ICONV(3C) Standard C Library Functions ICONV(3C)
NAME
iconv - code conversion function
SYNOPSIS
Default
#include <iconv.h>
extern size_t iconv(
iconv_t cd,
const char **restrict inbuf,
size_t *restrict inbytesleft,
char **restrict outbuf,
size_t *restrict outbytesleft);
SUSv3 #include <iconv.h>
size_t iconv(
iconv_t cd,
char **restrict inbuf,
size_t *restrict inbytesleft,
char **restrict outbuf,
size_t *restrict outbytesleft);
DESCRIPTION
The
iconv() function converts the sequence of characters from one code
set, in the array specified by
inbuf, into a sequence of corresponding
characters in another code set, in the array specified by
outbuf. The
code sets are those specified in the
iconv_open() call that returned the
conversion descriptor,
cd. The
inbuf argument points to a variable that
points to the first character in the input buffer and
inbytesleft indicates the number of bytes to the end of the buffer to be converted.
The
outbuf argument points to a variable that points to the first
available byte in the output buffer and
outbytesleft indicates the number
of the available bytes to the end of the buffer.
For state-dependent encodings, the conversion descriptor
cd is placed
into its initial shift state by a call for which
inbuf is a null pointer,
or for which
inbuf points to a null pointer. When
iconv() is called in
this way, and if
outbuf is not a null pointer or a pointer to a null
pointer, and
outbytesleft points to a positive value,
iconv() will place,
into the output buffer, the byte sequence to change the output buffer to
its initial shift state. If the output buffer is not large enough to
hold the entire reset sequence,
iconv() will fail and set
errno to
E2BIG. Subsequent calls with
inbuf as other than a null pointer or a
pointer to a null pointer cause the conversion to take place from the
current state of the conversion descriptor.
If a sequence of input bytes does not form a valid character in the
specified code set, conversion stops after the previous successfully
converted character. If the input buffer ends with an incomplete
character or shift sequence, conversion stops after the previous
successfully converted bytes. If the output buffer is not large enough to
hold the entire converted input, conversion stops just prior to the input
bytes that would cause the output buffer to overflow. The variable
pointed to by
inbuf is updated to point to the byte following the last
byte successfully used in the conversion. The value pointed to by
inbytesleft is decremented to reflect the number of bytes still not
converted in the input buffer. The variable pointed to by
outbuf is
updated to point to the byte following the last byte of converted output
data. The value pointed to by
outbytesleft is decremented to reflect the
number of bytes still available in the output buffer. For state-dependent
encodings, the conversion descriptor is updated to reflect the shift
state in effect at the end of the last successfully converted byte
sequence.
If
iconv() encounters a character in the input buffer that is legal, but
for which an identical character does not exist in the target code set,
iconv() performs an implementation-defined conversion on this character.
RETURN VALUES
The
iconv() function updates the variables pointed to by the arguments
to reflect the extent of the conversion and returns the number of non-
identical conversions performed. If the entire string in the input
buffer is converted, the value pointed to by
inbytesleft will be
0. If
the input conversion is stopped due to any conditions mentioned above,
the value pointed to by
inbytesleft will be non-zero and
errno is set
to indicate the condition. If an error occurs
iconv() returns
(size_t) -1 and sets
errno to indicate the error.
ERRORS
The
iconv() function will fail if:
EILSEQ Input conversion stopped due to an input byte that does not
belong to the input code set.
E2BIG Input conversion stopped due to lack of space in the output
buffer.
EINVAL Input conversion stopped due to an incomplete character or
shift sequence at the end of the input buffer.
The
iconv() function may fail if:
EBADF The
cd argument is not a valid open conversion descriptor.
EXAMPLES
Example 1: Using the iconv() Functions
The following example uses the
iconv() functions:
#include <stdio.h>
#include <errno.h>
#include <string.h>
#include <iconv.h>
#include <stdlib.h>
/*
* For state-dependent encodings, changes the state of the
* conversion descriptor to initial shift state. Also, outputs
* the byte sequence to change the state to initial state.
* This code is assuming the iconv call for initializing the
* state will not fail due to lack of space in the output buffer.
