commit bash-20101124 snapshot

lib/glob/smatch.c

@@ -365,6 +365,16 @@ xstrmatch (pattern, string, flags)
   int ret;
   size_t n;
   wchar_t *wpattern, *wstring;
+  size_t plen, slen, mplen, mslen;
+
+#if 0
+  plen = strlen (pattern);
+  mplen = mbstrlen (pattern);
+  if (plen == mplen && strlen (string) == mbstrlen (string))
+#else
+  if (mbsmbchar (string) == 0 && mbsmbchar (pattern) == 0)
+#endif
+    return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));
 
   if (MB_CUR_MAX == 1)
     return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));

lib/glob/smatch.c~

@@ -0,0 +1,398 @@
+/* strmatch.c -- ksh-like extended pattern matching for the shell and filename
+		globbing. */
+
+/* Copyright (C) 1991-2005 Free Software Foundation, Inc.
+
+   This file is part of GNU Bash, the Bourne Again SHell.
+   
+   Bash 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.
+
+   Bash 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 Bash.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <config.h>
+
+#include <stdio.h>	/* for debugging */
+				
+#include "strmatch.h"
+#include <chartypes.h>
+
+#include "bashansi.h"
+#include "shmbutil.h"
+#include "xmalloc.h"
+
+/* First, compile `sm_loop.c' for single-byte characters. */
+#define CHAR	unsigned char
+#define U_CHAR	unsigned char
+#define XCHAR	char
+#define INT	int
+#define L(CS)	CS
+#define INVALID	-1
+
+#undef STREQ
+#undef STREQN
+#define STREQ(a, b) ((a)[0] == (b)[0] && strcmp(a, b) == 0)
+#define STREQN(a, b, n) ((a)[0] == (b)[0] && strncmp(a, b, n) == 0)
+
+/* We use strcoll(3) for range comparisons in bracket expressions,
+   even though it can have unwanted side effects in locales
+   other than POSIX or US.  For instance, in the de locale, [A-Z] matches
+   all characters. */
+
+#if defined (HAVE_STRCOLL)
+/* Helper function for collating symbol equivalence. */
+static int rangecmp (c1, c2)
+     int c1, c2;
+{
+  static char s1[2] = { ' ', '\0' };
+  static char s2[2] = { ' ', '\0' };
+  int ret;
+
+  /* Eight bits only.  Period. */
+  c1 &= 0xFF;
+  c2 &= 0xFF;
+
+  if (c1 == c2)
+    return (0);
+
+  s1[0] = c1;
+  s2[0] = c2;
+
+  if ((ret = strcoll (s1, s2)) != 0)
+    return ret;
+  return (c1 - c2);
+}
+#else /* !HAVE_STRCOLL */
+#  define rangecmp(c1, c2)	((int)(c1) - (int)(c2))
+#endif /* !HAVE_STRCOLL */
+
+#if defined (HAVE_STRCOLL)
+static int
+collequiv (c1, c2)
+     int c1, c2;
+{
+  return (rangecmp (c1, c2) == 0);
+}
+#else
+#  define collequiv(c1, c2)	((c1) == (c2))
+#endif
+
+#define _COLLSYM	_collsym
+#define __COLLSYM	__collsym
+#define POSIXCOLL	posix_collsyms
+#include "collsyms.h"
+
+static int
+collsym (s, len)
+     CHAR *s;
+     int len;
+{
+  register struct _collsym *csp;
+  char *x;
+
+  x = (char *)s;
+  for (csp = posix_collsyms; csp->name; csp++)
+    {
+      if (STREQN(csp->name, x, len) && csp->name[len] == '\0')
+	return (csp->code);
+    }
+  if (len == 1)
+    return s[0];
+  return INVALID;
+}
+
+/* unibyte character classification */
+#if !defined (isascii) && !defined (HAVE_ISASCII)
+#  define isascii(c)	((unsigned int)(c) <= 0177)
+#endif
+
+enum char_class
+  {
+    CC_NO_CLASS = 0,
+    CC_ASCII, CC_ALNUM, CC_ALPHA, CC_BLANK, CC_CNTRL, CC_DIGIT, CC_GRAPH,
