Fix psql's copy of utf2ucs() to match the backend's copy exactly;

in particular, propagate a fix in the test to see whether a UTF8 character has
length 4 bytes.  This is likely of little real-world consequence because
5-or-more-byte UTF8 sequences are not supported by Postgres nor seen anywhere
in the wild, but still we may as well get it right.  Problem found by Joseph
Adams.

Bug is aboriginal, so back-patch all the way.
This commit is contained in:
Tom Lane 2010-08-16 00:06:31 +00:00
parent 7f4de11c29
commit 00fb7f5e58

View File

@ -3,7 +3,7 @@
*
* Copyright (c) 2000-2009, PostgreSQL Global Development Group
*
* $PostgreSQL: pgsql/src/bin/psql/mbprint.c,v 1.35 2009/06/11 14:49:08 momjian Exp $
* $PostgreSQL: pgsql/src/bin/psql/mbprint.c,v 1.35.2.1 2010/08/16 00:06:31 tgl Exp $
*
* XXX this file does not really belong in psql/. Perhaps move to libpq?
* It also seems that the mbvalidate function is redundant with existing
@ -53,28 +53,20 @@ utf2ucs(const unsigned char *c)
if ((*c & 0x80) == 0)
return (pg_wchar) c[0];
else if ((*c & 0xe0) == 0xc0)
{
return (pg_wchar) (((c[0] & 0x1f) << 6) |
(c[1] & 0x3f));
}
else if ((*c & 0xf0) == 0xe0)
{
return (pg_wchar) (((c[0] & 0x0f) << 12) |
((c[1] & 0x3f) << 6) |
(c[2] & 0x3f));
}
else if ((*c & 0xf0) == 0xf0)
{
else if ((*c & 0xf8) == 0xf0)
return (pg_wchar) (((c[0] & 0x07) << 18) |
((c[1] & 0x3f) << 12) |
((c[2] & 0x3f) << 6) |
(c[3] & 0x3f));
}
else
{
/* that is an invalid code on purpose */
return 0xffffffff;
}
}