Fixed an issue in the backtracking optimization of character repeats in JIT (#135)

This commit is contained in:
Zoltan Herczeg 2022-07-14 05:25:39 +02:00 committed by GitHub
parent 3e52db5209
commit 4851890ede
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 14 additions and 10 deletions

View File

@ -29,6 +29,9 @@ supported (even though that function would do nothing in that case) at the
request of a user who doesn't even want to link with pcre_jit_compile.o. Also
tidied up an untidy #ifdef arrangement in pcre2test.
8. Fixed an issue in the backtracking optimization of character repeats in
JIT. Furthermore optimize star repetitions, not just plus repetitions.
Version 10.40 15-April-2022
---------------------------

View File

@ -11517,19 +11517,19 @@ if (exact > 1)
}
}
else if (exact == 1)
{
compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks, TRUE);
if (early_fail_type == type_fail_range)
{
OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), early_fail_ptr);
OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), early_fail_ptr + (int)sizeof(sljit_sw));
OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, TMP2, 0);
OP2(SLJIT_SUB, TMP2, 0, STR_PTR, 0, TMP2, 0);
add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_LESS_EQUAL, TMP2, 0, TMP1, 0));
if (early_fail_type == type_fail_range)
{
/* Range end first, followed by range start. */
OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), early_fail_ptr);
OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), early_fail_ptr + (int)sizeof(sljit_sw));
OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, TMP2, 0);
OP2(SLJIT_SUB, TMP2, 0, STR_PTR, 0, TMP2, 0);
add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_LESS_EQUAL, TMP2, 0, TMP1, 0));
OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), early_fail_ptr + (int)sizeof(sljit_sw), STR_PTR, 0);
}
OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), early_fail_ptr, STR_PTR, 0);
OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), early_fail_ptr + (int)sizeof(sljit_sw), STR_PTR, 0);
}
switch(opcode)

View File

@ -354,6 +354,7 @@ static struct regression_test_case regression_test_cases[] = {
{ MU, A, 0, 0, "_[ab]+_*a", "_aa" },
{ MU, A, 0, 0, "#(A+)#\\d+", "#A#A#0" },
{ MU, A, 0, 0, "(?P<size>\\d+)m|M", "4M" },
{ M, PCRE2_NEWLINE_CRLF, 0, 0, "\\n?.+#", "\n,\n,#" },
/* Bracket repeats with limit. */
{ MU, A, 0, 0, "(?:(ab){2}){5}M", "abababababababababababM" },