tests: change copyright year from 2011 to 2012 in sample-test
[coreutils/ericb.git] / tests / misc / join
bloba892a10d24870ef63ea9ebb80bff87132b79b2c5
1 #!/usr/bin/perl
2 # Test join.
4 # Copyright (C) 2008-2011 Free Software Foundation, Inc.
6 # This program is free software: you can redistribute it and/or modify
7 # it under the terms of the GNU General Public License as published by
8 # the Free Software Foundation, either version 3 of the License, or
9 # (at your option) any later version.
11 # This program is distributed in the hope that it will be useful,
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 # GNU General Public License for more details.
16 # You should have received a copy of the GNU General Public License
17 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19 use strict;
21 my $limits = getlimits ();
23 # Turn off localization of executable's output.
24 @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
26 my $prog = 'join';
28 my $delim = chr 0247;
29 sub t_subst ($)
31 (my $s = $_[0]) =~ s/:/$delim/g;
32 return $s;
35 my @tv = (
36 # test name
37 # flags file-1 file-2 expected output expected return code
39 ['1a', '-a1', ["a 1\n", "b\n"], "a 1\n", 0],
40 ['1b', '-a2', ["a 1\n", "b\n"], "b\n", 0], # Got "\n"
41 ['1c', '-a1 -a2', ["a 1\n", "b\n"], "a 1\nb\n", 0], # Got "a 1\n\n"
42 ['1d', '-a1', ["a 1\nb\n", "b\n"], "a 1\nb\n", 0],
43 ['1e', '-a2', ["a 1\nb\n", "b\n"], "b\n", 0],
44 ['1f', '-a2', ["b\n", "a\nb\n"], "a\nb\n", 0],
46 ['2a', '-a1 -e .', ["a\nb\nc\n", "a x y\nb\nc\n"], "a x y\nb\nc\n", 0],
47 ['2b', '-a1 -e . -o 2.1,2.2,2.3', ["a\nb\nc\n", "a x y\nb\nc\n"],
48 "a x y\nb . .\nc . .\n", 0],
49 ['2c', '-a1 -e . -o 2.1,2.2,2.3', ["a\nb\nc\nd\n", "a x y\nb\nc\n"],
50 "a x y\nb . .\nc . .\n. . .\n", 0],
52 ['3a', '-t:', ["a:1\nb:1\n", "a:2:\nb:2:\n"], "a:1:2:\nb:1:2:\n", 0],
54 # operate on whole line (as sort does by default)
55 ['3b', '-t ""', ["a 1\nb 1\n", "a 1\nb 2\n"], "a 1\n", 0],
56 # use NUL as the field delimiter
57 ['3c', '-t "\\0"', ["a\0a\n", "a\0b\n"], "a\0a\0b\n", 0],
59 # Just like -a1 and -a2 when there are no pairable lines
60 ['4a', '-v 1', ["a 1\n", "b\n"], "a 1\n", 0],
61 ['4b', '-v 2', ["a 1\n", "b\n"], "b\n", 0],
63 ['4c', '-v 1', ["a 1\nb\n", "b\n"], "a 1\n", 0],
64 ['4d', '-v 2', ["a 1\nb\n", "b\n"], "", 0],
65 ['4e', '-v 2', ["b\n", "a 1\nb\n"], "a 1\n", 0],
66 ['5a', '-a1 -e - -o 1.1,2.2',
67 ["a 1\nb 2\n", "a 11\nb\n"], "a 11\nb -\n", 0],
68 ['5b', '-a1 -e - -o 1.1,2.2',
69 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\nfeb 15"],
70 "apr 06\naug 14\ndec -\nfeb 15\n", 0],
71 ['5c', '-a1 -e - -o 1.1,2.2',
72 ["aug 20\ndec 18\n", "aug 14\ndate\nfeb 15"],
73 "aug 14\ndec -\n", 0],
74 ['5d', '-a1 -e - -o 1.1,2.2',
75 ["dec 18\n", ""], "dec -\n", 0],
76 ['5e', '-a2 -e - -o 1.1,2.2',
77 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\nfeb 15\n"],
78 "apr 06\naug 14\n- -\nfeb 15\n", 0],
79 ['5f', '-a2 -e - -o 2.2,1.1',
