-/* strtrans.c - Translate and untranslate strings with ANSI-C escape
- sequences. */
+/* strtrans.c - Translate and untranslate strings with ANSI-C escape sequences. */
-/* Copyright (C) 2000
- Free Software Foundation, Inc.
+/* Copyright (C) 2000-2011 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 2, or (at your option) any later
- version.
+ 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.
+ 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; see the file COPYING. If not, write to the Free Software
- Foundation, 59 Temple Place, Suite 330, Boston, MA 02111 USA. */
+ 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 "shell.h"
+#include "shmbchar.h"
+#include "shmbutil.h"
+
#ifdef ESC
#undef ESC
#endif
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 */
+ 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 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++;
case 'a': c = '\a'; break;
case 'v': c = '\v'; break;
#else
- case 'a': c = '\007'; break;
+ case 'a': c = (int) 0x07; break;
case 'v': c = (int) 0x0B; break;
#endif
case 'b': c = '\b'; break;
case 'n': c = '\n'; break;
case 'r': c = '\r'; break;
case 't': c = '\t'; break;
- case '0': case '1': case '2': case '3':
- case '4': case '5': case '6': case '7':
+ 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
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 */
- if (temp == 2)
+ 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 <= 0x7f) /* <= 0x7f translates directly */
+ {
+ c = v;
+ break;
+ }
+ else
+ {
+ temp = u32cconv (v, r);
+ r += temp;
+ continue;
+ }
+#endif
case '\\':
break;
- case '\'':
+ case '\'': case '"': case '?':
if (flags & 1)
*r++ = '\\';
break;
*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 $'\c\\' do backslash escaping */
c = TOCTRL(c);
break;
}
/*FALLTHROUGH*/
- default: *r++ = '\\'; break;
+ default:
+ if ((flags & 4) == 0)
+ *r++ = '\\';
+ break;
}
if ((flags & 2) && (c == CTLESC || c == CTLNUL))
*r++ = CTLESC;
int flags, *rlen;
{
char *r, *ret, *s;
- int l, rsize, t;
+ int l, rsize;
unsigned char c;
+ size_t clen;
+ int b;
+#if defined (HANDLE_MULTIBYTE)
+ wchar_t wc;
+#endif
if (str == 0 || *str == 0)
return ((char *)0);
*r++ = '$';
*r++ = '\'';
- for (s = str, l = 0; *s; s++)
+ s = str;
+
+ for (s = str; c = *s; s++)
{
- c = *s;
- l = 1; /* 1 == add backslash; 0 == no backslash */
+ b = l = 1; /* 1 == add backslash; 0 == no backslash */
+ clen = 1;
+
switch (c)
{
case ESC: c = 'E'; break;
case '\a': c = 'a'; break;
case '\v': c = 'v'; break;
#else
- case '\007': c = 'a'; break;
+ case 0x07: c = 'a'; break;
case 0x0b: c = 'v'; break;
#endif
case '\'':
break;
default:
+#if defined (HANDLE_MULTIBYTE)
+ b = is_basic (c);
+ /* XXX - clen comparison to 0 is dicey */
+ if ((b == 0 && ((clen = mbrtowc (&wc, s, MB_CUR_MAX, 0)) < 0 || MB_INVALIDCH (clen) || iswprint (wc) == 0)) ||
+ (b == 1 && ISPRINT (c) == 0))
+#else
if (ISPRINT (c) == 0)
+#endif
{
*r++ = '\\';
*r++ = TOCHAR ((c >> 6) & 07);
l = 0;
break;
}
+ if (b == 0 && clen == 0)
+ break;
+
if (l)
*r++ = '\\';
- *r++ = c;
+
+ if (clen == 1)
+ *r++ = c;
+ else
+ {
+ for (b = 0; b < (int)clen; b++)
+ *r++ = (unsigned char)s[b];
+ s += clen - 1; /* -1 because of the increment above */
+ }
}
*r++ = '\'';
return ret;
}
+#if defined (HANDLE_MULTIBYTE)
+int
+ansic_wshouldquote (string)
+ const char *string;
+{
+ const wchar_t *wcs;
+ wchar_t wcc;
+
+ wchar_t *wcstr = NULL;
+ size_t slen;
+
+
+ slen = mbstowcs (wcstr, string, 0);
+
+ if (slen == -1)
+ slen = 0;
+ wcstr = (wchar_t *)xmalloc (sizeof (wchar_t) * (slen + 1));
+ mbstowcs (wcstr, string, slen + 1);
+
+ for (wcs = wcstr; wcc = *wcs; wcs++)
+ if (iswprint(wcc) == 0)
+ {
+ free (wcstr);
+ return 1;
+ }
+
+ free (wcstr);
+ return 0;
+}
+#endif
+
/* return 1 if we need to quote with $'...' because of non-printing chars. */
int
ansic_shouldquote (string)
return 0;
for (s = string; c = *s; s++)
- if (ISPRINT (c) == 0)
- return 1;
+ {
+#if defined (HANDLE_MULTIBYTE)
+ if (is_basic (c) == 0)
+ return (ansic_wshouldquote (s));
+#endif
+ if (ISPRINT (c) == 0)
+ return 1;
+ }
return 0;
}
projects / platform / upstream / bash.git / blobdiff