Debian Codegraph @

tests/turkish-I-without-dot

raw
1 #!/bin/sh
2 # grep -i would misbehave for any matched line containing a character
3 # (like "I" in the tr_TR.utf8 locale) whose lower-case representation
4 # occupies more bytes (two in this case, for 0xc4b1, aka U+0131).
5
6 # Copyright (C) 2011-2025 Free Software Foundation, Inc.
7
8 # This program is free software: you can redistribute it and/or modify
9 # it under the terms of the GNU General Public License as published by
10 # the Free Software Foundation, either version 3 of the License, or
11 # (at your option) any later version.
12
13 # This program is distributed in the hope that it will be useful,
14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 # GNU General Public License for more details.
17
18 # You should have received a copy of the GNU General Public License
19 # along with this program. If not, see <https://www.gnu.org/licenses/>.
20
21 . "${srcdir=.}/init.sh"; path_prepend_ ../src
22
23 require_tr_utf8_locale_
24 require_compiled_in_MB_support
25
26 # Before this change, grep could print a lot of uninitialized memory:
27 # $ printf "IIIIIII\n" > in
28 # $ for i in $(seq 10); do LC_ALL=tr_TR.utf8 src/grep -i . in|wc -c; done
29 # 760
30 # 754
31 # 585
32 # 298
33 # 273
34 # 458
35 # 660
36 # 552
37 # 936
38 # 678
39
40 fail=0
41
42 printf "IIIIIII\n" > in || framework_failure_
43 LC_ALL=tr_TR.utf8 grep -i .... in > out || fail=1
44 compare out in || fail=1
45
46 # Also exercise the case in which the original string and the lower-case
47 # buffer have precisely the same length (22 bytes here), yet internal
48 # offsets do differ. Lengths are the same because while some bytes shrink
49 # when converted to lower case, others grow, and here they balance out.
50 i='I\304\260'
51 printf "$i$i$i$i$i$i$i\n" > in || framework_failure_
52 LC_ALL=tr_TR.utf8 grep -i .... in > out || fail=1
53 compare out in || fail=1
54
55 Exit $fail