Inheritance diagram for Bio::EnsEMBL::Hive::AnalysisJob:

Public Member Functions
public	input_id ()

public	param_id_stack ()

public	accu_id_stack ()

public	role_id ()

public	status ()

public	retry_count ()

public	when_completed ()

public	runtime_msec ()

public	query_count ()

public	set_and_update_status ()

public	stdout_file ()

public	stderr_file ()

public	accu_hash ()

public Boolean	autoflow ()

public	lethal_for_worker ()

public	transient_error ()

public	incomplete ()

public	died_somewhere ()

public	load_stack_and_accu ()

public	load_parameters ()

public	flattened_stack_and_accu ()

public	fan_cache ()

public	dataflow_output_id ()

public	url_query_params ()

public	toString ()

public	fetch_local_blocking_semaphore ()

Public Member Functions inherited from Bio::EnsEMBL::Hive::Storable
public Bio::EnsEMBL::Hive::Storable	new ()

public Int	dbID ()

public Bio::EnsEMBL::Hive::DBSQL::BaseAdaptor	adaptor ()

public	DESTROY ()

public	AUTOLOAD ()

Public Member Functions inherited from Bio::EnsEMBL::Hive::Cacheable
public	hive_pipeline ()

public	is_local_to ()

public	count_local_and_remote_objects ()

public	relative_display_name ()

public	relative_url ()

public	display_name ()

public	unikey ()

Public Member Functions inherited from Bio::EnsEMBL::Hive::Params
public	new ()

public	fuse_param_hashes ()

public	param_init ()

protected	_param_possibly_overridden ()

protected	_param_silent ()

public Any	param_required ()

public Boolean	param_exists ()

public Boolean	param_is_defined ()

public Any	param ()

public	param_substitute ()

public	mysql_conn ()

public	mysql_dbname ()

public	csvq ()

protected	_subst_one_hashpair ()

Detailed Description

Description

    An AnalysisJob is the link between the input_id control data, the analysis and
    the rule system.  It also tracks the state of the job as it is processed

Definition at line 13 of file AnalysisJob.pm.

Member Function Documentation

◆ accu_hash()

public Bio::EnsEMBL::Hive::AnalysisJob::accu_hash ( )

Undocumented method

Code:

click to view

◆ accu_id_stack()

public Bio::EnsEMBL::Hive::AnalysisJob::accu_id_stack ( )

Undocumented method

Code:

click to view

◆ autoflow()

public Boolean Bio::EnsEMBL::Hive::AnalysisJob::autoflow ( )

    Title   :  autoflow
    Function:  Gets/sets flag for whether the job should
               be automatically dataflowed on branch 1 when the job completes.
               If the subclass manually sends a job along branch 1 with dataflow_output_id,
               the autoflow will turn itself off.
    Returns :  boolean (1=default|0)

Code:

click to view

◆ dataflow_output_id()

public Bio::EnsEMBL::Hive::AnalysisJob::dataflow_output_id ( )

    Title        :  dataflow_output_id
    Arg[1](req)  :  <string> $output_id 
    Arg[2](opt)  :  <int> $branch_name_or_code (optional, defaults to 1)
    Usage        :  $self->dataflow_output_id($output_id, $branch_name_or_code);
    Function:  
      If a RunnableDB(Process) needs to create jobs, this allows it to have jobs 
      created and flowed through the dataflow rules of the workflow graph.
      This 'output_id' becomes the 'input_id' of the newly created job at
      the ends of the dataflow pipes.  The optional 'branch_name_or_code' determines
      which dataflow pipe(s) to flow the job through.

Code:

click to view

sub dataflow_output_id {
    my ($self, $output_ids, $branch_name_or_code) = @_;
 
    my $input_id                = $self->input_id();
    my $hive_use_param_stack    = $self->hive_pipeline->hive_use_param_stack;
 
    $output_ids    =  destringify($output_ids) unless ref($output_ids);     # destringify the string
    $output_ids    = [ $output_ids ] unless(ref($output_ids) eq 'ARRAY');   # force previously used single values into an arrayref
 
    my @destringified_output_ids;
    foreach my $output_id (@$output_ids) {
        $output_id = destringify($output_id) unless ref($output_id);        # destringify the string
        if ((defined $output_id) and (ref($output_id) ne 'HASH')) {         # Only undefs and hashrefs work as input_ids
            die stringify($output_id)." is not a hashref ! Cannot dataflow";
        }
        push @destringified_output_ids, $output_id;
    }
 