+    CC_LOWER, CC_PRINT, CC_PUNCT, CC_SPACE, CC_UPPER, CC_WORD, CC_XDIGIT
+  };
+
+static char const *const cclass_name[] =
+  {
+    "",
+    "ascii", "alnum", "alpha", "blank", "cntrl", "digit", "graph",
+    "lower", "print", "punct", "space", "upper", "word", "xdigit"
+  };
+
+#define N_CHAR_CLASS (sizeof(cclass_name) / sizeof (cclass_name[0]))
+
+static int
+is_cclass (c, name)
+     int c;
+     const char *name;
+{
+  enum char_class char_class = CC_NO_CLASS;
+  int i, result;
+
+  for (i = 1; i < N_CHAR_CLASS; i++)
+    {
+      if (STREQ (name, cclass_name[i]))
+	{
+	  char_class = (enum char_class)i;
+	  break;
+	}
+    }
+
+  if (char_class == 0)
+    return -1;
+
+  switch (char_class)
+    {
+      case CC_ASCII:
+	result = isascii (c);
+	break;
+      case CC_ALNUM:
+	result = ISALNUM (c);
+	break;
+      case CC_ALPHA:
+	result = ISALPHA (c);
+	break;
+      case CC_BLANK:  
+	result = ISBLANK (c);
+	break;
+      case CC_CNTRL:
+	result = ISCNTRL (c);
+	break;
+      case CC_DIGIT:
+	result = ISDIGIT (c);
+	break;
+      case CC_GRAPH:
+	result = ISGRAPH (c);
+	break;
+      case CC_LOWER:
+	result = ISLOWER (c);
+	break;
+      case CC_PRINT: 
+	result = ISPRINT (c);
+	break;
+      case CC_PUNCT:
+	result = ISPUNCT (c);
+	break;
+      case CC_SPACE:
+	result = ISSPACE (c);
+	break;
+      case CC_UPPER:
+	result = ISUPPER (c);
+	break;
+      case CC_WORD:
+        result = (ISALNUM (c) || c == '_');
+	break;
+      case CC_XDIGIT:
+	result = ISXDIGIT (c);
+	break;
+      default:
+	result = -1;
+	break;
+    }
+
+  return result;  
+}
+
+/* Now include `sm_loop.c' for single-byte characters. */
+/* The result of FOLD is an `unsigned char' */
+# define FOLD(c) ((flags & FNM_CASEFOLD) \
+	? TOLOWER ((unsigned char)c) \
+	: ((unsigned char)c))
+
+#define FCT			internal_strmatch
+#define GMATCH			gmatch
+#define COLLSYM			collsym
+#define PARSE_COLLSYM		parse_collsym
+#define BRACKMATCH		brackmatch
+#define PATSCAN			patscan
+#define STRCOMPARE		strcompare
+#define EXTMATCH		extmatch
+#define STRCHR(S, C)		strchr((S), (C))
+#define STRCOLL(S1, S2)		strcoll((S1), (S2))
+#define STRLEN(S)		strlen(S)
+#define STRCMP(S1, S2)		strcmp((S1), (S2))
+#define RANGECMP(C1, C2)	rangecmp((C1), (C2))
+#define COLLEQUIV(C1, C2)	collequiv((C1), (C2))
+#define CTYPE_T			enum char_class
+#define IS_CCLASS(C, S)		is_cclass((C), (S))
+#include "sm_loop.c"
+
+#if HANDLE_MULTIBYTE
+
+#  define CHAR		wchar_t
+#  define U_CHAR	wint_t
+#  define XCHAR		wchar_t
+#  define INT		wint_t
+#  define L(CS)		L##CS
+#  define INVALID	WEOF
+
+#  undef STREQ
+#  undef STREQN
+#  define STREQ(s1, s2) ((wcscmp (s1, s2) == 0))
+#  define STREQN(a, b, n) ((a)[0] == (b)[0] && wcsncmp(a, b, n) == 0)
+
+static int
+rangecmp_wc (c1, c2)
+     wint_t c1, c2;
+{
+  static wchar_t s1[2] = { L' ', L'\0' };
+  static wchar_t s2[2] = { L' ', L'\0' };
+
+  if (c1 == c2)
+    return 0;
+
+  s1[0] = c1;
+  s2[0] = c2;
+
+  return (wcscoll (s1, s2));
+}
+
+static int
+collequiv_wc (c, equiv)
+     wint_t c, equiv;
+{
+  return (!(c - equiv));
+}
+
+/* Helper function for collating symbol. */
+#  define _COLLSYM	_collwcsym
+#  define __COLLSYM	__collwcsym
+#  define POSIXCOLL	posix_collwcsyms
