--with-charset was not up to date

ctype_ucs2 and ctype_ujis were skipped in mistake

acconfig.h

@@ -68,40 +68,37 @@
 
 /* Define charsets you want */
 #undef HAVE_CHARSET_armscii8
+#undef HAVE_CHARSET_ascii
 #undef HAVE_CHARSET_big5
+#undef HAVE_CHARSET_cp1250
 #undef HAVE_CHARSET_cp1251
+#undef HAVE_CHARSET_cp1256
 #undef HAVE_CHARSET_cp1257
-#undef HAVE_CHARSET_croat
+#undef HAVE_CHARSET_cp850
-#undef HAVE_CHARSET_czech
+#undef HAVE_CHARSET_cp852
-#undef HAVE_CHARSET_danish
+#undef HAVE_CHARSET_cp866
 #undef HAVE_CHARSET_dec8
-#undef HAVE_CHARSET_dos
+#undef HAVE_CHARSET_euckr
-#undef HAVE_CHARSET_estonia
-#undef HAVE_CHARSET_euc_kr
 #undef HAVE_CHARSET_gb2312
 #undef HAVE_CHARSET_gbk
-#undef HAVE_CHARSET_german1
 #undef HAVE_CHARSET_greek
 #undef HAVE_CHARSET_hebrew
 #undef HAVE_CHARSET_hp8
-#undef HAVE_CHARSET_hungarian
+#undef HAVE_CHARSET_keybcs2
-#undef HAVE_CHARSET_koi8_ru
+#undef HAVE_CHARSET_koi8r
-#undef HAVE_CHARSET_koi8_ukr
+#undef HAVE_CHARSET_koi8u
 #undef HAVE_CHARSET_latin1
-#undef HAVE_CHARSET_latin1_de
 #undef HAVE_CHARSET_latin2
 #undef HAVE_CHARSET_latin5
+#undef HAVE_CHARSET_latin7
+#undef HAVE_CHARSET_macce
+#undef HAVE_CHARSET_macroman
 #undef HAVE_CHARSET_sjis
 #undef HAVE_CHARSET_swe7
 #undef HAVE_CHARSET_tis620
 #undef HAVE_CHARSET_ucs2
 #undef HAVE_CHARSET_ujis
-#undef HAVE_CHARSET_usa7
 #undef HAVE_CHARSET_utf8
-#undef HAVE_CHARSET_win1250
-#undef HAVE_CHARSET_win1250ch
-#undef HAVE_CHARSET_win1251ukr
-#undef HAVE_CHARSET_win1251
 
 /* ZLIB and compress: */
 #undef HAVE_COMPRESS

configure.in

@@ -2226,28 +2226,35 @@ AC_SUBST(readline_h_ln_cmd)
 
 
 dnl In order to add new charset, you must add charset name to
-dnl this CHARSETS_AVAILABLE list and sql/share/charsets/Index.
+dnl this CHARSETS_AVAILABLE list and sql/share/charsets/Index.xml.
 dnl If the character set uses strcoll or other special handling,
 dnl you must also create strings/ctype-$charset_name.c
 
 AC_DIVERT_PUSH(0)
-CHARSETS_AVAILABLE="armscii8 big5 cp1251 cp1257
+
-                    croat czech danish dec8 dos estonia euc_kr gb2312 gbk
+define(CHARSETS_AVAILABLE1,ascii armscii8 ascii big5 cp1250 cp1251 cp1256 cp1257)
-                    german1 greek hebrew hp8 hungarian koi8_ru koi8_ukr
+define(CHARSETS_AVAILABLE2,cp850 cp852 cp866 dec8 euckr gb2312 gbk)
-                    latin1 latin1_de latin2 latin5 sjis swe7 tis620 ucs2 ujis
+define(CHARSETS_AVAILABLE3,greek hebrew hp8 keybcs2 koi8r koi8u)
-                    usa7 utf8 win1250 win1250ch win1251ukr"
+define(CHARSETS_AVAILABLE4,latin1 latin2 latin5 latin7 macce macroman)
-CHARSETS_DEPRECATED="win1251"
+define(CHARSETS_AVAILABLE5,sjis swe7 tis620 ucs2 ujis utf8)
-CHARSETS_COMPLEX="big5 czech euc_kr gb2312 gbk latin1_de sjis tis620 ucs2 ujis utf8 win1250ch"
+
 DEFAULT_CHARSET=latin1
+CHARSETS_AVAILABLE="CHARSETS_AVAILABLE1 CHARSETS_AVAILABLE2 CHARSETS_AVAILABLE3 CHARSETS_AVAILABLE4 CHARSETS_AVAILABLE5"
+CHARSETS_COMPLEX="big5 cp1250 euckr gb2312 gbk latin1 latin2 sjis tis620 ucs2 ujis utf8"
+
 AC_DIVERT_POP
 
