Second insert into analysis_data for job_creation added extra overhead.

Removed select before store (made new method store_if_needed if that functionality is required by users)
and added option in AnalysisJobAdaptor::CreateNewJob to pass input_analysis_data_id
so if already know the CreateNewJob will be as fast as before.  Plus there are no limits on the
size of the input_id string.

modules/Bio/EnsEMBL/Hive/DBSQL/AnalysisDataAdaptor.pm

@@ -56,7 +56,6 @@ sub fetch_by_dbID {
   return $data;
 }
 
-
 #
 # STORE METHODS
 #
@@ -66,6 +65,21 @@ sub store {
   my ($self, $data) = @_;
   my $data_id;
   
+  return 0 unless($data);
+  
+  my $sth2 = $self->prepare("INSERT INTO analysis_data (data) VALUES (?)");
+  $sth2->execute($data);
+  $data_id = $sth2->{'mysql_insertid'};
+  $sth2->finish;
+
+  return $data_id;
+}
+
+
+sub store_if_needed {
+  my ($self, $data) = @_;
+  my $data_id;
+
   return 0 unless($data);
 
   my $sth = $self->prepare("SELECT analysis_data_id FROM analysis_data WHERE data = ?");
@@ -78,15 +92,9 @@ sub store {
     return $data_id;
   }
 
-  my $sth2 = $self->prepare("INSERT INTO analysis_data (data) VALUES (?)");
-  $sth2->execute($data);
-  $data_id = $sth2->{'mysql_insertid'};
-  $sth2->finish;
-
-  return $data_id;
+  return $self->store($data);
 }
 
-
 1;
 
 

modules/Bio/EnsEMBL/Hive/DBSQL/AnalysisJobAdaptor.pm

@@ -63,11 +63,11 @@ sub CreateNewJob {
 
   return undef unless(scalar @args);
 
-  my ($input_id, $analysis, $prev_analysis_job_id, $blocked) =
-     rearrange([qw(INPUT_ID ANALYSIS input_job_id BLOCK )], @args);
+  my ($input_id, $input_analysis_data_id, $analysis, $prev_analysis_job_id, $blocked) =
+     rearrange([qw(INPUT_ID INPUT_ANALYSIS_DATA_ID ANALYSIS input_job_id BLOCK )], @args);
 
   $prev_analysis_job_id=0 unless($prev_analysis_job_id);
-  throw("must define input_id") unless($input_id);
+  throw("must define input_id or input_analysis_data_id") unless($input_id or $input_analysis_data_id);
   throw("must define analysis") unless($analysis);
   throw("analysis must be [Bio::EnsEMBL::Analysis] not a [$analysis]")
     unless($analysis->isa('Bio::EnsEMBL::Analysis'));
@@ -76,8 +76,10 @@ sub CreateNewJob {
 
   my $dbc = $analysis->adaptor->db->dbc;
 
-  my $dataDBA = new Bio::EnsEMBL::Hive::DBSQL::AnalysisDataAdaptor($dbc);
-  my $input_analysis_data_id = $dataDBA->store($input_id);
+  unless(defined($input_analysis_data_id)) {
+    my $dataDBA = $analysis->adaptor->db->get_AnalysisDataAdaptor;
+    $input_analysis_data_id = $dataDBA->store($input_id);
+  }
     
   my $sql = "INSERT ignore into analysis_job ".
             " SET input_analysis_data_id=\"$input_analysis_data_id\" ".