d79ff51157
* Clarify docs of raw_alignment * Set Go and Rust string encoding for binary string search. * Add detailed doxygen about string search in bin plugins. * Add the number string code points as detail to string search hits. * Add helper to check if string encoding needs scanning. * Add helper to generate a string wildcard pattern. The pattern is supposed to match any human readable string. Before the string search refactor there was no explicit definition what characters mark the end of a string and which ones don't. This pattern should match strings of the old interpretation. * Enable the RzBin plugin to search strings with direct matching instead of scanning. This significantly speeds up the string search when a binary is opened. The prerequisite is that the plugin specifies the string encoding. * Enforce UTF-8 for initial string search. * Add custom string search for PE files. * Clean up and document rz_utf8_encode * Don't demote explicit UTF-8 encoding to ASCII. * Increase min JIT stack size due to not reproducable search results. * Simplify wildcard regex pattern.
46 lines
1.2 KiB
C
46 lines
1.2 KiB
C
// SPDX-FileCopyrightText: 2023 RizinOrg <info@rizin.re>
|
|
// SPDX-FileCopyrightText: 2023 deroad <wargio@libero.it>
|
|
// SPDX-License-Identifier: LGPL-3.0-only
|
|
#include <rz_bin.h>
|
|
#include "i/private.h"
|
|
|
|
RZ_IPI void rz_bin_set_and_process_strings(RzBinFile *bf, RzBinObject *o) {
|
|
RzBin *bin = bf->rbin;
|
|
|
|
rz_bin_string_database_free(o->strings);
|
|
if (!(bin->filter_rules & RZ_BIN_REQ_STRINGS)) {
|
|
o->strings = rz_bin_string_database_new(NULL);
|
|
return;
|
|
}
|
|
|
|
RzPVector *strings = NULL;
|
|
RzBinPlugin *plugin = o->plugin;
|
|
|
|
/**
|
|
* We call rz_bin_file_strings only if the seach mode is not `auto`
|
|
* or if the plugin fails to generate the string vector.
|
|
*/
|
|
if (bin->str_search_cfg.mode != RZ_BIN_STRING_SEARCH_MODE_AUTO ||
|
|
!plugin->strings ||
|
|
!(strings = plugin->strings(bf))) {
|
|
switch (bf->o->lang) {
|
|
default:
|
|
break;
|
|
case RZ_BIN_LANGUAGE_GO:
|
|
case RZ_BIN_LANGUAGE_RUST:
|
|
bin->str_search_cfg.string_encoding = RZ_STRING_ENC_UTF8;
|
|
break;
|
|
}
|
|
strings = rz_bin_file_strings(bf, &bin->str_search_cfg);
|
|
}
|
|
|
|
void **it;
|
|
RzBinString *string;
|
|
rz_pvector_foreach (strings, it) {
|
|
string = *it;
|
|
// rebase physical address
|
|
string->paddr += o->opts.loadaddr;
|
|
}
|
|
|
|
o->strings = rz_bin_string_database_new(strings);
|
|
}
|