1 files changed, 78 insertions, 0 deletions
diff --git a/tests/multibyte-white-space b/tests/multibyte-white-space
new file mode 100755
index 0000000..c2a493b
--- /dev/null
+++ b/tests/multibyte-white-space
@@ -0,0 +1,78 @@
+#! /bin/sh
+# Test whether \s matches SP and UTF-8 multi-byte white space characters.
+#
+# Copyright (C) 2013-2016 Free Software Foundation, Inc.
+#
+# Copying and distribution of this file, with or without modification,
+# are permitted in any medium without royalty provided the copyright
+# notice and this notice are preserved.
+
+. "${srcdir=.}/init.sh"; path_prepend_ ../src
+
+require_en_utf8_locale_
+
+LC_ALL=en_US.UTF-8
+export LC_ALL
+
+# It would have been nice to be able to use all UTF8 characters
+# with the Unicode WSpace=Y character property,
+# https://en.wikipedia.org/wiki/Whitespace_character, but that
+# would currently cause distracting failures everywhere I've tried.
+
+# FIXME: including any the following in the list below would
+# make this test fail on Fedora 19/glibc-2.17-18.fc19.
+# Restore them to the list once it is fixed.
+these_fail_with_glibc='
+U+00A0 NO-BREAK SPACE:            c2 a0
+U+2007 FIGURE SPACE:              e2 80 87
+U+200B ZERO WIDTH SPACE:          e2 80 8b
+U+202F NARROW NO-BREAK SPACE:     e2 80 af
+'
+fail_with_other='
+U+000A Line feed:                 0a
+U+0085 Next line:                 85
+'
+
+utf8_space_characters=$(sed 's/.*://;s/  */\\x/g' <<\EOF
+U+0009 Horizontal Tab:            09
+U+000B Vertical Tab:              0b
+U+000C Form feed:                 0c
+U+000D Carriage return:           0d
+U+0020 SPACE:                     20
+U+1680 OGHAM SPACE MARK:          e1 9a 80
+U+2000 EN QUAD:                   e2 80 80
+U+2001 EM QUAD:                   e2 80 81
+U+2002 EN SPACE:                  e2 80 82
+U+2003 EM SPACE:                  e2 80 83
+U+2004 THREE-PER-EM SPACE:        e2 80 84
+U+2005 FOUR-PER-EM SPACE:         e2 80 85
+U+2006 SIX-PER-EM SPACE:          e2 80 86
+U+2008 PUNCTUATION SPACE:         e2 80 88
+U+2009 THIN SPACE:                e2 80 89
+U+200A HAIR SPACE:                e2 80 8a
+U+205F MEDIUM MATHEMATICAL SPACE: e2 81 9f
+U+3000 IDEOGRAPHIC SPACE:         e3 80 80
+EOF
+)
+
+fail=0
+
+for i in $utf8_space_characters; do
+  hex_printf_ "$i" | grep -q '^\s$' \
+      || { warn_ "$i FAILED to match \\s"; fail=1; }
+  hex_printf_ "$i" | grep -q '\S'
+  test $? = 1 \
+      || { warn_ "$i vs. \\S FAILED"; fail=1; }
+done
+
+
+# This is a separate test, only nominally related to \s.
+# It is solely to get coverage of a code path (exercising dfa.c's
+# match_mb_charset function) that would have otherwise been untouched.
+# However, as of the change-set adding this new test, match_mb_charset
+# is unreachable via grep.
+printf '\0' | grep -aE '^\s?$' > out 2>&1
+test $? = 1 || fail=1
+compare /dev/null out
+
+Exit $fail