aboutsummaryrefslogtreecommitdiffstats
path: root/lib/sh
diff options
context:
space:
mode:
Diffstat (limited to 'lib/sh')
-rw-r--r--lib/sh/Makefile.in26
-rw-r--r--lib/sh/casemod.c7
-rw-r--r--lib/sh/dprintf.c70
-rw-r--r--lib/sh/eaccess.c25
-rw-r--r--lib/sh/fnxform.c199
-rw-r--r--lib/sh/fpurge.c96
-rw-r--r--lib/sh/mbscasecmp.c78
-rw-r--r--lib/sh/mbschr.c78
-rw-r--r--lib/sh/oslib.c9
-rw-r--r--lib/sh/shmatch.c2
-rw-r--r--lib/sh/shmbchar.c92
-rw-r--r--lib/sh/shquote.c10
-rw-r--r--lib/sh/snprintf.c2
-rw-r--r--lib/sh/strcasestr.c46
-rw-r--r--lib/sh/strchrnul.c144
-rw-r--r--lib/sh/strftime.c49
-rw-r--r--lib/sh/strtrans.c34
-rw-r--r--lib/sh/tmpfile.c2
-rw-r--r--lib/sh/unicode.c235
-rw-r--r--lib/sh/wcswidth.c46
20 files changed, 1200 insertions, 50 deletions
diff --git a/lib/sh/Makefile.in b/lib/sh/Makefile.in
index 80f6cc5..d97cd99 100644
--- a/lib/sh/Makefile.in
+++ b/lib/sh/Makefile.in
@@ -2,7 +2,7 @@
# Makefile for the Bash library
#
#
-# Copyright (C) 1998-2009 Free Software Foundation, Inc.
+# Copyright (C) 1998-2010 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
@@ -91,7 +91,8 @@ CSOURCES = clktck.c clock.c getcwd.c getenv.c oslib.c setlinebuf.c \
strtoll.c strtoull.c strtoimax.c strtoumax.c memset.c strstr.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 fdprintf.c input_avail.c mbscasecmp.c fnxform.c
+ casemod.c dprintf.c input_avail.c mbscasecmp.c fnxform.c \
+ strchrnul.c unicode.c wcswidth.c shmbchar.c
# The header files for this library.
HSOURCES =
@@ -105,7 +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 \
- fdprintf.o input_avail.o mbscasecmp.o fnxform.o ${LIBOBJS}
+ input_avail.o mbscasecmp.o fnxform.o unicode.o shmbchar.o ${LIBOBJS}
SUPPORT = Makefile
@@ -144,7 +145,7 @@ casemod.o: casemod.c
clktck.o: clktck.c
clock.o: clock.c
eaccess.o: eaccess.c
-fdprintf.o: fdprintf.c
+dprintf.o: dprintf.c
fmtullong.o: fmtullong.c
fmtulong.o: fmtulong.c
fmtumax.o: fmtumax.c
@@ -168,6 +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
@@ -195,6 +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
@@ -214,7 +217,7 @@ casemod.o: ${BUILD_DIR}/config.h
clktck.o: ${BUILD_DIR}/config.h
clock.o: ${BUILD_DIR}/config.h
eaccess.o: ${BUILD_DIR}/config.h
-fdprintf.o: ${BUILD_DIR}/config.h
+dprintf.o: ${BUILD_DIR}/config.h
fmtullong.o: ${BUILD_DIR}/config.h
fmtulong.o: ${BUILD_DIR}/config.h
fmtumax.o: ${BUILD_DIR}/config.h
@@ -238,6 +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
@@ -265,6 +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
@@ -505,9 +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}/shmbchar.h
zgetline.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
zgetline.o: ${BASHINCDIR}/stdc.h
@@ -526,10 +534,10 @@ 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
-fdprintf.o: ${BASHINCDIR}/stdc.h
+dprintf.o: ${BASHINCDIR}/stdc.h
input_avail.o: ${topdir}/bashansi.h ${BASHINCDIR}/ansi_stdlib.h
input_avail.o: ${BASHINCDIR}/stdc.h
@@ -542,3 +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
diff --git a/lib/sh/casemod.c b/lib/sh/casemod.c
index d85549a..3127d8c 100644
--- a/lib/sh/casemod.c
+++ b/lib/sh/casemod.c
@@ -111,6 +111,13 @@ sh_modcase (string, pat, flags)
mbstate_t state;
#endif
+ if (string == 0 || *string == 0)
+ {
+ ret = (char *)xmalloc (1);
+ ret[0] = '\0';
+ return ret;
+ }
+
#if defined (HANDLE_MULTIBYTE)
memset (&state, 0, sizeof (mbstate_t));
#endif
diff --git a/lib/sh/dprintf.c b/lib/sh/dprintf.c
new file mode 100644
index 0000000..b3b5d64
--- /dev/null
+++ b/lib/sh/dprintf.c
@@ -0,0 +1,70 @@
+/* dprintf -- printf to a file descriptor */
+
+/* Copyright (C) 2008-2010 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/>.
+*/
+
+#ifdef HAVE_CONFIG_H
+# include <config.h>
+#endif
+
+#include <stdc.h>
+
+#if defined (HAVE_UNISTD_H)
+# include <unistd.h>
+#endif
+
+#if defined (PREFER_STDARG)
+# include <stdarg.h>
+#else
+# include <varargs.h>
+#endif
+
+#include <stdio.h>
+
+int
+#if defined (PREFER_STDARG)
+dprintf(int fd, const char *format, ...)
+#else
+dprintf(fd, format, va_alist)
+ int fd;
+ const char *format;
+ va_dcl
+#endif
+{
+ FILE *fp;
+ int fd2, rc, r2;
+ va_list args;
+
+ if ((fd2 = dup(fd)) < 0)
+ return -1;
+ fp = fdopen (fd2, "w");
+ if (fp == 0)
+ {
+ close (fd2);
+ return -1;
+ }
+
+ SH_VA_START (args, format);
+ rc = vfprintf (fp, format, args);
+ fflush (fp);
+ va_end (args);
+
+ r2 = fclose (fp); /* check here */
+
+ return rc;
+}
diff --git a/lib/sh/eaccess.c b/lib/sh/eaccess.c
index 989bc22..d9bca8c 100644
--- a/lib/sh/eaccess.c
+++ b/lib/sh/eaccess.c
@@ -1,6 +1,6 @@
/* eaccess.c - eaccess replacement for the shell, plus other access functions. */
-/* Copyright (C) 2006 Free Software Foundation, Inc.
