binutils-gdb/readline/mbutil.c
Patrick Palka 4a11f20659 Sync readline/ to version 7.0 alpha
This patch syncs our upstream copy of readline from version 6.2 to the
latest version, 7.0 alpha (released July 10 2015).

I essentially copied what was done the last time readline was synced,
when Jan updated to readline 6.2 in 2011:
http://sourceware.org/ml/gdb-patches/2011-05/msg00003.html

Procedure:

1. I extracted the readline-7.0-alpha tarball on top of readline/.
2. I deleted all the new files under doc/ that were deliberately omitted
   before.
3. I regenerated readline/configure and readline/examples/rlfe/configure
   using autoconf 2.64.  No other configure files need regenerating.
4. I updated the function gdb_printable_part in completer.c with a
   trivial change made to the readline function it is based off of,
   printable_part in readline/complete.c.  There is more work to be done in
   completer.c to sync it with readline/complete.c, but it is non-trivial
   and should probably be done separately anyway.

Local patches that had to be reapplied:

    None.  readline 7.0 alpha contains all of our local readline
    patches.

New files in readline/:

    colors.{c,h}
    examples/{hist_erasedups,hist_purgecmd,rl-callbacktest,rlbasic}.c
    parse-colors.{c,h}
    readline.pc.in
    configure.ac

Deleted files in readline/:

    configure.in

Regressions:

After the sync there is one testsuite regression, the test
"signal SIGINT" in gdb.gdb/selftest.exp which now FAILs.  Previously,
the readline 6.2 SIGINT handler would temporarily reinstall the
underlying application's SIGINT handler and immediately re-raise SIGINT
so that the orginal handler gets invoked.  But now (since readline 6.3)
its SIGINT handler does not re-raise SIGINT or directly invoke the
original handler; it now sets a flag marking that SIGINT was raised, and
waits until readline explicitly has control to call the application's
SIGINT handler.  Anyway, because SIGINT is no longer re-raised from
within readline's SIGINT handler, doing "signal SIGINT" with a stopped
inferior gdb process will no longer resume and then immediately stop the
process (since there is no 2nd SIGINT to immediately catch).  Instead,
the inferior gdb process will now just print "Quit" and continue to run.
So with this commit, this particular test case is adjusted to reflect
this change in behavior (we now have to send a 2nd SIGINT manually to
stop it).

Aside from this one testsuite regression, I personally noticed no
regression in user-visible behavior.  Though I only tested on x86_64
and on i686 Debian Stretch.

Getting this kind of change in at the start of the GDB 7.11 development
cycle will allow us to get a lot of passive testing from developers and
from bleeding-edge users.

readline/ChangeLog.gdb:

	Import readline 7.0 alpha
	* configure: Regenerate.
	* examples/rlfe/configure: Regenerate.

gdb/ChangeLog:

	* completer.c (gdb_printable_part): Sync with readline function
	it is based off of.

gdb/testsuite/ChangeLog:

	* gdb.gdb/selftest.exp (test_with_self): Update test to now
	expect the GDB inferior to no longer immediately stop after
	being resumed with "signal SIGINT".
2015-07-25 09:53:01 -04:00

