Merge branch 'version/2.6'

* version/2.6:
  Making bacct options configurable according to cluster
  update documentation related to JSON serialisation of events including dataflow
  Create example PipeConfig using SystemCmd to create dataflow from a JSON file

docs/advanced_usage/json.rst

+Serialising dataflow events with JSON
+=====================================
+
+There are some facilities to support serialisaiton of events such as dataflow as JSON files or streams.
+
+The :ref:`Runnable API <runnable_api_dataflows>` provides a method
+``dataflow_output_ids_from_json($filename, $default_branch)`` to read a set of paramaters (output IDs)
+serialised as JSON from a flat file.
+
+Additionally, eHive uses JSON serialisation to interface Runnables written in guest languages (such as Python)
+with Workers. This is handled by, and documented in, ``Bio::EnsEMBL::Hive::GuestProcess``. This could serve
+as an example for advanced users wishing to construct infrastructure to transmit events between eHive
+and other systems.

docs/creating_runnables/runnable_api.rst

@@ -138,4 +138,4 @@ to easily generate events. The method takes two arguments:
    the default branch number.
 #. The default branch number (defaults to 1).
 
-
+Use of this is demonstrated in the Runnable :doxehive:`Bio::EnsEMBL::Hive::RunnableDB::SystemCmd`

docs/index.rst

@@ -74,6 +74,7 @@ User documentation
    advanced_usage/mpi
    advanced_usage/slack
    advanced_usage/continuous_pipelines
+   advanced_usage/json
 
 .. toctree::
    :caption: External plugins

hive_config.json

@@ -36,6 +36,9 @@
             "EBI" : {
                 "SubmissionOptions"  : "",
                 "TotalRunningWorkersMax"    : 10000
+            },
+            "codon" : {
+                "BacctExtraOptions"  : "-f -"
             }
         },
         "SGE" : {

modules/Bio/EnsEMBL/Hive/Examples/SystemCmd/PipeConfig/InjectJSONDataflow_conf.pm

+=pod
+
+=head1 NAME
+
+    Bio::EnsEMBL::Hive::Examples::SystemCmd::PipeConfig::InjectJSONDataflow_conf
+
+=head1 SYNOPSIS
+
+    init_pipeline.pl Bio::EnsEMBL::Hive::Examples::SystemCmd::PipeConfig::InjectJSONDataflow_conf --pipeline_url $HIVE_URL
+
+    seed_pipeline.pl -url $HIVE_URL -logic_name perform_cmd -input_id "{'cmd' => 'sleep 0', 'dataflow_file' => './sample_files/Inject_JSON_Dataflow_example.json'}"
+
+    runWorker.pl -url $HIVE_URL
+
+=head1 DESCRIPTION
+
+    This is an example of using the SystemCmd runnable to create dataflow events using parameters read from a JSON file.
+    There is a sample file located in ${EHIVE_ROOT_DIR}/modules/Bio/EnsEMBL/Hive/Examples/SystemCmd/PipeConfig/sample_files/
+    This file is called Inject_JSON_Dataflow_example.json
+
+    Each line of this file contains an optional branch number, followed by a complete JSON serialisation of the parameters (output_id)
+    appearing on the same line. For example, a line to direct dataflow on branch 2 might look like:
+
+          2 {"parameter_name" : "parameter_value"}
+
+    If no branch number is provided, then dataflow of those parameters will occour on the branch number
+    passed to SystemCmd in the 'dataflow_branch' parameter, if given. Otherwise, it will default to
+    branch 1 (autoflow).
+
+    Note that a command must be provided to SystemCmd using the 'cmd' parameter, even if JSON parameter injection
+    is the only desired behaviour.
+
+
+=head1 LICENSE
+
+    Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
+    Copyright [2016-2021] EMBL-European Bioinformatics Institute
+
+    Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License.
+    You may obtain a copy of the License at
+
+         http://www.apache.org/licenses/LICENSE-2.0
+
+    Unless required by applicable law or agreed to in writing, software distributed under the License
+    is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+    See the License for the specific language governing permissions and limitations under the License.
+
+=head1 CONTACT
+
+    Please subscribe to the Hive mailing list:  http://listserver.ebi.ac.uk/mailman/listinfo/ehive-users  to discuss Hive-related questions or to be notified of our updates
+
+=cut
+
+
+package Bio::EnsEMBL::Hive::Examples::SystemCmd::PipeConfig::InjectJSONDataflow_conf;
+
+use strict;
+use warnings;
+use base ('Bio::EnsEMBL::Hive::PipeConfig::HiveGeneric_conf');
+
+
+sub pipeline_analyses {
+    return [
+        {   -logic_name    => 'perform_cmd',
+            -module        => 'Bio::EnsEMBL::Hive::RunnableDB::SystemCmd',
+            -flow_into     => {
+                    1 => ['autoflow_test'],
+                    2 => ['branch2_test'],
+                    3 => ['branch3_test'],
+                    4 => ['branch4_test'],
+            },
+        },
+        {   -logic_name    => 'autoflow_test',
+            -module        => 'Bio::EnsEMBL::Hive::RunnableDB::Dummy',
+        },
+        {   -logic_name    => 'branch2_test',
+            -module        => 'Bio::EnsEMBL::Hive::RunnableDB::Dummy',
+        },
+        {   -logic_name    => 'branch3_test',
+            -module        => 'Bio::EnsEMBL::Hive::RunnableDB::Dummy',
+        },
+        {   -logic_name    => 'branch4_test',
+            -module        => 'Bio::EnsEMBL::Hive::RunnableDB::Dummy',
+        },
+    ];
+}
+
+1;
+