-dnl fix this later..
-dnl  [  --with-charset=CHARSET  Use CHARSET by default (one of: $CHARSETS_AVAILABLE; Default is $DEFAULT_CHARSET)],
-
 AC_ARG_WITH(charset,
-  [  --with-charset=CHARSET  Use CHARSET by default (Default is latin1)],
+   [  --with-charset=CHARSET
-  [default_charset="$withval"],
+                          Default character set, use one of:
-  [default_charset="$DEFAULT_CHARSET"])
+                          CHARSETS_AVAILABLE1
+                          CHARSETS_AVAILABLE2
+                          CHARSETS_AVAILABLE3
+                          CHARSETS_AVAILABLE4
+                          CHARSETS_AVAILABLE5],
+   [default_charset="$withval"],
+   [default_charset="$DEFAULT_CHARSET"])
+
 
 AC_ARG_WITH(extra-charsets,
   [  --with-extra-charsets=CHARSET[,CHARSET,...]
@@ -2256,73 +2263,77 @@ AC_ARG_WITH(extra-charsets,
   [extra_charsets="$withval"],
   [extra_charsets="none"])
 
+
 AC_MSG_CHECKING("character sets")
 
+CHARSETS="$default_charset latin1 utf8"
+
 if test "$extra_charsets" = no; then
-  CHARSETS=""
+  CHARSETS="$CHARSETS"
 elif test "$extra_charsets" = none; then
-  CHARSETS=""
+  CHARSETS="$CHARSETS"
 elif test "$extra_charsets" = complex; then
-  CHARSETS="$CHARSETS_COMPLEX"
+  CHARSETS="$CHARSETS $CHARSETS_COMPLEX"
 elif test "$extra_charsets" = all; then
-  CHARSETS="$CHARSETS_AVAILABLE $CHARSETS_DEPRECATED"
+  CHARSETS="$CHARSETS $CHARSETS_AVAILABLE"
 else
-  CHARSETS=`echo $extra_charsets | sed -e 's/,/ /g'`
+  EXTRA_CHARSETS=`echo $extra_charsets | sed -e 's/,/ /g'`
+  CHARSETS="$CHARSETS $EXTRA_CHARSETS"
 fi
 
-CHARSETS="$default_charset $CHARSETS"
-
-use_mb="no"
 
