summaryrefslogtreecommitdiff
path: root/tests/euc-mb
blob: b6250462d7d00f1549fe42c6353efee7c729ca84 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
#!/bin/sh
# test that matches starting in the middle of a multibyte char aren't rejected
# too greedily.
# Derived from https://savannah.gnu.org/bugs/?23814
. "${srcdir=.}/init.sh"; path_prepend_ ../src

# Add "." to PATH for the use of get-mb-cur-max.
path_prepend_ .

require_compiled_in_MB_support

locale=ja_JP.EUC-JP

make_input () {
  echo "$1" | tr AB '\244\263'
}

euc_grep () {
  pat=$(make_input "$1")
  LC_ALL=$locale grep "$pat"
}

case $(get-mb-cur-max $locale) in
  2|3) ;;
  *) skip_ 'EUC-JP locale not found' ;;
esac

fail=0

# Does EUC-JP work at all?
make_input BABA |euc_grep AB && fail=1

# Here are two cases in which a KWSet search matches in the middle
# of a multibyte character.  The first ensures that the DFA matcher
# finds the real match at the end of line.  The second ensures that
# while the KWSet match found a false positive, the DFA matcher
# determines there is no match after all.
make_input BABAAB |euc_grep AB > out || fail=1
make_input BABAAB > exp || framework_failure_
compare exp out || fail=1
make_input BABABA |euc_grep AB; test $? = 1 || fail=1
make_input BABABA |euc_grep '^x\|AB'; test $? = 1 || fail=1

# -P supports only unibyte and UTF-8 locales.
LC_ALL=$locale grep -P x /dev/null
test $? = 2 || fail=1

Exit $fail