summaryrefslogtreecommitdiff
path: root/tests/misc/uniq
blob: 91028a9c7fd1abf7da216b822d5cb9144f54ea11 (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
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
#!/usr/bin/perl
# Test uniq.

# Copyright (C) 2008-2012 Free Software Foundation, Inc.

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

use strict;

my $limits = getlimits ();

my $prog = 'uniq';
my $try = "Try '$prog --help' for more information.\n";

# Turn off localization of executable's output.
@ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;

# When possible, create a "-z"-testing variant of each test.
sub add_z_variants($)
{
  my ($tests) = @_;
  my @new;
 TEST:
  foreach my $t (@$tests)
    {
      push @new, $t;

      # skip the obsolete-syntax tests
      $t->[0] =~ /^obs-plus/
        and next;

      my @args;
      my @list_of_hash;

      foreach my $e (@$t)
        {
          !ref $e
            and push (@args, $e), next;

          ref $e && ref $e eq 'HASH'
            or (warn "$0: $t->[0]: unexpected entry type\n"), next;
          my $tmp = $e;
          foreach my $k (qw(IN OUT))
            {
              my $val = $e->{$k};
              # skip any test whose input or output already contains a NUL byte
              if (defined $val)
                {
                  $val =~ /\0/
                    and next TEST;

                  # Convert each NL in input or output to \0.
                  $val =~ s/\n/\0/g;
                  $tmp = {$k => $val};
                  last;
                }
            }
          push @list_of_hash, $tmp;
        }

      shift @args; # discard test name

      # skip any test that uses the -z option
      grep /z/, @args
        and next;

      push @new, ["$t->[0]-z", '-z', @args, @list_of_hash];
    }
  return @new;
}

# I've only ever triggered the problem in a non-C locale.
my $locale = $ENV{LOCALE_FR};
! defined $locale || $locale eq 'none'
  and CuSkip::skip "$prog: skipping this test -- no appropriate locale\n";

# See if isblank returns true for nbsp.
my $x = qx!env printf '\xa0'| LC_ALL=$locale tr '[:blank:]' x!;
# If so, expect just one line of output in the schar test.
# Otherwise, expect two.
my $in = " y z\n\xa0 y z\n";
my $schar_exp = $x eq 'x' ? " y z\n" : $in;

my @Tests =
(
  # Test for a subtle, system-and-locale-dependent bug in uniq.
 ['schar', '-f1',  {IN => $in}, {OUT => $schar_exp},
  {ENV => "LC_ALL=$locale"}],
 ['1', '', {IN=>''}, {OUT=>''}],
 ['2', '', {IN=>"a\na\n"}, {OUT=>"a\n"}],
 ['3', '', {IN=>"a\na"}, {OUT=>"a\n"}],
 ['4', '', {IN=>"a\nb"}, {OUT=>"a\nb\n"}],
 ['5', '', {IN=>"a\na\nb"}, {OUT=>"a\nb\n"}],
 ['6', '', {IN=>"b\na\na\n"}, {OUT=>"b\na\n"}],
 ['7', '', {IN=>"a\nb\nc\n"}, {OUT=>"a\nb\nc\n"}],

 # Ensure that newlines are not interpreted with -z.
 ['2z', '-z', {IN=>"a\na\n"}, {OUT=>"a\na\n\0"}],
 ['3z', '-z', {IN=>"a\na"}, {OUT=>"a\na\0"}],
 ['4z', '-z', {IN=>"a\nb"}, {OUT=>"a\nb\0"}],
 ['5z', '-z', {IN=>"a\na\nb"}, {OUT=>"a\na\nb\0"}],
 ['20z', '-dz', {IN=>"a\na\n"}, {OUT=>""}],

