/* Encoding utility from UTF-8 to another charset and vice versa
Copyright (C) 2001, 2002 Peter Verthez
- Permission granted to do anything with this file that you want, as long
- as the above copyright is retained in all copies.
- THERE IS NO WARRANTY - USE AT YOUR OWN RISK
+ The UTF8 tools library is free software; you can redistribute it
+ and/or modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ The Gedcom parser library is distributed in the hope that it will be
+ useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with the Gedcom parser library; if not, write to the
+ Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ 02111-1307 USA.
*/
/* $Id$ */
/* $Name$ */
-#include "utf8.h"
+#include "utf8tools.h"
#include <stdlib.h>
#include <string.h>
#include <errno.h>
char* unknown;
};
-void reset_conv_buffer(conv_buffer_t buf)
+static void reset_conv_buffer(conv_buffer_t buf)
{
memset(buf->buffer, 0, buf->size);
}
}
}
-char* grow_conv_buffer(conv_buffer_t buf, char* curr_pos)
+static char* grow_conv_buffer(conv_buffer_t buf, char* curr_pos)
{
size_t outlen, new_size;
char* new_buffer;
}
}
-char* convert_from_utf8(convert_t conv, const char* input, int* conv_fails)
+char* convert_from_utf8(convert_t conv, const char* input, int* conv_fails,
+ size_t* output_len)
{
- size_t insize = strlen(input);
+ size_t insize;
size_t outsize;
ICONV_CONST char* inptr = (ICONV_CONST char*) input;
char *outptr;
size_t nconv;
struct conv_buffer* outbuf;
- if (!conv || !conv->outbuf) {
- if (conv_fails != NULL) *conv_fails = insize;
+ if (!conv || !conv->outbuf || !input) {
+ if (conv_fails != NULL) *conv_fails = (input ? strlen(input) : 0);
return NULL;
}
+ insize = strlen(input);
/* make sure we start from an empty state */
iconv(conv->from_utf8, NULL, NULL, NULL, NULL);
if (conv_fails != NULL) *conv_fails = 0;
}
nconv = iconv(conv->from_utf8, &inptr, &insize, &outptr, &outsize);
}
+ if (output_len) *output_len = outptr - outbuf->buffer;
return outbuf->buffer;
}
-char* convert_to_utf8(convert_t conv, const char* input)
+char* convert_to_utf8(convert_t conv, const char* input, size_t input_len)
{
- size_t insize = strlen(input);
size_t outsize;
ICONV_CONST char *inptr = (ICONV_CONST char*) input;
char *outptr;
size_t nconv;
struct conv_buffer* outbuf;
- if (!conv || !conv->outbuf)
+ if (!conv || !conv->outbuf || !input)
return NULL;
/* make sure we start from an empty state */
iconv(conv->to_utf8, NULL, NULL, NULL, NULL);
outptr = outbuf->buffer;
outsize = outbuf->size;
reset_conv_buffer(conv->outbuf);
- nconv = iconv(conv->to_utf8, &inptr, &insize, &outptr, &outsize);
+ nconv = iconv(conv->to_utf8, &inptr, &input_len, &outptr, &outsize);
while (nconv == (size_t)-1) {
if (errno == E2BIG) {
/* grow the output buffer */
/* EBADF is an error which should be captured by the first if above */
return NULL;
}
- nconv = iconv(conv->to_utf8, &inptr, &insize, &outptr, &outsize);
+ nconv = iconv(conv->to_utf8, &inptr, &input_len, &outptr, &outsize);
}
return outbuf->buffer;
}
if (!conv || !conv->outbuf)
return NULL;
+ if (!input) {
+ iconv(conv->to_utf8, NULL, NULL, NULL, NULL);
+ reset_conv_buffer(inbuf);
+ conv->insize = 0;
+ return NULL;
+ }
+
/* set up input buffer (concatenate to what was left previous time) */
/* can't use strcpy, because possible null bytes from unicode */
while (conv->insize + input_len > inbuf->size)