 for cs in $CHARSETS
 do
   case $cs in 
     armscii8)
       AC_DEFINE(HAVE_CHARSET_armscii8)
-      use_mb="yes"
+      ;;
+    ascii)
+      AC_DEFINE(HAVE_CHARSET_ascii)
       ;;
     big5)
       AC_DEFINE(HAVE_CHARSET_big5)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
+      AC_DEFINE(USE_MB_IDENT)
+      ;;
+    cp1250)
+      AC_DEFINE(HAVE_CHARSET_cp1250)
       ;;
     cp1251)
       AC_DEFINE(HAVE_CHARSET_cp1251)
       ;;
+    cp1256)
+      AC_DEFINE(HAVE_CHARSET_cp1256)
+      ;;
     cp1257)
       AC_DEFINE(HAVE_CHARSET_cp1257)
       ;;
-    croat)
+    cp850)
-      AC_DEFINE(HAVE_CHARSET_croat)
+      AC_DEFINE(HAVE_CHARSET_cp850)
       ;;
-    czech)
+    cp852)
-      AC_DEFINE(HAVE_CHARSET_czech)
+      AC_DEFINE(HAVE_CHARSET_cp852)
       ;;
-    danish)
+    cp866)
-      AC_DEFINE(HAVE_CHARSET_danish)
+      AC_DEFINE(HAVE_CHARSET_cp866)
       ;;
     dec8)
       AC_DEFINE(HAVE_CHARSET_dec8)
       ;;
-    dos)
+    euckr)
-      AC_DEFINE(HAVE_CHARSET_dos)
+      AC_DEFINE(HAVE_CHARSET_euckr)
-      ;;
+      AC_DEFINE(USE_MB)
-    estonia)
+      AC_DEFINE(USE_MB_IDENT)
-      AC_DEFINE(HAVE_CHARSET_estonia)
-      ;;
-    euc_kr)
-      AC_DEFINE(HAVE_CHARSET_euc_kr)
-      use_mb="yes"
       ;;
     gb2312)
       AC_DEFINE(HAVE_CHARSET_gb2312)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
+      AC_DEFINE(USE_MB_IDENT)
       ;;
     gbk)
       AC_DEFINE(HAVE_CHARSET_gbk)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
-      ;;
+      AC_DEFINE(USE_MB_IDENT)
-    german1)
-      AC_DEFINE(HAVE_CHARSET_german1)
       ;;
     greek)
       AC_DEFINE(HAVE_CHARSET_greek)
@@ -2333,30 +2344,37 @@ do
     hp8)
       AC_DEFINE(HAVE_CHARSET_hp8)
       ;;
-    hungarian)
+    keybcs2)
-      AC_DEFINE(HAVE_CHARSET_hungarian)
+      AC_DEFINE(HAVE_CHARSET_keybcs2)
       ;;
-    koi8_ru)
+    koi8r)
-      AC_DEFINE(HAVE_CHARSET_koi8_ru)
+      AC_DEFINE(HAVE_CHARSET_koi8r)
       ;;
-    koi8_ukr)
+    koi8u)
-      AC_DEFINE(HAVE_CHARSET_koi8_ukr)
+      AC_DEFINE(HAVE_CHARSET_koi8u)
       ;;
     latin1)
       AC_DEFINE(HAVE_CHARSET_latin1)
       ;;
-    latin1_de)
-      AC_DEFINE(HAVE_CHARSET_latin1_de)
-      ;;
     latin2)
       AC_DEFINE(HAVE_CHARSET_latin2)
       ;;
     latin5)
       AC_DEFINE(HAVE_CHARSET_latin5)
       ;;
+    latin7)
+      AC_DEFINE(HAVE_CHARSET_latin7)
+      ;;
+    macce)
+      AC_DEFINE(HAVE_CHARSET_macce)
+      ;;
+    macroman)
+      AC_DEFINE(HAVE_CHARSET_macroman)
+      ;;
     sjis)
       AC_DEFINE(HAVE_CHARSET_sjis)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
+      AC_DEFINE(USE_MB_IDENT)
       ;;
     swe7)
       AC_DEFINE(HAVE_CHARSET_swe7)
@@ -2366,49 +2384,25 @@ do
       ;;
     ucs2)
       AC_DEFINE(HAVE_CHARSET_ucs2)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
+      AC_DEFINE(USE_MB_IDENT)
       ;;
     ujis)
       AC_DEFINE(HAVE_CHARSET_ujis)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
-      ;;
+      AC_DEFINE(USE_MB_IDENT)
-    usa7)
-      AC_DEFINE(HAVE_CHARSET_usa7)
       ;;
     utf8)
       AC_DEFINE(HAVE_CHARSET_utf8)
-      use_mb="yes"
+      AC_DEFINE(USE_MB)
-      ;;
+      AC_DEFINE(USE_MB_IDENT)
-    win1250)
-      AC_DEFINE(HAVE_CHARSET_win1250)
-      ;;
-    win1250ch)
-      AC_DEFINE(HAVE_CHARSET_win1250ch)
-      ;;
-    win1251)
-      AC_DEFINE(HAVE_CHARSET_win1251)
-      ;;
-    win1251ukr)
-      AC_DEFINE(HAVE_CHARSET_win1251ukr)
       ;;
     *)
-      AC_MSG_ERROR([Charset $cs not available. (Available $CHARSETS_AVAILABLE).
+      AC_MSG_ERROR([Charset $cs not available. (Available are: $CHARSETS_AVAILABLE).
       See the Installation chapter in the Reference Manual.]);
   esac
 done
 