+/* Copyright (C) 2006-2010 Free Software Foundation, Inc.
This file is part of GNU Bash, the Bourne Again SHell.
@@ -198,11 +198,20 @@ sh_eaccess (path, mode)
char *path;
int mode;
{
+ int ret;
+
if (path_is_devfd (path))
return (sh_stataccess (path, mode));
-#if defined (HAVE_EACCESS) /* FreeBSD */
- return (eaccess (path, mode));
+#if defined (HAVE_FACCESSAT) && defined (AT_EACCESS)
+ return (faccessat (AT_FDCWD, path, mode, AT_EACCESS));
+#elif defined (HAVE_EACCESS) /* FreeBSD */
+ ret = eaccess (path, mode); /* XXX -- not always correct for X_OK */
+# if defined (__FreeBSD__)
+ if (ret == 0 && current_user.euid == 0 && mode == X_OK)
+ return (sh_stataccess (path, mode));
+# endif
+ return ret;
#elif defined (EFF_ONLY_OK) /* SVR4(?), SVR4.2 */
return access (path, mode|EFF_ONLY_OK);
#else
@@ -215,7 +224,15 @@ sh_eaccess (path, mode)
# endif
if (current_user.uid == current_user.euid && current_user.gid == current_user.egid)
- return (access (path, mode));
+ {
+ ret = access (path, mode);
+#if defined (__FreeBSD__) || defined (SOLARIS)
+ if (ret == 0 && current_user.euid == 0 && mode == X_OK)
+ return (sh_stataccess (path, mode));
+#endif
+ return ret;
+
+ }
return (sh_stataccess (path, mode));
#endif
diff --git a/lib/sh/fnxform.c b/lib/sh/fnxform.c
new file mode 100644
index 0000000..d7e1b5a
--- /dev/null
+++ b/lib/sh/fnxform.c
@@ -0,0 +1,199 @@
+/* fnxform - use iconv(3) to transform strings to and from "filename" format */
+
+/* Copyright (C) 2009-2010 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>
+#if defined (HAVE_UNISTD_H)
+# include <unistd.h>
+#endif
+#include "bashansi.h"
+#include <stdio.h>
+#include "bashtypes.h"
+
+#include "stdc.h"
+#include "bashintl.h"
+#include <xmalloc.h>
+
+#if defined (HAVE_ICONV)
+# include <iconv.h>
+#endif
+
+#if defined (HAVE_LOCALE_CHARSET)
+extern const char *locale_charset __P((void));
+#else
+extern char *get_locale_var __P((char *));
+#endif
+
+#if defined (HAVE_ICONV)
+static iconv_t conv_fromfs = (iconv_t)-1;
+static iconv_t conv_tofs = (iconv_t)-1;
+
+#define OUTLEN_MAX 4096
+
+static char *outbuf = 0;
+static size_t outlen = 0;
+
+static char *curencoding __P((void));
+static void init_tofs __P((void));
+static void init_fromfs __P((void));
+
+static char *
+curencoding ()
+{
+ char *loc;
+#if defined (HAVE_LOCALE_CHARSET)
+ loc = (char *)locale_charset ();
+ return loc;
+#else
+ char *dot, *mod;
+
+ loc = get_locale_var ("LC_CTYPE");
+ if (loc == 0 || *loc == 0)
+ return "";
+ dot = strchr (loc, '.');
+ if (dot == 0)
+ return loc;
+ mod = strchr (dot, '@');
+ if (mod)
+ *mod = '\0';
+ return ++dot;
+#endif
+}
+
+static void
+init_tofs ()
+{
+ char *cur;
+
+ cur = curencoding ();
+ conv_tofs = iconv_open ("UTF-8-MAC", cur);
+}
+
+static void
+init_fromfs ()
+{
+ char *cur;
+
+ cur = curencoding ();
+ conv_fromfs = iconv_open (cur, "UTF-8-MAC");
+}
+
+char *
+fnx_tofs (string, len)
+ char *string;
+ size_t len;
+{
+#ifdef MACOSX
+ ICONV_CONST char *inbuf;
+ char *tempbuf;
+ size_t templen;
+
+ if (conv_tofs == (iconv_t)-1)
+ init_tofs ();
+ if (conv_tofs == (iconv_t)-1)
+ return string;
+
+ /* Free and reallocate outbuf if it's *too* big */
+ if (outlen >= OUTLEN_MAX && len < OUTLEN_MAX - 8)
+ {
+ free (outbuf);
+ outbuf = 0;
+ outlen = 0;
+ }
+
+ inbuf = string;
+ if (outbuf == 0 || outlen < len + 8)
+ {
+ outlen = len + 8;
+ outbuf = outbuf ? xrealloc (outbuf, outlen + 1) : xmalloc (outlen + 1);
+ }
+ tempbuf = outbuf;
+ templen = outlen;
+
+ iconv (conv_tofs, NULL, NULL, NULL, NULL);
+
+ if (iconv (conv_tofs, &inbuf, &len, &tempbuf, &templen) == (size_t)-1)
+ return string;
+
+ *tempbuf = '\0';
+ return outbuf;
+#else
+ return string;
+#endif
+}
+
+char *
+fnx_fromfs (string, len)
+ char *string;
+ size_t len;
+{
+#ifdef MACOSX
+ ICONV_CONST char *inbuf;
+ char *tempbuf;
+ size_t templen;
+
+ if (conv_fromfs == (iconv_t)-1)
+ init_fromfs ();
+ if (conv_fromfs == (iconv_t)-1)
+ return string;
+
+ /* Free and reallocate outbuf if it's *too* big */
+ if (outlen >= OUTLEN_MAX && len < OUTLEN_MAX - 8)
+ {
+ free (outbuf);
+ outbuf = 0;
+ outlen = 0;
+ }
+
+ inbuf = string;
+ if (outbuf == 0 || outlen < (len + 8))
+ {
+ outlen = len + 8;
+ outbuf = outbuf ? xrealloc (outbuf, outlen + 1) : xmalloc (outlen + 1);
+ }
+ tempbuf = outbuf;
+ templen = outlen;
+
+ iconv (conv_fromfs, NULL, NULL, NULL, NULL);
+
+ if (iconv (conv_fromfs, &inbuf, &len, &tempbuf, &templen) == (size_t)-1)
+ return string;
+
+ *tempbuf = '\0';
+ return outbuf;
+#else
+ return string;
+#endif
+}
+
+#else
+char *
+fnx_tofs (string)
+ char *string;
+{
+ return string;
+}
+
+char *
+fnx_fromfs (string)
+ char *string;
+{
+ return string;
+}
+#endif
diff --git a/lib/sh/fpurge.c b/lib/sh/fpurge.c
index f9e1b9d..13e8c78 100644
--- a/lib/sh/fpurge.c
+++ b/lib/sh/fpurge.c
@@ -1,6 +1,6 @@
/* fpurge - Flushing buffers of a FILE stream. */
-/* Copyright (C) 2007 Free Software Foundation, Inc.
