dnl PSPP - a program for statistical analysis.
dnl Copyright (C) 2017 Free Software Foundation, Inc.
dnl
dnl This program is free software: you can redistribute it and/or modify
dnl it under the terms of the GNU General Public License as published by
dnl the Free Software Foundation, either version 3 of the License, or
dnl (at your option) any later version.
dnl
dnl This program is distributed in the hope that it will be useful,
dnl but WITHOUT ANY WARRANTY; without even the implied warranty of
dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
dnl GNU General Public License for more details.
dnl
dnl You should have received a copy of the GNU General Public License
dnl along with this program.  If not, see <http://www.gnu.org/licenses/>.
dnl
AT_BANNER([SORT CASES])

m4_divert_push([PREPARE_TESTS])
[sort_cases_gen_data () {
  cat > gen-data.py <<'EOF'
#! /usr/bin/python3

import random
import sys

data = []
for i in range(int(sys.argv[1])):
    data += [i] * int(sys.argv[2])
random.shuffle(data)

data_txt = open('data.txt', 'w')
for i, item in enumerate(data):
    data_txt.write('%s %s\n' % (item, i))
data_txt.close()

shuffled = ((item, i) for i, item in enumerate(data))
expout = open('expout', 'w')
for item, i in sorted(shuffled):
    expout.write(' %8d %8d \n' % (item, i))
expout.close()
EOF
  $PYTHON3 gen-data.py "$@"]
}
m4_divert_pop([PREPARE_TESTS])

m4_define([SORT_CASES_TEST],
  [AT_SETUP([sort m4_eval([$1 * $2]) cases[]m4_if([$2], [1], [], [ ($1 unique)])[]m4_if([$3], [], [], [ with $3 buffers])])
   AT_KEYWORDS([SORT CASES $4])
   AT_CHECK([sort_cases_gen_data $1 $2 $3])
   AT_CAPTURE_FILE([data.txt])
   AT_CAPTURE_FILE([output.txt])
   AT_CAPTURE_FILE([sort-cases.sps])
   AT_DATA([sort-cases.sps], [dnl
DATA LIST LIST NOTABLE FILE='data.txt'/x y (F8).
SORT CASES BY x[]m4_if([$3], [], [], [/BUFFERS=$3]).
PRINT OUTFILE='output.txt'/x y.
EXECUTE.
])
   AT_CHECK([pspp --testing-mode -o pspp.csv sort-cases.sps])
   AT_CHECK([cat output.txt], [0], [expout])
   AT_CLEANUP])

SORT_CASES_TEST(100, 5, 2)
SORT_CASES_TEST(100, 5, 3)
SORT_CASES_TEST(100, 5, 4)
SORT_CASES_TEST(100, 5, 5)
SORT_CASES_TEST(100, 5, 10)
SORT_CASES_TEST(100, 5, 50)
SORT_CASES_TEST(100, 5, 100)
SORT_CASES_TEST(100, 5)

SORT_CASES_TEST(100, 10, 2)
SORT_CASES_TEST(100, 10, 3)
SORT_CASES_TEST(100, 10, 5)
SORT_CASES_TEST(100, 10)

SORT_CASES_TEST(1000, 5, 5, slow)
SORT_CASES_TEST(1000, 5, 50, slow)
SORT_CASES_TEST(1000, 5, [], slow)

SORT_CASES_TEST(100, 100, 3, slow)
SORT_CASES_TEST(100, 100, 5, slow)
SORT_CASES_TEST(100, 100, [], slow)

SORT_CASES_TEST(10000, 5, 500, slow)

SORT_CASES_TEST(50000, 1, [], slow)

dnl Bug #33089 caused SORT CASES to delete filtered cases permanently.
AT_SETUP([SORT CASES preserves filtered cases])
AT_DATA([sort-cases.sps], [dnl
DATA LIST FREE /x.
BEGIN DATA.
5 4 3 2 1 0
END DATA.
COMPUTE mod2 = MOD(x, 2).
LIST.
FILTER BY mod2.
LIST.
SORT CASES BY x.
LIST.
FILTER OFF.
LIST.
])
AT_CHECK([pspp -O format=csv sort-cases.sps], [0], [dnl
Table: Data List
x,mod2
5.00,1.00
4.00,.00
3.00,1.00
2.00,.00
1.00,1.00
.00,.00

Table: Data List
x,mod2
5.00,1.00
3.00,1.00
1.00,1.00

Table: Data List
x,mod2
1.00,1.00
3.00,1.00
5.00,1.00

Table: Data List
x,mod2
.00,.00
1.00,1.00
2.00,.00
3.00,1.00
4.00,.00
5.00,1.00
])
AT_CLEANUP