Unicode escapes in strings and identifiers

1 files changed, 36 insertions, 1 deletions

diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c
index 2f11b3aa9b0..2c6c3f3ff1c 100644
--- a/src/backend/utils/mb/wchar.c
+++ b/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 1.67 2008/10/27 19:37:22 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.68 2008/10/29 08:04:53 petere Exp $
  *
  */
 /* can be used in either frontend or backend */
@@ -419,6 +419,41 @@ pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
 	return cnt;
 }
 
+
+/*
+ * Map a Unicode code point to UTF-8.  utf8string must have 4 bytes of
+ * space allocated.
+ */
+unsigned char *
+unicode_to_utf8(pg_wchar c, unsigned char *utf8string)
+{
+	if (c <= 0x7F)
+	{
+		utf8string[0] = c;
+	}
+	else if (c <= 0x7FF)
+	{
+		utf8string[0] = 0xC0 | ((c >> 6) & 0x1F);
+		utf8string[1] = 0x80 | (c & 0x3F);
+	}
+	else if (c <= 0xFFFF)
+	{
+		utf8string[0] = 0xE0 | ((c >> 12) & 0x0F);
+		utf8string[1] = 0x80 | ((c >> 6) & 0x3F);
+		utf8string[2] = 0x80 | (c & 0x3F);
+	}
+	else
+	{
+		utf8string[0] = 0xF0 | ((c >> 18) & 0x07);
+		utf8string[1] = 0x80 | ((c >> 12) & 0x3F);
+		utf8string[2] = 0x80 | ((c >> 6) & 0x3F);
+		utf8string[3] = 0x80 | (c & 0x3F);
+	}
+
+	return utf8string;
+}
+
+
 /*
  * Return the byte length of a UTF8 character pointed to by s
  *