Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
When Onigmo try to parse a regular expression "[{\x{111111}x", it causes out of bounds read in parse_char_class().
Here is a POC code based on sample/syntax.c
/* * perl_syntax2.c */ #include <stdio.h> #include <string.h> #include "onigmo.h" extern int exec(const OnigSyntaxType* syntax, char* apattern, char* astr) { int r; unsigned char *start, *range, *end; regex_t* reg; OnigErrorInfo einfo; OnigRegion *region; UChar* pattern = (UChar* )apattern; UChar* str = (UChar* )astr; fprintf(stderr, "pattern %s (%lu)\n", pattern, strlen((char*)pattern)); r = onig_new(®, pattern, pattern + strlen((char* )pattern), ONIG_OPTION_DEFAULT, ONIG_ENCODING_ASCII, syntax, &einfo); if (r != ONIG_NORMAL) { OnigUChar s[ONIG_MAX_ERROR_MESSAGE_LEN]; onig_error_code_to_str(s, r, &einfo); fprintf(stderr, "ERROR: %s\n", s); return -1; } region = onig_region_new(); end = str + strlen((char* )str); start = str; range = end; r = onig_search(reg, str, end, start, range, region, ONIG_OPTION_NONE); if (r >= 0) { int i; fprintf(stderr, "match at %d\n", r); for (i = 0; i < region->num_regs; i++) { fprintf(stderr, "%d: (%ld-%ld)\n", i, region->beg[i], region->end[i]); } r = 0; } else if (r == ONIG_MISMATCH) { fprintf(stderr, "search fail\n"); r = -1; } else { /* error */ OnigUChar s[ONIG_MAX_ERROR_MESSAGE_LEN]; onig_error_code_to_str(s, r); fprintf(stderr, "ERROR: %s\n", s); return -1; } onig_region_free(region, 1 /* 1:free self, 0:free contents only */); onig_free(reg); onig_end(); return r; } extern int main(int argc, char* argv[]) { int r = 0; char regex[] = "[{\\x{111111}x"; r |= exec(ONIG_SYNTAX_PERL, regex, "bgh8x"); onig_end(); return r; }
gcc -o perl_syntax2 perl_syntax2.c -lonigmo ./perl_syntax2 pattern [{\x{111111}x (13) Segmentation fault (core dumped)
Here is a crash log.
$ gdb -q ./perl_syntax2 -c core Core was generated by `./perl_syntax2'. Program terminated with signal SIGSEGV, Segmentation fault. #0 0x00007f324371343d in next_state_val (cc=cc@entry=0x56418051b460, asc_cc=asc_cc@entry=0x0, from=from@entry=0x7ffc2b22a988, to=120, from_israw=from_israw@entry=0x7ffc2b22a994, to_israw=to_israw@entry=0, intype=CCV_SB, type=0x7ffc2b22a990, state=0x7ffc2b22a98c, env=0x7ffc2b22ad60) at regparse.c:4461 4461 BITSET_SET_BIT_CHKDUP(cc->bs, (int )(*from)); (gdb) bt #0 0x00007f324371343d in next_state_val (cc=cc@entry=0x56418051b460, asc_cc=asc_cc@entry=0x0, from=from@entry=0x7ffc2b22a988, to=120, from_israw=from_israw@entry=0x7ffc2b22a994, to_israw=to_israw@entry=0, intype=CCV_SB, type=0x7ffc2b22a990, state=0x7ffc2b22a98c, env=0x7ffc2b22ad60) at regparse.c:4461 #1 0x00007f32437174e9 in parse_char_class (np=0x7ffc2b22abc0, asc_np=asc_np@entry=0x7ffc2b22aac8, tok=tok@entry=0x7ffc2b22ac80, src=src@entry=0x7ffc2b22ac78, end=0x7ffc2b22b1e7 "", env=0x7ffc2b22ad60) at regparse.c:4704 #2 0x00007f324371a862 in parse_exp (np=np@entry=0x7ffc2b22abc0, tok=tok@entry=0x7ffc2b22ac80, term=term@entry=0, src=src@entry=0x7ffc2b22ac78, end=end@entry=0x7ffc2b22b1e7 "", env=env@entry=0x7ffc2b22ad60) at regparse.c:6334 #3 0x00007f324371cb74 in parse_branch (top=top@entry=0x7ffc2b22ac20, tok=tok@entry=0x7ffc2b22ac80, term=term@entry=0, src=src@entry=0x7ffc2b22ac78, end=end@entry=0x7ffc2b22b1e7 "", env=env@entry=0x7ffc2b22ad60) at regparse.c:6503 #4 0x00007f324371cd14 in parse_subexp (top=top@entry=0x7ffc2b22ad18, tok=tok@entry=0x7ffc2b22ac80, term=term@entry=0, src=src@entry=0x7ffc2b22ac78, end=end@entry=0x7ffc2b22b1e7 "", env=env@entry=0x7ffc2b22ad60) at regparse.c:6549 #5 0x00007f324371cf71 in parse_regexp (env=0x7ffc2b22ad60, end=0x7ffc2b22b1e7 "", src=0x7ffc2b22ac78, top=0x7ffc2b22ad18) at regparse.c:6598 #6 onig_parse_make_tree (root=root@entry=0x7ffc2b22ad18, pattern=pattern@entry=0x7ffc2b22b1da "[{\\x{111111}x", end=0x7ffc2b22b1e7 "", reg=reg@entry=0x56418051b260, env=env@entry=0x7ffc2b22ad60) at regparse.c:6643 #7 0x00007f32437240f8 in onig_compile (reg=0x56418051b260, pattern=pattern@entry=0x7ffc2b22b1da "[{\\x{111111}x", pattern_end=pattern_end@entry=0x7ffc2b22b1e7 "", einfo=einfo@entry=0x7ffc2b22b120) at regcomp.c:5659 #8 0x00007f3243724a3b in onig_new (reg=0x7ffc2b22b0e8, pattern=0x7ffc2b22b1da "[{\\x{111111}x", pattern_end=0x7ffc2b22b1e7 "", option=0, enc=0x56417f01cca0 <OnigEncodingASCII>, syntax=0x56417f01cd40 <OnigSyntaxPerl>, einfo=0x7ffc2b22b120) at regcomp.c:5887 #9 0x000056417ee1bbe1 in exec (syntax=0x56417f01cd40 <OnigSyntaxPerl>, apattern=0x7ffc2b22b1da "[{\\x{111111}x", astr=0x56417ee1bf9a "bgh8x") at ./perl_syntax2.c:20 #10 0x000056417ee1bea9 in main (argc=1, argv=0x7ffc2b22b2d8) at ./perl_syntax2.c:68
Thanks
The text was updated successfully, but these errors were encountered:
Fix out-of-bounds read in parse_char_class() (Close #139)
d4cf99d
/[\x{111111}]/ causes out-of-bounds read when encoding is a single byte encoding. \x{111111} is an invalid codepoint for a single byte encoding. Check if it is a valid codepoint.
Thank you for the report. I confirmed that this happens only when a single byte encoding is used. I added checks for invalid codepoints.
Sorry, something went wrong.
Successfully merging a pull request may close this issue.
When Onigmo try to parse a regular expression "[{\x{111111}x", it causes out of bounds read in parse_char_class().
Here is a POC code based on sample/syntax.c
Here is a crash log.
Thanks
The text was updated successfully, but these errors were encountered: