pmodules/bash
0
0
Fork 0
mirror of https://https.git.savannah.gnu.org/git/bash.git synced 2026-07-01 09:29:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

commit bash-20100520 snapshot

Browse Source
This commit is contained in:
Chet Ramey
2011-12-12 21:59:12 -05:00
parent cdb599a168
commit eb0b2ad86b
43 changed files with 10828 additions and 9327 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/sh/Makefile.in
+2 -2
View File
@@ -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
strchrnul.c unicode.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 ${LIBOBJS}
input_avail.o mbscasecmp.o fnxform.o unicode.o ${LIBOBJS}
SUPPORT = Makefile
lib/sh/strtrans.c
+32 -1
View File
@@ -49,13 +49,20 @@ ansicstr (string, len, flags, sawc, rlen)
char *string;
int len, flags, *sawc, *rlen;
{
int c, temp;
int c, temp, v;
char *ret, *r, *s;
#if defined (HANDLE_MULTIBYTE)
char mbch[25]; /* 25 > MB_LEN_MAX, plus can handle 4-byte UTF-8 and large Unicode characters*/
#endif
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 +135,30 @@ 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
{
memset (mbch, '\0', sizeof (mbch));
temp = u32cconv (v, r);
r += temp;
continue;
}
#endif
case '\\':
break;
case '\'': case '"': case '?':
lib/sh/strtrans.c~
+310
View File
@@ -0,0 +1,310 @@
/* strtrans.c - Translate and untranslate strings with ANSI-C escape sequences. */
/* 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>
#if defined (HAVE_UNISTD_H)
# include <unistd.h>
#endif
#include <bashansi.h>
#include <stdio.h>
#include <chartypes.h>
#include "shell.h"
#ifdef ESC
#undef ESC
#endif
#define ESC '\033' /* ASCII */
/* Convert STRING by expanding the escape sequences specified by the
ANSI C standard. If SAWC is non-null, recognize `\c' and use that
as a string terminator. If we see \c, set *SAWC to 1 before
returning. LEN is the length of STRING. If (FLAGS&1) is non-zero,
that we're translating a string for `echo -e', and therefore should not
treat a single quote as a character that may be escaped with a backslash.
If (FLAGS&2) is non-zero, we're expanding for the parser and want to
quote CTLESC and CTLNUL with CTLESC. If (flags&4) is non-zero, we want
to remove the backslash before any unrecognized escape sequence. */
char *
ansicstr (string, len, flags, sawc, rlen)
char *string;
int len, flags, *sawc, *rlen;
{
int c, temp, v;
char *ret, *r, *s;
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++;
if (c != '\\' || *s == '\0')
*r++ = c;
else
{
switch (c = *s++)
{
#if defined (__STDC__)
case 'a': c = '\a'; break;
case 'v': c = '\v'; break;
#else
case 'a': c = '\007'; break;
case 'v': c = (int) 0x0B; break;
#endif
case 'b': c = '\b'; break;
case 'e': case 'E': /* ESC -- non-ANSI */
c = ESC; break;
case 'f': c = '\f'; break;
case 'n': c = '\n'; break;
case 'r': c = '\r'; break;
case 't': c = '\t'; break;
case '1': case '2': case '3':
case '4': case '5': case '6':
case '7':
#if 1
if (flags & 1)
{
*r++ = '\\';
break;
}
/*FALLTHROUGH*/
#endif
case '0':
/* If (FLAGS & 1), we're translating a string for echo -e (or
the equivalent xpg_echo option), so we obey the SUSv3/
POSIX-2001 requirement and accept 0-3 octal digits after
a leading `0'. */
temp = 2 + ((flags & 1) && (c == '0'));
for (c -= '0'; ISOCTAL (*s) && temp--; s++)
c = (c * 8) + OCTVALUE (*s);
c &= 0xFF;
break;
case 'x': /* Hex digit -- non-ANSI */
if ((flags & 2) && *s == '{')
{
flags |= 16; /* internal flag value */
s++;
}
/* Consume at least two hex characters */
for (temp = 2, c = 0; ISXDIGIT ((unsigned char)*s) && temp--; s++)
c = (c * 16) + HEXVALUE (*s);
/* DGK says that after a `\x{' ksh93 consumes ISXDIGIT chars
until a non-xdigit or `}', so potentially more than two
chars are consumed. */
if (flags & 16)
{
for ( ; ISXDIGIT ((unsigned char)*s); s++)
c = (c * 16) + HEXVALUE (*s);
flags &= ~16;
if (*s == '}')
s++;
