From 1bcd2bebc69163c541baa548f1204ccd1b830d25 Mon Sep 17 00:00:00 2001
From: Alexander Barkov <bar@mnogosearch.org>
Date: Tue, 8 Oct 2013 18:25:17 +0400
Subject: [PATCH] MDEV-4425 Regexp enhancements Do not pass PCRE_UCP flag for
 binary data. This makes bytes 0x80..FF not to belong to generic character
 classes \d (digit) and \w (word character).

SELECT 0xFF RLIKE '\\w';
 -> 0

Note, this change does not affect non-binary data,
which is still examined with the PCRE_UCP flag by default.
---
 mysql-test/r/func_regexp_pcre.result | 6 ++++++
 mysql-test/t/func_regexp_pcre.test   | 4 ++++
 sql/item_cmpfunc.h                   | 5 +++--
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/mysql-test/r/func_regexp_pcre.result b/mysql-test/r/func_regexp_pcre.result
index 4ae66e24eda..ebbdedc6999 100644
--- a/mysql-test/r/func_regexp_pcre.result
+++ b/mysql-test/r/func_regexp_pcre.result
@@ -234,6 +234,12 @@ class	ch	ch RLIKE class
 \p{Tamil}	㐗	0
 \p{Tamil}	갷	0
 DROP TABLE t1, t2;
+SELECT 0xFF RLIKE '\\w';
+0xFF RLIKE '\\w'
+0
+SELECT 0xFF RLIKE '(*UCP)\\w';
+0xFF RLIKE '(*UCP)\\w'
+1
 SELECT '\n' RLIKE '(*CR)';
 '\n' RLIKE '(*CR)'
 1
diff --git a/mysql-test/t/func_regexp_pcre.test b/mysql-test/t/func_regexp_pcre.test
index 7a4be163001..4892d9931da 100644
--- a/mysql-test/t/func_regexp_pcre.test
+++ b/mysql-test/t/func_regexp_pcre.test
@@ -46,6 +46,10 @@ INSERT INTO t2 VALUES ('[[:alpha:]]'),('[[:digit:]]');
 SELECT class, ch, ch RLIKE class FROM t1, t2 ORDER BY class, BINARY ch;
 DROP TABLE t1, t2;
 
+# Checking that UCP is disabled by default for binary data
+SELECT 0xFF RLIKE '\\w';
+SELECT 0xFF RLIKE '(*UCP)\\w';
+
 # newline character
 SELECT '\n' RLIKE '(*CR)';
 SELECT '\n' RLIKE '(*LF)';
diff --git a/sql/item_cmpfunc.h b/sql/item_cmpfunc.h
index e8574a573e7..2d89b8d65db 100644
--- a/sql/item_cmpfunc.h
+++ b/sql/item_cmpfunc.h
@@ -1511,8 +1511,9 @@ public:
   {}
   void init(CHARSET_INFO *data_charset, int extra_flags, uint nsubpatterns)
   {
-    m_library_flags= PCRE_UCP | extra_flags |
-                    (data_charset != &my_charset_bin ? PCRE_UTF8 : 0) |
+    m_library_flags= extra_flags |
+                    (data_charset != &my_charset_bin ?
+                     (PCRE_UTF8 | PCRE_UCP) : 0) |
                     ((data_charset->state &
                      (MY_CS_BINSORT | MY_CS_CSSORT)) ? 0 : PCRE_CASELESS);