/* mbutil.c -- readline multibyte character utility functions */
|
/* mbutil.c -- readline multibyte character utility functions */
|
|
|
/* Copyright (C) 2001-2005 Free Software Foundation, Inc.
|
/* Copyright (C) 2001-2005 Free Software Foundation, Inc.
|
|
|
This file is part of the GNU Readline Library, a library for
|
This file is part of the GNU Readline Library, a library for
|
reading lines of text with interactive input and history editing.
|
reading lines of text with interactive input and history editing.
|
|
|
The GNU Readline Library is free software; you can redistribute it
|
The GNU Readline Library is free software; you can redistribute it
|
and/or modify it under the terms of the GNU General Public License
|
and/or modify it under the terms of the GNU General Public License
|
as published by the Free Software Foundation; either version 2, or
|
as published by the Free Software Foundation; either version 2, or
|
(at your option) any later version.
|
(at your option) any later version.
|
|
|
The GNU Readline Library is distributed in the hope that it will be
|
The GNU Readline Library is distributed in the hope that it will be
|
useful, but WITHOUT ANY WARRANTY; without even the implied warranty
|
useful, but WITHOUT ANY WARRANTY; without even the implied warranty
|
of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
GNU General Public License for more details.
|
GNU General Public License for more details.
|
|
|
The GNU General Public License is often shipped with GNU software, and
|
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
|
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,
|
have a copy of the license, write to the Free Software Foundation,
|
59 Temple Place, Suite 330, Boston, MA 02111 USA. */
|
59 Temple Place, Suite 330, Boston, MA 02111 USA. */
|
#define READLINE_LIBRARY
|
#define READLINE_LIBRARY
|
|
|
#if defined (HAVE_CONFIG_H)
|
#if defined (HAVE_CONFIG_H)
|
# include <config.h>
|
# include <config.h>
|
#endif
|
#endif
|
|
|
#include <sys/types.h>
|
#include <sys/types.h>
|
#include <fcntl.h>
|
#include <fcntl.h>
|
#include "posixjmp.h"
|
#include "posixjmp.h"
|
|
|
#if defined (HAVE_UNISTD_H)
|
#if defined (HAVE_UNISTD_H)
|
# include <unistd.h> /* for _POSIX_VERSION */
|
# include <unistd.h> /* for _POSIX_VERSION */
|
#endif /* HAVE_UNISTD_H */
|
#endif /* HAVE_UNISTD_H */
|
|
|
#if defined (HAVE_STDLIB_H)
|
#if defined (HAVE_STDLIB_H)
|
# include <stdlib.h>
|
# include <stdlib.h>
|
#else
|
#else
|
# include "ansi_stdlib.h"
|
# include "ansi_stdlib.h"
|
#endif /* HAVE_STDLIB_H */
|
#endif /* HAVE_STDLIB_H */
|
|
|
#include <stdio.h>
|
#include <stdio.h>
|
#include <ctype.h>
|
#include <ctype.h>
|
|
|
/* System-specific feature definitions and include files. */
|
/* System-specific feature definitions and include files. */
|
#include "rldefs.h"
|
#include "rldefs.h"
|
#include "rlmbutil.h"
|
#include "rlmbutil.h"
|
|
|
#if defined (TIOCSTAT_IN_SYS_IOCTL)
|
#if defined (TIOCSTAT_IN_SYS_IOCTL)
|
# include <sys/ioctl.h>
|
# include <sys/ioctl.h>
|
#endif /* TIOCSTAT_IN_SYS_IOCTL */
|
#endif /* TIOCSTAT_IN_SYS_IOCTL */
|
|
|
/* Some standard library routines. */
|
/* Some standard library routines. */
|
#include "readline.h"
|
#include "readline.h"
|
|
|
#include "rlprivate.h"
|
#include "rlprivate.h"
|
#include "xmalloc.h"
|
#include "xmalloc.h"
|
|
|
/* Declared here so it can be shared between the readline and history
|
/* Declared here so it can be shared between the readline and history