80 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\nfeb 15\n"],
81 "06 apr\n14 aug\n- -\n15 feb\n", 0],
82 ['5g', '-a1 -e - -o 2.2,1.1',
83 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\nfeb 15\n"],
84 "06 apr\n14 aug\n- dec\n15 feb\n", 0],
86 ['5h', '-a1 -e - -o 2.2,1.1',
87 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\n"],
88 "06 apr\n14 aug\n- dec\n- feb\n", 0],
89 ['5i', '-a1 -e - -o 1.1,2.2',
90 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\n"],
91 "apr 06\naug 14\ndec -\nfeb -\n", 0],
93 ['5j', '-a2 -e - -o 2.2,1.1',
94 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\n"],
95 "06 apr\n14 aug\n- -\n", 0],
96 ['5k', '-a2 -e - -o 2.2,1.1',
97 ["apr 15\naug 20\ndec 18\nfeb 05\n", "apr 06\naug 14\ndate\n"],
98 "06 apr\n14 aug\n- -\n", 0],
100 ['5l', '-a1 -e - -o 2.2,1.1',
101 ["apr 15\naug 20\ndec 18\n", "apr 06\naug 14\ndate\nfeb 15\n"],
102 "06 apr\n14 aug\n- dec\n", 0],
103 ['5m', '-a2 -e - -o 2.2,1.1',
104 ["apr 15\naug 20\ndec 18\n", "apr 06\naug 14\ndate\nfeb 15\n"],
105 "06 apr\n14 aug\n- -\n15 -\n", 0],
107 ['6a', '-e -',
108 ["a 1\nb 2\nd 4\n", "a 21\nb 22\nc 23\nf 26\n"],
109 "a 1 21\nb 2 22\n", 0],
110 ['6b', '-a1 -e -',
111 ["a 1\nb 2\nd 4\n", "a 21\nb 22\nc 23\nf 26\n"],
112 "a 1 21\nb 2 22\nd 4\n", 0],
113 ['6c', '-a1 -e -',
114 ["a 21\nb 22\nc 23\nf 26\n", "a 1\nb 2\nd 4\n"],
115 "a 21 1\nb 22 2\nc 23\nf 26\n", 0],
117 ['7a', '-a1 -e . -o 2.7',
118 ["a\nb\nc\n", "a x y\nb\nc\n"], ".\n.\n.\n", 0],
120 ['8a', '-a1 -e . -o 0,1.2',
121 ["a\nb\nc\nd G\n", "a x y\nb\nc\ne\n"],
122 "a .\nb .\nc .\nd G\n", 0],
123 ['8b', '-a1 -a2 -e . -o 0,1.2',
124 ["a\nb\nc\nd G\n", "a x y\nb\nc\ne\n"],
125 "a .\nb .\nc .\nd G\ne .\n", 0],
127 # From David Dyck
128 ['9a', '', [" a 1\n b 2\n", " a Y\n b Z\n"], "a 1 Y\nb 2 Z\n", 0],
130 # -o 'auto'
131 ['10a', '-a1 -a2 -e . -o auto',
132 ["a 1 2\nb 1\nd 1 2\n", "a 3 4\nb 3 4\nc 3 4\n"],
133 "a 1 2 3 4\nb 1 . 3 4\nc . . 3 4\nd 1 2 . .\n", 0],
134 ['10b', '-a1 -a2 -j3 -e . -o auto',
135 ["a 1 2\nb 1\nd 1 2\n", "a 3 4\nb 3 4\nc 3 4\n"],
136 "2 a 1 . .\n. b 1 . .\n2 d 1 . .\n4 . . a 3\n4 . . b 3\n4 . . c 3\n"],
137 ['10c', '-a1 -1 1 -2 4 -e. -o auto',
138 ["a 1 2\nb 1\nd 1 2\n", "a 3 4\nb 3 4\nc 3 4\n"],
139 "a 1 2 . . .\nb 1 . . . .\nd 1 2 . . .\n"],
140 ['10d', '-a2 -1 1 -2 4 -e. -o auto',
141 ["a 1 2\nb 1\nd 1 2\n", "a 3 4\nb 3 4\nc 3 4\n"],
142 ". . . a 3 4\n. . . b 3 4\n. . . c 3 4\n"],
143 ['10e', '-o auto',
144 ["a 1 2\nb 1 2 discard\n", "a 3 4\nb 3 4 discard\n"],
145 "a 1 2 3 4\nb 1 2 3 4\n"],
146 ['10f', '-t, -o auto',
147 ["a,1,,2\nb,1,2\n", "a,3,4\nb,3,4\n"],
148 "a,1,,2,3,4\nb,1,2,,3,4\n"],
150 # From Tim Smithers: fixed in 1.22l
151 ['trailing-sp', '-t: -1 1 -2 1', ["a:x \n", "a:y \n"], "a:x :y \n", 0],
153 # From Paul Eggert: fixed in 1.22n
154 ['sp-vs-blank', '', ["\f 1\n", "\f 2\n"], "\f 1 2\n", 0],
156 # From Paul Eggert: fixed in 1.22n (this would fail on Solaris7,
157 # with LC_ALL set to en_US).