 # Make sure that eight bit characters work
 ['8', '', {IN=>"ö\nv\n"}, {OUT=>"ö\nv\n"}],
 # Test output of -u option; only unique lines
 ['9', '-u', {IN=>"a\na\n"}, {OUT=>""}],
 ['10', '-u', {IN=>"a\nb\n"}, {OUT=>"a\nb\n"}],
 ['11', '-u', {IN=>"a\nb\na\n"}, {OUT=>"a\nb\na\n"}],
 ['12', '-u', {IN=>"a\na\n"}, {OUT=>""}],
 ['13', '-u', {IN=>"a\na\n"}, {OUT=>""}],
 #['5',  '-u',  "a\na\n",          "",                0],
 # Test output of -d option; only repeated lines
 ['20', '-d', {IN=>"a\na\n"}, {OUT=>"a\n"}],
 ['21', '-d', {IN=>"a\nb\n"}, {OUT=>""}],
 ['22', '-d', {IN=>"a\nb\na\n"}, {OUT=>""}],
 ['23', '-d', {IN=>"a\na\nb\n"}, {OUT=>"a\n"}],
 # Check the key options
 # If we skip over fields or characters, is the output deterministic?
 ['obs30', '-1', {IN=>"a a\nb a\n"}, {OUT=>"a a\n"}],
 ['31', qw(-f 1), {IN=>"a a\nb a\n"}, {OUT=>"a a\n"}],
 ['32', qw(-f 1), {IN=>"a a\nb b\n"}, {OUT=>"a a\nb b\n"}],
 ['33', qw(-f 1), {IN=>"a a a\nb a c\n"}, {OUT=>"a a a\nb a c\n"}],
 ['34', qw(-f 1), {IN=>"b a\na a\n"}, {OUT=>"b a\n"}],
 ['35', qw(-f 2), {IN=>"a a c\nb a c\n"}, {OUT=>"a a c\n"}],
 # Skip over characters.
 ['obs-plus40', '+1', {IN=>"aaa\naaa\n"}, {OUT=>"aaa\n"}],
 ['obs-plus41', '+1', {IN=>"baa\naaa\n"}, {OUT=>"baa\n"}],
 ['42', qw(-s 1), {IN=>"aaa\naaa\n"}, {OUT=>"aaa\n"}],
 ['43', qw(-s 2), {IN=>"baa\naaa\n"}, {OUT=>"baa\n"}],
 ['obs-plus44', qw(+1 --), {IN=>"aaa\naaa\n"}, {OUT=>"aaa\n"}],
 ['obs-plus45', qw(+1 --), {IN=>"baa\naaa\n"}, {OUT=>"baa\n"}],
 # Skip over fields and characters
 ['50', qw(-f 1 -s 1), {IN=>"a aaa\nb ab\n"}, {OUT=>"a aaa\nb ab\n"}],
 ['51', qw(-f 1 -s 1), {IN=>"a aaa\nb aaa\n"}, {OUT=>"a aaa\n"}],
 ['52', qw(-s 1 -f 1), {IN=>"a aaa\nb ab\n"}, {OUT=>"a aaa\nb ab\n"}],
 ['53', qw(-s 1 -f 1), {IN=>"a aaa\nb aaa\n"}, {OUT=>"a aaa\n"}],
 # Fixed in 2.0.15
 ['54', qw(-s 4), {IN=>"abc\nabcd\n"}, {OUT=>"abc\n"}],
 # Supported in 2.0.15
 ['55', qw(-s 0), {IN=>"abc\nabcd\n"}, {OUT=>"abc\nabcd\n"}],
 ['56', qw(-s 0), {IN=>"abc\n"}, {OUT=>"abc\n"}],
 ['57', qw(-w 0), {IN=>"abc\nabcd\n"}, {OUT=>"abc\n"}],
 # Only account for a number of characters
 ['60', qw(-w 1), {IN=>"a a\nb a\n"}, {OUT=>"a a\nb a\n"}],
 ['61', qw(-w 3), {IN=>"a a\nb a\n"}, {OUT=>"a a\nb a\n"}],
 ['62', qw(-w 1 -f 1), {IN=>"a a a\nb a c\n"}, {OUT=>"a a a\n"}],
 ['63', qw(-f 1 -w 1), {IN=>"a a a\nb a c\n"}, {OUT=>"a a a\n"}],
 # The blank after field one is checked too
 ['64', qw(-f 1 -w 4), {IN=>"a a a\nb a c\n"}, {OUT=>"a a a\nb a c\n"}],
 ['65', qw(-f 1 -w 3), {IN=>"a a a\nb a c\n"}, {OUT=>"a a a\n"}],
