From c785bf16095624e47d9af976aaa751295a66f3d5 Mon Sep 17 00:00:00 2001
From: Ben Pfaff <blp@cs.stanford.edu>
Date: Thu, 1 Mar 2012 22:32:42 -0800
Subject: [PATCH] identifier: Apply isdigit() only to values in valid range.

Applying isdigit() to a value that is not EOF or in the range
0...UCHAR_MAX yields undefined behavior and in fact caused a
segfault on several Debian architectures for U+FFFD.

Found by "lexer properly reports scan errors" test on Debian buildds.
---
 src/data/identifier.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/data/identifier.c b/src/data/identifier.c
index f1c22ef1b5..a757b31e3a 100644
--- a/src/data/identifier.c
+++ b/src/data/identifier.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 1997-9, 2000, 2005, 2009, 2010, 2011 Free Software Foundation, Inc.
+   Copyright (C) 1997-9, 2000, 2005, 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
 
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -196,8 +196,9 @@ lex_uc_is_id1 (ucs4_t uc)
 bool
 lex_uc_is_idn (ucs4_t uc)
 {
-  return (is_ascii_id1 (uc) || isdigit (uc) || uc == '.' || uc == '_'
-          || (uc >= 0x80 && uc_is_property_id_continue (uc)));
+  return (uc < 0x80
+          ? is_ascii_id1 (uc) || isdigit (uc) || uc == '.' || uc == '_'
+          : uc >= 0x80 && uc_is_property_id_continue (uc));
 }
 
 /* Returns true if Unicode code point UC is a space that separates tokens. */
-- 
2.30.2