|
libraries. */
|
libraries. */
|
#if defined (HANDLE_MULTIBYTE)
|
#if defined (HANDLE_MULTIBYTE)
|
int rl_byte_oriented = 0;
|
int rl_byte_oriented = 0;
|
#else
|
#else
|
int rl_byte_oriented = 1;
|
int rl_byte_oriented = 1;
|
#endif
|
#endif
|
|
|
/* **************************************************************** */
|
/* **************************************************************** */
|
/* */
|
/* */
|
/* Multibyte Character Utility Functions */
|
/* Multibyte Character Utility Functions */
|
/* */
|
/* */
|
/* **************************************************************** */
|
/* **************************************************************** */
|
|
|
#if defined(HANDLE_MULTIBYTE)
|
#if defined(HANDLE_MULTIBYTE)
|
|
|
static int
|
static int
|
_rl_find_next_mbchar_internal (string, seed, count, find_non_zero)
|
_rl_find_next_mbchar_internal (string, seed, count, find_non_zero)
|
char *string;
|
char *string;
|
int seed, count, find_non_zero;
|
int seed, count, find_non_zero;
|
{
|
{
|
size_t tmp;
|
size_t tmp;
|
mbstate_t ps;
|
mbstate_t ps;
|
int point;
|
int point;
|
wchar_t wc;
|
wchar_t wc;
|
|
|
tmp = 0;
|
tmp = 0;
|
|
|
memset(&ps, 0, sizeof (mbstate_t));
|
memset(&ps, 0, sizeof (mbstate_t));
|
if (seed < 0)
|
if (seed < 0)
|
seed = 0;
|
seed = 0;
|
if (count <= 0)
|
if (count <= 0)
|
return seed;
|
return seed;
|
|
|
point = seed + _rl_adjust_point (string, seed, &ps);
|
point = seed + _rl_adjust_point (string, seed, &ps);
|
/* if this is true, means that seed was not pointed character
|
/* if this is true, means that seed was not pointed character
|
started byte. So correct the point and consume count */
|
started byte. So correct the point and consume count */
|
if (seed < point)
|
if (seed < point)
|
count--;
|
count--;
|
|
|
while (count > 0)
|
while (count > 0)
|
{
|
{
|
tmp = mbrtowc (&wc, string+point, strlen(string + point), &ps);
|
tmp = mbrtowc (&wc, string+point, strlen(string + point), &ps);
|
if (MB_INVALIDCH ((size_t)tmp))
|
if (MB_INVALIDCH ((size_t)tmp))
|
{
|
{
|
/* invalid bytes. asume a byte represents a character */
|
/* invalid bytes. asume a byte represents a character */
|
point++;
|
point++;
|
count--;
|
count--;
|
/* reset states. */
|
/* reset states. */
|
memset(&ps, 0, sizeof(mbstate_t));
|
memset(&ps, 0, sizeof(mbstate_t));
|
}
|
}
|
else if (MB_NULLWCH (tmp))
|
else if (MB_NULLWCH (tmp))
|
break; /* found wide '\0' */
|
break; /* found wide '\0' */
|
else
|
else
|
{
|
{
|
/* valid bytes */
|
/* valid bytes */
|
point += tmp;
|
point += tmp;
|
if (find_non_zero)
|
if (find_non_zero)
|
{
|
{
|
if (wcwidth (wc) == 0)
|
if (wcwidth (wc) == 0)
|
continue;
|
continue;
|
else
|
else
|
count--;
|
count--;
|
}
|
}
|
else
|
else
|
count--;
|
count--;
|
}
|
}
|
}
|
}
|
|
|
if (find_non_zero)
|
if (find_non_zero)
|
{
|
{
|
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
|
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
|
while (tmp > 0 && wcwidth (wc) == 0)
|
while (tmp > 0 && wcwidth (wc) == 0)
|
{
|
{
|
point += tmp;
|
point += tmp;
|
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
|
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
|
if (MB_NULLWCH (tmp) || MB_INVALIDCH (tmp))
|
if (MB_NULLWCH (tmp) || MB_INVALIDCH (tmp))
|
break;
|
break;
|
}
|
}
|
}
|
}
|
|
|
return point;
|
return point;
|
}
|
}
|
|
|
static int
|
static int
|
_rl_find_prev_mbchar_internal (string, seed, find_non_zero)
|
_rl_find_prev_mbchar_internal (string, seed, find_non_zero)
|