        # map branch names to numbers:
    my $branch_code = Bio::EnsEMBL::Hive::DBSQL::DataflowRuleAdaptor::branch_name_2_code($branch_name_or_code);
 
        # if branch_code is set to 1 (explicitly or implicitly), turn off automatic dataflow:
    $self->autoflow(0) if($branch_code == 1);
 
    my @output_job_ids = ();
 
        # fan rules come sorted before funnel rules for the same branch_code:
    foreach my $df_rule ( @{ $self->analysis->dataflow_rules_by_branch->{$branch_code} || [] } ) {
 
        my $targets_grouped_by_condition    = $df_rule->get_my_targets_grouped_by_condition;    # the pairs are deliberately ordered to put the DEFAULT branch last
        my @conditions                      = map { $_->[0] } @$targets_grouped_by_condition;
 
        my $total_output_ids_for_the_rule = 0;
 
        foreach my $output_id (@destringified_output_ids) {  # filter the output_ids and place them into the [2] part of $targets_grouped_by_condition
            my $condition_match_count = 0;
            foreach my $condition_idx (0..@conditions-1) {
                my $unsubstituted_condition = $conditions[$condition_idx];
 
                if(defined($unsubstituted_condition)) {
                    if(my $substituted_condition = $self->param_substitute('#expr('.$unsubstituted_condition.')expr#', $output_id)) {
                        $condition_match_count++;
                    } else {
                        next;   # non-DEFAULT condition branch failed
                    }
                } elsif($condition_match_count) {
                    next;   # DEFAULT condition branch failed, because one of the conditions fired
                } else {
                    # DEFAULT condition branch succeeded => follow to the push
                }
 
                push @{$targets_grouped_by_condition->[$condition_idx][2]}, $output_id;
                $total_output_ids_for_the_rule += scalar( @{ $targets_grouped_by_condition->[$condition_idx][1] } );
            }
        }
 
        my $fan_cache_for_this_rule = exists($self->fan_cache->{"$df_rule"}) && $self->fan_cache->{"$df_rule"};
        if($fan_cache_for_this_rule && @$fan_cache_for_this_rule && $total_output_ids_for_the_rule!=1) {
            die "The total number of funnel output_ids (considering ".scalar(@conditions)." conditions) was $total_output_ids_for_the_rule, but expected to be 1. Please investigate";
        }
 
        foreach my $triple (@$targets_grouped_by_condition) {
            my ($unsubstituted_condition, $df_targets, $filtered_output_ids) = @$triple;
 
            if($filtered_output_ids && @$filtered_output_ids) {
 
                foreach my $df_target (@$df_targets) {
 
                    my $extend_param_stack  = $hive_use_param_stack || $df_target->extend_param_stack;                      # this boolean is df_target-specific
                    my $default_param_hash  = $extend_param_stack ? {} : $input_id;                                         # this is what undefs will turn into
 
                    my @pre_substituted_output_ids = map { $_ // $default_param_hash } @$filtered_output_ids;
 
                        # parameter substitution into input_id_template is also df_target-specific:
                    my $output_ids_for_this_rule;
                    if(my $template_string = $df_target->input_id_template()) {
                        my $template_hash = destringify($template_string);
                        $output_ids_for_this_rule = [ map { $self->param_substitute($template_hash, $_) } @pre_substituted_output_ids ];
                    } else {
                        $output_ids_for_this_rule = \@pre_substituted_output_ids;
                    }
 
                    my $target_object       = $df_target->to_analysis;
                    my $same_db_dataflow    = $self->analysis->hive_pipeline == $target_object->hive_pipeline;
 
                    unless($same_db_dataflow) {
                        my $prev_transient_error = $self->transient_error(); # make a note of previously set transience status
                        $self->transient_error(0);
                        @$output_ids_for_this_rule = map { $self->flattened_stack_and_accu( $_, $extend_param_stack ); } @$output_ids_for_this_rule;
                        $self->transient_error($prev_transient_error);
                    }
 
                    my ($stored_listref) = $target_object->dataflow( $output_ids_for_this_rule, $self, $same_db_dataflow, $extend_param_stack, $df_rule );
 
                    push @output_job_ids, @$stored_listref;
 
