Revision: 1273
http://www.exim.org/viewvc/pcre2?view=rev&revision=1273
Author: zherczeg
Date: 2020-09-19 04:49:32 +0100 (Sat, 19 Sep 2020)
Log Message:
-----------
Fixed a bug in character set matching when JIT is enabled.
Modified Paths:
--------------
code/trunk/ChangeLog
code/trunk/src/pcre2_jit_compile.c
code/trunk/src/pcre2_jit_test.c
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2020-09-15 14:36:23 UTC (rev 1272)
+++ code/trunk/ChangeLog 2020-09-19 03:49:32 UTC (rev 1273)
@@ -73,7 +73,10 @@
returns on subsequent fragments. For example, the pattern /A/ failed to match
the subject \xe5A. Fixes Bugzilla #2642.
+14. Fixed a bug in character set matching when JIT is enabled and both unicode
+scripts and unicode classes are present at the same time.
+
Version 10.35 09-May-2020
---------------------------
Modified: code/trunk/src/pcre2_jit_compile.c
===================================================================
--- code/trunk/src/pcre2_jit_compile.c 2020-09-15 14:36:23 UTC (rev 1272)
+++ code/trunk/src/pcre2_jit_compile.c 2020-09-19 03:49:32 UTC (rev 1273)
@@ -7672,17 +7672,37 @@
}
cc = ccbegin;
- }
- if (needschar)
- OP1(SLJIT_MOV, TMP1, 0, RETURN_ADDR, 0);
+ if (needstype)
+ {
+ /* TMP2 has already been shifted by 2 */
+ if (!needschar)
+ {
+ OP2(SLJIT_ADD, TMP1, 0, TMP2, 0, TMP2, 0);
+ OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, TMP2, 0);
- if (needstype)
+ OP1(SLJIT_MOV_U8, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, chartype));
+ }
+ else
+ {
+ OP2(SLJIT_ADD, TMP1, 0, TMP2, 0, TMP2, 0);
+ OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, TMP1, 0);
+
+ OP1(SLJIT_MOV, TMP1, 0, RETURN_ADDR, 0);
+ OP1(SLJIT_MOV_U8, RETURN_ADDR, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, chartype));
+ typereg = RETURN_ADDR;
+ }
+ }
+ else if (needschar)
+ OP1(SLJIT_MOV, TMP1, 0, RETURN_ADDR, 0);
+ }
+ else if (needstype)
{
+ OP2(SLJIT_SHL, TMP1, 0, TMP2, 0, SLJIT_IMM, 3);
+ OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 2);
+
if (!needschar)
{
- OP2(SLJIT_SHL, TMP1, 0, TMP2, 0, SLJIT_IMM, 3);
- OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 2);
OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, TMP2, 0);
OP1(SLJIT_MOV_U8, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, chartype));
@@ -7689,8 +7709,6 @@
}
else
{
- OP2(SLJIT_SHL, TMP1, 0, TMP2, 0, SLJIT_IMM, 2);
- OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 3);
OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, TMP1, 0);
OP1(SLJIT_MOV, TMP1, 0, RETURN_ADDR, 0);
@@ -7698,6 +7716,8 @@
typereg = RETURN_ADDR;
}
}
+ else if (needschar)
+ OP1(SLJIT_MOV, TMP1, 0, RETURN_ADDR, 0);
}
#endif /* SUPPORT_UNICODE */
Modified: code/trunk/src/pcre2_jit_test.c
===================================================================
--- code/trunk/src/pcre2_jit_test.c 2020-09-15 14:36:23 UTC (rev 1272)
+++ code/trunk/src/pcre2_jit_test.c 2020-09-19 03:49:32 UTC (rev 1273)
@@ -409,6 +409,7 @@
{ MUP, A, 0, 0 | F_PROPERTY, "[\xc3\xa2-\xc3\xa6\xc3\x81-\xc3\x84\xe2\x80\xa8-\xe2\x80\xa9\xe6\x92\xad\\p{Zs}]{2,}", "\xe2\x80\xa7\xe2\x80\xa9\xe6\x92\xad \xe6\x92\xae" },
{ 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}]", " " },
/* Possible empty brackets. */
{ MU, A, 0, 0, "(?:|ab||bc|a)+d", "abcxabcabd" },
