server/gen_test_char.c

   1 /* Licensed to the Apache Software Foundation (ASF) under one or more
   2  * contributor license agreements.  See the NOTICE file distributed with
   3  * this work for additional information regarding copyright ownership.
   4  * The ASF licenses this file to You under the Apache License, Version 2.0
   5  * (the "License"); you may not use this file except in compliance with
   6  * the License.  You may obtain a copy of the License at
   7  *
   8  *     http://www.apache.org/licenses/LICENSE-2.0
   9  *
  10  * Unless required by applicable law or agreed to in writing, software
  11  * distributed under the License is distributed on an "AS IS" BASIS,
  12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13  * See the License for the specific language governing permissions and
  14  * limitations under the License.
  15  */
  16
  17 #include "apr.h"
  18 #include "apr_lib.h"
  19
  20 #if APR_HAVE_STDIO_H
  21 #include <stdio.h>
  22 #endif
  23 #if APR_HAVE_STRING_H
  24 #include <string.h>
  25 #endif
  26
  27 /* A bunch of functions in util.c scan strings looking for certain characters.
  28  * To make that more efficient we encode a lookup table.
  29  */
  30 #define T_ESCAPE_SHELL_CMD    (0x01)
  31 #define T_ESCAPE_PATH_SEGMENT (0x02)
  32 #define T_OS_ESCAPE_PATH      (0x04)
  33 #define T_HTTP_TOKEN_STOP     (0x08)
  34 #define T_ESCAPE_LOGITEM      (0x10)
  35 #define T_ESCAPE_FORENSIC     (0x20)
  36
  37 int main(int argc, char *argv[])
  38 {
  39     unsigned c;
  40     unsigned char flags;
  41
  42     printf("/* this file is automatically generated by gen_test_char, "
  43            "do not edit */\n"
  44            "#define T_ESCAPE_SHELL_CMD     (%u)\n"
  45            "#define T_ESCAPE_PATH_SEGMENT  (%u)\n"
  46            "#define T_OS_ESCAPE_PATH       (%u)\n"
  47            "#define T_HTTP_TOKEN_STOP      (%u)\n"
  48            "#define T_ESCAPE_LOGITEM       (%u)\n"
  49            "#define T_ESCAPE_FORENSIC      (%u)\n"
  50            "\n"
  51            "static const unsigned char test_char_table[256] = {",
  52            T_ESCAPE_SHELL_CMD,
  53            T_ESCAPE_PATH_SEGMENT,
  54            T_OS_ESCAPE_PATH,
  55            T_HTTP_TOKEN_STOP,
  56            T_ESCAPE_LOGITEM,
  57            T_ESCAPE_FORENSIC);
  58
  59     for (c = 0; c < 256; ++c) {
  60         flags = 0;
  61         if (c % 20 == 0)
  62             printf("\n    ");
  63
  64         /* escape_shell_cmd */
  65 #if defined(WIN32) || defined(OS2)
  66         /* Win32/OS2 have many of the same vulnerable characters
  67          * as Unix sh, plus the carriage return and percent char.
  68          * The proper escaping of these characters varies from unix
  69          * since Win32/OS2 use carets or doubled-double quotes,
  70          * and neither lf nor cr can be escaped.  We escape unix
  71          * specific as well, to assure that cross-compiled unix
  72          * applications behave similiarly when invoked on win32/os2.
  73          *
  74          * Rem please keep in-sync with apr's list in win32/filesys.c
  75          */
  76         if (c && strchr("&;`'\"|*?~<>^()[]{}$\\\n\r%", c)) {
  77             flags |= T_ESCAPE_SHELL_CMD;
  78         }
  79 #else
  80         if (c && strchr("&;`'\"|*?~<>^()[]{}$\\\n", c)) {
  81             flags |= T_ESCAPE_SHELL_CMD;
  82         }
  83 #endif
  84
  85         if (!apr_isalnum(c) && !strchr("$-_.+!*'(),:@&=~", c)) {
  86             flags |= T_ESCAPE_PATH_SEGMENT;
  87         }
  88
  89         if (!apr_isalnum(c) && !strchr("$-_.+!*'(),:@&=/~", c)) {
  90             flags |= T_OS_ESCAPE_PATH;
  91         }
  92
  93         /* these are the "tspecials" (RFC2068) or "separators" (RFC2616) */
  94         if (c && (apr_iscntrl(c) || strchr(" \t()<>@,;:\\\"/[]?={}", c))) {
  95             flags |= T_HTTP_TOKEN_STOP;
  96         }
  97
  98         /* For logging, escape all control characters,
  99          * double quotes (because they delimit the request in the log file)
 100          * backslashes (because we use backslash for escaping)
 101          * and 8-bit chars with the high bit set
 102          */
 103         if (c && (!apr_isprint(c) || c == '"' || c == '\\' || apr_iscntrl(c))) {
 104             flags |= T_ESCAPE_LOGITEM;
 105         }
 106
 107         /* For forensic logging, escape all control characters, top bit set,
 108          * :, | (used as delimiters) and % (used for escaping).
 109          */
 110         if (!apr_isprint(c) || c == ':' || c == '|' || c == '%'
 111             || apr_iscntrl(c) || !c) {
 112             flags |= T_ESCAPE_FORENSIC;
 113         }
 114
 115         printf("%u%c", flags, (c < 255) ? ',' : ' ');
 116     }
 117
 118     printf("\n};\n");
 119
 120     return 0;
 121 }