Created
June 4, 2015 17:08
-
-
Save indraniel/a31f7ad3d0750c4a1d95 to your computer and use it in GitHub Desktop.
Filter for NCBI SRA documents (produced by "srasearch init-dump/increment-dump") that have have been "Received" after a certain time point
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use warnings; | |
use strict; | |
use DateTime; | |
use DateTime::Format::Strptime; | |
use IO::Uncompress::Gunzip qw($GunzipError); | |
use JSON; | |
my $input_dump = $ARGV[0]; | |
my $threshold_date = $ARGV[1]; | |
unless ($input_dump) { | |
die "[err] Please supply an SRA Dump as input!\n"; | |
} | |
unless ($threshold_date) { | |
die "[err] Please supply a threshold_date (YYYY-MM-DD) as input!\n"; | |
} | |
filter($input_dump, $threshold_date); | |
exit(0); | |
sub filter { | |
my ($input_dump, $threshold_date) = @_; | |
my $z = IO::Uncompress::Gunzip->new( $input_dump ) | |
or die "IO::Uncompress::Gunzip failed: $GunzipError\n"; | |
my $strp = DateTime::Format::Strptime->new(pattern => '%Y-%m-%dT%H:%M:%SZ'); | |
my $threshold = $strp->parse_datetime(join('T', $threshold_date, '00:00:00Z')); | |
while (my $line = <$z>) { | |
chomp($line); | |
my ($id, $json) = split(/,/, $line, 2); | |
#print $id, "\n"; | |
#print $json, "\n"; | |
my $entry = decode_json($json); | |
my $received = $strp->parse_datetime($entry->{'Received'} ); | |
if (keep($received, $threshold)) { | |
print $line, "\n"; | |
} | |
} | |
} | |
sub keep { | |
my ($received, $threshold) = @_; | |
my $delta = $received - $threshold; | |
if ($delta->is_zero || $delta->is_positive) { | |
return 1; | |
} | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment