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([BEGIN DATA])

# BEGIN DATA can run as a command in itself, or it can appear as part
# of the first procedure.  First, test it after a procedure.
AT_SETUP([BEGIN DATA as part of a procedure])
AT_DATA([begin-data.sps], [dnl
TITLE 'Test BEGIN DATA ... END DATA'.

DATA LIST /a b 1-2.
LIST.
BEGIN DATA.
12
34
56
78
90
END DATA.
])
AT_CHECK([pspp -O format=csv begin-data.sps], [0], [dnl
Table: Reading 1 record from INLINE.
Variable,Record,Columns,Format
a,1,1-1,F1.0
b,1,2-2,F1.0

Table: Data List
a,b
1,2
3,4
5,6
7,8
9,0
])
AT_CLEANUP

# Also test BEGIN DATA as an independent command.
AT_SETUP([BEGIN DATA as an independent command])
AT_DATA([begin-data.sps], [dnl
data list /A B 1-2.
begin data.
09
87
65
43
21
end data.
list.
])
AT_CHECK([pspp -O format=csv begin-data.sps], [0], [dnl
Table: Reading 1 record from INLINE.
Variable,Record,Columns,Format
A,1,1-1,F1.0
B,1,2-2,F1.0

Table: Data List
A,B
0,9
8,7
6,5
4,3
2,1
])
AT_CLEANUP

m4_define([DATA_READER_BINARY],
  [AT_SETUP([read and write files with $1])
$3
   AT_DATA([input.txt], [dnl
07-22-2007
10-06-2007
321
07-14-1789
08-26-1789
4
01-01-1972
12-31-1999
682
])
   AT_DATA([make-binary.py], [[
#! /usr/bin/python3

import struct
import sys

# This random number generator and the test for it below are drawn
# from Park and Miller, "Random Number Generators: Good Ones are Hard
# to Come By", Communications of the ACM 31:10 (October 1988).  It is
# documented to function properly on systems with a 46-bit or longer
# real significand, which includes systems that have 64-bit IEEE reals
# (with 53-bit significand).  The test should catch any systems for
# which this is not true, in any case.
def my_rand(modulus):
    global seed
    a = 16807
    m = 2147483647
    tmp = a * seed
    seed = tmp - m * (tmp // m)
    return seed % modulus

# Test the random number generator for reproducibility,
# then reset the seed
seed = 1
for i in range(10000):
    my_rand(1)
assert seed == 1043618065
seed = 1

# ASCII to EBCDIC translation table
ascii2ebcdic = (
    0x00, 0x01, 0x02, 0x03, 0x37, 0x2d, 0x2e, 0x2f, 
    0x16, 0x05, 0x25, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, 
    0x10, 0x11, 0x12, 0x13, 0x3c, 0x3d, 0x32, 0x26, 
    0x18, 0x19, 0x3f, 0x27, 0x1c, 0x1d, 0x1e, 0x1f, 
    0x40, 0x5a, 0x7f, 0x7b, 0x5b, 0x6c, 0x50, 0x7d, 
    0x4d, 0x5d, 0x5c, 0x4e, 0x6b, 0x60, 0x4b, 0x61, 
    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 
    0xf8, 0xf9, 0x7a, 0x5e, 0x4c, 0x7e, 0x6e, 0x6f, 
    0x7c, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 
    0xc8, 0xc9, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 
    0xd7, 0xd8, 0xd9, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 
    0xe7, 0xe8, 0xe9, 0xad, 0xe0, 0xbd, 0x9a, 0x6d, 
    0x79, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 
    0x88, 0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 
    0x97, 0x98, 0x99, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 
    0xa7, 0xa8, 0xa9, 0xc0, 0x4f, 0xd0, 0x5f, 0x07, 
    0x20, 0x21, 0x22, 0x23, 0x24, 0x15, 0x06, 0x17, 
    0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x09, 0x0a, 0x1b, 
    0x30, 0x31, 0x1a, 0x33, 0x34, 0x35, 0x36, 0x08, 
    0x38, 0x39, 0x3a, 0x3b, 0x04, 0x14, 0x3e, 0xe1, 
    0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 
    0x49, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 
    0x58, 0x59, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 
    0x68, 0x69, 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 
    0x76, 0x77, 0x78, 0x80, 0x8a, 0x8b, 0x8c, 0x8d, 
    0x8e, 0x8f, 0x90, 0x6a, 0x9b, 0x9c, 0x9d, 0x9e, 
    0x9f, 0xa0, 0xaa, 0xab, 0xac, 0x4a, 0xae, 0xaf, 
    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 
    0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xa1, 0xbe, 0xbf, 
    0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xda, 0xdb, 
    0xdc, 0xdd, 0xde, 0xdf, 0xea, 0xeb, 0xec, 0xed, 
    0xee, 0xef, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff)
assert len(ascii2ebcdic) == 256