modules/Bio/EnsEMBL/Hive/Examples/SystemCmd/PipeConfig/sample_files/Inject_JSON_Dataflow_example.json

+{"addressed_to_one"  : "message for one"}
+2 {"addressed_to_two"  : "message for two"}
+4 {"addressed_to_four" : "message for four" , "also_addressed_to_four" : "second message for four"}

modules/Bio/EnsEMBL/Hive/Meadow/LSF.pm

@@ -322,7 +322,8 @@ sub get_report_entries_for_process_ids {
 
     unless ($self->config_get('AccountingDisabled')) {
         while (my $pid_batch = join(' ', map { "'$_'" } splice(@_, 0, 20))) {  # can't fit too many pids on one shell cmdline
-            my $cmd = "bacct -f - -l $pid_batch";
+            my $bacct_opts = $self->config_get('BacctExtraOptions') || "";
+            my $cmd = "bacct $bacct_opts -l $pid_batch";
 
 #           warn "LSF::get_report_entries_for_process_ids() running cmd:\n\t$cmd\n";
 
@@ -348,7 +349,8 @@ sub get_report_entries_for_time_interval {
         my $to_timepiece = Time::Piece->strptime($to_time, '%Y-%m-%d %H:%M:%S') + 2*ONE_MINUTE;
         $to_time = $to_timepiece->strftime('%Y/%m/%d/%H:%M');
 
-        my $cmd = "bacct -f - -l -C $from_time,$to_time ".($username ? "-u $username" : '');
+        my $bacct_opts = $self->config_get('BacctExtraOptions') || "";
+        my $cmd = "bacct $bacct_opts -l -C $from_time,$to_time ".($username ? "-u $username" : '');
 
 #        warn "LSF::get_report_entries_for_time_interval() running cmd:\n\t$cmd\n";
 

modules/Bio/EnsEMBL/Hive/RunnableDB/SystemCmd.pm

@@ -15,7 +15,19 @@
     The command line must be stored in the parameters() as the value corresponding to the 'cmd' key.
     It allows to pass in other parameters and use the parameter substitution mechanism in its full glory.
 
