#!/bin/sh
# Ensure non-ASCII UTF-8 characters are correctly identified as
# word-constituents
#
# Copyright (C) 2023 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
require_pcre_

echo . | grep -qP '(*UTF).' 2>/dev/null \
  || skip_ 'PCRE unicode support is compiled out'
echo 0 | grep -qP '(?aD)\d' \
  || skip_ 'PCRE 10.42 and older lack PCRE2_EXTRA_ASCII_BSD'

fail=0

echo 'Perú' > in || framework_failure_

echo 'ú' > exp || framework_failure_
grep -Po '.\b' in > out || fail=1
compare exp out || fail=1

echo 'rú' > exp || framework_failure_
grep -Po 'r\w' in > out || fail=1
compare exp out || fail=1

Exit $fail