379 lines
8.8 KiB
C

/* mbutil.c -- readline multibyte character utility functions */
/* Copyright (C) 2001-2009 Free Software Foundation, Inc.
This file is part of the GNU Readline Library (Readline), a library
for reading lines of text with interactive input and history editing.
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.
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.
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)
# include <config.h>
#endif
#include <sys/types.h>
#include <fcntl.h>
#include "posixjmp.h"
#if defined (HAVE_UNISTD_H)
# include <unistd.h> /* for _POSIX_VERSION */
#endif /* HAVE_UNISTD_H */
#if defined (HAVE_STDLIB_H)
# include <stdlib.h>
#else
# include "ansi_stdlib.h"
#endif /* HAVE_STDLIB_H */
#include <stdio.h>
#include <ctype.h>
/* System-specific feature definitions and include files. */
#include "rldefs.h"
#include "rlmbutil.h"
#if defined (TIOCSTAT_IN_SYS_IOCTL)
# include <sys/ioctl.h>
#endif /* TIOCSTAT_IN_SYS_IOCTL */
/* Some standard library routines. */
#include "readline.h"
#include "rlprivate.h"
#include "xmalloc.h"
/* Declared here so it can be shared between the readline and history
libraries. */
#if defined (HANDLE_MULTIBYTE)
int rl_byte_oriented = 0;
#else
int rl_byte_oriented = 1;
#endif
/* Ditto */
int _rl_utf8locale = 0;
/* **************************************************************** */
/* */
/* Multibyte Character Utility Functions */
/* */
/* **************************************************************** */
#if defined(HANDLE_MULTIBYTE)
static int
_rl_find_next_mbchar_internal (string, seed, count, find_non_zero)
char *string;
int seed, count, find_non_zero;
{
size_t tmp, len;
mbstate_t ps;
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 pointing to a byte indicating
the beginning of a multibyte character. Correct the point and consume
one char. */
if (seed < point)
count--;
while (count > 0)
{
len = strlen (string + point);
if (len == 0)
break;
tmp = mbrtowc (&wc, string+point, len, &ps);
if (MB_INVALIDCH ((size_t)tmp))
{
/* invalid bytes. assume a byte represents a character */
point++;
count--;
/* reset states. */
memset(&ps, 0, sizeof(mbstate_t));
}
else if (MB_NULLWCH (tmp))
break; /* found wide '\0' */
else
{
/* valid bytes */
point += tmp;
if (find_non_zero)
{
if (WCWIDTH (wc) == 0)
continue;
else
count--;
}
else
count--;
}
}
if (find_non_zero)
{
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
while (MB_NULLWCH (tmp) == 0 && MB_INVALIDCH (tmp) == 0 && WCWIDTH (wc) == 0)
{
point += tmp;
tmp = mbrtowc (&wc, string + point, strlen (string + point), &ps);
}
}
return point;
}
static int
_rl_find_prev_mbchar_internal (string, seed, find_non_zero)
char *string;
int seed, find_non_zero;
{
mbstate_t ps;
int prev, non_zero_prev, point, length;
size_t tmp;
wchar_t wc;
memset(&ps, 0, sizeof(mbstate_t));
length = strlen(string);
if (seed < 0)
return 0;
else if (length < seed)
return length;
prev = non_zero_prev = point = 0;
while (point < seed)
{
tmp = mbrtowc (&wc, string + point, length - point, &ps);
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
a single character anyway. */
tmp = 1;
/* 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 (MB_NULLWCH (tmp))
break; /* Found '\0' char. Can this happen? */
else
{
if (find_non_zero)
{
if (WCWIDTH (wc) != 0)
prev = point;
}
else
prev = point;
}
point += tmp;
}
return prev;
}
/* 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,
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 it couldn't parse a complete multibyte character. */
int
_rl_get_char_len (src, ps)
char *src;
mbstate_t *ps;
{
size_t tmp;
tmp = mbrlen((const char *)src, (size_t)strlen (src), ps);
if (tmp == (size_t)(-2))
{
/* shorted to compose multibyte char */
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 */
if (ps)
memset (ps, 0, sizeof(mbstate_t));
return -1;
}
else if (tmp == (size_t)0)
return 0;
else
return (int)tmp;
}
/* compare the specified two characters. If the characters matched,
return 1. Otherwise return 0. */
int
_rl_compare_chars (buf1, pos1, ps1, buf2, pos2, ps2)
char *buf1;
int pos1;
mbstate_t *ps1;
char *buf2;
int pos2;
mbstate_t *ps2;
{
int i, w1, w2;
if ((w1 = _rl_get_char_len (&buf1[pos1], ps1)) <= 0 ||
(w2 = _rl_get_char_len (&buf2[pos2], ps2)) <= 0 ||
(w1 != w2) ||
(buf1[pos1] != buf2[pos2]))
return 0;
for (i = 1; i < w1; i++)
if (buf1[pos1+i] != buf2[pos2+i])
return 0;
return 1;
}
/* adjust pointed byte and find mbstate of the point of string.
adjusted point will be point <= adjusted_point, and returns
differences of the byte(adjusted_point - point).
if point is invalied (point < 0 || more than string length),
it returns -1 */
int
_rl_adjust_point (string, point, ps)
char *string;
int point;
mbstate_t *ps;
{
size_t tmp = 0;
int length;
int pos = 0;
length = strlen(string);
if (point < 0)
return -1;
if (length < point)
return -1;
while (pos < point)
{
tmp = mbrlen (string + pos, length - pos, ps);
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
a single character anyway. */
pos++;
/* clear the state of the byte sequence, because
in this case effect of mbstate is undefined */
if (ps)
memset (ps, 0, sizeof (mbstate_t));
}
else if (MB_NULLWCH (tmp))
pos++;
else
pos += tmp;
}
return (pos - point);
}
int
_rl_is_mbchar_matched (string, seed, end, mbchar, length)
char *string;
int seed, end;
char *mbchar;
int length;
{
int i;
if ((end - seed) < length)
return 0;
for (i = 0; i < length; i++)
if (string[seed + i] != mbchar[i])
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.
If flags is MB_FIND_NONZERO, we look for non-zero-width multibyte
characters. */
#undef _rl_find_next_mbchar
int
_rl_find_next_mbchar (string, seed, count, flags)
char *string;
int seed, count, flags;
{
#if defined (HANDLE_MULTIBYTE)
return _rl_find_next_mbchar_internal (string, seed, count, flags);
#else
return (seed + count);
#endif
}
/* Find previous character started byte point of the specified seed.
Returned point will be point <= seed. If flags is MB_FIND_NONZERO,
we look for non-zero-width multibyte characters. */
#undef _rl_find_prev_mbchar
int
_rl_find_prev_mbchar (string, seed, flags)
char *string;
int seed, flags;
{
#if defined (HANDLE_MULTIBYTE)
return _rl_find_prev_mbchar_internal (string, seed, flags);
#else
return ((seed == 0) ? seed : seed - 1);
#endif
}