3 HEX-style pattern matching
5 Copyright (C) 2009-2017
6 Free Software Foundation, Inc.
9 Slava Zanko <slavazanko@gmail.com>, 2009.
11 This file is part of the Midnight Commander.
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.
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.
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/>.
31 #include "lib/global.h"
32 #include "lib/strutil.h"
33 #include "lib/search.h"
34 #include "lib/strescape.h"
38 /*** global variables ****************************************************************************/
40 /*** file scope macro definitions ****************************************************************/
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
;
50 /*** file scope type declarations ****************************************************************/
52 /*** file scope variables ************************************************************************/
54 /*** file scope functions ************************************************************************/
57 mc_search__hex_translate_to_regex (const GString
* astr
, mc_search_hex_parse_error_t
* error_ptr
,
64 mc_search_hex_parse_error_t error
= MC_SEARCH_HEX_E_OK
;
66 buff
= g_string_sized_new (64);
70 while (loop
< str_len
&& error
== MC_SEARCH_HEX_E_OK
)
75 if (g_ascii_isspace (str
[loop
]))
77 /* Eat-up whitespace between tokens. */
78 while (g_ascii_isspace (str
[loop
]))
81 /* cppcheck-suppress invalidscanf */
82 else if (sscanf (str
+ loop
, "%x%n", &val
, &ptr
) == 1)
85 error
= MC_SEARCH_HEX_E_NUM_OUT_OF_RANGE
;
88 g_string_append_printf (buff
, "\\x%02X", val
);
92 else if (str
[loop
] == '"')
98 while (loop2
< str_len
)
100 if (str
[loop2
] == '"')
102 if (str
[loop2
] == '\\' && loop2
+ 1 < str_len
)
104 g_string_append_c (buff
, str
[loop2
]);
108 if (str
[loop2
] == '\0')
109 error
= MC_SEARCH_HEX_E_UNMATCHED_QUOTES
;
114 error
= MC_SEARCH_HEX_E_INVALID_CHARACTER
;
117 if (error
!= MC_SEARCH_HEX_E_OK
)
119 g_string_free (buff
, TRUE
);
120 if (error_ptr
!= NULL
)
122 if (error_pos_ptr
!= NULL
)
123 *error_pos_ptr
= loop
;
130 /*** public functions ****************************************************************************/
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
)
137 mc_search_hex_parse_error_t error
= MC_SEARCH_HEX_E_OK
;
141 * We may be searching in binary data, which is often invalid UTF-8.
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
149 * To do this, we specify "ASCII" as the charset.
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.
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.)
163 * Switching out of UTF-8 has another advantage:
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.
170 * [1] mc_search__cond_struct_new_init_regex
171 * [2] mc_search__cond_struct_new_regex_ci_str
173 if (str_isutf8 (charset
))
176 tmp
= mc_search__hex_translate_to_regex (mc_search_cond
->str
, &error
, &error_pos
);
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
);
189 case MC_SEARCH_HEX_E_NUM_OUT_OF_RANGE
:
192 ("Number out of range (should be in byte range, 0 <= n <= 0xFF, expressed in hex)");
194 case MC_SEARCH_HEX_E_INVALID_CHARACTER
:
195 desc
= _("Invalid character");
197 case MC_SEARCH_HEX_E_UNMATCHED_QUOTES
:
198 desc
= _("Unmatched quotes character");
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
);
210 /* --------------------------------------------------------------------------------------------- */
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
)
216 return mc_search__run_regex (lc_mc_search
, user_data
, start_search
, end_search
, found_len
);
219 /* --------------------------------------------------------------------------------------------- */
222 mc_search_hex_prepare_replace_str (mc_search_t
* lc_mc_search
, GString
* replace_str
)
225 return g_string_new_len (replace_str
->str
, replace_str
->len
);
228 /* --------------------------------------------------------------------------------------------- */