+#  include "collsyms.h"
+
+static wint_t
+collwcsym (s, len)
+     wchar_t *s;
+     int len;
+{
+  register struct _collwcsym *csp;
+
+  for (csp = posix_collwcsyms; csp->name; csp++)
+    {
+      if (STREQN(csp->name, s, len) && csp->name[len] == L'\0')
+	return (csp->code);
+    }
+  if (len == 1)
+    return s[0];
+  return INVALID;
+}
+
+static int
+is_wcclass (wc, name)
+     wint_t wc;
+     wchar_t *name;
+{
+  char *mbs;
+  mbstate_t state;
+  size_t mbslength;
+  wctype_t desc;
+  int want_word;
+
+  if ((wctype ("ascii") == (wctype_t)0) && (wcscmp (name, L"ascii") == 0))
+    {
+      int c;
+
+      if ((c = wctob (wc)) == EOF)
+	return 0;
+      else
+        return (c <= 0x7F);
+    }
+
+  want_word = (wcscmp (name, L"word") == 0);
+  if (want_word)
+    name = L"alnum";
+
+  memset (&state, '\0', sizeof (mbstate_t));
+  mbs = (char *) malloc (wcslen(name) * MB_CUR_MAX + 1);
+  mbslength = wcsrtombs(mbs, (const wchar_t **)&name, (wcslen(name) * MB_CUR_MAX + 1), &state);
+
+  if (mbslength == (size_t)-1 || mbslength == (size_t)-2)
+    {
+      free (mbs);
+      return -1;
+    }
+  desc = wctype (mbs);
+  free (mbs);
+
+  if (desc == (wctype_t)0)
+    return -1;
+
+  if (want_word)
+    return (iswctype (wc, desc) || wc == L'_');
+  else
+    return (iswctype (wc, desc));
+}
+
+/* Now include `sm_loop.c' for multibyte characters. */
+#define FOLD(c) ((flags & FNM_CASEFOLD) && iswupper (c) ? towlower (c) : (c))
+#define FCT			internal_wstrmatch
+#define GMATCH			gmatch_wc
+#define COLLSYM			collwcsym
+#define PARSE_COLLSYM		parse_collwcsym
+#define BRACKMATCH		brackmatch_wc
+#define PATSCAN			patscan_wc
+#define STRCOMPARE		wscompare
+#define EXTMATCH		extmatch_wc
+#define STRCHR(S, C)		wcschr((S), (C))
+#define STRCOLL(S1, S2)		wcscoll((S1), (S2))
+#define STRLEN(S)		wcslen(S)
+#define STRCMP(S1, S2)		wcscmp((S1), (S2))
+#define RANGECMP(C1, C2)	rangecmp_wc((C1), (C2))
+#define COLLEQUIV(C1, C2)	collequiv_wc((C1), (C2))
+#define CTYPE_T			enum char_class
+#define IS_CCLASS(C, S)		is_wcclass((C), (S))
+#include "sm_loop.c"
+
+#endif /* HAVE_MULTIBYTE */
+
+int
+xstrmatch (pattern, string, flags)
+     char *pattern;
+     char *string;
+     int flags;
+{
+#if HANDLE_MULTIBYTE
+  int ret;
+  size_t n;
+  wchar_t *wpattern, *wstring;
+  size_t plen, slen, mplen, mslen;
+
+  plen = strlen (pattern);
+  mplen = mbstrlen (pattern);
+  if (plen == mplen && strlen (string) == mbstrlen (string))
+    return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));
+
+  if (MB_CUR_MAX == 1)
+    return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));
+
+  n = xdupmbstowcs (&wpattern, NULL, pattern);
+  if (n == (size_t)-1 || n == (size_t)-2)
+    return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));
+
+  n = xdupmbstowcs (&wstring, NULL, string);
+  if (n == (size_t)-1 || n == (size_t)-2)
+    {
+      free (wpattern);
+      return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));
+    }
+
+  ret = internal_wstrmatch (wpattern, wstring, flags);
+
+  free (wpattern);
+  free (wstring);
+
+  return ret;
+#else
+  return (internal_strmatch ((unsigned char *)pattern, (unsigned char *)string, flags));
+#endif /* !HANDLE_MULTIBYTE */
+}

