From 4851890ede31313655e19180f4959ed348fee580 Mon Sep 17 00:00:00 2001 From: Zoltan Herczeg Date: Thu, 14 Jul 2022 05:25:39 +0200 Subject: [PATCH] Fixed an issue in the backtracking optimization of character repeats in JIT (#135) --- ChangeLog | 3 +++ src/pcre2_jit_compile.c | 20 ++++++++++---------- src/pcre2_jit_test.c | 1 + 3 files changed, 14 insertions(+), 10 deletions(-) diff --git a/ChangeLog b/ChangeLog index 5c980f9..65718ae 100644 --- a/ChangeLog +++ b/ChangeLog @@ -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 --------------------------- diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c index e638c24..b3cffbe 100644 --- a/src/pcre2_jit_compile.c +++ b/src/pcre2_jit_compile.c @@ -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) diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c index bb141a0..81c9582 100644 --- a/src/pcre2_jit_test.c +++ b/src/pcre2_jit_test.c @@ -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\\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" },