+/* Copyright (C) 2007-2010 Free Software Foundation, Inc.
This file is part of GNU Bash, the Bourne Again SHell.
@@ -36,6 +36,90 @@ extern int fpurge __P((FILE *stream));
#endif
#include <stdlib.h>
+/* Inline contents of gnulib:stdio-impl.h */
+
+/* Many stdio implementations have the same logic and therefore can share
+ the same implementation of stdio extension API, except that some fields
+ have different naming conventions, or their access requires some casts. */
+
+/* BSD stdio derived implementations. */
+
+#if defined __NetBSD__ /* NetBSD */
+/* Get __NetBSD_Version__. */
+# include <sys/param.h>
+#endif
+
+#if defined __sferror || defined __DragonFly__ /* FreeBSD, NetBSD, OpenBSD, DragonFly, MacOS X, Cygwin */
+
+# if defined __DragonFly__ /* DragonFly */
+ /* See <http://www.dragonflybsd.org/cvsweb/src/lib/libc/stdio/priv_stdio.h?rev=HEAD&content-type=text/x-cvsweb-markup>. */
+# define fp_ ((struct { struct __FILE_public pub; \
+ struct { unsigned char *_base; int _size; } _bf; \
+ void *cookie; \
+ void *_close; \
+ void *_read; \
+ void *_seek; \
+ void *_write; \
+ struct { unsigned char *_base; int _size; } _ub; \
+ int _ur; \
+ unsigned char _ubuf[3]; \
+ unsigned char _nbuf[1]; \
+ struct { unsigned char *_base; int _size; } _lb; \
+ int _blksize; \
+ fpos_t _offset; \
+ /* More fields, not relevant here. */ \
+ } *) fp)
+ /* See <http://www.dragonflybsd.org/cvsweb/src/include/stdio.h?rev=HEAD&content-type=text/x-cvsweb-markup>. */
+# define _p pub._p
+# define _flags pub._flags
+# define _r pub._r
+# define _w pub._w
+# else
+# define fp_ fp
+# endif
+
+# if (defined __NetBSD__ && __NetBSD_Version__ >= 105270000) || defined __OpenBSD__ /* NetBSD >= 1.5ZA, OpenBSD */
+ /* See <http://cvsweb.netbsd.org/bsdweb.cgi/src/lib/libc/stdio/fileext.h?rev=HEAD&content-type=text/x-cvsweb-markup>
+ and <http://www.openbsd.org/cgi-bin/cvsweb/src/lib/libc/stdio/fileext.h?rev=HEAD&content-type=text/x-cvsweb-markup> */
+ struct __sfileext
+ {
+ struct __sbuf _ub; /* ungetc buffer */
+ /* More fields, not relevant here. */
+ };
+# define fp_ub ((struct __sfileext *) fp->_ext._base)->_ub
+# else /* FreeBSD, NetBSD <= 1.5Z, DragonFly, MacOS X, Cygwin */
+# define fp_ub fp_->_ub
+# endif
+
+# define HASUB(fp) (fp_ub._base != NULL)
+
+#endif
+
+/* SystemV derived implementations. */
+
+#if defined _IOERR
+
+# if defined __sun && defined _LP64 /* Solaris/{SPARC,AMD64} 64-bit */
+# define fp_ ((struct { unsigned char *_ptr; \
+ unsigned char *_base; \
+ unsigned char *_end; \
+ long _cnt; \
+ int _file; \
+ unsigned int _flag; \
+ } *) fp)
+# else
+# define fp_ fp
+# endif
+
+# if defined _SCO_DS /* OpenServer */
+# define _cnt __cnt
+# define _ptr __ptr
+# define _base __base
+# define _flag __flag
+# endif
+
+#endif
+
int
fpurge (FILE *fp)
{
@@ -45,7 +129,7 @@ fpurge (FILE *fp)
/* The __fpurge function does not have a return value. */
return 0;
-#elif HAVE_FPURGE /* FreeBSD, NetBSD, OpenBSD, DragonFly, MacOS X */
+#elif HAVE_FPURGE /* FreeBSD, NetBSD, OpenBSD, DragonFly, MacOS X, Cygwin 1.7 */
/* Call the system's fpurge function. */
# undef fpurge
@@ -59,10 +143,10 @@ fpurge (FILE *fp)
<stdio.h> on BSD systems says:
"The following always hold: if _flags & __SRD, _w is 0."