lib/readline/doc/readline.3

@@ -763,10 +763,14 @@ as if the "!\fIn\fP" history expansion had been specified.
 .B
 yank\-last\-arg (M\-.\^, M\-_\^)
 Insert the last argument to the previous command (the last word of
-the previous history entry).  With an argument,
-behave exactly like \fByank\-nth\-arg\fP.
+the previous history entry).
+With a numeric argument, behave exactly like \fByank\-nth\-arg\fP.
 Successive calls to \fByank\-last\-arg\fP move back through the history
-list, inserting the last argument of each line in turn.
+list, inserting the last word (or the word specified by the argument to
+the first call) of each line in turn.
+Any numeric argument supplied to these successive calls determines
+the direction to move through the history.  A negative argument switches
+the direction through the history (back or forward).
 The history expansion facilities are used to extract the last argument,
 as if the "!$" history expansion had been specified.
 .PD

lib/readline/doc/readline.3~

@@ -492,6 +492,11 @@ completion.
 If set to \fBOff\fP, the leading `.' must be
 supplied by the user in the filename to be completed.
 .TP
+.B menu\-complete\-display\-prefix (Off)
+If set to \fBOn\fP, menu completion displays the common prefix of the
+list of possible completions (which may be empty) before cycling through
+the list.
+.TP
 .B output\-meta (Off)
 If set to \fBOn\fP, readline will display characters with the
 eighth bit set directly rather than as a meta-prefixed escape

lib/readline/doc/rluser.texi

@@ -1120,10 +1120,14 @@ as if the @samp{!@var{n}} history expansion had been specified.
 
 @item yank-last-arg (M-. or M-_)
 Insert last argument to the previous command (the last word of the
-previous history entry).  With an
-argument, behave exactly like @code{yank-nth-arg}.
+previous history entry).
+With a numeric argument, behave exactly like @code{yank-nth-arg}.
 Successive calls to @code{yank-last-arg} move back through the history
-list, inserting the last argument of each line in turn.
+list, inserting the last word (or the word specified by the argument to
+the first call) of each line in turn.
+Any numeric argument supplied to these successive calls determines
+the direction to move through the history.  A negative argument switches
+the direction through the history (back or forward).
 The history expansion facilities are used to extract the last argument,
 as if the @samp{!$} history expansion had been specified.
 

lib/readline/doc/rluser.texi~

@@ -591,6 +591,12 @@ If set to @samp{off}, the leading @samp{.} must be
 supplied by the user in the filename to be completed.
 This variable is @samp{on} by default.
 
+@item menu-complete-display-prefix
+@vindex menu-complete-display-prefix
+If set to @samp{on}, menu completion displays the common prefix of the
+list of possible completions (which may be empty) before cycling through
+the list.  The default is @samp{off}.
+
 @item output-meta
 @vindex output-meta
 If set to @samp{on}, Readline will display characters with the
@@ -1114,10 +1120,14 @@ as if the @samp{!@var{n}} history expansion had been specified.
 
 @item yank-last-arg (M-. or M-_)
 Insert last argument to the previous command (the last word of the
-previous history entry).  With an
-argument, behave exactly like @code{yank-nth-arg}.
+previous history entry).
+With a numeric argument, behave exactly like @code{yank-nth-arg}.
 Successive calls to @code{yank-last-arg} move back through the history
-list, inserting the last argument of each line in turn.
+list, inserting the last word (or the word specified by the argument to
+the first call) of each line in turn.
+Any numeric argument supplied to these successive calls determines
+the direction to move through the history.  A negative argument switches
+the direction through the history (back or forward).
 The history expansion facilities are used to extract the last argument,
 as if the @samp{!$} history expansion had been specified.
 
@@ -1229,7 +1239,7 @@ Kill from point to the end of the current word, or if between
 words, to the end of the next word.
 Word boundaries are the same as @code{shell-forward-word}.
 
-@item backward-kill-word ()
+@item shell-backward-kill-word ()
 Kill the word behind point.
 Word boundaries are the same as @code{shell-backward-word}.
 @end ifset

lib/readline/kill.c

@@ -640,7 +640,7 @@ rl_yank_last_arg (count, key)
     {
       if (undo_needed)
 	rl_do_undo ();
-      if (count < 1)
+      if (count < 0)		/* XXX - was < 1 */
         direction = -direction;
       history_skip += direction;
       if (history_skip < 0)

lib/readline/kill.c~

@@ -147,7 +147,7 @@ _rl_copy_to_kill_ring (text, append)
 	  strcat (new, old);
 	}
       xfree (old);
-      free (text);
+      xfree (text);
       rl_kill_ring[slot] = new;
     }
   else
@@ -601,7 +601,7 @@ rl_yank_nth_arg_internal (count, ignore, history_skip)
 #endif /* VI_MODE */
 
   rl_insert_text (arg);
-  free (arg);
+  xfree (arg);
 
   rl_end_undo_group ();
   return 0;

lib/sh/Makefile.in

@@ -92,7 +92,7 @@ CSOURCES = clktck.c clock.c getcwd.c getenv.c oslib.c setlinebuf.c \
 	   mktime.c strftime.c mbschr.c zcatfd.c zmapfd.c winsize.c eaccess.c \
 	   wcsdup.c fpurge.c zgetline.c mbscmp.c uconvert.c ufuncs.c \
 	   casemod.c dprintf.c input_avail.c mbscasecmp.c fnxform.c \
-	   strchrnul.c unicode.c wcswidth.c
+	   strchrnul.c unicode.c wcswidth.c shmbchar.c
 