158 # Unfortunately, that Solaris7's en_US locale folds case (making
159 # the first input file sorted) is not portable, so this test would
160 # fail on e.g. Linux systems, because the input to join isn't sorted.
161 # ['lc-collate', '', ["a 1a\nB 1B\n", "B 2B\n"], "B 1B 2B\n", 0],
163 # Based on a report from Antonio Rendas. Fixed in 2.0.9.
164 ['8-bit-t', t_subst "-t:",
165 [t_subst "a:1\nb:1\n", t_subst "a:2:\nb:2:\n"],
166 t_subst "a:1:2:\nb:1:2:\n", 0],
168 # fields > SIZE_MAX are silently interpreted as SIZE_MAX
169 ['bigfield1', "-1 $limits->{UINTMAX_OFLOW} -2 2",
170 ["a\n", "b\n"], " a b\n", 0],
171 ['bigfield2', "-1 $limits->{SIZE_OFLOW} -2 2",
172 ["a\n", "b\n"], " a b\n", 0],
174 # FIXME: change this to ensure the diagnostic makes sense
175 ['invalid-j', '-j x', {}, "", 1,
176 "$prog: invalid field number: `x'\n"],
178 # With ordering check, inputs in order
179 ['chkodr-1', '--check-order',
180 [" a 1\n b 2\n", " a Y\n b Z\n"], "a 1 Y\nb 2 Z\n", 0],
182 # Without check, inputs in order
183 ['chkodr-2', '--nocheck-order',
184 [" a 1\n b 2\n", " a Y\n b Z\n"], "a 1 Y\nb 2 Z\n", 0],
186 # Without check, both inputs out of order (in fact, in reverse order)
187 # but all pairable. Support for this is a GNU extension.
188 ['chkodr-3', '--nocheck-order',
189 [" b 1\n a 2\n", " b Y\n a Z\n"], "b 1 Y\na 2 Z\n", 0],
191 # The extension should work without --nocheck-order, since that is the
192 # default.
193 ['chkodr-4', '',
194 [" b 1\n a 2\n", " b Y\n a Z\n"], "b 1 Y\na 2 Z\n", 0],
196 # With check, both inputs out of order (in fact, in reverse order)
197 ['chkodr-5', '--check-order',
198 [" b 1\n a 2\n", " b Y\n a Z\n"], "", 1,
199 "$prog: chkodr-5.1:2: is not sorted: a 2\n"],
201 # Similar, but with only file 2 not sorted.
202 ['chkodr-5b', '--check-order',
203 [" a 2\n b 1\n", " b Y\n a Z\n"], "", 1,
204 "$prog: chkodr-5b.2:2: is not sorted: a Z\n"],
206 # Similar, but with the offending line having length 0 (excluding newline).
207 ['chkodr-5c', '--check-order',
208 [" a 2\n b 1\n", " b Y\n\n"], "", 1,
209 "$prog: chkodr-5c.2:2: is not sorted: \n"],
211 # Similar, but elicit a warning for each input file (without --check-order).