If this invariant is not fulfilled and the stream is read-write but
- currently writing, subsequent putc or fputc calls will write directly
+ currently reading, subsequent putc or fputc calls will write directly
into the buffer, although they shouldn't be allowed to. */
- if ((fp->_flags & __SRD) != 0)
- fp->_w = 0;
+ if ((fp_->_flags & __SRD) != 0)
+ fp_->_w = 0;
# endif
return result;
@@ -101,7 +185,7 @@ fpurge (FILE *fp)
fp->_wcount = 0;
fp->_ungetc_count = 0;
return 0;
-# elif defined _IOERR /* AIX, HP-UX, IRIX, OSF/1, Solaris, OpenServer, mingw */
+# elif defined _IOERR || defined __TANDEM /* AIX, HP-UX, IRIX, OSF/1, Solaris, OpenServer, mingw */
fp->_ptr = fp->_base;
if (fp->_ptr != NULL)
fp->_cnt = 0;
diff --git a/lib/sh/mbscasecmp.c b/lib/sh/mbscasecmp.c
new file mode 100644
index 0000000..3828164
--- /dev/null
+++ b/lib/sh/mbscasecmp.c
@@ -0,0 +1,78 @@
+/* mbscasecmp - case-insensitive multibyte string comparison. */
+
+/* Copyright (C) 2009 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>
+
+#if !defined (HAVE_MBSCASECMP) && defined (HANDLE_MULTIBYTE)
+
+#include <stdlib.h>
+#include <stddef.h>
+#include <string.h>
+
+#include <wchar.h>
+#include <wctype.h>
+
+/* Compare MBS1 and MBS2 without regard to case. */
+int
+mbscasecmp (mbs1, mbs2)
+ const char *mbs1;
+ const char *mbs2;
+{
+ int len1, len2;
+ wchar_t c1, c2, l1, l2;
+
+ len1 = len2 = 0;
+ /* Reset multibyte characters to their initial state. */
+ (void) mblen ((char *) NULL, 0);
+
+ do
+ {
+ len1 = mbtowc (&c1, mbs1, MB_CUR_MAX);
+ len2 = mbtowc (&c2, mbs2, MB_CUR_MAX);
+
+ if (len1 == 0)
+ return len2 == 0 ? 0 : -1;
+ else if (len2 == 0)
+ return 1;
+ else if (len1 > 0 && len2 < 0)
+ return -1;
+ else if (len1 < 0 && len2 > 0)
+ return 1;
+ else if (len1 < 0 && len2 < 0)
+ {
+ len1 = strlen (mbs1);
+ len2 = strlen (mbs2);
+ return (len1 == len2 ? memcmp (mbs1, mbs2, len1)
+ : ((len1 < len2) ? (memcmp (mbs1, mbs2, len1) > 0 ? 1 : -1)
+ : (memcmp (mbs1, mbs2, len2) >= 0 ? 1 : -1)));
+ }
+
+ l1 = towlower (c1);
+ l2 = towlower (c2);
+
+ mbs1 += len1;
+ mbs2 += len2;
+ }
+ while (l1 == l2);
+
+ return l1 - l2;
+}
+
+#endif
diff --git a/lib/sh/mbschr.c b/lib/sh/mbschr.c
new file mode 100644
index 0000000..5143d64
--- /dev/null
+++ b/lib/sh/mbschr.c
@@ -0,0 +1,78 @@
+/* mbschr.c - strchr(3) that handles multibyte characters. */
+
+/* Copyright (C) 2002 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>
+
+#ifdef HAVE_STDLIB_H
+# include <stdlib.h>
+#endif
+
+#include "bashansi.h"
+#include "shmbutil.h"
+
+#undef mbschr
+
+/* In some locales, the non-first byte of some multibyte characters have
+ the same value as some ascii character. Faced with these strings, a
+ legacy strchr() might return the wrong value. */
+
+char *
+#if defined (PROTOTYPES)
+mbschr (const char *s, int c)
+#else
+mbschr (s, c)
+ const char *s;
+ int c;
+#endif
+{
+#if HANDLE_MULTIBYTE
+ char *pos;
+ mbstate_t state;
+ size_t strlength, mblength;
+
+ /* The locale encodings with said weird property are BIG5, BIG5-HKSCS,
+ GBK, GB18030, SHIFT_JIS, and JOHAB. They exhibit the problem only
+ when c >= 0x30. We can therefore use the faster bytewise search if
+ c <= 0x30. */
+ if ((unsigned char)c >= '0' && MB_CUR_MAX > 1)
+ {
+ pos = (char *)s;
+ memset (&state, '\0', sizeof(mbstate_t));
+ strlength = strlen (s);
+
+ while (strlength > 0)
+ {
+ mblength = mbrlen (pos, strlength, &state);
+ if (mblength == (size_t)-2 || mblength == (size_t)-1 || mblength == (size_t)0)
+ mblength = 1;
+
+ if (mblength == 1 && c == (unsigned char)*pos)
+ return pos;
+
+ strlength -= mblength;
+ pos += mblength;
+ }
+
+ return ((char *)NULL);
+ }
+ else
+#endif
+ return (strchr (s, c));
+}
diff --git a/lib/sh/oslib.c b/lib/sh/oslib.c
index d47f9dc..b3470d1 100644
--- a/lib/sh/oslib.c
+++ b/lib/sh/oslib.c
@@ -1,6 +1,6 @@
/* oslib.c - functions present only in some unix versions. */
-/* Copyright (C) 1995 Free Software Foundation, Inc.
+/* Copyright (C) 1995,2010 Free Software Foundation, Inc.
This file is part of GNU Bash, the Bourne Again SHell.