 # The header files for this library.
 HSOURCES = 
@@ -106,7 +106,7 @@ OBJECTS = clktck.o clock.o getenv.o oslib.o setlinebuf.o strnlen.o \
 	  strtrans.o snprintf.o mailstat.o fmtulong.o \
 	  fmtullong.o fmtumax.o zcatfd.o zmapfd.o winsize.o wcsdup.o \
 	  fpurge.o zgetline.o mbscmp.o uconvert.o ufuncs.o casemod.o \
-	  input_avail.o mbscasecmp.o fnxform.o unicode.o ${LIBOBJS}
+	  input_avail.o mbscasecmp.o fnxform.o unicode.o shmbchar.o ${LIBOBJS}
 
 SUPPORT = Makefile
 
@@ -169,6 +169,7 @@ pathcanon.o: pathcanon.c
 pathphys.o: pathphys.c
 rename.o: rename.c
 setlinebuf.o: setlinebuf.c
+shmbchar.o: shmbchar.c
 shquote.o: shquote.c
 shtty.o: shtty.c
 snprintf.o: snprintf.c
@@ -240,6 +241,7 @@ pathcanon.o: ${BUILD_DIR}/config.h
 pathphys.o: ${BUILD_DIR}/config.h
 rename.o: ${BUILD_DIR}/config.h
 setlinebuf.o: ${BUILD_DIR}/config.h
+shmbchare.o: ${BUILD_DIR}/config.h
 shquote.o: ${BUILD_DIR}/config.h
 shtty.o: ${BUILD_DIR}/config.h
 snprintf.o: ${BUILD_DIR}/config.h
@@ -513,7 +515,7 @@ wcswidth.o: ${BASHINCDIR}/stdc.h
 
 mbschr.o: ${topdir}/bashansi.h
 mbschr.o: ${BASHINCDIR}/ansi_stdlib.h
-mbschr.o: ${BASHINCDIR}/shmbutil.h
+mbschr.o: ${BASHINCDIR}/shmbutil.h ${BASHINCDIR}/shmbchar.h
 
 zgetline.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 zgetline.o: ${BASHINCDIR}/stdc.h
@@ -532,7 +534,7 @@ casemod.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 casemod.o: ${BASHINCDIR}/stdc.h
 casemod.o: ${topdir}/xmalloc.h
 casemod.o: ${topdir}/bashtypes.h
-casemod.o: ${BASHINCDIR}/shmbutil.h
+casemod.o: ${BASHINCDIR}/shmbutil.h ${BASHINCDIR}/shmbchar.h
 casemod.o: ${topdir}/bashintl.h ${LIBINTL_H} ${BASHINCDIR}/gettext.h
 
 dprintf.o: ${BASHINCDIR}/stdc.h
@@ -548,3 +550,5 @@ fnxform.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 fnxform.o: ${BASHINCDIR}/stdc.h
 fnxform.o: ${topdir}/bashtypes.h
 fnxform.o: ${topdir}/bashintl.h ${LIBINTL_H} ${BASHINCDIR}/gettext.h
+
+shmbchar.o: ${BASHINCDIR}/shmbchar.h

lib/sh/Makefile.in~

@@ -92,7 +92,7 @@ CSOURCES = clktck.c clock.c getcwd.c getenv.c oslib.c setlinebuf.c \
 	   mktime.c strftime.c mbschr.c zcatfd.c zmapfd.c winsize.c eaccess.c \
 	   wcsdup.c fpurge.c zgetline.c mbscmp.c uconvert.c ufuncs.c \
 	   casemod.c dprintf.c input_avail.c mbscasecmp.c fnxform.c \
-	   strchrnul.c unicode.c
+	   strchrnul.c unicode.c wcswidth.c shmbchar.c
 
