tests/uniq/uniq-collate.sh

   1 #!/bin/sh
   2 # before coreutils-8.32, uniq would not distinguish
   3 # items which compared equal with strcoll()
   4 # So ensure we avoid strcoll() for the following cases.
   5
   6 # Copyright (C) 2020-2024 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 . "${srcdir=.}/tests/init.sh"; path_prepend_ ./src
  22 print_ver_ uniq printf
  23
  24 gen_input()
  25 {
  26   env LC_ALL=$LOCALE_FR_UTF8 printf "$@" > in || framework_failure_
  27 }
  28
  29 # strcoll() used to return 0 comparing the following strings
  30 # which was fixed somewhere between glibc-2.22 and glibc-2.30
  31 gen_input '%s\n' 'ⁿᵘˡˡ' 'ܥܝܪܐܩ'
  32 test $(LC_ALL=$LOCALE_FR_UTF8 uniq < in | wc -l) = 2 || fail=1
  33
  34 # normalization in strcoll is inconsistent across platforms.
  35 # glibc based systems at least do _not_ normalize in strcoll,
  36 # while cygwin systems for example may do so.
  37 # á composed and decomposed, are generally not compared equal
  38 gen_input '\u00E1\na\u0301\n'
  39 test $(LC_ALL=$LOCALE_FR_UTF8 uniq < in | wc -l) = 2 || fail=1
  40 # Similarly with the following equivalent hangul characters
  41 gen_input '\uAC01\n\u1100\u1161\u11A8\n'
  42 test $(LC_ALL=ko_KR.utf8 uniq < in | wc -l) = 2 || fail=1
  43
  44 # Note if running in the wrong locale,
  45 # strcoll may indicate the strings match when they don't.
  46 # I.e., cjk and hangul will now work even if
  47 # uniq is running in the wrong locale
  48 # hangul (ko_KR.utf8)
  49 gen_input '\uAC00\n\uAC01\n'
  50 test $(LC_ALL=en_US.utf8 uniq < in | wc -l) = 2 || fail=1
  51 # CJK (zh_CN.utf8)
  52 gen_input '\u3400\n\u3401\n'
  53 test $(LC_ALL=en_US.utf8 uniq < in | wc -l) = 2 || fail=1
  54
  55 # Note strcoll() ignores certain characters,
  56 # but not if the strings are otherwise equal.
  57 # I.e., the following on glibc-2.30 at least,
  58 # as expected, does not print a single item,
  59 # but testing here for illustration
  60 gen_input ',a\n.a\n'
  61 test $(LC_ALL=$LOCALE_FR_UTF8 uniq < in | wc -l) = 2 || fail=1
  62
  63 Exit $fail