@@ -37,6 +37,10 @@
#include <filecntl.h>
#include <bashansi.h>
+#if !defined (HAVE_KILLPG)
+# include <signal.h>
+#endif
+
#include <stdio.h>
#include <errno.h>
#include <chartypes.h>
@@ -209,7 +213,8 @@ gethostname (name, namelen)
# else /* !HAVE_UNAME */
int
gethostname (name, namelen)
- int name, namelen;
+ char *name;
+ int namelen;
{
strncpy (name, "unknown", namelen);
name[namelen] = '\0';
diff --git a/lib/sh/shmatch.c b/lib/sh/shmatch.c
index 6de1dc1..3abefed 100644
--- a/lib/sh/shmatch.c
+++ b/lib/sh/shmatch.c
@@ -62,7 +62,7 @@ sh_regmatch (string, pattern, flags)
#if defined (ARRAY_VARS)
rematch = (SHELL_VAR *)NULL;
#endif
-
+
rflags = REG_EXTENDED;
if (glob_ignore_case || match_ignore_case)
rflags |= REG_ICASE;
diff --git a/lib/sh/shmbchar.c b/lib/sh/shmbchar.c
new file mode 100644
index 0000000..c5badc1
--- /dev/null
+++ b/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
diff --git a/lib/sh/shquote.c b/lib/sh/shquote.c
index a267d38..a1e9146 100644
--- a/lib/sh/shquote.c
+++ b/lib/sh/shquote.c
@@ -42,10 +42,11 @@
Used by alias and trap, among others. */
char *
sh_single_quote (string)
- char *string;
+ const char *string;
{
register int c;
- char *result, *r, *s;
+ char *result, *r;
+ const char *s;
result = (char *)xmalloc (3 + (4 * strlen (string)));
r = result;
@@ -72,10 +73,11 @@ sh_single_quote (string)
/* Quote STRING using double quotes. Return a new string. */
char *
sh_double_quote (string)
- char *string;
+ const char *string;
{
register unsigned char c;
- char *result, *r, *s;
+ char *result, *r;
+ const char *s;
result = (char *)xmalloc (3 + (2 * strlen (string)));
r = result;
diff --git a/lib/sh/snprintf.c b/lib/sh/snprintf.c
index d681b16..d46b2d9 100644
--- a/lib/sh/snprintf.c
+++ b/lib/sh/snprintf.c
@@ -9,7 +9,7 @@
Unix snprintf implementation.
derived from inetutils/libinetutils/snprintf.c Version 1.1
- Copyright (C) 2001,2006 Free Software Foundation, Inc.
+ Copyright (C) 2001,2006,2010 Free Software Foundation, Inc.
This file is part of GNU Bash, the Bourne Again SHell.
diff --git a/lib/sh/strcasestr.c b/lib/sh/strcasestr.c
new file mode 100644
index 0000000..c819b3e
--- /dev/null
+++ b/lib/sh/strcasestr.c
@@ -0,0 +1,46 @@
+/* strcasestr.c - Find if one string appears as a substring of another string,
+ without regard to case. */
+
+/* Copyright (C) 2000 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 <bashansi.h>
+#include <chartypes.h>
+
+#include <stdc.h>
+
+/* Determine if s2 occurs in s1. If so, return a pointer to the
+ match in s1. The compare is case insensitive. This is a
+ case-insensitive strstr(3). */
+char *
+strcasestr (s1, s2)
+ const char *s1;
+ const char *s2;
+{
+ register int i, l, len, c;
+
+ c = TOLOWER ((unsigned char)s2[0]);
+ len = strlen (s1);
+ l = strlen (s2);
+ for (i = 0; (len - i) >= l; i++)
+ if ((TOLOWER ((unsigned char)s1[i]) == c) && (strncasecmp (s1 + i, s2, l) == 0))
+ return ((char *)s1 + i);
+ return ((char *)0);
+}
diff --git a/lib/sh/strchrnul.c b/lib/sh/strchrnul.c
new file mode 100644
index 0000000..2e1608e
--- /dev/null
+++ b/lib/sh/strchrnul.c
@@ -0,0 +1,144 @@
+/* Searching in a string.
+ Copyright (C) 2003, 2007, 2008, 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>
+
+/* Specification. */
+#include <string.h>
+
+ /* On 32-bit hardware, choosing longword to be a 32-bit unsigned
+ long instead of a 64-bit uintmax_t tends to give better
+ performance. On 64-bit hardware, unsigned long is generally 64
+ bits already. Change this typedef to experiment with
+ performance. */
+ typedef unsigned long int longword;
+
+/* Find the first occurrence of C in S or the final NUL byte. */
+char *
+strchrnul (s, c_in)
+ const char *s;
+ int c_in;
+{
+ const unsigned char *char_ptr;
+ const longword *longword_ptr;
+ longword repeated_one;
+ longword repeated_c;
+ unsigned char c;
+
+ c = (unsigned char) c_in;
+ if (c == 0) /* find final null byte */
+ return (char *)(s ? (s + strlen (s)) : s);
+
+ /* Handle the first few bytes by reading one byte at a time.
+ Do this until CHAR_PTR is aligned on a longword boundary. */
+ for (char_ptr = (const unsigned char *) s;
+ (size_t) char_ptr % sizeof (longword) != 0;
+ ++char_ptr)
+ if (!*char_ptr || *char_ptr == c)
+ return (char *) char_ptr;
+
+ longword_ptr = (const longword *) char_ptr;
+
+ /* All these elucidatory comments refer to 4-byte longwords,
+ but the theory applies equally well to any size longwords. */
+
+ /* Compute auxiliary longword values:
+ repeated_one is a value which has a 1 in every byte.
+ repeated_c has c in every byte. */
+ repeated_one = 0x01010101;
+ repeated_c = c | (c << 8);
+ repeated_c |= repeated_c << 16;
+ if (0xffffffffU < (longword) -1)
+ {
+ repeated_one |= repeated_one << 31 << 1;
+ repeated_c |= repeated_c << 31 << 1;
+ if (8 < sizeof (longword))
+ {
+ size_t i;
+
+ for (i = 64; i < sizeof (longword) * 8; i *= 2)
+ {
+ repeated_one |= repeated_one << i;
+ repeated_c |= repeated_c << i;
+ }
+ }
+ }
+
+ /* Instead of the traditional loop which tests each byte, we will
+ test a longword at a time. The tricky part is testing if *any of
+ the four* bytes in the longword in question are equal to NUL or
+ c. We first use an xor with repeated_c. This reduces the task
+ to testing whether *any of the four* bytes in longword1 or
+ longword2 is zero.
+
+ Let's consider longword1. We compute tmp =
+ ((longword1 - repeated_one) & ~longword1) & (repeated_one << 7).
