |
} | |
} | |
free(res); | |
res = NULL; | |
break; | |
} | |
iconv_close(ic); | |
} | |
if (res) { | |
len -= obl; | |
res[len] = 0; | |
} | |
return res; | |
} | |
int main(void) { | |
char *str = atou("A fun\xe7\xe3o atou() \xe9 incr\xedvel!"); | |
printf("%s\n", str); | |
free(str); | |
return EXIT_SUCCESS; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment