/* mbutil.c -- readline multibyte character utility functions */
-/* Copyright (C) 2001 Free Software Foundation, Inc.
+/* Copyright (C) 2001-2009 Free Software Foundation, Inc.
- This file is part of the GNU Readline Library, a library for
- reading lines of text with interactive input and history editing.
+ This file is part of the GNU Readline Library (Readline), a library
+ for reading lines of text with interactive input and history editing.
- The GNU Readline Library is free software; you can redistribute it
- and/or modify it under the terms of the GNU General Public License
- as published by the Free Software Foundation; either version 2, or
+ Readline is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
- The GNU Readline 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
+ Readline 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 General Public License for more details.
- The GNU General Public License is often shipped with GNU software, and
- is generally kept in a file called COPYING or LICENSE. If you do not
- have a copy of the license, write to the Free Software Foundation,
- 59 Temple Place, Suite 330, Boston, MA 02111 USA. */
+ You should have received a copy of the GNU General Public License
+ along with Readline. If not, see <http://www.gnu.org/licenses/>.
+*/
+
#define READLINE_LIBRARY
#if defined (HAVE_CONFIG_H)
char *string;
int seed, count, find_non_zero;
{
- size_t tmp = 0;
+ size_t tmp, len;
mbstate_t ps;
- int point = 0;
+ int point;
wchar_t wc;
+ tmp = 0;
+
memset(&ps, 0, sizeof (mbstate_t));
if (seed < 0)
seed = 0;
if (count <= 0)
return seed;
- point = seed + _rl_adjust_point(string, seed, &ps);
- /* if this is true, means that seed was not pointed character
- started byte. So correct the point and consume count */
+ point = seed + _rl_adjust_point (string, seed, &ps);
+ /* if this is true, means that seed was not pointing to a byte indicating
+ the beginning of a multibyte character. Correct the point and consume
+ one char. */
if (seed < point)
- count --;
+ count--;
while (count > 0)
{
- tmp = mbrtowc (&wc, string+point, strlen(string + point), &ps);
- if ((size_t)(tmp) == (size_t)-1 || (size_t)(tmp) == (size_t)-2)
+ len = strlen (string + point);
+ if (len == 0)
+ break;
+ tmp = mbrtowc (&wc, string+point, len, &ps);
+ if (MB_INVALIDCH ((size_t)tmp))
{
- /* invalid bytes. asume a byte represents a character */
+ /* invalid bytes. assume a byte represents a character */
point++;
count--;
/* reset states. */
memset(&ps, 0, sizeof(mbstate_t));
}
- else if (tmp == (size_t)0)
- /* found '\0' char */
- break;
+ else if (MB_NULLWCH (tmp))
+ break; /* found wide '\0' */
else
{
/* valid bytes */
if (find_non_zero)
{
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
- while (wcwidth (wc) == 0)
+ while (MB_NULLWCH (tmp) == 0 && MB_INVALIDCH (tmp) == 0 && wcwidth (wc) == 0)
{
point += tmp;
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
- if (tmp == (size_t)(0) || tmp == (size_t)(-1) || tmp == (size_t)(-2))
- break;
}
}
- return point;
+
+ return point;
}
static int
while (point < seed)
{
tmp = mbrtowc (&wc, string + point, length - point, &ps);
- if ((size_t)(tmp) == (size_t)-1 || (size_t)(tmp) == (size_t)-2)
+ if (MB_INVALIDCH ((size_t)tmp))
{
/* in this case, bytes are invalid or shorted to compose
multibyte char, so assume that the first byte represents
/* clear the state of the byte sequence, because
in this case effect of mbstate is undefined */
memset(&ps, 0, sizeof (mbstate_t));
+
+ /* Since we're assuming that this byte represents a single
+ non-zero-width character, don't forget about it. */
+ prev = point;
}
- else if (tmp == 0)
+ else if (MB_NULLWCH (tmp))
break; /* Found '\0' char. Can this happen? */
else
{
if (tmp == (size_t)(-2))
{
/* shorted to compose multibyte char */
- memset (ps, 0, sizeof(mbstate_t));
+ if (ps)
+ memset (ps, 0, sizeof(mbstate_t));
return -2;
}
else if (tmp == (size_t)(-1))
{
/* invalid to compose multibyte char */
/* initialize the conversion state */
- memset (ps, 0, sizeof(mbstate_t));
+ if (ps)
+ memset (ps, 0, sizeof(mbstate_t));
return -1;
}
else if (tmp == (size_t)0)
return 1. Otherwise return 0. */
int
_rl_compare_chars (buf1, pos1, ps1, buf2, pos2, ps2)
- char *buf1, *buf2;
- mbstate_t *ps1, *ps2;
- int pos1, pos2;
+ char *buf1;
+ int pos1;
+ mbstate_t *ps1;
+ char *buf2;
+ int pos2;
+ mbstate_t *ps2;
{
int i, w1, w2;
while (pos < point)
{
tmp = mbrlen (string + pos, length - pos, ps);
- if((size_t)(tmp) == (size_t)-1 || (size_t)(tmp) == (size_t)-2)
+ if (MB_INVALIDCH ((size_t)tmp))
{
/* in this case, bytes are invalid or shorted to compose
multibyte char, so assume that the first byte represents
pos++;
/* clear the state of the byte sequence, because
in this case effect of mbstate is undefined */
- memset (ps, 0, sizeof (mbstate_t));
+ if (ps)
+ memset (ps, 0, sizeof (mbstate_t));
}
+ else if (MB_NULLWCH (tmp))
+ pos++;
else
pos += tmp;
}
return 0;
return 1;
}
+
+wchar_t
+_rl_char_value (buf, ind)
+ char *buf;
+ int ind;
+{
+ size_t tmp;
+ wchar_t wc;
+ mbstate_t ps;
+ int l;
+
+ if (MB_LEN_MAX == 1 || rl_byte_oriented)
+ return ((wchar_t) buf[ind]);
+ l = strlen (buf);
+ if (ind >= l - 1)
+ return ((wchar_t) buf[ind]);
+ memset (&ps, 0, sizeof (mbstate_t));
+ tmp = mbrtowc (&wc, buf + ind, l - ind, &ps);
+ if (MB_INVALIDCH (tmp) || MB_NULLWCH (tmp))
+ return ((wchar_t) buf[ind]);
+ return wc;
+}
#endif /* HANDLE_MULTIBYTE */
/* Find next `count' characters started byte point of the specified seed.