+ That is, we perform the following operations:
+ 1. Subtract repeated_one.
+ 2. & ~longword1.
+ 3. & a mask consisting of 0x80 in every byte.
+ Consider what happens in each byte:
+ - If a byte of longword1 is zero, step 1 and 2 transform it into 0xff,
+ and step 3 transforms it into 0x80. A carry can also be propagated
+ to more significant bytes.
+ - If a byte of longword1 is nonzero, let its lowest 1 bit be at
+ position k (0 <= k <= 7); so the lowest k bits are 0. After step 1,
+ the byte ends in a single bit of value 0 and k bits of value 1.
+ After step 2, the result is just k bits of value 1: 2^k - 1. After
+ step 3, the result is 0. And no carry is produced.
+ So, if longword1 has only non-zero bytes, tmp is zero.
+ Whereas if longword1 has a zero byte, call j the position of the least
+ significant zero byte. Then the result has a zero at positions 0, ...,
+ j-1 and a 0x80 at position j. We cannot predict the result at the more
+ significant bytes (positions j+1..3), but it does not matter since we
+ already have a non-zero bit at position 8*j+7.
+
+ The test whether any byte in longword1 or longword2 is zero is equivalent
+ to testing whether tmp1 is nonzero or tmp2 is nonzero. We can combine
+ this into a single test, whether (tmp1 | tmp2) is nonzero.
+
+ This test can read more than one byte beyond the end of a string,
+ depending on where the terminating NUL is encountered. However,
+ this is considered safe since the initialization phase ensured
+ that the read will be aligned, therefore, the read will not cross
+ page boundaries and will not cause a fault. */
+
+ while (1)
+ {
+ longword longword1 = *longword_ptr ^ repeated_c;
+ longword longword2 = *longword_ptr;
+
+ if (((((longword1 - repeated_one) & ~longword1)
+ | ((longword2 - repeated_one) & ~longword2))
+ & (repeated_one << 7)) != 0)
+ break;
+ longword_ptr++;
+ }
+
+ char_ptr = (const unsigned char *) longword_ptr;
+
+ /* At this point, we know that one of the sizeof (longword) bytes
+ starting at char_ptr is == 0 or == c. On little-endian machines,
+ we could determine the first such byte without any further memory
+ accesses, just by looking at the tmp result from the last loop
+ iteration. But this does not work on big-endian machines.
+ Choose code that works in both cases. */
+
+ char_ptr = (unsigned char *) longword_ptr;
+ while (*char_ptr && (*char_ptr != c))
+ char_ptr++;
+ return (char *) char_ptr;
+}
diff --git a/lib/sh/strftime.c b/lib/sh/strftime.c
index 572baae..aa3fc85 100644
--- a/lib/sh/strftime.c
+++ b/lib/sh/strftime.c
@@ -24,9 +24,6 @@
* It also doesn't worry about multi-byte characters.
* So there.
*
- * This file is also shipped with GAWK (GNU Awk), gawk specific bits of
- * code are included if GAWK is defined.
- *
* Arnold Robbins
* January, February, March, 1991
* Updated March, April 1992
@@ -39,6 +36,8 @@
* Updated July, 1997
* Updated October, 1999
* Updated September, 2000
+ * Updated December, 2001
+ * Updated January, 2011
*
* Fixes from ado@elsie.nci.nih.gov,
* February 1991, May 1992
@@ -54,14 +53,15 @@
* July 1997
* Moved to C99 specification.
* September 2000
+ * Fixes from Tanaka Akira <akr@m17n.org>
+ * December 2001
*/
#include <config.h>
-#ifndef GAWK
#include <stdio.h>
#include <ctype.h>
#include <time.h>
-#endif
+
#if defined(TM_IN_SYS_TIME)
#include <sys/types.h>
#include <sys/time.h>
@@ -74,9 +74,7 @@
#define SUNOS_EXT 1 /* stuff in SunOS strftime routine */
#define VMS_EXT 1 /* include %v for VMS date format */
#define HPUX_EXT 1 /* non-conflicting stuff in HP-UX date */
-#ifndef GAWK
#define POSIX_SEMANTICS 1 /* call tzset() if TZ changes */
-#endif
#undef strchr /* avoid AIX weirdness */
@@ -114,6 +112,11 @@ extern int timezone, altzone;
#undef min /* just in case */
+/* format for %+ -- currently unused */
+#ifndef NATIONAL_FORMAT
+#define NATIONAL_FORMAT "%a %b %e %H:%M:%S %Z %Y"
+#endif
+
/* min --- return minimum of two numbers */
static inline int
@@ -141,7 +144,8 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
char *start = s;
auto char tbuf[100];
long off;
- int i, w, y;
+ int i, w;
+ long y;
static short first = 1;
#ifdef POSIX_SEMANTICS
static char *savetz = NULL;
@@ -282,7 +286,7 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
case 'C':
century:
- sprintf(tbuf, "%02d", (timeptr->tm_year + 1900) / 100);
+ sprintf(tbuf, "%02ld", (timeptr->tm_year + 1900L) / 100);
break;
case 'd': /* day of the month, 01 - 31 */
@@ -319,16 +323,16 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
