From: t-ishii@sra.co.jp

Hi, here are patches I promised (against 6.3.2):

* character_length(), position(), substring() are now aware of
          multi-byte characters
* add octet_length()
* add --with-mb option to configure
* new regression tests for EUC_KR
  (contributed by "Soonmyung. Hong" <hong@lunaris.hanmesoft.co.kr>)
* add some test cases to the EUC_JP regression test
* fix problem in regress/regress.sh in case of System V
* fix toupper(), tolower() to handle 8bit chars

note that:

o  patches for both configure.in and configure are
included. maybe the one for configure is not necessary.

o pg_proc.h was modified to add octet_length(). I used OIDs
(1374-1379) for that. Please let me know if these numbers are not
appropriate.

3 files changed, 24 insertions, 5 deletions

diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index cf0826b69ba..335139cdbeb 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -6,7 +6,7 @@
  *
  * Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_proc.h,v 1.53 1998/04/27 04:08:07 momjian Exp $
+ * $Id: pg_proc.h,v 1.54 1998/04/27 17:08:41 scrappy Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -201,6 +201,8 @@ DATA(insert OID = 1257 (  textlen		   PGUID 11 f t f 1 f 23 "25" 100 0 1 0  foo
 DESCR("length");
 DATA(insert OID = 1258 (  textcat		   PGUID 11 f t f 2 f 25 "25 25" 100 0 1 0	foo bar ));
 DESCR("concat");
+DATA(insert OID = 1377 (  textoctetlen		   PGUID 11 f t f 1 f 23 "25" 100 0 1 0  foo bar ));
+DESCR("octet length");
 DATA(insert OID =  84 (  boolne			   PGUID 11 f t f 2 f 16 "16 16" 100 0 0 100  foo bar ));
 DESCR("not equal");
 
@@ -1444,7 +1446,11 @@ DESCR("does not match regex., case-insensitive");
 
 DATA(insert OID = 1251 (  bpcharlen		   PGUID 11 f t f 1 f 23 "1042" 100 0 0 100  foo bar ));
 DESCR("octet length");
+DATA(insert OID = 1378 (  bpcharoctetlen		   PGUID 11 f t f 1 f 23 "1042" 100 0 0 100  foo bar ));
+DESCR("octet length");
 DATA(insert OID = 1253 (  varcharlen	   PGUID 11 f t f 1 f 23 "1043" 100 0 0 100  foo bar ));
+DESCR("character length");
+DATA(insert OID = 1379 (  varcharoctetlen	   PGUID 11 f t f 1 f 23 "1043" 100 0 0 100  foo bar ));
 DESCR("octet length");
 
 DATA(insert OID = 1263 (  text_timespan    PGUID 11 f t f 1 f 1186 "25" 100 0 0 100  foo bar ));
@@ -1550,10 +1556,17 @@ DESCR("convert");
 DATA(insert OID = 1370 (  timestamp			 PGUID 14 f t f 1 f 1296 "1184" 100 0 0 100  "select datetime_stamp($1)" - ));
 DESCR("convert");
 DATA(insert OID = 1371 (  length			 PGUID 14 f t f 1 f   23   "25" 100 0 0 100  "select textlen($1)" - ));
-DESCR("octet length");
+DESCR("character length");
 DATA(insert OID = 1372 (  length			 PGUID 14 f t f 1 f   23   "1042" 100 0 0 100  "select bpcharlen($1)" - ));
-DESCR("octet length");
+DESCR("character length");
 DATA(insert OID = 1373 (  length			 PGUID 14 f t f 1 f   23   "1043" 100 0 0 100  "select varcharlen($1)" - ));
+DESCR("character length");
+
+DATA(insert OID = 1374 (  octet_length			 PGUID 14 f t f 1 f   23   "25" 100 0 0 100  "select textoctetlen($1)" - ));
+DESCR("octet length");
+DATA(insert OID = 1375 (  octet_length			 PGUID 14 f t f 1 f   23   "1042" 100 0 0 100  "select bpcharoctetlen($1)" - ));
+DESCR("octet length");
+DATA(insert OID = 1376 (  octet_length			 PGUID 14 f t f 1 f   23   "1043" 100 0 0 100  "select varcharoctetlen($1)" - ));
 DESCR("octet length");
 
 DATA(insert OID = 1380 (  date_part    PGUID 14 f t f 2 f  701 "25 1184" 100 0 0 100  "select datetime_part($1, $2)" - ));
diff --git a/src/include/regex/pg_wchar.h b/src/include/regex/pg_wchar.h
index 616f76cfec5..b135df82f12 100644
--- a/src/include/regex/pg_wchar.h
+++ b/src/include/regex/pg_wchar.h
@@ -1,4 +1,4 @@
-/* $Id: pg_wchar.h,v 1.1 1998/03/15 07:38:47 scrappy Exp $ */
+/* $Id: pg_wchar.h,v 1.2 1998/04/27 17:09:12 scrappy Exp $ */
 
 #ifndef PG_WCHAR_H
 #define PG_WCHAR_H
@@ -39,6 +39,9 @@ extern int pg_char_and_wchar_strcmp(const char *, const pg_wchar *);
 extern int pg_wchar_strncmp(const pg_wchar *, const pg_wchar *, size_t);
 extern int pg_char_and_wchar_strncmp(const char *, const pg_wchar *, size_t);
 extern size_t pg_wchar_strlen(const pg_wchar *);
+extern int pg_mblen(const unsigned char *);
+extern int pg_mbstrlen(const unsigned char *);
+extern int pg_mbstrlen_with_len(const unsigned char *, int);
 #endif
 
 #endif
diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h
index 44def35ef78..9e83ba12e60 100644
--- a/src/include/utils/builtins.h
+++ b/src/include/utils/builtins.h
@@ -6,7 +6,7 @@
  *
  * Copyright (c) 1994, Regents of the University of California
  *
- * $Id: builtins.h,v 1.40 1998/04/26 04:09:25 momjian Exp $
+ * $Id: builtins.h,v 1.41 1998/04/27 17:09:28 scrappy Exp $
  *
  * NOTES
  *	  This should normally only be included by fmgr.h.
@@ -400,6 +400,7 @@ extern bool bpchargt(char *arg1, char *arg2);
 extern bool bpcharge(char *arg1, char *arg2);
 extern int32 bpcharcmp(char *arg1, char *arg2);
 extern int32 bpcharlen(char *arg);
+extern int32 bpcharoctetlen(char *arg);
 extern uint32 hashbpchar(struct varlena * key);
 
 extern char *varcharin(char *s, int dummy, int16 atttypmod);
@@ -412,6 +413,7 @@ extern bool varchargt(char *arg1, char *arg2);
 extern bool varcharge(char *arg1, char *arg2);
 extern int32 varcharcmp(char *arg1, char *arg2);
 extern int32 varcharlen(char *arg);
+extern int32 varcharoctetlen(char *arg);
 extern uint32 hashvarchar(struct varlena * key);
 
 /* varlena.c */
@@ -425,6 +427,7 @@ extern bool text_le(text *arg1, text *arg2);
 extern bool text_gt(text *arg1, text *arg2);
 extern bool text_ge(text *arg1, text *arg2);
 extern int32 textlen(text *arg);
+extern int32 textoctetlen(text *arg);
 extern int32 textpos(text *arg1, text *arg2);
 extern text *text_substr(text *string, int32 m, int32 n);