Back out fix for Unicode characters above 0x10000

doc/src/sgml/postgres.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/postgres.sgml,v 1.65 2004/11/12 21:50:53 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/postgres.sgml,v 1.66 2004/12/03 01:20:14 momjian Exp $
 -->
 
 <!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook V4.2//EN" [
@@ -179,6 +179,7 @@ $PostgreSQL: pgsql/doc/src/sgml/postgres.sgml,v 1.65 2004/11/12 21:50:53 tgl Exp
   &lobj;
   &ecpg;
   &infoschema;
+  &external_projects;
 
  </part>
 

src/backend/utils/mb/wchar.c

@@ -1,7 +1,7 @@
 /*
  * conversion functions between pg_wchar and multibyte streams.
  * Tatsuo Ishii
- * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.39 2004/12/02 22:37:13 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.40 2004/12/03 01:20:20 momjian Exp $
  *
  * WIN1250 client encoding updated by Pavel Behal
  *
@@ -343,31 +343,6 @@ pg_johab_dsplen(const unsigned char *s)
 	return (pg_euc_dsplen(s));
 }
 
-bool isLegalUTF8(const UTF8 *source, int len) {
-        UTF8 a;
-        const UTF8 *srcptr = source+len;
-        if(!source || (pg_utf_mblen(source) != len)) return false;
-        switch (len) {
-            default: return false;
-            /* Everything else falls through when "true"... */
-            case 6: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
-            case 5: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
-            case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
-            case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
-            case 2: if ((a = (*--srcptr)) > 0xBF) return false;
-            switch (*source) {
-                    /* no fall-through in this inner switch */
-                    case 0xE0: if (a < 0xA0) return false; break;
-                    case 0xF0: if (a < 0x90) return false; break;
-                    case 0xF4: if (a > 0x8F) return false; break;
-                    default:  if (a < 0x80) return false;
-            }
-            case 1: if (*source >= 0x80 && *source < 0xC2) return false;
-            if (*source > 0xFD) return false;
-        }
-        return true;
-}
-
 /*
  * convert UTF-8 string to pg_wchar (UCS-2)
  * caller should allocate enough space for "to"
@@ -423,7 +398,7 @@ pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
  * returns the byte length of a UTF-8 word pointed to by s
  */
 int
-pg_utf_mblen(const UTF8 *s)
+pg_utf_mblen(const unsigned char *s)
 {
 	int			len = 1;
 
@@ -431,19 +406,13 @@ pg_utf_mblen(const UTF8 *s)
 		len = 1;
 	else if ((*s & 0xe0) == 0xc0)
 		len = 2;
-        else if ((*s & 0xf0) == 0xe0)
+	else if ((*s & 0xe0) == 0xe0)
 		len = 3;
-        else if ((*s & 0xf8) == 0xf0)
-                len = 4;
-        else if ((*s & 0xfc) == 0xf8)
-                len = 5;
-        else if ((*s & 0xfe) == 0xfc)
-                len = 6;
 	return (len);
 }
 
 static int
-pg_utf_dsplen(const UTF8 *s)
+pg_utf_dsplen(const unsigned char *s)
 {
 	return 1;					/* XXX fix me! */
 }
@@ -752,7 +721,7 @@ pg_wchar_tbl pg_wchar_table[] = {
 	{pg_euckr2wchar_with_len, pg_euckr_mblen, pg_euckr_dsplen, 3},		/* 3; PG_EUC_KR */
 	{pg_euctw2wchar_with_len, pg_euctw_mblen, pg_euctw_dsplen, 3},		/* 4; PG_EUC_TW */
 	{pg_johab2wchar_with_len, pg_johab_mblen, pg_johab_dsplen, 3},		/* 5; PG_JOHAB */
-	{pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 6},		/* 6; PG_UNICODE */
+	{pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 3},	/* 6; PG_UNICODE */
 	{pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, 3}, /* 7; PG_MULE_INTERNAL */
 	{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1},	/* 8; PG_LATIN1 */
 	{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1},	/* 9; PG_LATIN2 */
@@ -853,15 +822,18 @@ pg_verifymbstr(const unsigned char *mbstr, int len, bool noError)
 
 	while (len > 0 && *mbstr)
 	{
+		/* special UTF-8 check */
+		if (encoding == PG_UTF8 && (*mbstr & 0xf8) == 0xf0)
+		{
+			if (noError)
+				return false;
+			ereport(ERROR,
+					(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
+					 errmsg("Unicode characters greater than or equal to 0x10000 are not supported")));
+		}
+
 		l = pg_mblen(mbstr);
 
-		/* special UTF-8 check */
-		if (encoding == PG_UTF8) {
-			if(!isLegalUTF8(mbstr,l)) {
-				if (noError) return false;
-				ereport(ERROR,(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),errmsg("Invalid UNICODE byte sequence detected near character %c",*mbstr)));
-			}
-		} else {
 		for (i = 1; i < l; i++)
 		{
 			/*
@@ -891,10 +863,10 @@ pg_verifymbstr(const unsigned char *mbstr, int len, bool noError)
 			}
 		}
 
-		}
 		len -= l;
 		mbstr += l;
 	}
+
 	return true;
 }
 

src/include/mb/pg_wchar.h

@@ -1,4 +1,4 @@
-/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.54 2004/12/02 22:37:14 momjian Exp $ */
+/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.55 2004/12/03 01:20:33 momjian Exp $ */
 
 #ifndef PG_WCHAR_H
 #define PG_WCHAR_H
@@ -17,14 +17,6 @@
  */
 typedef unsigned int pg_wchar;
 
-
-/*
- * The UTF types
- */
-typedef unsigned int	UTF32;  /* at least 32 bits */
-typedef unsigned short	UTF16;  /* at least 16 bits */
-typedef unsigned char	UTF8;   /* typically 8 bits */
-
 /*
  * various definitions for EUC
  */
@@ -348,6 +340,4 @@ extern void mic2latin(unsigned char *mic, unsigned char *p, int len, int lc);
 extern void latin2mic_with_table(unsigned char *l, unsigned char *p, int len, int lc, unsigned char *tab);
 extern void mic2latin_with_table(unsigned char *mic, unsigned char *p, int len, int lc, unsigned char *tab);
 
-extern bool isLegalUTF8(const UTF8 *source, int len);
-
 #endif   /* PG_WCHAR_H */