addendum-03A-emulate-non-utf8-multibyte-STATIC.patch

diff --git a/src/port/pg_utf8_fallback.c b/src/port/pg_utf8_fallback.c
index 1615c48233..af1d636331 100644
--- a/src/port/pg_utf8_fallback.c
+++ b/src/port/pg_utf8_fallback.c
@@ -17,8 +17,91 @@
 
 #include "port/pg_utf8.h"
 
+static bool
+pg_utf8_islegal(const unsigned char *source, int length)
+{
+	unsigned char a;
+
+	switch (length)
+	{
+		default:
+			/* reject lengths 5 and 6 for now */
+			return false;
+		case 4:
+			a = source[3];
+			if (a < 0x80 || a > 0xBF)
+				return false;
+			/* FALL THRU */
+		case 3:
+			a = source[2];
+			if (a < 0x80 || a > 0xBF)
+				return false;
+			/* FALL THRU */
+		case 2:
+			a = source[1];
+			switch (*source)
+			{
+				case 0xE0:
+					if (a < 0xA0 || a > 0xBF)
+						return false;
+					break;
+				case 0xED:
+					if (a < 0x80 || a > 0x9F)
+						return false;
+					break;
+				case 0xF0:
+					if (a < 0x90 || a > 0xBF)
+						return false;
+					break;
+				case 0xF4:
+					if (a < 0x80 || a > 0x8F)
+						return false;
+					break;
+				default:
+					if (a < 0x80 || a > 0xBF)
+						return false;
+					break;
+			}
+			/* FALL THRU */
+		case 1:
+			a = *source;
+			if (a >= 0x80 && a < 0xC2)
+				return false;
+			if (a > 0xF4)
+				return false;
+			break;
+	}
+	return true;
+}
+
+static int
+pg_utf8_verifychar(const unsigned char *s, int len)
+{
+	int			l;
 
-#define IS_CONTINUATION_BYTE(c) (((c) & 0b11000000) == 0b10000000)
+	if ((*s & 0x80) == 0)
+	{
+		if (*s == '\0')
+			return -1;
+		return 1;
+	}
+	else if ((*s & 0xe0) == 0xc0)
+		l = 2;
+	else if ((*s & 0xf0) == 0xe0)
+		l = 3;
+	else if ((*s & 0xf8) == 0xf0)
+		l = 4;
+	else
+		l = 1;
+
+	if (l > len)
+		return -1;
+
+	if (!pg_utf8_islegal(s, l))
+		return -1;
+
+	return l;
+}
 
 /*
  * See the comment in common/wchar.c under "multibyte sequence validators".
@@ -27,7 +110,6 @@ int
 pg_validate_utf8_fallback(const unsigned char *s, int len)
 {
 	const unsigned char *start = s;
-	unsigned char b1, b2, b3, b4;
 
 	while (len > 0)
 	{
@@ -49,81 +131,12 @@ pg_validate_utf8_fallback(const unsigned char *s, int len)
 				break;
 			l = 1;
 		}
-		/* code points U+0080 through U+07FF */
-		else if ((*s & 0b11100000) == 0b11000000)
-		{
-			l = 2;
-			if (len < l)
-				break;
-
-			b1 = *s;
-			b2 = *(s + 1);
-
-			if (!IS_CONTINUATION_BYTE(b2))
-				break;
-
-			/* check 2-byte overlong: 1100.000x.10xx.xxxx */
-			if (b1 < 0xC2)
-				break;
-		}
-		/* code points U+0800 through U+D7FF and U+E000 through U+FFFF */
-		else if ((*s & 0b11110000) == 0b11100000)
-		{
-			l = 3;
-			if (len < l)
-				break;
-
-			b1 = *s;
-			b2 = *(s + 1);
-			b3 = *(s + 2);
-
-			if (!IS_CONTINUATION_BYTE(b2) ||
-				!IS_CONTINUATION_BYTE(b3))
-				break;
-
-			/* check 3-byte overlong: 1110.0000 1001.xxxx 10xx.xxxx */
-			if (b1 == 0xE0 && b2 < 0xA0)
-				break;
-
-			/* check surrogate: 1110.1101 101x.xxxx 10xx.xxxx */
-			if (b1 == 0xED && b2 > 0x9F)
-				break;
-		}
-		/* code points U+010000 through U+10FFFF */
-		else if ((*s & 0b11111000) == 0b11110000)
+		else
 		{
-			l = 4;
-			if (len < l)
-				break;
-
-			b1 = *s;
-			b2 = *(s + 1);
-			b3 = *(s + 2);
-			b4 = *(s + 3);
-
-			if (!IS_CONTINUATION_BYTE(b2) ||
-				!IS_CONTINUATION_BYTE(b3) ||
-				!IS_CONTINUATION_BYTE(b4))
-				break;
-
-			/*
-			 * check 4-byte overlong:
-			 * 1111.0000 1000.xxxx 10xx.xxxx 10xx.xxxx
-			 */
-			if (b1 == 0xF0 && b2 < 0x90)
-				break;
-
-			/*
-			 * check too large:
-			 * 1111.0100 1001.xxxx 10xx.xxxx 10xx.xxxx
-			 */
-			if ((b1 == 0xF4 && b2 > 0x8F) || b1 > 0xF4)
+			l = pg_utf8_verifychar(s, len);
+			if (l == -1)
 				break;
 		}
-		else
-			/* invalid byte */
-			break;
-
 		s += l;
 		len -= l;
 	}