-=head1 CONFIGURATION EXAMPLE
+    This Runnable also allows the creation of dataflow using JSON stored in an external file.
+    Each line of this file contains an optional branch number, followed by a complete JSON serialisation of the parameters (output_id)
+    appearing on the same single line. For example, a line to direct dataflow on branch 2 might look like:
+
+          2 {"parameter_name" : "parameter_value"}
+
+    If no branch number is provided, then dataflow of those parameters will occour on the branch number
+    passed to SystemCmd in the 'dataflow_branch' parameter, if given. Otherwise, it will default to
+    branch 1 (autoflow).
+
+    A sample file is provided at ${EHIVE_ROOT_DIR}/modules/Bio/EnsEMBL/Hive/Examples/SystemCmd/PipeConfig/sample_files/Inject_JSON_Dataflow_example.json
+
+=head1 CONFIGURATION EXAMPLES
 
     # The following example shows how to configure SystemCmd in a PipeConfig module
     # to create a MySQL snapshot of the Hive database before executing a critical operation.
@@ -31,6 +43,17 @@
             },
         },
 
+    # The following example shows how to configure SystemCmd in a PipeConfig module
+    # to generate dataflow events based on parameters stored as JSON in a file named "some_parameters.json"
+
+        {  -logic_name => 'inject_parameters_from_file',
+           -module     => 'Bio::EnsEMBL::Hive::RunnableDB::SystemCmd',
+           -parameters => {
+                'dataflow_file' => 'some_parameters.json',
+                'cmd'           => 'sleep 0', # a command must be provided in the cmd parameter
+           },
+        },
+
 =head1 LICENSE
 
     Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute

t/04.meadow/lsf.t

@@ -207,14 +207,15 @@ my $expected_bacct = {
 };
 
 $lsf_meadow->config_set("AccountingDisabled", 0);
+my $bacct_opts = $lsf_meadow->config_get('BacctExtraOptions') || "";
 lives_and( sub {
-    local $ENV{EHIVE_EXPECTED_BACCT} = '-f - -l 34 56[7]';
+    local $ENV{EHIVE_EXPECTED_BACCT} = $bacct_opts.'-l 34 56[7]';
     my $h = $lsf_meadow->get_report_entries_for_process_ids(34, '56[7]');
     is_deeply($h, $expected_bacct, 'Got bacct output');
 }, 'Can call bacct on process_ids');
 
 lives_and( sub {
-    local $ENV{EHIVE_EXPECTED_BACCT} = '-f - -l -C 2020/10/11/12:23,2020/12/12/23:58 -u kb3';
+    local $ENV{EHIVE_EXPECTED_BACCT} = $bacct_opts.'-l -C 2020/10/11/12:23,2020/12/12/23:58 -u kb3';
     my $h = $lsf_meadow->get_report_entries_for_time_interval('2020-10-11 12:23:45', '2020-12-12 23:56:59', 'kb3');
     is_deeply($h, $expected_bacct, 'Got bacct output');
 }, 'Can call bacct on a date range');
@@ -222,13 +223,13 @@ lives_and( sub {
 
 $lsf_meadow->config_set("AccountingDisabled", 1);
 lives_and( sub {
-    local $ENV{EHIVE_EXPECTED_BACCT} = '-f - -l 34 56[7]';
+    local $ENV{EHIVE_EXPECTED_BACCT} = $bacct_opts.'-l 34 56[7]';
     my $h = $lsf_meadow->get_report_entries_for_process_ids(34, '56[7]');
     is_deeply($h, {}, 'No bacct output when accounting disabled');
 }, 'Suppressed bacct when AccountingDisabled when checking process_ids');
 
 lives_and( sub {
-    local $ENV{EHIVE_EXPECTED_BACCT} = '-f - -l -C 2015/10/11/12:23,2015/12/12/23:58 -u kb3';
+    local $ENV{EHIVE_EXPECTED_BACCT} = $bacct_opts.'-l -C 2015/10/11/12:23,2015/12/12/23:58 -u kb3';
     my $h = $lsf_meadow->get_report_entries_for_time_interval('2015-10-11 12:23:45', '2015-12-12 23:56:59', 'kb3');
     is_deeply($h, {}, 'No bacct output when accounting disabled');
 }, 'Suppressed bacct when AccountingDisabled when checking a date range');