readseq/Stdfiles

/* Stdfiles 
	generate standard files to test readseq
*/

C
#include <stdio.h>
/* no sequence formats use chars > #126, ignore these */
main(void)
{
	int c;
	puts("> alphabet['!'..'~']");
	for (c = '!'; c <= '~'; c++) putc(c,stdout);
	putc('\n', stdout);
}

link  -w  -t MPST -c 'MPS ' c.o  <20>
		"{Libraries}"Interface.o  "{Libraries}"ToolLibs.o <20>
		"{Libraries}"Runtime.o  "{CLibraries}"StdClib.o 
link.out > alphabet.orig


C
#include <stdio.h>
main(void)
{
/* note: symbols "*" and "/" removed as terminators for various formats */
const char *aminos		= "ABCDEFGHIKLMNPQRSTVWXYZ";  
const char *primenuc	= "ACGTU";
const char *allsymbols 	= "_.-?<>{}[]()!@#$%^&=+;:'|`~\"\\";

	char *c, all[256];
	int	count;
	
	strcpy(all, aminos);
	strcat(all, primenuc);
	strcat(all, allsymbols);
	puts("> nucleic/amino test");
	for (count=0; count<4; count++) {
		for (c = all; *c!=0; c++) putc(*c, stdout);
		putc('\n', stdout);
		}
}

link  -w  -t MPST -c 'MPS ' c.o  <20>
		"{Libraries}"Interface.o  "{Libraries}"ToolLibs.o <20>
		"{Libraries}"Runtime.o  "{CLibraries}"StdClib.o 
link.out > nucleic.std

#--------------------------

#standards (ship w/ readseq)
#note: not all alphabet.orig chars are expected to be passed by
#     readseq.  Numbers are dropped.
readseq -p alphabet.orig > alphabet.std
readseq -p -C  alphabet.std > upper.std

cat alphabet.orig
	> alphabet['!'..'~']
	!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~

cat alphabet.std
	>alphabet['!'..'~'], 83 bases, 9429 checksum.
	!"#$%&'()*+-./:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]
	^_`abcdefghijklmnopqrstuvwxyz{|}~

cat upper.std
	>alphabet['!'..'~'], 83 bases, 9429 checksum.
	!"#$%&'()*+-./:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]
	^_`ABCDEFGHIJKLMNOPQRSTUVWXYZ{|}~

cat nucleic.std
	> nucleic/amino test
	ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}[]()!@#$%^&=+;:'|`~"\
	ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}[]()!@#$%^&=+;:'|`~"\
	ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}[]()!@#$%^&=+;:'|`~"\
	ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}[]()!@#$%^&=+;:'|`~"\

readseq -p nucleic.std
	>nucleic/amino test, 228 bases, 5952 checksum.
	ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}[]()!@#$%^&=+;
	:'|`~"\ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}[]()!@#
	$%^&=+;:'|`~"\ABCDEFGHIKLMNPQRSTVWXYZACGTU_.-?<>{}
	[]()!@#$%^&=+;:'|`~"\ABCDEFGHIKLMNPQRSTVWXYZACGTU_
	.-?<>{}[]()!@#$%^&=+;:'|`~"\


#----------------------------------

#test for general read/write of all chars:
readseq -p alphabet.std -otest.alpha
diff test.alpha alphabet.std

#test for valid toupper, general read/write:
readseq -p -C  alphabet.std -otest.upper
diff test.upper upper.std
#for vms, use "-C" to preserve case
# readseq -p "-C"  alphabet.std -otest.upper

#test for multiple sequence file conversions
# leave out gcg, raw; 
# test of long seq conversion ?
# test of mail-header seq conversion ?

#test for valid format conversions
readseq -v -p -f1 nucleic.std -otest.f1
readseq -v -p -f2 test.f1 -otest.f2
readseq -v -p -f3 test.f2 -otest.f3
readseq -v -p -f4 test.f3 -otest.f4
readseq -v -p -f5 test.f4 -otest.f5
readseq -v -p -f6 test.f5 -otest.f6
readseq -v -p -f7 test.f6 -otest.f7
readseq -v -p -f8 test.f7 -otest.f8
readseq -v -p -f1 test.f8 -otest.f1b   
diff test.f1 test.f1b
compare test.f1 test.f1b

readseq -v -p -f13 test.f8 -otest.f13   # raw, drops name
readseq -v -p -f9 test.f8 -otest.f9   	# zuker, little used
#readseq -v -p -f10 test.f9 -otest.f10  # olsen, input only (output=raw)
readseq -v -p -f11 test.f8 -otest.f11	# phylip 3.2, output only
readseq -v -p -f12 test.f8 -otest.f12	# phylip 3.3, output only
readseq -v -p -f14 test.f8 -otest.f14	# phylip 3.4, output only


#clean up
rm test.<2E>


#-----------------------------
# some general tests

readseq -h 

readseq