#!/bin/sh
# Ensure that grep -P's \d matches only the 10 ASCII digits.
# With, grep-3.9, \d would match e.g., the multibyte Arabic digits.
# The same applied to \D.
#
# 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

# $ printf %s ٠١٢٣٤٥٦٧٨٩|od -An -to1 -w10 |sed 's/ /\\/g'; : arabic digits
# \331\240\331\241\331\242\331\243\331\244
# \331\245\331\246\331\247\331\250\331\251
printf '\331\240\331\241\331\242\331\243\331\244' > in || framework_failure_
printf '\331\245\331\246\331\247\331\250\331\251' >> in || framework_failure_
printf '\n' >> in || framework_failure_

# Ensure that \d matches no character.
returns_ 1 grep -P '\d' in > out || fail=1
compare /dev/null out || fail=1

# Ensure that ^\D+$ matches the entire line.
grep -P '^\D+$' in > out || fail=1
compare in out || fail=1

# When built with PCRE2 10.43 and newer, one may use (?aD) and (?-aD)
# to toggle between modes.  (?aD) is the default (making \d == [0-9]).
# (?-aD) relaxes \d, making it match "all" digits.
# Use mixed digits as input: Arabic 0 and ASCII 4: ٠4
printf '\331\2404\n' > in2 || framework_failure_

returns_ 1 grep -P '\d\d' in2 > out || fail=1
compare /dev/null out || fail=1

grep -P '(?-aD)\d(?aD)\d' in2 > out || fail=1
compare in2 out || fail=1

returns_ 1 grep -P '\d(?-aD)\d' in2 > out || fail=1
compare /dev/null out || fail=1

Exit $fail