 # Make sure we don't break if the file contains \0
 ['90', '', {IN=>"a\0a\na\n"}, {OUT=>"a\0a\na\n"}],
 # Check fields seperated by tabs and by spaces
 ['91', '', {IN=>"a\ta\na a\n"}, {OUT=>"a\ta\na a\n"}],
 ['92', qw(-f 1), {IN=>"a\ta\na a\n"}, {OUT=>"a\ta\na a\n"}],
 ['93', qw(-f 2), {IN=>"a\ta a\na a a\n"}, {OUT=>"a\ta a\n"}],
 ['94', qw(-f 1), {IN=>"a\ta\na\ta\n"}, {OUT=>"a\ta\n"}],
 # Check the count option; add tests for other options too
 ['101', '-c', {IN=>"a\nb\n"}, {OUT=>"      1 a\n      1 b\n"}],
 ['102', '-c', {IN=>"a\na\n"}, {OUT=>"      2 a\n"}],
 # Check the local -D (--all-repeated) option
 ['110', '-D', {IN=>"a\na\n"}, {OUT=>"a\na\n"}],
 ['111', qw(-D -w1), {IN=>"a a\na b\n"}, {OUT=>"a a\na b\n"}],
 ['112', qw(-D -c), {IN=>"a a\na b\n"}, {OUT=>""}, {EXIT=>1}, {ERR=>
  "$prog: printing all duplicated lines and repeat counts is meaningless\n$try"}
  ],
 ['113', '--all-repeated=separate', {IN=>"a\na\n"}, {OUT=>"a\na\n"}],
 ['114', '--all-repeated=separate',
  {IN=>"a\na\nb\nc\nc\n"}, {OUT=>"a\na\n\nc\nc\n"}],
 ['115', '--all-repeated=separate',
  {IN=>"a\na\nb\nb\nc\n"}, {OUT=>"a\na\n\nb\nb\n"}],
 ['116', '--all-repeated=prepend', {IN=>"a\na\n"}, {OUT=>"\na\na\n"}],
 ['117', '--all-repeated=prepend',
  {IN=>"a\na\nb\nc\nc\n"}, {OUT=>"\na\na\n\nc\nc\n"}],
 ['118', '--all-repeated=prepend', {IN=>"a\nb\n"}, {OUT=>""}],
 ['119', '--all-repeated=badoption', {IN=>"a\n"}, {OUT=>""}, {EXIT=>1},
  {ERR=>"$prog: invalid argument 'badoption' for '--all-repeated'\n"
        . "Valid arguments are:\n"
        . "  - 'none'\n"
        . "  - 'prepend'\n"
        . "  - 'separate'\n"
        . $try}],
 # Check that -d and -u suppress all output, as POSIX requires.
 ['120', qw(-d -u), {IN=>"a\na\n\b"}, {OUT=>""}],
 ['121', "-d -u -w$limits->{UINTMAX_OFLOW}", {IN=>"a\na\n\b"}, {OUT=>""}],
 ['122', "-d -u -w$limits->{SIZE_OFLOW}", {IN=>"a\na\n\b"}, {OUT=>""}],
 # Check that --zero-terminated is synonymous with -z.
 ['123', '--zero-terminated', {IN=>"a\na\nb"}, {OUT=>"a\na\nb\0"}],
 ['124', '--zero-terminated', {IN=>"a\0a\0b"}, {OUT=>"a\0b\0"}],
);

# Set _POSIX2_VERSION=199209 in the environment of each obs-plus* test.
foreach my $t (@Tests)
  {
    $t->[0] =~ /^obs-plus/
      and push @$t, {ENV=>'_POSIX2_VERSION=199209'};
  }

@Tests = add_z_variants \@Tests;
@Tests = triple_test \@Tests;

my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};

my $fail = run_tests ($prog, $prog, \@Tests, $save_temps, $verbose);
exit $fail;