 # The header files for this library.
 HSOURCES = 
@@ -106,7 +106,7 @@ OBJECTS = clktck.o clock.o getenv.o oslib.o setlinebuf.o strnlen.o \
 	  strtrans.o snprintf.o mailstat.o fmtulong.o \
 	  fmtullong.o fmtumax.o zcatfd.o zmapfd.o winsize.o wcsdup.o \
 	  fpurge.o zgetline.o mbscmp.o uconvert.o ufuncs.o casemod.o \
-	  input_avail.o mbscasecmp.o fnxform.o unicode.o ${LIBOBJS}
+	  input_avail.o mbscasecmp.o fnxform.o unicode.o shmbchar.o ${LIBOBJS}
 
 SUPPORT = Makefile
 
@@ -169,6 +169,7 @@ pathcanon.o: pathcanon.c
 pathphys.o: pathphys.c
 rename.o: rename.c
 setlinebuf.o: setlinebuf.c
+shmbchar.o: shmbchar.c
 shquote.o: shquote.c
 shtty.o: shtty.c
 snprintf.o: snprintf.c
@@ -196,6 +197,7 @@ uconvert.o: uconvert.c
 ufuncs.o: ufuncs.c
 vprint.o: vprint.c
 wcsdup.o: wcsdup.c
+wcswidth.o: wcswidth.c
 mbschr.o: mbschr.c
 zcatfd.o: zcatfd.c
 zmapfd.o: zmapfd.c
@@ -239,6 +241,7 @@ pathcanon.o: ${BUILD_DIR}/config.h
 pathphys.o: ${BUILD_DIR}/config.h
 rename.o: ${BUILD_DIR}/config.h
 setlinebuf.o: ${BUILD_DIR}/config.h
+shmbchare.o: ${BUILD_DIR}/config.h
 shquote.o: ${BUILD_DIR}/config.h
 shtty.o: ${BUILD_DIR}/config.h
 snprintf.o: ${BUILD_DIR}/config.h
@@ -266,6 +269,7 @@ uconvert.o: ${BUILD_DIR}/config.h
 ufuncs.o: ${BUILD_DIR}/config.h
 vprint.o: ${BUILD_DIR}/config.h
 wcsdup.o: ${BUILD_DIR}/config.h
+wcswidth.o: ${BUILD_DIR}/config.h
 mbschr.o: ${BUILD_DIR}/config.h
 zcatfd.o: ${BUILD_DIR}/config.h
 zgetline.o: ${BUILD_DIR}/config.h
@@ -506,9 +510,12 @@ wcsdup.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 wcsdup.o: ${BASHINCDIR}/stdc.h
 wcsdup.o: ${topdir}/xmalloc.h
 
+wcswidth.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
+wcswidth.o: ${BASHINCDIR}/stdc.h
+
 mbschr.o: ${topdir}/bashansi.h
 mbschr.o: ${BASHINCDIR}/ansi_stdlib.h
-mbschr.o: ${BASHINCDIR}/shmbutil.h
+mbschr.o: ${BASHINCDIR}/shmbutil.h ${BASHINCDIR}/shmchar.h
 
 zgetline.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 zgetline.o: ${BASHINCDIR}/stdc.h
@@ -527,7 +534,7 @@ casemod.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 casemod.o: ${BASHINCDIR}/stdc.h
 casemod.o: ${topdir}/xmalloc.h
 casemod.o: ${topdir}/bashtypes.h
-casemod.o: ${BASHINCDIR}/shmbutil.h
+casemod.o: ${BASHINCDIR}/shmbutil.h ${BASHINCDIR}/shmchar.h
 casemod.o: ${topdir}/bashintl.h ${LIBINTL_H} ${BASHINCDIR}/gettext.h
 
 dprintf.o: ${BASHINCDIR}/stdc.h
@@ -543,3 +550,5 @@ fnxform.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
 fnxform.o: ${BASHINCDIR}/stdc.h
 fnxform.o: ${topdir}/bashtypes.h
 fnxform.o: ${topdir}/bashintl.h ${LIBINTL_H} ${BASHINCDIR}/gettext.h
+
+shmbchar.o: ${BASHINCDIR}/shmbchar.h

lib/sh/fnxform.c

@@ -72,7 +72,7 @@ curencoding ()
   mod = strchr (dot, '@');
   if (mod)
     *mod = '\0';
-  return dot;
+  return ++dot;
 #endif
 }  
 

