From b8ae02a2896778b8984c7f51566c7f0f56fa8b56 Mon Sep 17 00:00:00 2001 From: "schwarze@openbsd.org" Date: Tue, 21 Aug 2018 13:56:27 +0000 Subject: [PATCH] upstream: AIX reports the CODESET as "ISO8859-1" in the POSIX locale. Treating that as a safe encoding is OK because even when other systems return that string for real ISO8859-1, it is still safe in the sense that it is ASCII-compatible and stateless. Issue reported by Val dot Baranov at duke dot edu. Additional information provided by Michael dot Felt at felt dot demon dot nl. Tested by Michael Felt on AIX 6.1 and by Val Baranov on AIX 7.1. Tweak and OK djm@. OpenBSD-Commit-ID: 36f1210e0b229817d10eb490d6038f507b8256a7 --- utf8.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/utf8.c b/utf8.c index bc131385f..db7cb8f35 100644 --- a/utf8.c +++ b/utf8.c @@ -1,4 +1,4 @@ -/* $OpenBSD: utf8.c,v 1.7 2017/05/31 09:15:42 deraadt Exp $ */ +/* $OpenBSD: utf8.c,v 1.8 2018/08/21 13:56:27 schwarze Exp $ */ /* * Copyright (c) 2016 Ingo Schwarze * @@ -53,6 +53,8 @@ static int vasnmprintf(char **, size_t, int *, const char *, va_list); * For state-dependent encodings, recovery is impossible. * For arbitrary encodings, replacement of non-printable * characters would be non-trivial and too fragile. + * The comments indicate what nl_langinfo(CODESET) + * returns for US-ASCII on various operating systems. */ static int @@ -60,9 +62,12 @@ dangerous_locale(void) { char *loc; loc = nl_langinfo(CODESET); - return strcmp(loc, "US-ASCII") != 0 && strcmp(loc, "UTF-8") != 0 && - strcmp(loc, "ANSI_X3.4-1968") != 0 && strcmp(loc, "646") != 0 && - strcmp(loc, "") != 0; + return strcmp(loc, "UTF-8") != 0 && + strcmp(loc, "US-ASCII") != 0 && /* OpenBSD */ + strcmp(loc, "ANSI_X3.4-1968") != 0 && /* Linux */ + strcmp(loc, "ISO8859-1") != 0 && /* AIX */ + strcmp(loc, "646") != 0 && /* Solaris, NetBSD */ + strcmp(loc, "") != 0; /* Solaris 6 */ } static int