#!/usr/local/bin/perl
#
$TITLE = 'ReadSeq.pl v.1.1 - a WWW interface for readseq';
$COPYRIGHT = 'Copyright (c) 1996-1997,
ISHIKAWA Jun';
$DATE = '$Date: 1997/02/22 20:17:15 $';
#
# This program is provided free of charge to educational, charity or
# not-for-profit organisations provided the Copyright notice remains intact.
# Commercial organizations should contact the author for licensing details.
# No warranty is made, either expressed or implied. `USE AT YOUR OWN RISK'.
#
#------------ You must set the following variable --------------
# Where is your readseq binary?
$READSEQ = "/home/bioact/jun/bin/sparc/readseq";
#------------ No further configuration required -----------------
alarm(600); # Timeout: generate SIGALRM after 10 min.
$SIG{'INT'} = $SIG{'TERM'} =
$SIG{'STOP'} = $SIG{'QUIT'} = $SIG{'ALRM'} = '&stop';
#get data
if ($ENV{'REQUEST_METHOD'} eq "POST") {
read(STDIN, $buffer, $ENV{'CONTENT_LENGTH'});
%FORM = &parse($buffer);
&cooking;
} else {
&print_form;
}
exit;
# -------- subroutines --------
sub cooking {
$|=1; # force flush buffer
print "Content-Type: text/html\n\n";
print "Result: $FORM{'format'} format\n";
print "\n";
print "";
open(CMD,"| $READSEQ -p -f=$FORM{'format'} $FORM{'case'} $FORM{'reverse'} $FORM{'opt'}");
print CMD $FORM{'sequence'},"\n";
close(CMD);
print "";
}
sub parse { # parse parameters
local(%form, @pairs, $name, $value);
@pairs = split(/&/,$_[0]);
foreach (@pairs) {
($name, $value) = split /=/;
$value =~ tr/\+/ /;
$value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex($1))/eg;
$form{$name} = $value;
}
return %form;
}
sub stop { exit 1; }
sub print_form {
print <<"HTML";
Content-Type: text/html
$TITLE
$TITLE*
$DATE
$COPYRIGHT
Source code (Perl script) is available.
The brief usage of options is as follows. The ``[ ]'' denote
optional parts of the syntax:
options
-a[ll] select All sequences
-degap[=-] remove gap symbols
-i[tem=2,3,4] select Item number(s) from several
-l[ist] List sequences only
-r[everse] change to Reverse-complement
Pretty format options:
-wid[th]=# sequence line width
-tab=# left indent
-col[space]=# column space within sequence line on output
-gap[count] count gap chars in sequence numbers
-nameleft, -nameright[=#] name on left/right side [=max width]
-nametop name at top/bottom
-numleft, -numright seq index on left/right side
-numtop, -numbot index on top/bottom
-match[=.] use match base for 2..n species
-inter[line=#] blank line(s) between sequence blocks
*
Readseq reads and writes nucleic/protein sequences in various
formats. Data files may have multiple sequences.
Readseq, copyright 1990 by
D.G. Gilbert,
is particularly useful as it automatically detects many
sequence formats, and interconverts among them.
Change Log
- Version 1.1
- Substituted
\$ENB{'SCRIPT_NAME'}
for \$CGIPATH.
Moved -all option to "Other option(s)".
- Version 1.0
- Initial release.
HTML
}
# ------- end of readseq.pl -------