lib/sh/shmbchar.c

@@ -0,0 +1,92 @@
+/* Copyright (C) 2001, 2006, 2009, 2010 Free Software Foundation, Inc.
+
+   This program 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.
+
+   This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+
+#include <config.h>
+
+#if defined (HANDLE_MULTIBYTE)
+#include <stdlib.h>
+#include <limits.h>
+
+#include <shmbutil.h>
+#include <shmbchar.h>
+
+#if IS_BASIC_ASCII
+
+/* Bit table of characters in the ISO C "basic character set".  */
+const unsigned int is_basic_table [UCHAR_MAX / 32 + 1] =
+{
+  0x00001a00,           /* '\t' '\v' '\f' */
+  0xffffffef,           /* ' '...'#' '%'...'?' */
+  0xfffffffe,           /* 'A'...'Z' '[' '\\' ']' '^' '_' */
+  0x7ffffffe            /* 'a'...'z' '{' '|' '}' '~' */
+  /* The remaining bits are 0.  */
+};
+
+#endif /* IS_BASIC_ASCII */
+
+size_t
+mbstrlen (s)
+     const char *s;
+{
+  size_t clen, nc;
+  mbstate_t mbs = { 0 }, mbsbak = { 0 };
+  int f;
+
+  nc = 0;
+  while (*s && (clen = (f = is_basic (*s)) ? 1 : mbrlen(s, MB_CUR_MAX, &mbs)) != 0)
+    {
+      if (MB_INVALIDCH(clen))
+	{
+	  clen = 1;	/* assume single byte */
+	  mbs = mbsbak;
+	}
+
+      if (f == 0)
+	mbsbak = mbs;
+
+      s += clen;
+      nc++;
+    }
+  return nc;
+}
+
+/* Return pointer to first multibyte char in S, or NULL if none. */
+char *
+mbsmbchar (s)
+     const char *s;
+{
+  char *t;
+  size_t clen;
+  mbstate_t mbs = { 0 };
+
+  for (t = (char *)s; *t; t++)
+    {
+      if (is_basic (*t))
+	continue;
+
+      clen = mbrlen (t, MB_CUR_MAX, &mbs);
+
+      if (clen == 0)
+        return 0;
+      if (MB_INVALIDCH(clen))
+	continue;
+
+      if (clen > 1)
+	return t;
+    }
+  return 0;
+}
+#endif

lib/sh/shmbchar.c.save1

@@ -0,0 +1,64 @@
+/* Copyright (C) 2001, 2006, 2009, 2010 Free Software Foundation, Inc.
+
+   This program 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.
+
+   This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+
+#include <config.h>
+
+#if defined (HANDLE_MULTIBYTE)
+#include <stdlib.h>
+#include <limits.h>
+
+#include <shmbutil.h>
+#include <shmbchar.h>
+
+#if IS_BASIC_ASCII
+
+/* Bit table of characters in the ISO C "basic character set".  */
+const unsigned int is_basic_table [UCHAR_MAX / 32 + 1] =
+{
+  0x00001a00,           /* '\t' '\v' '\f' */
+  0xffffffef,           /* ' '...'#' '%'...'?' */
+  0xfffffffe,           /* 'A'...'Z' '[' '\\' ']' '^' '_' */
+  0x7ffffffe            /* 'a'...'z' '{' '|' '}' '~' */
+  /* The remaining bits are 0.  */
+};
+
+#endif /* IS_BASIC_ASCII */
+
+size_t
+mbstrlen (s)
+     const char *s;
+{
+  size_t clen, nc;
+  mbstate_t mbs = { 0 }, mbsbak = { 0 };
+
+  nc = 0;
+  while (*s && (clen = is_basic (*s) ? 1 : mbrlen(s, MB_CUR_MAX, &mbs)) != 0)
+    {
+      if (MB_INVALIDCH(clen))
+	{
+	  clen = 1;	/* assume single byte */
+	  mbs = mbsbak;
+	}
+
+      if (is_basic (*s) == 0)
+	mbsbak = mbs;
+
+      s += clen;
+      nc++;
+    }
+  return nc;
+}
+#endif