*/
w = iso8601wknum(timeptr);
if (timeptr->tm_mon == 11 && w == 1)
- y = 1900 + timeptr->tm_year + 1;
+ y = 1900L + timeptr->tm_year + 1;
else if (timeptr->tm_mon == 0 && w >= 52)
- y = 1900 + timeptr->tm_year - 1;
+ y = 1900L + timeptr->tm_year - 1;
else
- y = 1900 + timeptr->tm_year;
+ y = 1900L + timeptr->tm_year;
if (*format == 'G')
- sprintf(tbuf, "%d", y);
+ sprintf(tbuf, "%ld", y);
else
- sprintf(tbuf, "%02d", y % 100);
+ sprintf(tbuf, "%02ld", y % 100);
break;
case 'h': /* abbreviated month name */
@@ -387,7 +391,7 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
strftime(tbuf, sizeof tbuf, "%H:%M", timeptr);
break;
-#if defined(HAVE_MKTIME) || defined(GAWK)
+#if defined(HAVE_MKTIME)
case 's': /* time as seconds since the Epoch */
{
struct tm non_const_timeptr;
@@ -396,7 +400,7 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
sprintf(tbuf, "%ld", mktime(& non_const_timeptr));
break;
}
-#endif /* defined(HAVE_MKTIME) || defined(GAWK) */
+#endif /* defined(HAVE_MKTIME) */
case 'S': /* second, 00 - 60 */
i = range(0, timeptr->tm_sec, 60);
@@ -452,7 +456,7 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
case 'Y': /* year with century */
fullyear:
- sprintf(tbuf, "%d", 1900 + timeptr->tm_year);
+ sprintf(tbuf, "%ld", 1900L + timeptr->tm_year);
break;
/*
@@ -495,6 +499,7 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
# ifdef HPUX
off = -timezone / 60;
# else
+ /* ADR: 4 August 2001, fixed this per gazelle@interaccess.com */
off = -(daylight ? altzone : timezone) / 60;
# endif /* !HPUX */
#else /* !HAVE_TZNAME */
@@ -509,7 +514,7 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
} else {
tbuf[0] = '+';
}
- sprintf(tbuf+1, "%02d%02d", off/60, off%60);
+ sprintf(tbuf+1, "%02ld%02ld", off/60, off%60);
break;
case 'Z': /* time zone name or abbrevation */
@@ -558,10 +563,10 @@ strftime(char *s, size_t maxsize, const char *format, const struct tm *timeptr)
#ifdef VMS_EXT
case 'v': /* date as dd-bbb-YYYY */
- sprintf(tbuf, "%2d-%3.3s-%4d",
+ sprintf(tbuf, "%2d-%3.3s-%4ld",
range(1, timeptr->tm_mday, 31),
months_a[range(0, timeptr->tm_mon, 11)],
- timeptr->tm_year + 1900);
+ timeptr->tm_year + 1900L);
for (i = 3; i < 6; i++)
if (islower(tbuf[i]))
tbuf[i] = toupper(tbuf[i]);
@@ -594,7 +599,7 @@ out:
/* isleap --- is a year a leap year? */
static int
-isleap(int year)
+isleap(long year)
{
return ((year % 4 == 0 && year % 100 != 0) || year % 400 == 0);
}
@@ -677,7 +682,7 @@ iso8601wknum(const struct tm *timeptr)
dec31ly.tm_mon = 11;
dec31ly.tm_mday = 31;
dec31ly.tm_wday = (jan1day == 0) ? 6 : jan1day - 1;
- dec31ly.tm_yday = 364 + isleap(dec31ly.tm_year + 1900);
+ dec31ly.tm_yday = 364 + isleap(dec31ly.tm_year + 1900L);
weeknum = iso8601wknum(& dec31ly);
#endif
}
diff --git a/lib/sh/strtrans.c b/lib/sh/strtrans.c
index 355a306..2265782 100644
--- a/lib/sh/strtrans.c
+++ b/lib/sh/strtrans.c
@@ -1,6 +1,6 @@
/* strtrans.c - Translate and untranslate strings with ANSI-C escape sequences. */
-/* Copyright (C) 2000 Free Software Foundation, Inc.
+/* Copyright (C) 2000-2010 Free Software Foundation, Inc.
This file is part of GNU Bash, the Bourne Again SHell.
@@ -51,11 +51,16 @@ ansicstr (string, len, flags, sawc, rlen)
{
int c, temp;
char *ret, *r, *s;
+ unsigned long v;
if (string == 0 || *string == '\0')
return ((char *)NULL);
+#if defined (HANDLE_MULTIBYTE)
+ ret = (char *)xmalloc (4*len + 1);
+#else
ret = (char *)xmalloc (2*len + 1); /* 2*len for possible CTLESC */
+#endif
for (r = ret, s = string; s && *s; )
{
c = *s++;
@@ -128,6 +133,29 @@ ansicstr (string, len, flags, sawc, rlen)
}
c &= 0xFF;
break;
+#if defined (HANDLE_MULTIBYTE)
+ case 'u':
+ case 'U':
+ temp = (c == 'u') ? 4 : 8; /* \uNNNN \UNNNNNNNN */
+ for (v = 0; ISXDIGIT ((unsigned char)*s) && temp--; s++)
+ v = (v * 16) + HEXVALUE (*s);
+ if (temp == ((c == 'u') ? 4 : 8))
+ {
+ *r++ = '\\'; /* c remains unchanged */
+ break;
+ }
+ else if (v <= UCHAR_MAX)
+ {
+ c = v;
+ break;
+ }
+ else
+ {
+ temp = u32cconv (v, r);
+ r += temp;
+ continue;
+ }
+#endif
case '\\':
break;
case '\'': case '"': case '?':
@@ -143,9 +171,13 @@ ansicstr (string, len, flags, sawc, rlen)
*rlen = r - ret;
return ret;
}
+ else if ((flags & 1) == 0 && *s == 0)
+ ; /* pass \c through */
else if ((flags & 1) == 0 && (c = *s))
{
s++;
+ if ((flags & 2) && c == '\\' && c == *s)
+ s++; /* Posix requires $'\c\\' do backslash escaping */
c = TOCTRL(c);
break;
}
diff --git a/lib/sh/tmpfile.c b/lib/sh/tmpfile.c