*/
#define INIT_SHIFT_STATE(cd, fptr, ileft, tptr, oleft) \
{ \
fptr = NULL; \
ileft = 0; \
tptr = to; \
oleft = BUFSIZ; \
(void) iconv(cd, &fptr, &ileft, &tptr, &oleft); \
(void) fwrite(to, 1, BUFSIZ - oleft, stdout); \
}
int
main(int argc, char **argv)
{
iconv_t cd;
char from[BUFSIZ], to[BUFSIZ];
char *from_code, *to_code;
char *tptr;
const char *fptr;
size_t ileft, oleft, num, ret;
if (argc != 3) {
(void) fprintf(stderr,
"Usage: %s from_codeset to_codeset\\n", argv[0]);
return (1);
}
from_code = argv[1];
to_code = argv[2];
cd = iconv_open((const char *)to_code, (const char *)from_code);
if (cd == (iconv_t)-1) {
/*
* iconv_open failed
*/
(void) fprintf(stderr,
"iconv_open(%s, %s) failed\\n", to_code, from_code);
return (1);
}
ileft = 0;
while ((ileft +=
(num = fread(from + ileft, 1, BUFSIZ - ileft, stdin))) > 0) {
if (num == 0) {
/*
* Input buffer still contains incomplete character
* or sequence. However, no more input character.
*/
/*
* Initializes the conversion descriptor and outputs
* the sequence to change the state to initial state.
*/
INIT_SHIFT_STATE(cd, fptr, ileft, tptr, oleft);
(void) iconv_close(cd);
(void) fprintf(stderr, "Conversion error\\n");
return (1);
}
fptr = from;
for (;;) {
tptr = to;
oleft = BUFSIZ;
ret = iconv(cd, &fptr, &ileft, &tptr, &oleft);
if (ret != (size_t)-1) {
/*
* iconv succeeded
*/
/*
* Outputs converted characters
*/
(void) fwrite(to, 1, BUFSIZ - oleft, stdout);
break;
}
/*
* iconv failed
*/
if (errno == EINVAL) {
/*
* Incomplete character or shift sequence
*/
/*
* Outputs converted characters
*/
(void) fwrite(to, 1, BUFSIZ - oleft, stdout);
/*
* Copies remaining characters in input buffer
* to the top of the input buffer.
*/
(void) memmove(from, fptr, ileft);
/*
* Tries to fill input buffer from stdin
*/
break;
} else if (errno == E2BIG) {
/*
* Lack of space in output buffer
*/
/*
* Outputs converted characters
*/
(void) fwrite(to, 1, BUFSIZ - oleft, stdout);
/*
* Tries to convert remaining characters in
* input buffer with emptied output buffer
*/
continue;
} else if (errno == EILSEQ) {
/*
* Illegal character or shift sequence
*/
/*
* Outputs converted characters
*/
(void) fwrite(to, 1, BUFSIZ - oleft, stdout);
/*
* Initializes the conversion descriptor and
* outputs the sequence to change the state to
* initial state.
*/
INIT_SHIFT_STATE(cd, fptr, ileft, tptr, oleft);
(void) iconv_close(cd);
(void) fprintf(stderr,
"Illegal character or sequence\\n");
return (1);
} else if (errno == EBADF) {
/*
* Invalid conversion descriptor.
* Actually, this shouldn't happen here.
*/
(void) fprintf(stderr, "Conversion error\\n");
return (1);
} else {
/*
* This errno is not defined
*/
(void) fprintf(stderr, "iconv error\\n");
return (1);
}
}
}
/*
* Initializes the conversion descriptor and outputs
* the sequence to change the state to initial state.
*/
INIT_SHIFT_STATE(cd, fptr, ileft, tptr, oleft);
(void) iconv_close(cd);
return (0);
}
FILES
/usr/lib/iconv/*.so conversion modules for 32-bit
/usr/lib/iconv/sparcv9/*.so conversion modules for 64-bit sparc
/usr/lib/iconv/amd64/*.so conversion modules for 64-bit amd64
/usr/lib/iconv/geniconvtbl/binarytables/*.bt conversion binary tables
ATTRIBUTES
See
attributes(7) for descriptions of the following attributes:
+--------------------+-----------------+
| ATTRIBUTE TYPE | ATTRIBUTE VALUE |
+--------------------+-----------------+
|Interface Stability | Standard |
+--------------------+-----------------+
|MT-Level | MT-Safe |
+--------------------+-----------------+
SEE ALSO
geniconvtbl(1),
iconv(1),
iconv_close(3C),
iconv_open(3C),
geniconvtbl(5),
attributes(7),
iconv(7),
iconv_unicode(7),
standards(7) October 6, 2004
ICONV(3C)