glibc/wcsmbs/wmemrtowcs.c

158 lines
3.7 KiB
C

/* Copyright (C) 1997 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Ulrich Drepper <drepper@gnu.org>, 1997.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public License as
published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version.
The GNU C 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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with the GNU C Library; see the file COPYING.LIB. If not,
write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
#include <errno.h>
#include <wchar.h>
#ifndef EILSEQ
#define EILSEQ EINVAL
#endif
/* We don't need the state really because we don't have shift states
to maintain between calls to this function. */
static mbstate_t internal;
/* This is a non-standard function but it is very useful in the
implementation of stdio because we have to deal with unterminated
buffers. At most NMC bytes will be converted. */
size_t
__wmemrtowcs (dst, src, nmc, len, ps)
wchar_t *dst;
const char **src;
size_t nmc;
size_t len;
mbstate_t *ps;
{
size_t written = 0;
const char *run = *src;
const char *last = run + nmc;
wchar_t value;
size_t count;
if (ps == NULL)
ps = &internal;
/* Get information from last use of this state. */
count = ps->count;
value = ps->value;
if (dst == NULL)
/* The LEN parameter has to be ignored if we don't actually write
anything. */
len = ~0;
/* Copy all words. */
while (written < len && run < last)
{
unsigned char byte;
/* Store address of next byte to process. */
*src = run;
/* Start reading a new character only if we are in the initial
state. */
if (count == 0)
{
byte = *run++;
/* We expect a start of a new multibyte character. */
if (byte < 0x80)
{
/* One byte sequence. */
count = 0;
value = byte;
}
else if ((byte & 0xe0) == 0xc0)
{
count = 1;
value = byte & 0x1f;
}
else if ((byte & 0xf0) == 0xe0)
{
/* We expect three bytes. */
count = 2;
value = byte & 0x0f;
}
else if ((byte & 0xf8) == 0xf0)
{
/* We expect four bytes. */
count = 3;
value = byte & 0x07;
}
else if ((byte & 0xfc) == 0xf8)
{
/* We expect five bytes. */
count = 4;
value = byte & 0x03;
}
else if ((byte & 0xfe) == 0xfc)
{
/* We expect six bytes. */
count = 5;
value = byte & 0x01;
}
else
{
/* This is an illegal encoding. */
__set_errno (EILSEQ);
return (size_t) -1;
}
}
/* Read the possible remaining bytes. */
while (run < last && count > 0)
{
byte = *run++;
--count;
if ((byte & 0xc0) != 0x80)
{
/* This is an illegal encoding. */
__set_errno (EILSEQ);
return (size_t) -1;
}
value <<= 6;
value |= byte & 0x3f;
}
/* If this character is only partially available remember this. */
if (run == last && count != 0)
{
ps->count = count;
ps->value = value;
break;
}
/* Store value is required. */
if (dst != NULL)
*dst++ = value;
/* Increment counter of produced words. */
++written;
}
/* Store address of next byte to process. */
*src = run;
return written;
}
weak_alias (__wmemrtowcs, wmemrtowcs)