tar: support -T - and -X -

[oweals/busybox.git] / libbb / process_escape_sequence.c

diff --git a/libbb/process_escape_sequence.c b/libbb/process_escape_sequence.c
index e6b5fc99550c8b2fad6729b20949ebcb5f6a3f97..346ecfa1e2c0c5de4bc299ee10c12d4c465ce685 100644 (file)
--- a/libbb/process_escape_sequence.c
+++ b/libbb/process_escape_sequence.c
@@ -5,84 +5,108 @@
  * Copyright (C) Manuel Novoa III <mjn3@codepoet.org>
  * and Vladimir Oleynik <dzo@simtreas.ru>
  *
- * 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 2 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, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- *
+ * Licensed under GPLv2 or later, see file LICENSE in this source tree.
  */
 
-#include <string.h>
-#include <stdio.h>
-#include <limits.h>
-#include <ctype.h>
 #include "libbb.h"
 
-#define isodigit(c) ((c) >= '0' && (c) <= '7')
-#define hextobin(c) ((c)>='a'&&(c)<='f' ? (c)-'a'+10 : (c)>='A'&&(c)<='F' ? (c)-'A'+10 : (c)-'0')
-#define octtobin(c) ((c) - '0')
-char bb_process_escape_sequence(const char **ptr)
+#define WANT_HEX_ESCAPES 1
+
+/* Usual "this only works for ascii compatible encodings" disclaimer. */
+#undef _tolower
+#define _tolower(X) ((X)|((char) 0x20))
+
+char FAST_FUNC bb_process_escape_sequence(const char **ptr)
 {
-       const char *p, *q;
-       unsigned int num_digits, r, n, hexescape;
-       static const char charmap[] = {
-               'a',  'b',  'f',  'n',  'r',  't',  'v',  '\\', 0,
-               '\a', '\b', '\f', '\n', '\r', '\t', '\v', '\\', '\\' };
+       const char *q;
+       unsigned num_digits;
+       unsigned n;
+       unsigned base;
 
-       n = r = hexescape = num_digits = 0;
+       num_digits = n = 0;
+       base = 8;
        q = *ptr;
 
-       if (*q == 'x') {
-               hexescape++;
+       if (WANT_HEX_ESCAPES && *q == 'x') {
                ++q;
+               base = 16;
+               ++num_digits;
        }
 
+       /* bash requires leading 0 in octal escapes:
+        * \02 works, \2 does not (prints \ and 2).
+        * We treat \2 as a valid octal escape sequence. */
        do {
-               if (hexescape && isxdigit(*q)) {
-                       r = n * 16 + hextobin(*q);
-               } else if (isodigit(*q)) {
-                       r = n * 8 + octtobin(*q);
-               }
-               if (r <= UCHAR_MAX) {
-                       n = r;
-                       ++q;
-                       if (++num_digits < 3) {
-                               continue;
+               unsigned r;
+#if !WANT_HEX_ESCAPES
+               unsigned d = (unsigned char)(*q) - '0';
+#else
+               unsigned d = (unsigned char)_tolower(*q) - '0';
+               if (d >= 10)
+                       d += ('0' - 'a' + 10);
+#endif
+               if (d >= base) {
+                       if (WANT_HEX_ESCAPES && base == 16) {
+                               --num_digits;
+                               if (num_digits == 0) {
+                                       /* \x<bad_char>: return '\',
+                                        * leave ptr pointing to x */
+                                       return '\\';
+                               }
                        }
+                       break;
+               }
+
+               r = n * base + d;
+               if (r > UCHAR_MAX) {
+                       break;
                }
-               break;
-       } while (1);
 
-       if (num_digits == 0) {  /* mnemonic escape sequence? */
-               p = charmap;
+               n = r;
+               ++q;
+       } while (++num_digits < 3);
+
+       if (num_digits == 0) {
+               /* Not octal or hex escape sequence.
+                * Is it one-letter one? */
+
+               /* bash builtin "echo -e '\ec'" interprets \e as ESC,
+                * but coreutils "/bin/echo -e '\ec'" does not.
+                * Manpages tend to support coreutils way.
+                * Update: coreutils added support for \e on 28 Oct 2009. */
+               static const char charmap[] ALIGN1 = {
+                       'a',  'b', 'e', 'f',  'n',  'r',  't',  'v',  '\\', '\0',
+                       '\a', '\b', 27, '\f', '\n', '\r', '\t', '\v', '\\', '\\',
+               };
+               const char *p = charmap;
                do {
                        if (*p == *q) {
                                q++;
                                break;
                        }
-               } while (*++p);
-               n = *(p+(sizeof(charmap)/2));
+               } while (*++p != '\0');
+               /* p points to found escape char or NUL,
+                * advance it and find what it translates to.
+                * Note that \NUL and unrecognized sequence \z return '\'
+                * and leave ptr pointing to NUL or z. */
+               n = p[sizeof(charmap) / 2];
        }
 
        *ptr = q;
+
        return (char) n;
 }
 
-/* END CODE */
-/*
-Local Variables:
-c-file-style: "linux"
-c-basic-offset: 4
-tab-width: 4
-End:
-*/
+char* FAST_FUNC strcpy_and_process_escape_sequences(char *dst, const char *src)
+{
+       while (1) {
+               char c, c1;
+               c = c1 = *src++;
+               if (c1 == '\\')
+                       c1 = bb_process_escape_sequence(&src);
+               *dst = c1;
+               if (c == '\0')
+                       return dst;
+               dst++;
+       }
+}