lib/search/hex.c

   1 /*
   2    Search text engine.
   3    HEX-style pattern matching
   4
   5    Copyright (C) 2009-2019
   6    Free Software Foundation, Inc.
   7
   8    Written by:
   9    Slava Zanko <slavazanko@gmail.com>, 2009.
  10
  11    This file is part of the Midnight Commander.
  12
  13    The Midnight Commander is free software: you can redistribute it
  14    and/or modify it under the terms of the GNU General Public License as
  15    published by the Free Software Foundation, either version 3 of the License,
  16    or (at your option) any later version.
  17
  18    The Midnight Commander is distributed in the hope that it will be useful,
  19    but WITHOUT ANY WARRANTY; without even the implied warranty of
  20    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21    GNU General Public License for more details.
  22
  23    You should have received a copy of the GNU General Public License
  24    along with this program.  If not, see <http://www.gnu.org/licenses/>.
  25  */
  26
  27 #include <config.h>
  28
  29 #include <stdio.h>
  30
  31 #include "lib/global.h"
  32 #include "lib/strutil.h"
  33 #include "lib/search.h"
  34 #include "lib/strescape.h"
  35
  36 #include "internal.h"
  37
  38 /*** global variables ****************************************************************************/
  39
  40 /*** file scope macro definitions ****************************************************************/
  41
  42 typedef enum
  43 {
  44     MC_SEARCH_HEX_E_OK,
  45     MC_SEARCH_HEX_E_NUM_OUT_OF_RANGE,
  46     MC_SEARCH_HEX_E_INVALID_CHARACTER,
  47     MC_SEARCH_HEX_E_UNMATCHED_QUOTES
  48 } mc_search_hex_parse_error_t;
  49
  50 /*** file scope type declarations ****************************************************************/
  51
  52 /*** file scope variables ************************************************************************/
  53
  54 /*** file scope functions ************************************************************************/
  55
  56 static GString *
  57 mc_search__hex_translate_to_regex (const GString * astr, mc_search_hex_parse_error_t * error_ptr,
  58                                    int *error_pos_ptr)
  59 {
  60     GString *buff;
  61     const char *str;
  62     gsize str_len;
  63     gsize loop = 0;
  64     mc_search_hex_parse_error_t error = MC_SEARCH_HEX_E_OK;
  65
  66     buff = g_string_sized_new (64);
  67     str = astr->str;
  68     str_len = astr->len;
  69
  70     while (loop < str_len && error == MC_SEARCH_HEX_E_OK)
  71     {
  72         unsigned int val;
  73         int ptr;
  74
  75         if (g_ascii_isspace (str[loop]))
  76         {
  77             /* Eat-up whitespace between tokens. */
  78             while (g_ascii_isspace (str[loop]))
  79                 loop++;
  80         }
  81         /* cppcheck-suppress invalidscanf */
  82         else if (sscanf (str + loop, "%x%n", &val, &ptr) == 1)
  83         {
  84             if (val > 255)
  85                 error = MC_SEARCH_HEX_E_NUM_OUT_OF_RANGE;
  86             else
  87             {
  88                 g_string_append_printf (buff, "\\x%02X", val);
  89                 loop += ptr;
  90             }
  91         }
  92         else if (str[loop] == '"')
  93         {
  94             gsize loop2;
  95
  96             loop2 = loop + 1;
  97
  98             while (loop2 < str_len)
  99             {
 100                 if (str[loop2] == '"')
 101                     break;
 102                 if (str[loop2] == '\\' && loop2 + 1 < str_len)
 103                     loop2++;
 104                 g_string_append_c (buff, str[loop2]);
 105                 loop2++;
 106             }
 107
 108             if (str[loop2] == '\0')
 109                 error = MC_SEARCH_HEX_E_UNMATCHED_QUOTES;
 110             else
 111                 loop = loop2 + 1;
 112         }
 113         else
 114             error = MC_SEARCH_HEX_E_INVALID_CHARACTER;
 115     }
 116
 117     if (error != MC_SEARCH_HEX_E_OK)
 118     {
 119         g_string_free (buff, TRUE);
 120         if (error_ptr != NULL)
 121             *error_ptr = error;
 122         if (error_pos_ptr != NULL)
 123             *error_pos_ptr = loop;
 124         return NULL;
 125     }
 126
 127     return buff;
 128 }
 129
 130 /*** public functions ****************************************************************************/
 131
 132 void
 133 mc_search__cond_struct_new_init_hex (const char *charset, mc_search_t * lc_mc_search,
 134                                      mc_search_cond_t * mc_search_cond)
 135 {
 136     GString *tmp;
 137     mc_search_hex_parse_error_t error = MC_SEARCH_HEX_E_OK;
 138     int error_pos = 0;
 139
 140     /*
 141      * We may be searching in binary data, which is often invalid UTF-8.