                } # /foreach my $df_target
            } # /if(filtered_output_ids are workable)
        } # /foreach my $unsubstituted_condition
    } # /foreach my $df_rule
 
    return \@output_job_ids;
}

◆ died_somewhere()

public Bio::EnsEMBL::Hive::AnalysisJob::died_somewhere ( )

Undocumented method

Code:

click to view

◆ fan_cache()

public Bio::EnsEMBL::Hive::AnalysisJob::fan_cache ( )

Undocumented method

Code:

click to view

◆ fetch_local_blocking_semaphore()

public Bio::EnsEMBL::Hive::AnalysisJob::fetch_local_blocking_semaphore ( )

Undocumented method

Code:

click to view

◆ flattened_stack_and_accu()

public Bio::EnsEMBL::Hive::AnalysisJob::flattened_stack_and_accu ( )

Undocumented method

Code:

click to view

◆ incomplete()

public Bio::EnsEMBL::Hive::AnalysisJob::incomplete ( )

Undocumented method

Code:

click to view

◆ input_id()

public Bio::EnsEMBL::Hive::AnalysisJob::input_id ( )

Undocumented method

Code:

click to view

◆ lethal_for_worker()

public Bio::EnsEMBL::Hive::AnalysisJob::lethal_for_worker ( )

Undocumented method

Code:

click to view

◆ load_parameters()

public Bio::EnsEMBL::Hive::AnalysisJob::load_parameters ( )

Undocumented method

Code:

click to view

◆ load_stack_and_accu()

public Bio::EnsEMBL::Hive::AnalysisJob::load_stack_and_accu ( )

Undocumented method

Code:

click to view

◆ param_id_stack()

public Bio::EnsEMBL::Hive::AnalysisJob::param_id_stack ( )

Undocumented method

Code:

click to view

◆ query_count()

public Bio::EnsEMBL::Hive::AnalysisJob::query_count ( )

Undocumented method

Code:

click to view

◆ retry_count()

public Bio::EnsEMBL::Hive::AnalysisJob::retry_count ( )

Undocumented method

Code:

click to view

◆ role_id()

public Bio::EnsEMBL::Hive::AnalysisJob::role_id ( )

Undocumented method

Code:

click to view

◆ runtime_msec()

public Bio::EnsEMBL::Hive::AnalysisJob::runtime_msec ( )

Undocumented method

Code:

click to view

◆ set_and_update_status()

public Bio::EnsEMBL::Hive::AnalysisJob::set_and_update_status ( )

Undocumented method

Code:

click to view

◆ status()

public Bio::EnsEMBL::Hive::AnalysisJob::status ( )

Undocumented method

Code:

click to view

◆ stderr_file()

public Bio::EnsEMBL::Hive::AnalysisJob::stderr_file ( )

Undocumented method

Code:

click to view

◆ stdout_file()

public Bio::EnsEMBL::Hive::AnalysisJob::stdout_file ( )

Undocumented method

Code:

click to view

◆ toString()

public Bio::EnsEMBL::Hive::AnalysisJob::toString ( )

Undocumented method

Code:

click to view

◆ transient_error()

public Bio::EnsEMBL::Hive::AnalysisJob::transient_error ( )

Undocumented method

Code:

click to view

◆ url_query_params()

public Bio::EnsEMBL::Hive::AnalysisJob::url_query_params ( )

Undocumented method

Code:

click to view

◆ when_completed()

public Bio::EnsEMBL::Hive::AnalysisJob::when_completed ( )

Undocumented method

Code:

click to view

The documentation for this class was generated from the following file:

modules/Bio/EnsEMBL/Hive/AnalysisJob.pm

Public Member Functions

Detailed Description

Description

Member Function Documentation

◆ accu_hash()

◆ accu_id_stack()

◆ autoflow()

◆ dataflow_output_id()

◆ died_somewhere()

◆ fan_cache()

◆ fetch_local_blocking_semaphore()

◆ flattened_stack_and_accu()

◆ incomplete()

◆ input_id()

◆ lethal_for_worker()

◆ load_parameters()

◆ load_stack_and_accu()

◆ param_id_stack()

◆ query_count()

◆ retry_count()

◆ role_id()

◆ runtime_msec()

◆ set_and_update_status()

◆ status()

◆ stderr_file()

◆ stdout_file()

◆ toString()

◆ transient_error()

◆ url_query_params()

◆ when_completed()