index a87c254..0bbc287 100644
--- a/lib/sh/tmpfile.c
+++ b/lib/sh/tmpfile.c
@@ -40,7 +40,7 @@
extern int errno;
#endif
-#define BASEOPENFLAGS (O_CREAT | O_TRUNC | O_EXCL)
+#define BASEOPENFLAGS (O_CREAT | O_TRUNC | O_EXCL | O_BINARY)
#define DEFAULT_TMPDIR "." /* bogus default, should be changed */
#define DEFAULT_NAMEROOT "shtmp"
diff --git a/lib/sh/unicode.c b/lib/sh/unicode.c
new file mode 100644
index 0000000..d34fa08
--- /dev/null
+++ b/lib/sh/unicode.c
@@ -0,0 +1,235 @@
+/* unicode.c - functions to convert unicode characters */
+
+/* Copyright (C) 2010 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>
+
+#if defined (HANDLE_MULTIBYTE)
+
+#include <stdc.h>
+#include <wchar.h>
+#include <bashansi.h>
+#ifdef HAVE_UNISTD_H
+#include <unistd.h>
+#endif
+#include <limits.h>
+
+#if HAVE_ICONV
+# include <iconv.h>
+#endif
+
+#include <xmalloc.h>
+
+#ifndef USHORT_MAX
+# ifdef USHRT_MAX
+# define USHORT_MAX USHRT_MAX
+# else
+# define USHORT_MAX ((unsigned short) ~(unsigned short)0)
+# endif
+#endif
+
+#if !defined (STREQ)
+# define STREQ(a, b) ((a)[0] == (b)[0] && strcmp ((a), (b)) == 0)
+#endif /* !STREQ */
+
+#if defined (HAVE_LOCALE_CHARSET)
+extern const char *locale_charset __P((void));
+#else
+extern char *get_locale_var __P((char *));
+#endif
+
+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, *t;
+
+ 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
+u32tochar (wc, s)
+ wchar_t wc;
+ char *s;
+{
+ unsigned long x;
+ int l;
+
+ x = wc;
+ l = (x <= UCHAR_MAX) ? 1 : ((x <= USHORT_MAX) ? 2 : 4);
+
+ if (x <= UCHAR_MAX)
+ s[0] = x & 0xFF;
+ else if (x <= USHORT_MAX) /* assume unsigned short = 16 bits */
+ {
+ s[0] = (x >> 8) & 0xFF;
+ s[1] = x & 0xFF;
+ }
+ else
+ {
+ s[0] = (x >> 24) & 0xFF;
+ s[1] = (x >> 16) & 0xFF;
+ s[2] = (x >> 8) & 0xFF;
+ s[3] = x & 0xFF;
+ }
+ s[l] = '\0';
+ return l;
+}
+
+int
+u32toutf8 (wc, s)
+ wchar_t wc;
+ char *s;
+{
+ int l;
+
+ l = (wc < 0x0080) ? 1 : ((wc < 0x0800) ? 2 : 3);
+
+ if (wc < 0x0080)
+ s[0] = (unsigned char)wc;
+ else if (wc < 0x0800)
+ {
+ s[0] = (wc >> 6) | 0xc0;
+ s[1] = (wc & 0x3f) | 0x80;
+ }
+ else
+ {
+ s[0] = (wc >> 12) | 0xe0;
+ s[1] = ((wc >> 6) & 0x3f) | 0x80;
+ s[2] = (wc & 0x3f) | 0x80;
+ }
+ s[l] = '\0';
+ return l;
+}
+
+/* convert a single unicode-32 character into a multibyte string and put the
+ result in S, which must be large enough (at least MB_LEN_MAX bytes) */
+int
+u32cconv (c, s)
+ unsigned long c;
+ char *s;
+{
+ wchar_t wc;
+ int n;
+#if HAVE_ICONV
+ const char *charset;
+ char obuf[25], *optr;
+ size_t obytesleft;
+ const char *iptr;
+ size_t sn;
+#endif
+
+ wc = c;
+
+#if __STDC_ISO_10646__
+ if (sizeof (wchar_t) == 4)
+ {
+ n = wctomb (s, wc);
+ return n;
+ }
+#endif
+
+#if HAVE_NL_LANGINFO
+ codeset = nl_langinfo (CODESET);
+ if (STREQ (codeset, "UTF-8"))
+ {
+ n = u32toutf8 (wc, s);
+ return n;
+ }
+#endif
+
+#if HAVE_ICONV
+ /* 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
+ {
+ localconv = iconv_open (charset, "UTF-8");
+ if (localconv == (iconv_t)-1)
+ localconv = iconv_open (charset, "ASCII");
+ }
+ u32init = 1;
+ }
+
+ if (utf8locale)
+ {
+ n = u32toutf8 (wc, s);
+ return n;
+ }
+
+ if (localconv == (iconv_t)-1)
+ {
+ n = u32tochar (wc, s);
+ return n;
+ }
+
+ n = u32toutf8 (wc, s);
+
+ optr = obuf;
+ obytesleft = sizeof (obuf);
+ iptr = s;
+ sn = n;
+
+ iconv (localconv, NULL, NULL, NULL, NULL);
+
+ if (iconv (localconv, (ICONV_CONST char **)&iptr, &sn, &optr, &obytesleft) == (size_t)-1)
+ return n; /* You get utf-8 if iconv fails */
+
+ *optr = '\0';
+
+ /* number of chars to be copied is optr - obuf if we want to do bounds
+ checking */
+ strcpy (s, obuf);
+ return (optr - obuf);
+#endif
+
+ n = u32tochar (wc, s); /* fallback */
+ return n;
+}
+
+#endif /* HANDLE_MULTIBYTE */
diff --git a/lib/sh/wcswidth.c b/lib/sh/wcswidth.c
new file mode 100644
index 0000000..1a30d9f
--- /dev/null
+++ b/lib/sh/wcswidth.c
@@ -0,0 +1,46 @@
+/* wcswidth.c - compute display width of wide character string */
+
+/* Copyright (C) 2010 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>
+
+#if defined (HANDLE_MULTIBYTE) && !defined (HAVE_WCSWIDTH)
+
+#include <stdc.h>
+#include <wchar.h>
+#include <bashansi.h>
+
+int
+wcswidth(pwcs, n)
+ const wchar_t *pwcs;
+ size_t n;
+{
+ wchar_t wc;
+ int len, l;
+
+ len = 0;
+ while (n-- > 0 && (wc = *pwcs++) != L'\0')
+ {
+ if ((l = wcwidth(wc)) < 0)
+ return (-1);
+ len += l;
+ }
+ return (len);
+}
+#endif
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-23 19:59:44 +0000