 142      *
 143      * We have to create a non UTF-8 regex (that is, G_REGEX_RAW) or else, as
 144      * the data is invalid UTF-8, both GLib's PCRE and our
 145      * mc_search__g_regex_match_full_safe() are going to fail us. The former by
 146      * not finding all bytes, the latter by overwriting the supposedly invalid
 147      * UTF-8 with NULs.
 148      *
 149      * To do this, we specify "ASCII" as the charset.
 150      *
 151      * In fact, we can specify any charset other than "UTF-8": any such charset
 152      * will trigger G_REGEX_RAW (see [1]). The output of [2] will be the same
 153      * for all charsets because it skips the \xXX symbols
 154      * mc_search__hex_translate_to_regex() outputs.
 155      *
 156      * But "ASCII" is the best choice because a hex pattern may contain a
 157      * quoted string: this way we know [2] will ignore any characters outside
 158      * ASCII letters range (these ignored chars will be copied verbatim to the
 159      * output and will match as-is; in other words, in a case-sensitive manner;
 160      * If the user is interested in case-insensitive searches of international
 161      * text, he shouldn't be using hex search in the first place.)
 162      *
 163      * Switching out of UTF-8 has another advantage:
 164      *
 165      * When doing case-insensitive searches, GLib treats \xXX symbols as normal
 166      * letters and therefore matches both "a" and "A" for the hex pattern
 167      * "0x61". When we switch out of UTF-8, we're switching to using [2], which
 168      * doesn't have this issue.
 169      *
 170      * [1] mc_search__cond_struct_new_init_regex
 171      * [2] mc_search__cond_struct_new_regex_ci_str
 172      */
 173     if (str_isutf8 (charset))
 174         charset = "ASCII";
 175
 176     tmp = mc_search__hex_translate_to_regex (mc_search_cond->str, &error, &error_pos);
 177     if (tmp != NULL)
 178     {
 179         g_string_free (mc_search_cond->str, TRUE);
 180         mc_search_cond->str = tmp;
 181         mc_search__cond_struct_new_init_regex (charset, lc_mc_search, mc_search_cond);
 182     }
 183     else
 184     {
 185         const char *desc;
 186
 187         switch (error)
 188         {
 189         case MC_SEARCH_HEX_E_NUM_OUT_OF_RANGE:
 190             desc =
 191                 _
 192                 ("Number out of range (should be in byte range, 0 <= n <= 0xFF, expressed in hex)");
 193             break;
 194         case MC_SEARCH_HEX_E_INVALID_CHARACTER:
 195             desc = _("Invalid character");
 196             break;
 197         case MC_SEARCH_HEX_E_UNMATCHED_QUOTES:
 198             desc = _("Unmatched quotes character");
 199             break;
 200         default:
 201             desc = "";
 202         }
 203
 204         lc_mc_search->error = MC_SEARCH_E_INPUT;
 205         lc_mc_search->error_str =
 206             g_strdup_printf (_("Hex pattern error at position %d:\n%s."), error_pos + 1, desc);
 207     }
 208 }
 209
 210 /* --------------------------------------------------------------------------------------------- */
 211
 212 gboolean
 213 mc_search__run_hex (mc_search_t * lc_mc_search, const void *user_data,
 214                     gsize start_search, gsize end_search, gsize * found_len)
 215 {
 216     return mc_search__run_regex (lc_mc_search, user_data, start_search, end_search, found_len);
 217 }
 218
 219 /* --------------------------------------------------------------------------------------------- */
 220
 221 GString *
 222 mc_search_hex_prepare_replace_str (mc_search_t * lc_mc_search, GString * replace_str)
 223 {
 224     (void) lc_mc_search;
 225     return g_string_new_len (replace_str->str, replace_str->len);
 226 }
 227
 228 /* --------------------------------------------------------------------------------------------- */