212 ['chkodr-5d', '',
213 ["a\nx\n\n", "b\ny\n\n"], "", 1,
214 "$prog: chkodr-5d.1:3: is not sorted: \n" .
215 "$prog: chkodr-5d.2:3: is not sorted: \n"],
217 # Similar, but make it so each offending line has no newline.
218 ['chkodr-5e', '',
219 ["a\nx\no", "b\ny\np"], "", 1,
220 "$prog: chkodr-5e.1:3: is not sorted: o\n" .
221 "$prog: chkodr-5e.2:3: is not sorted: p\n"],
223 # Without order check, both inputs out of order and some lines
224 # unpairable. This is NOT supported by the GNU extension. All that
225 # we really care about for this test is that the return status is
226 # zero, since that is the only way to actually verify that the
227 # --nocheck-order option had any effect. We don't actually want to
228 # guarantee that join produces this output on stdout.
229 ['chkodr-6', '--nocheck-order',
230 [" b 1\n a 2\n", " b Y\n c Z\n"], "b 1 Y\n", 0],
232 # Before 6.10.143, this would mistakenly fail with the diagnostic:
233 # join: File 1 is not in sorted order
234 ['chkodr-7', '-12', ["2 a\n1 b\n", "2 c\n1 d"], "", 0],
236 # After 8.9, join doesn't report disorder by default
237 # when comparing against an empty input file.
238 ['chkodr-8', '', ["2 a\n1 b\n", ""], "", 0],
240 # Test '--header' feature
241 ['header-1', '--header',
242 [ "ID Name\n1 A\n2 B\n", "ID Color\n1 red\n"], "ID Name Color\n1 A red\n", 0],
244 # '--header' with '--check-order' : The header line is out-of-order but the
245 # actual data is in order. This join should succeed.
246 ['header-2', '--header --check-order',
247 ["ID Name\n1 A\n2 B\n", "ID Color\n2 green\n"],
248 "ID Name Color\n2 B green\n", 0],
250 # '--header' with '--check-order' : The header line is out-of-order AND the
251 # actual data out-of-order. This join should fail.
252 ['header-3', '--header --check-order',
253 ["ID Name\n2 B\n1 A\n", "ID Color\n2 blue\n"], "ID Name Color\n", 1,
254 "$prog: header-3.1:3: is not sorted: 1 A\n"],
256 # '--header' with specific output format '-o'.
257 # output header line should respect the requested format
258 ['header-4', '--header -o "0,1.3,2.2"',
259 ["ID Group Name\n1 Foo A\n2 Bar B\n", "ID Color\n2 blue\n"],
260 "ID Name Color\n2 B blue\n", 0],
262 # '--header' always outputs headers from the first file
263 # even if the headers from the second file don't match
264 ['header-5', '--header',
265 [ "ID1 Name\n1 A\n2 B\n", "ID2 Color\n1 red\n"],
266 "ID1 Name Color\n1 A red\n", 0],
268 # '--header' doesn't check order of a header
269 # even if there is no header in the second file
270 ['header-6', '--header -a1',
271 [ "ID1 Name\n1 A\n", ""],
272 "ID1 Name\n1 A\n", 0],
276 # Convert the above old-style test vectors to the newer
277 # format used by Coreutils.pm.
279 my @Tests;
280 foreach my $t (@tv)
282 my ($test_name, $flags, $in, $exp, $ret, $err_msg) = @$t;
283 my $new_ent = [$test_name, $flags];
284 if (!ref $in)
286 push @$new_ent, {IN=>$in};
288 elsif (ref $in eq 'HASH')
290 # ignore
292 else
294 foreach my $e (@$in)
296 push @$new_ent, {IN=>$e};
299 push @$new_ent, {OUT=>$exp};
300 $ret
301 and push @$new_ent, {EXIT=>$ret}, {ERR=>$err_msg};
302 push @Tests, $new_ent;
305 @Tests = triple_test \@Tests;
307 my $save_temps = $ENV{DEBUG};
308 my $verbose = $ENV{VERBOSE};
310 my $fail = run_tests ($prog, $prog, \@Tests, $save_temps, $verbose);
311 exit $fail;