}
/* \x followed by non-hex digits is passed through unchanged */
else if (temp == 2)
{
*r++ = '\\';
c = 'x';
}
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
{
memset (mbch, '\0', sizeof (mbch));
temp = u32cconv (v, r);
r += temp;
continue;
}
#endif
case '\\':
break;
case '\'': case '"': case '?':
if (flags & 1)
*r++ = '\\';
break;
case 'c':
if (sawc)
{
*sawc = 1;
*r = '\0';
if (rlen)
*rlen = r - ret;
return ret;
}
else if ((flags & 1) == 0 && (c = *s))
{
s++;
c = TOCTRL(c);
break;
}
/*FALLTHROUGH*/
default:
if ((flags & 4) == 0)
*r++ = '\\';
break;
}
if ((flags & 2) && (c == CTLESC || c == CTLNUL))
*r++ = CTLESC;
*r++ = c;
}
}
*r = '\0';
if (rlen)
*rlen = r - ret;
return ret;
}
/* Take a string STR, possibly containing non-printing characters, and turn it
into a $'...' ANSI-C style quoted string. Returns a new string. */
char *
ansic_quote (str, flags, rlen)
char *str;
int flags, *rlen;
{
char *r, *ret, *s;
int l, rsize;
unsigned char c;
if (str == 0 || *str == 0)
return ((char *)0);
l = strlen (str);
rsize = 4 * l + 4;
r = ret = (char *)xmalloc (rsize);
*r++ = '$';
*r++ = '\'';
for (s = str, l = 0; *s; s++)
{
c = *s;
l = 1; /* 1 == add backslash; 0 == no backslash */
switch (c)
{
case ESC: c = 'E'; break;
#ifdef __STDC__
case '\a': c = 'a'; break;
case '\v': c = 'v'; break;
#else
case '\007': c = 'a'; break;
case 0x0b: c = 'v'; break;
#endif
case '\b': c = 'b'; break;
case '\f': c = 'f'; break;
case '\n': c = 'n'; break;
case '\r': c = 'r'; break;
case '\t': c = 't'; break;
case '\\':
case '\'':
break;
default:
if (ISPRINT (c) == 0)
{
*r++ = '\\';
*r++ = TOCHAR ((c >> 6) & 07);
*r++ = TOCHAR ((c >> 3) & 07);
*r++ = TOCHAR (c & 07);
continue;
}
l = 0;
break;
}
if (l)
*r++ = '\\';
*r++ = c;
}
*r++ = '\'';
*r = '\0';
if (rlen)
*rlen = r - ret;
return ret;
}
/* return 1 if we need to quote with $'...' because of non-printing chars. */
int
ansic_shouldquote (string)
const char *string;
{
const char *s;
unsigned char c;
if (string == 0)
return 0;
for (s = string; c = *s; s++)
if (ISPRINT (c) == 0)
return 1;
return 0;
}
/* $'...' ANSI-C expand the portion of STRING between START and END and
return the result. The result cannot be longer than the input string. */
char *
ansiexpand (string, start, end, lenp)
char *string;
int start, end, *lenp;
{
char *temp, *t;
int len, tlen;
temp = (char *)xmalloc (end - start + 1);
for (tlen = 0, len = start; len < end; )
temp[tlen++] = string[len++];
temp[tlen] = '\0';
if (*temp)
{
t = ansicstr (temp, tlen, 2, (int *)NULL, lenp);
free (temp);
return (t);
}
else
{
if (lenp)
*lenp = 0;
return (temp);
}
}
lib/sh/unicode.c
+205
View File
@@ -0,0 +1,205 @@
/* unicode.c - functions to convert unicode characters */
/* Copyright (C) 2006 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;
static iconv_t localconv;
/* 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;
char *iptr;
size_t sn;
#endif
wc = c;
#if __STDC_ISO_10646__
if (sizeof (wchar_t) == 4)
{
n = wctomb (wc, s);
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)
{
charset = locale_charset (); /* XXX - fix later */
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, &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 */
lib/sh/unicode.c~
+201
View File
@@ -0,0 +1,201 @@
/* unicode.c - functions to convert unicode characters */
/* Copyright (C) 2006 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 (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;
static iconv_t localconv;
/* 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;
char *iptr;
size_t sn;
#endif
wc = c;
#if __STDC_ISO_10646__
if (sizeof (wchar_t) == 4)
{
n = wctomb (wc, s);
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)
{
charset = locale_charset (); /* XXX - fix later */
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, &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 */