From 4d1dd8d86567b61b42131d8e271ce587f645ac8b Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Mon, 16 Aug 2010 00:06:54 +0000 Subject: [PATCH] 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. --- src/bin/psql/mbprint.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/src/bin/psql/mbprint.c b/src/bin/psql/mbprint.c index 27ee3f840f3..4b4dc187347 100644 --- a/src/bin/psql/mbprint.c +++ b/src/bin/psql/mbprint.c @@ -3,7 +3,7 @@ * * Copyright (c) 2000-2005, PostgreSQL Global Development Group * - * $PostgreSQL: pgsql/src/bin/psql/mbprint.c,v 1.16 2005/01/01 05:43:08 momjian Exp $ + * $PostgreSQL: pgsql/src/bin/psql/mbprint.c,v 1.16.4.1 2010/08/16 00:06:54 tgl Exp $ */ #include "postgres_fe.h" @@ -168,28 +168,20 @@ 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; - } } /* mb_utf_wcwidth : calculate column length for the utf8 string pwcs -- 2.39.5