Fix for the bug #24037 "Lossy Hebrew to Unicode conversion".

Added definitions for the following Hebrew characters as specified by the ISO/IEC 8859-8:1999:

LEFT-TO-RIGHT MARK (LRM)
RIGHT-TO-LEFT MARK (RLM)


sql/share/charsets/hebrew.xml:
  Added definitions for the following Hebrew characters as specified by the ISO/IEC 8859-8:1999:
  
  LEFT-TO-RIGHT MARK (LRM)
  RIGHT-TO-LEFT MARK (RLM)
strings/conf_to_src.c:
  Added a warning comment in the generated C source file.
strings/ctype-extra.c:
  Re-generated from sql/share/charsets/hebrew.xml
mysql-test/r/ctype_hebrew.result:
  Added the test case for bug #24037 "Lossy Hebrew to Unicode conversion"
mysql-test/t/ctype_hebrew.test:
  Added the test case for bug #24037 "Lossy Hebrew to Unicode conversion"

5 files changed, 49 insertions, 7 deletions

diff --git a/mysql-test/r/ctype_hebrew.result b/mysql-test/r/ctype_hebrew.result
new file mode 100644
index 00000000000..d938b2e47f3
--- /dev/null
+++ b/mysql-test/r/ctype_hebrew.result
@@ -0,0 +1,11 @@
+DROP TABLE IF EXISTS t1;
+SET NAMES hebrew;
+CREATE TABLE t1 (a char(1)) DEFAULT CHARSET=hebrew;
+INSERT INTO t1 VALUES (0xFD),(0xFE);
+ALTER TABLE t1 CONVERT TO CHARACTER SET utf8;
+SELECT HEX(a) FROM t1;
+HEX(a)
+E2808E
+E2808F
+DROP TABLE t1;
+End of 4.1 tests
diff --git a/mysql-test/t/ctype_hebrew.test b/mysql-test/t/ctype_hebrew.test
new file mode 100644
index 00000000000..f786d05141d
--- /dev/null
+++ b/mysql-test/t/ctype_hebrew.test
@@ -0,0 +1,16 @@
+#
+# BUG #24037: Lossy Hebrew to Unicode conversion
+#
+# Test if LRM and RLM characters are correctly converted to UTF-8
+--disable_warnings
+DROP TABLE IF EXISTS t1;
+--enable_warnings
+
+SET NAMES hebrew;
+CREATE TABLE t1 (a char(1)) DEFAULT CHARSET=hebrew;
+INSERT INTO t1 VALUES (0xFD),(0xFE);
+ALTER TABLE t1 CONVERT TO CHARACTER SET utf8;
+SELECT HEX(a) FROM t1;
+DROP TABLE t1;
+
+--echo End of 4.1 tests
diff --git a/sql/share/charsets/hebrew.xml b/sql/share/charsets/hebrew.xml
index 5bcf222a728..981f308bfb5 100644
--- a/sql/share/charsets/hebrew.xml
+++ b/sql/share/charsets/hebrew.xml
@@ -40,7 +40,7 @@
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  02 02 02 02 02 02 02 02 02 02 02 02 02 02 02 02
- 02 02 02 02 02 02 02 02 02 02 02 00 00 00 00 00
+ 02 02 02 02 02 02 02 02 02 02 02 00 00 20 20 00
  </map>
 </ctype>
 
@@ -106,7 +106,7 @@
 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000
 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 2017
 05D0 05D1 05D2 05D3 05D4 05D5 05D6 05D7 05D8 05D9 05DA 05DB 05DC 05DD 05DE 05DF
-05E0 05E1 05E2 05E3 05E4 05E5 05E6 05E7 05E8 05E9 05EA 0000 0000 0000 0000 0000
+05E0 05E1 05E2 05E3 05E4 05E5 05E6 05E7 05E8 05E9 05EA 0000 0000 200E 200F 0000
 </map>
 </unicode>
 
diff --git a/strings/conf_to_src.c b/strings/conf_to_src.c
index 505bf154bec..b0b943df02a 100644
--- a/strings/conf_to_src.c
+++ b/strings/conf_to_src.c
@@ -270,7 +270,14 @@ main(int argc, char **argv  __attribute__((unused)))
     }
   }
   
-  
+  fprintf(f, "/*\n");
+  fprintf(f, "  This file was generated by the conf_to_src utility. "
+          "Do not edit it directly,\n");
+  fprintf(f, "  edit the XML definitions in sql/share/charsets/ instead.\n\n");
+  fprintf(f, "  To re-generate, run the following in the strings/ "
+          "directory:\n");
+  fprintf(f, "    ./conf_to_src ../sql/share/charsets/ > FILE\n");
+  fprintf(f, "*/\n\n");
   fprintf(f,"#include <my_global.h>\n");
   fprintf(f,"#include <m_ctype.h>\n\n");
   
diff --git a/strings/ctype-extra.c b/strings/ctype-extra.c
index b680b69028c..63d33086a2e 100644
--- a/strings/ctype-extra.c
+++ b/strings/ctype-extra.c
@@ -1,3 +1,11 @@
+/*
+  This file was generated by the conf_to_src utility. Do not edit it directly,
+  edit the XML definitions in sql/share/charsets/ instead.
+
+  To re-generate, run the following in the strings/ directory:
+    ./conf_to_src ../sql/share/charsets/ > FILE
+*/
+
 #include <my_global.h>
 #include <m_ctype.h>
 
@@ -1169,7 +1177,7 @@ uchar ctype_hebrew_general_ci[] = {
 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,
-0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x00,0x00,0x00,0x00,0x00
+0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x00,0x00,0x20,0x20,0x00
 };
 
 uchar to_lower_hebrew_general_ci[] = {
@@ -1261,7 +1269,7 @@ uint16 to_uni_hebrew_general_ci[] = {
 0x05D0,0x05D1,0x05D2,0x05D3,0x05D4,0x05D5,0x05D6,0x05D7,
 0x05D8,0x05D9,0x05DA,0x05DB,0x05DC,0x05DD,0x05DE,0x05DF,
 0x05E0,0x05E1,0x05E2,0x05E3,0x05E4,0x05E5,0x05E6,0x05E7,
-0x05E8,0x05E9,0x05EA,0x0000,0x0000,0x0000,0x0000,0x0000
+0x05E8,0x05E9,0x05EA,0x0000,0x0000,0x200E,0x200F,0x0000
 };
 
 #endif
@@ -5100,7 +5108,7 @@ uchar ctype_hebrew_bin[] = {
 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,
-0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x00,0x00,0x00,0x00,0x00
+0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x00,0x00,0x20,0x20,0x00
 };
 
 uchar to_lower_hebrew_bin[] = {
@@ -5173,7 +5181,7 @@ uint16 to_uni_hebrew_bin[] = {
 0x05D0,0x05D1,0x05D2,0x05D3,0x05D4,0x05D5,0x05D6,0x05D7,
 0x05D8,0x05D9,0x05DA,0x05DB,0x05DC,0x05DD,0x05DE,0x05DF,
 0x05E0,0x05E1,0x05E2,0x05E3,0x05E4,0x05E5,0x05E6,0x05E7,
-0x05E8,0x05E9,0x05EA,0x0000,0x0000,0x0000,0x0000,0x0000
+0x05E8,0x05E9,0x05EA,0x0000,0x0000,0x200E,0x200F,0x0000
 };
 
 #endif