char *string;
|
char *string;
|
int seed, find_non_zero;
|
int seed, find_non_zero;
|
{
|
{
|
mbstate_t ps;
|
mbstate_t ps;
|
int prev, non_zero_prev, point, length;
|
int prev, non_zero_prev, point, length;
|
size_t tmp;
|
size_t tmp;
|
wchar_t wc;
|
wchar_t wc;
|
|
|
memset(&ps, 0, sizeof(mbstate_t));
|
memset(&ps, 0, sizeof(mbstate_t));
|
length = strlen(string);
|
length = strlen(string);
|
|
|
if (seed < 0)
|
if (seed < 0)
|
return 0;
|
return 0;
|
else if (length < seed)
|
else if (length < seed)
|
return length;
|
return length;
|
|
|
prev = non_zero_prev = point = 0;
|
prev = non_zero_prev = point = 0;
|
while (point < seed)
|
while (point < seed)
|
{
|
{
|
tmp = mbrtowc (&wc, string + point, length - point, &ps);
|
tmp = mbrtowc (&wc, string + point, length - point, &ps);
|
if (MB_INVALIDCH ((size_t)tmp))
|
if (MB_INVALIDCH ((size_t)tmp))
|
{
|
{
|
/* in this case, bytes are invalid or shorted to compose
|
/* in this case, bytes are invalid or shorted to compose
|
multibyte char, so assume that the first byte represents
|
multibyte char, so assume that the first byte represents
|
a single character anyway. */
|
a single character anyway. */
|
tmp = 1;
|
tmp = 1;
|
/* clear the state of the byte sequence, because
|
/* clear the state of the byte sequence, because
|
in this case effect of mbstate is undefined */
|
in this case effect of mbstate is undefined */
|
memset(&ps, 0, sizeof (mbstate_t));
|
memset(&ps, 0, sizeof (mbstate_t));
|
|
|
/* Since we're assuming that this byte represents a single
|
/* Since we're assuming that this byte represents a single
|
non-zero-width character, don't forget about it. */
|
non-zero-width character, don't forget about it. */
|
prev = point;
|
prev = point;
|
}
|
}
|
else if (MB_NULLWCH (tmp))
|
else if (MB_NULLWCH (tmp))
|
break; /* Found '\0' char. Can this happen? */
|
break; /* Found '\0' char. Can this happen? */
|
else
|
else
|
{
|
{
|
if (find_non_zero)
|
if (find_non_zero)
|
{
|
{
|
if (wcwidth (wc) != 0)
|
if (wcwidth (wc) != 0)
|
prev = point;
|
prev = point;
|
}
|
}
|
else
|
else
|
prev = point;
|
prev = point;
|
}
|
}
|
|
|
point += tmp;
|
point += tmp;
|
}
|
}
|
|
|
return prev;
|
return prev;
|
}
|
}
|
|
|
/* return the number of bytes parsed from the multibyte sequence starting
|
/* return the number of bytes parsed from the multibyte sequence starting
|
at src, if a non-L'\0' wide character was recognized. It returns 0,
|
at src, if a non-L'\0' wide character was recognized. It returns 0,
|
if a L'\0' wide character was recognized. It returns (size_t)(-1),
|
if a L'\0' wide character was recognized. It returns (size_t)(-1),
|
if an invalid multibyte sequence was encountered. It returns (size_t)(-2)
|
if an invalid multibyte sequence was encountered. It returns (size_t)(-2)
|
if it couldn't parse a complete multibyte character. */
|
if it couldn't parse a complete multibyte character. */
|
int
|
int
|
_rl_get_char_len (src, ps)
|
_rl_get_char_len (src, ps)
|
char *src;
|
char *src;
|
mbstate_t *ps;
|
mbstate_t *ps;
|
{
|
{
|
size_t tmp;
|
size_t tmp;
|
|
|
tmp = mbrlen((const char *)src, (size_t)strlen (src), ps);
|
tmp = mbrlen((const char *)src, (size_t)strlen (src), ps);
|
if (tmp == (size_t)(-2))
|
if (tmp == (size_t)(-2))
|
{
|
{
|
/* shorted to compose multibyte char */
|
/* shorted to compose multibyte char */
|
if (ps)
|
if (ps)
|
memset (ps, 0, sizeof(mbstate_t));
|
memset (ps, 0, sizeof(mbstate_t));
|
return -2;
|
return -2;
|
}
|
}
|
else if (tmp == (size_t)(-1))