-dnl Always compile latin1
-AC_DEFINE(HAVE_CHARSET_latin1)
-
-dnl Always compile utf8
-AC_DEFINE(HAVE_CHARSET_utf8)
-use_mb=yes
-
-if test "$use_mb" = "yes"
-then
-  AC_DEFINE(USE_MB)
-  AC_DEFINE(USE_MB_IDENT)
-fi
 
 AC_SUBST(default_charset)
 AC_DEFINE_UNQUOTED(DEFAULT_CHARSET_NAME,"$default_charset")

mysql-test/r/ctype_ujis.result

@@ -1,5 +1,5 @@
 drop table if exists t1;
-create table t1 (c text);
+create table t1 (c text character set ujis);
 insert into t1 values (0xa4a2),(0xa4a3);
 select hex(left(c,1)) from t1 group by c;
 hex(left(c,1))

mysql-test/r/have_ucs2.require

@@ -1,2 +1,2 @@
 Collation	Charset	Id	D	C	Sortlen
-ucs2_general_ci	ucs2	35	Y		0
+ucs2_general_ci	ucs2	35	Y	Y	1

mysql-test/r/have_ujis.require

@@ -1,2 +1,2 @@
 Collation	Charset	Id	D	C	Sortlen
-ujis_japanese_ci	ujis	12	Y		0
+ujis_japanese_ci	ujis	12	Y	Y	0

mysys/charset.c

@@ -407,11 +407,15 @@ static my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   MY_ADD_CHARSET(&my_charset_big5_bin);
 #endif
 
-#ifdef HAVE_CHARSET_czech
+#ifdef HAVE_CHARSET_cp1250
+  MY_ADD_CHARSET(&my_charset_cp1250_czech_ci);
+#endif
+
+#ifdef HAVE_CHARSET_latin2
   MY_ADD_CHARSET(&my_charset_latin2_czech_ci);
 #endif
 
-#ifdef HAVE_CHARSET_euc_kr
+#ifdef HAVE_CHARSET_euckr
   MY_ADD_CHARSET(&my_charset_euckr_korean_ci);
   MY_ADD_CHARSET(&my_charset_euckr_bin);
 #endif
@@ -451,10 +455,6 @@ static my_bool init_compiled_charsets(myf flags __attribute__((unused)))
   MY_ADD_CHARSET(&my_charset_utf8_bin);
 #endif
 
-#ifdef HAVE_CHARSET_win1250ch
-  MY_ADD_CHARSET(&my_charset_cp1250_czech_ci);
-#endif
-
   /* Copy compiled charsets */
   for (cs=compiled_charsets; cs->name; cs++)
   {

strings/ctype-czech.c

@@ -77,7 +77,7 @@
 
 #endif
 
-#ifdef HAVE_CHARSET_czech
+#ifdef HAVE_CHARSET_latin2
 
 /*
 	These are four tables for four passes of the algorithm. Please see

strings/ctype-euc_kr.c

@@ -30,7 +30,7 @@
 #include "m_string.h"
 #include "m_ctype.h"
 
-#ifdef HAVE_CHARSET_euc_kr
+#ifdef HAVE_CHARSET_euckr
 
 
 static uchar NEAR ctype_euc_kr[257] =

strings/ctype-win1250ch.c

@@ -45,6 +45,9 @@
 #include "m_string.h"
 #include "m_ctype.h"
 
+#ifdef HAVE_CHARSET_cp1250
+
+
 static uint16 tab_cp1250_uni[256]={
      0,0x0001,0x0002,0x0003,0x0004,0x0005,0x0006,0x0007,
 0x0008,0x0009,0x000A,0x000B,0x000C,0x000D,0x000E,0x000F,
@@ -673,4 +676,6 @@ CHARSET_INFO my_charset_cp1250_czech_ci =
 };
 
 
+#endif
+
 #endif