lib/CXGN/Bulk/BAC.pm

   1 package CXGN::Bulk::BAC;
   2 use strict;
   3 use warnings;
   4
   5 use CXGN::DB::DBICFactory;
   6 use CXGN::Genomic::Clone;
   7 use CXGN::Genomic::CloneIdentifiers;
   8 use CXGN::Genomic::Library;
   9 use CXGN::Tools::List qw/any/;
  10
  11 use base "CXGN::Bulk";
  12
  13 sub new {
  14     my $class = shift;
  15     my $self = $class->SUPER::new(@_);
  16
  17     #debug start#
  18     my $paramhash = $_[0];
  19     $self->debug("ID String from BAC.pm constructor");
  20     $self->debug("ids_string is " . $paramhash->{ids_string});
  21     #debug end#
  22
  23     return $self;
  24 }
  25
  26
  27
  28
  29
  30 our @field_list = qw(
  31                      chr_clone_name
  32                      cornell_clone_name
  33                      arizona_clone_name
  34                      clone_type
  35                      org_name
  36                      accession_name
  37                      library_name
  38                      estimated_length
  39                      genbank_accession
  40                     );
  41
  42 sub process_parameters
  43 {
  44     my $self = shift;
  45
  46     return 0
  47       unless length($self->{ids}) <= 1_000_000 && $self->{ids} =~ /\w/;
  48
  49     $self->{output_fields} = [grep $self->{$_} eq 'on', @field_list];
  50
  51     # clean up data retrieved
  52     my $ids = $self->{ids};
  53     $ids =~ s/[\n\s\r]+/ /g;
  54     my @ids = grep $_, split /\s+/, $ids;
  55     return 0 if @ids > 10_000; #limit to 10_000 ids to process
  56     return 0 unless any(@ids);
  57
  58     $self->{ids} = \@ids;
  59
  60     return 1; #params were OK if we got here
  61 }
  62
  63 sub process_ids
  64 {
  65     my $self = shift;
  66     $self -> {query_start_time} = time();
  67     my $dbh = $self->{db};
  68     my @output_fields = @{$self -> {output_fields}};
  69     my @notfound = ();
  70     my @return_data = ();
  71     my ($dump_fh, $notfound_fh) = $self -> create_dumpfile();
  72     my @bac_output;
  73     my $current_time= time() - $self -> {query_start_time};
  74     $self->debug("Time point 1: $current_time");
  75
  76     my $foundcount=0;
  77     my $notfoundcount=0;
  78     my $count=0;
  79
  80     my $chado = CXGN::DB::DBICFactory->open_schema('Bio::Chado::Schema');
  81
  82     # iterate through identifiers
  83     foreach my $id (@{$self->{ids}}) {
  84       $count++;
  85
  86       my $clone = CXGN::Genomic::Clone->retrieve_from_clone_name($id);
  87
  88       #ask rob if parser should choke when given zero
  89       unless ($clone) {
  90         print $notfound_fh (">$id\n");
  91         next;
  92       }
  93       my $lib = $clone->library_object;
  94
  95       # get organism name and accession
  96       my (undef, $oname, $cname) = $lib->accession_name();
  97
  98       my %data;
  99       @data{@field_list} = ($clone->clone_name_with_chromosome || '',
 100                             $clone->cornell_clone_name || '',
 101                             $clone->clone_name,
 102                             $clone->clone_type_object->name,
 103                             $oname,
 104                             $cname,
 105                             $lib->name,
 106                             $clone->estimated_length,
 107                             $clone->genbank_accession( $chado ),
 108                            );
 109       my @dump_fields = grep $self->{$_},@field_list;
 110
 111       print $dump_fh join("\t", @data{@dump_fields})."\n";
 112
 113     }
 114     $current_time = time() - $self->{query_start_time};
 115     $self->debug("Time point 2: $current_time");
 116     close $dump_fh;
 117     close $notfound_fh;
 118
 119     $self->{foundcount}= $foundcount;
 120     $self->{notfoundcount}= $notfoundcount;
 121     $current_time = time() - $self->{query_start_time};
 122     $self->{query_time} = time() - $self -> {query_start_time};
 123     $self->debug("Time point 3: $current_time");
 124 }
 125
 126 1;