|
else if (tmp == (size_t)(-1))
|
{
|
{
|
/* invalid to compose multibyte char */
|
/* invalid to compose multibyte char */
|
/* initialize the conversion state */
|
/* initialize the conversion state */
|
if (ps)
|
if (ps)
|
memset (ps, 0, sizeof(mbstate_t));
|
memset (ps, 0, sizeof(mbstate_t));
|
return -1;
|
return -1;
|
}
|
}
|
else if (tmp == (size_t)0)
|
else if (tmp == (size_t)0)
|
return 0;
|
return 0;
|
else
|
else
|
return (int)tmp;
|
return (int)tmp;
|
}
|
}
|
|
|
/* compare the specified two characters. If the characters matched,
|
/* compare the specified two characters. If the characters matched,
|
return 1. Otherwise return 0. */
|
return 1. Otherwise return 0. */
|
int
|
int
|
_rl_compare_chars (buf1, pos1, ps1, buf2, pos2, ps2)
|
_rl_compare_chars (buf1, pos1, ps1, buf2, pos2, ps2)
|
char *buf1;
|
char *buf1;
|
int pos1;
|
int pos1;
|
mbstate_t *ps1;
|
mbstate_t *ps1;
|
char *buf2;
|
char *buf2;
|
int pos2;
|
int pos2;
|
mbstate_t *ps2;
|
mbstate_t *ps2;
|
{
|
{
|
int i, w1, w2;
|
int i, w1, w2;
|
|
|
if ((w1 = _rl_get_char_len (&buf1[pos1], ps1)) <= 0 ||
|
if ((w1 = _rl_get_char_len (&buf1[pos1], ps1)) <= 0 ||
|
(w2 = _rl_get_char_len (&buf2[pos2], ps2)) <= 0 ||
|
(w2 = _rl_get_char_len (&buf2[pos2], ps2)) <= 0 ||
|
(w1 != w2) ||
|
(w1 != w2) ||
|
(buf1[pos1] != buf2[pos2]))
|
(buf1[pos1] != buf2[pos2]))
|
return 0;
|
return 0;
|
|
|
for (i = 1; i < w1; i++)
|
for (i = 1; i < w1; i++)
|
if (buf1[pos1+i] != buf2[pos2+i])
|
if (buf1[pos1+i] != buf2[pos2+i])
|
return 0;
|
return 0;
|
|
|
return 1;
|
return 1;
|
}
|
}
|
|
|
/* adjust pointed byte and find mbstate of the point of string.
|
/* adjust pointed byte and find mbstate of the point of string.
|
adjusted point will be point <= adjusted_point, and returns
|
adjusted point will be point <= adjusted_point, and returns
|
differences of the byte(adjusted_point - point).
|
differences of the byte(adjusted_point - point).
|
if point is invalied (point < 0 || more than string length),
|
if point is invalied (point < 0 || more than string length),
|
it returns -1 */
|
it returns -1 */
|
int
|
int
|
_rl_adjust_point(string, point, ps)
|
_rl_adjust_point(string, point, ps)
|
char *string;
|
char *string;
|
int point;
|
int point;
|
mbstate_t *ps;
|
mbstate_t *ps;
|
{
|
{
|
size_t tmp = 0;
|
size_t tmp = 0;
|
int length;
|
int length;
|
int pos = 0;
|
int pos = 0;
|
|
|
length = strlen(string);
|
length = strlen(string);
|
if (point < 0)
|
if (point < 0)
|
return -1;
|
return -1;
|
if (length < point)
|
if (length < point)
|
return -1;
|
return -1;
|
|
|
while (pos < point)
|
while (pos < point)
|
{
|
{
|
tmp = mbrlen (string + pos, length - pos, ps);
|
tmp = mbrlen (string + pos, length - pos, ps);
|
if (MB_INVALIDCH ((size_t)tmp))
|
if (MB_INVALIDCH ((size_t)tmp))
|
{
|
{
|
/* in this case, bytes are invalid or shorted to compose
|
/* in this case, bytes are invalid or shorted to compose
|
multibyte char, so assume that the first byte represents
|
multibyte char, so assume that the first byte represents
|
a single character anyway. */
|
a single character anyway. */
|
pos++;
|
pos++;
|
/* clear the state of the byte sequence, because
|
/* clear the state of the byte sequence, because
|
in this case effect of mbstate is undefined */
|
in this case effect of mbstate is undefined */
|
if (ps)
|
if (ps)
|
memset (ps, 0, sizeof (mbstate_t));
|
memset (ps, 0, sizeof (mbstate_t));
|
}
|
}
|
else if (MB_NULLWCH (tmp))
|
else if (MB_NULLWCH (tmp))
|
pos++;
|
pos++;
|
else
|
else
|
pos += tmp;
|
pos += tmp;
|
}
|
}
|
|
|
return (pos - point);
|
return (pos - point);
|
}
|
}
|
|
|
int
|
int
|
_rl_is_mbchar_matched (string, seed, end, mbchar, length)
|
_rl_is_mbchar_matched (string, seed, end, mbchar, length)
|
char *string;
|
char *string;
|
int seed, end;
|
int seed, end;
|
char *mbchar;
|
char *mbchar;
|
int length;
|
int length;
|
{
|
{
|
int i;
|
int i;
|
|
|
if ((end - seed) < length)
|
if ((end - seed) < length)
|
return 0;
|
return 0;
|
|
|
for (i = 0; i < length; i++)
|
for (i = 0; i < length; i++)
|
if (string[seed + i] != mbchar[i])
|
if (string[seed + i] != mbchar[i])
|
return 0;
|
return 0;
|
return 1;
|
return 1;
|
}
|
}
|
|
|
wchar_t
|
wchar_t
|
_rl_char_value (buf, ind)
|
_rl_char_value (buf, ind)
|
char *buf;
|
char *buf;
|
int ind;
|
int ind;
|
{
|
{
|
size_t tmp;
|
size_t tmp;
|
wchar_t wc;
|
wchar_t wc;
|
mbstate_t ps;
|
mbstate_t ps;
|
int l;
|
int l;
|
|
|
if (MB_LEN_MAX == 1 || rl_byte_oriented)
|
if (MB_LEN_MAX == 1 || rl_byte_oriented)
|
return ((wchar_t) buf[ind]);
|
return ((wchar_t) buf[ind]);
|
l = strlen (buf);
|
l = strlen (buf);
|
if (ind >= l - 1)
|
if (ind >= l - 1)
|
return ((wchar_t) buf[ind]);
|
return ((wchar_t) buf[ind]);
|
memset (&ps, 0, sizeof (mbstate_t));
|
memset (&ps, 0, sizeof (mbstate_t));
|
tmp = mbrtowc (&wc, buf + ind, l - ind, &ps);
|
tmp = mbrtowc (&wc, buf + ind, l - ind, &ps);
|
if (MB_INVALIDCH (tmp) || MB_NULLWCH (tmp))
|
if (MB_INVALIDCH (tmp) || MB_NULLWCH (tmp))
|
return ((wchar_t) buf[ind]);
|
return ((wchar_t) buf[ind]);
|
return wc;
|
return wc;
|
}
|
}
|
#endif /* HANDLE_MULTIBYTE */
|
#endif /* HANDLE_MULTIBYTE */
|
|
|
/* Find next `count' characters started byte point of the specified seed.
|
/* Find next `count' characters started byte point of the specified seed.
|
If flags is MB_FIND_NONZERO, we look for non-zero-width multibyte
|
If flags is MB_FIND_NONZERO, we look for non-zero-width multibyte
|
characters. */
|
characters. */
|
#undef _rl_find_next_mbchar
|
#undef _rl_find_next_mbchar
|
int
|
int
|
_rl_find_next_mbchar (string, seed, count, flags)
|
_rl_find_next_mbchar (string, seed, count, flags)
|
char *string;
|
char *string;
|
int seed, count, flags;
|
int seed, count, flags;
|
{
|
{
|
#if defined (HANDLE_MULTIBYTE)
|
#if defined (HANDLE_MULTIBYTE)
|
return _rl_find_next_mbchar_internal (string, seed, count, flags);
|
return _rl_find_next_mbchar_internal (string, seed, count, flags);
|
#else
|
#else
|
return (seed + count);
|
return (seed + count);
|
#endif
|
#endif
|
}
|
}
|
|
|
/* Find previous character started byte point of the specified seed.
|
/* Find previous character started byte point of the specified seed.
|
Returned point will be point <= seed. If flags is MB_FIND_NONZERO,
|
Returned point will be point <= seed. If flags is MB_FIND_NONZERO,
|
we look for non-zero-width multibyte characters. */
|
we look for non-zero-width multibyte characters. */
|
#undef _rl_find_prev_mbchar
|
#undef _rl_find_prev_mbchar
|
int
|
int
|
_rl_find_prev_mbchar (string, seed, flags)
|
_rl_find_prev_mbchar (string, seed, flags)
|
char *string;
|
char *string;
|
int seed, flags;
|
int seed, flags;
|
{
|
{
|
#if defined (HANDLE_MULTIBYTE)
|
#if defined (HANDLE_MULTIBYTE)
|
return _rl_find_prev_mbchar_internal (string, seed, flags);
|
return _rl_find_prev_mbchar_internal (string, seed, flags);
|
#else
|
#else
|
return ((seed == 0) ? seed : seed - 1);
|
return ((seed == 0) ? seed : seed - 1);
|
#endif
|
#endif
|
}
|
}
|
|
|
