From 5002a59a8289027b8a88c4933077a9b66e839d6c Mon Sep 17 00:00:00 2001
From: zherczeg <zherczeg@6239d852-aaf2-0410-a92c-79f79f948069>
Date: Sat, 19 Sep 2020 03:49:32 +0000
Subject: Fixed a bug in character set matching when JIT is enabled.

git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@1273 6239d852-aaf2-0410-a92c-79f79f948069
---
 ChangeLog               |  3 +++
 src/pcre2_jit_compile.c | 36 ++++++++++++++++++++++++++++--------
 src/pcre2_jit_test.c    |  1 +
 3 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 847476c..db0b9bc 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -73,6 +73,9 @@ first valid fragment of the subject, possibly causing incorrect "no match"
 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
 ---------------------------
diff --git a/src/pcre2_jit_compile.c b/src/pcre2_jit_compile.c
index edf64d5..04f0278 100644
--- a/src/pcre2_jit_compile.c
+++ b/src/pcre2_jit_compile.c
@@ -7672,25 +7672,43 @@ if (needstype || needsscript)
       }
 
     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);
+
+        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);
 
-  if (needstype)
+        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));
       }
     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 @@ if (needstype || needsscript)
       typereg = RETURN_ADDR;
       }
     }
+  else if (needschar)
+    OP1(SLJIT_MOV, TMP1, 0, RETURN_ADDR, 0);
   }
 #endif /* SUPPORT_UNICODE */
 
diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c
index b7856ad..d935887 100644
--- a/src/pcre2_jit_test.c
+++ b/src/pcre2_jit_test.c
@@ -409,6 +409,7 @@ static struct regression_test_case regression_test_cases[] = {
 	{ 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" },
-- 
cgit v1.2.1