lib/sh/shmbchar.c~

@@ -0,0 +1,91 @@
+/* Copyright (C) 2001, 2006, 2009, 2010 Free Software Foundation, Inc.
+
+   This program 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.
+
+   This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+
+#include <config.h>
+
+#if defined (HANDLE_MULTIBYTE)
+#include <stdlib.h>
+#include <limits.h>
+
+#include <shmbutil.h>
+#include <shmbchar.h>
+
+#if IS_BASIC_ASCII
+
+/* Bit table of characters in the ISO C "basic character set".  */
+const unsigned int is_basic_table [UCHAR_MAX / 32 + 1] =
+{
+  0x00001a00,           /* '\t' '\v' '\f' */
+  0xffffffef,           /* ' '...'#' '%'...'?' */
+  0xfffffffe,           /* 'A'...'Z' '[' '\\' ']' '^' '_' */
+  0x7ffffffe            /* 'a'...'z' '{' '|' '}' '~' */
+  /* The remaining bits are 0.  */
+};
+
+#endif /* IS_BASIC_ASCII */
+
+size_t
+mbstrlen (s)
+     const char *s;
+{
+  size_t clen, nc;
+  mbstate_t mbs = { 0 }, mbsbak = { 0 };
+
+  nc = 0;
+  while (*s && (clen = is_basic (*s) ? 1 : mbrlen(s, MB_CUR_MAX, &mbs)) != 0)
+    {
+      if (MB_INVALIDCH(clen))
+	{
+	  clen = 1;	/* assume single byte */
+	  mbs = mbsbak;
+	}
+
+      if (is_basic (*s) == 0)
+	mbsbak = mbs;
+
+      s += clen;
+      nc++;
+    }
+  return nc;
+}
+
+/* Return pointer to first multibyte char in S, or NULL if none. */
+char *
+mbsmbchar (s)
+     const char *s;
+{
+  char *t;
+  size_t clen;
+  mbstate_t mbs = { 0 };
+
+  for (t = (char *)s; *t; t++)
+    {
+      if (is_basic (*t))
+	continue;
+
+      clen = mbrlen (t, MB_CUR_MAX, &mbs);
+
+      if (clen == 0)
+        return 0;
+      if (MB_INVALIDCH(clen))
+	continue;
+
+      if (clen > 1)
+	return t;
+    }
+  return 0;
+}
+#endif

lib/sh/unicode.c

@@ -64,14 +64,19 @@ static iconv_t localconv;
 static char *
 stub_charset ()
 {
-  char *locale, *s;
+  char *locale, *s, *t;
 
   locale = get_locale_var ("LC_CTYPE");
-  if (locale == 0)
+  if (locale == 0 || *locale == 0)
     return "ASCII";
   s = strrchr (locale, '.');
   if (s)
-    return ++s;
+    {
+      t = strchr (s, '@');
+      if (t)
+	*t = 0;
+      return ++s;
+    }
   else if (STREQ (locale, "UTF-8"))
     return "UTF-8";
   else

lib/sh/unicode.c~

@@ -1,6 +1,6 @@
 /* unicode.c - functions to convert unicode characters */
 
-/* Copyright (C) 2006 Free Software Foundation, Inc.
+/* Copyright (C) 2010 Free Software Foundation, Inc.
 
    This file is part of GNU Bash, the Bourne Again SHell.
 
@@ -56,7 +56,33 @@ extern char *get_locale_var __P((char *));
 
 static int u32init = 0;
 static int utf8locale = 0;
+#if defined (HAVE_ICONV)
 static iconv_t localconv;
+#endif
+
+#ifndef HAVE_LOCALE_CHARSET
+static char *
+stub_charset ()
+{
+  char *locale, *s;
+
+  locale = get_locale_var ("LC_CTYPE");
+  if (locale == 0 || *locale == 0)
+    return "ASCII";
+  s = strrchr (locale, '.');
+  if (s)
+    {
+      t = strchr (s, '@');
+      if (t)
+	*t = 0;
+      return ++s;
+    }
+  else if (STREQ (locale, "UTF-8"))
+    return "UTF-8";
+  else
+    return "ASCII";
+}
+#endif
 
 /* u32toascii ? */
 int
@@ -127,7 +153,7 @@ u32cconv (c, s)
   const char *charset;
   char obuf[25], *optr;
   size_t obytesleft;
-  char *iptr;
+  const char *iptr;
   size_t sn;
 #endif
 
@@ -154,7 +180,11 @@ u32cconv (c, s)
   /* this is mostly from coreutils-8.5/lib/unicodeio.c */
   if (u32init == 0)
     {
+#  if HAVE_LOCALE_CHARSET
       charset = locale_charset ();	/* XXX - fix later */
+#  else
+      charset = stub_charset ();
+#  endif
       if (STREQ (charset, "UTF-8"))
 	utf8locale = 1;
       else
@@ -187,7 +217,7 @@ u32cconv (c, s)
 
   iconv (localconv, NULL, NULL, NULL, NULL);
 
-  if (iconv (localconv, &iptr, &sn, &optr, &obytesleft) == (size_t)-1)
+  if (iconv (localconv, (ICONV_CONST char **)&iptr, &sn, &optr, &obytesleft) == (size_t)-1)
     return n;	/* You get utf-8 if iconv fails */
 
   *optr = '\0';