def a2e(s):
    return bytearray((ascii2ebcdic[ord(c)] for c in s))

def dump_records(out, records):
    while records:
        n = min(my_rand(5) + 1, len(records))
        r = records[:n]
        records[:n] = []

        count = sum((len(rec) for rec in r))
        out.buffer.write(struct.pack(">H xx", count + 4))
        for rec in r:
            out.buffer.write(rec)

data = []
for line in open('input.txt', 'r'):
    data += [line.rstrip('\r\n')]

# MODE=BINARY
out = open('binary.bin', 'w')
for item in data:
    reclen = struct.pack("<I", len(item))
    out.buffer.write(reclen)
    out.buffer.write(bytearray([ord(c) for c in item]))
    out.buffer.write(reclen)
out.close()
    
# MODE=360 /RECFORM=FIXED /LRECL=32
out = open('fixed.bin', 'w')
lrecl = 32
for item in data:
    s = item[:lrecl]
    s += ' ' * (lrecl - len(s))
    assert len(s) == 32
    out.buffer.write(a2e(s))
out.close()

# MODE=360 /RECFORM=VARIABLE
out = open('variable.bin', 'w')
records = []
for item in data:
    records += [struct.pack('>H xx', len(item) + 4) + a2e(item)]
dump_records(out, records)
out.close()

# MODE=360 /RECFORM=SPANNED
out = open('spanned.bin', 'w')
records = []
for line in data:
    r = []
    while line:
        n = min(my_rand(5), len(line))
        r += [line[:n]]
        line = line[n:]
    for i, s in enumerate(r):
        scc = (0 if len(r) == 1
               else 1 if i == 0
               else 2 if i == len(r) - 1
               else 3)
        records += [struct.pack('>H B x', len(s) + 4, scc) + a2e(s)]
dump_records(out, records)
out.close()
]])
   AT_CHECK([$PYTHON3 make-binary.py])
   AT_DATA([data-reader.sps], [dnl
FILE HANDLE input/NAME='$2'/$1.
DATA LIST FIXED FILE=input NOTABLE
	/1 start 1-10 (ADATE)
	/2 end 1-10 (ADATE)
	/3 count 1-3.
LIST.

* Output the data to a new file in the same format.
FILE HANDLE OUTPUT/NAME='output.bin'/$1.
COMPUTE count=count + 1.
PRINT OUTFILE=output/start end count.
EXECUTE.
])
   AT_CHECK([pspp -O format=csv data-reader.sps], [0], [dnl
Table: Data List
start,end,count
07/22/2007,10/06/2007,321
07/14/1789,08/26/1789,4
01/01/1972,12/31/1999,682
])
   AT_CHECK([test -s output.bin])
   AT_DATA([data-reader-2.sps], [dnl
* Re-read the new data and list it, to verify that it was written correctly.
FILE HANDLE OUTPUT/NAME='output.bin'/$1.
DATA LIST FIXED FILE=output NOTABLE/
	start 2-11 (ADATE)
	end 13-22 (ADATE)
	count 24-26.
LIST.
])
   AT_CHECK([pspp -O format=csv data-reader-2.sps], [0], [dnl
Table: Data List
start,end,count
07/22/2007,10/06/2007,322
07/14/1789,08/26/1789,5
01/01/1972,12/31/1999,683
])
   AT_CLEANUP])

DATA_READER_BINARY([MODE=BINARY], [binary.bin])
DATA_READER_BINARY([MODE=360 /RECFORM=FIXED /LRECL=32], [fixed.bin],
  [AT_CHECK([i18n-test supports_encodings EBCDIC-US])])
DATA_READER_BINARY([MODE=360 /RECFORM=VARIABLE], [variable.bin],
  [AT_CHECK([i18n-test supports_encodings EBCDIC-US])])
DATA_READER_BINARY([MODE=360 /RECFORM=SPANNED], [spanned.bin],
  [AT_CHECK([i18n-test supports_encodings EBCDIC-US])])