From 50a51cb7e67268e6ad417eb07c9de9bfea5cc55a Mon Sep 17 00:00:00 2001 From: Zoltan Herczeg Date: Wed, 23 Mar 2022 07:53:25 +0000 Subject: [PATCH] Fixed a unicode properrty matching issue in JIT --- ChangeLog | 3 +++ src/pcre2_jit_compile.c | 2 +- src/pcre2_jit_test.c | 1 + 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/ChangeLog b/ChangeLog index d27542d..cd3da65 100644 --- a/ChangeLog +++ b/ChangeLog @@ -63,6 +63,9 @@ Version 10.39 29-October-2021 Reformat slightly to make it C89 compatible again. +23. Fixed a unicode properrty matching issue in JIT. The character was not +fully read in caseless matching. + Version 10.38 01-October-2021 ----------------------------- diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c index db2ce65..5baca9b 100644 --- a/src/pcre2_jit_compile.c +++ b/src/pcre2_jit_compile.c @@ -7473,7 +7473,7 @@ while (*cc != XCL_END) { SLJIT_ASSERT(*cc == XCL_PROP || *cc == XCL_NOTPROP); cc++; - if (*cc == PT_CLIST) + if (*cc == PT_CLIST && *cc == XCL_PROP) { other_cases = PRIV(ucd_caseless_sets) + cc[1]; while (*other_cases != NOTACHAR) diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c index 8dee16e..bf94c6d 100644 --- a/src/pcre2_jit_test.c +++ b/src/pcre2_jit_test.c @@ -412,6 +412,7 @@ static struct regression_test_case regression_test_cases[] = { { MUP, A, 0, 0 | F_PROPERTY, "[\\P{L&}]{2}[^\xc2\x85-\xc2\x89\\p{Ll}\\p{Lu}]{2}", "\xc3\xa9\xe6\x92\xad.a\xe6\x92\xad|\xc2\x8a#" }, { PCRE2_UCP, 0, 0, 0 | F_PROPERTY, "[a-b\\s]{2,5}[^a]", "AB baaa" }, { MUP, 0, 0, 0 | F_NOMATCH, "[^\\p{Hangul}\\p{Z}]", " " }, + { CMUP, 0, 0, 0, "[^S]\\B", "\xe2\x80\x8a" }, /* Possible empty brackets. */ { MU, A, 0, 0, "(?:|ab||bc|a)+d", "abcxabcabd" }, -- 2.27.0