Merge branch 'develop' of https://github.com/parklab/refinery-platform …

…into develop

.gitignore

@@ -62,6 +62,7 @@ refinery/ui/node_modules/
 media/
 static/
 isa-tab/
+import/
 *.conflict
 *.sublime-*
 .idea/

README.rst

@@ -65,6 +65,10 @@ Connect to the initialized VM:
     $ workon refinery-platform
     $ ./manage.py
 
+Log in to Refinery (http://192.168.50.50:8000/) with the default guest user account (username: guest, password: guest).
+
+Log in to Django admin UI (http://192.168.50.50:8000/admin/) with the default superuser account (username: admin, password: refinery).
+
 Please see `installation notes
 <https://refinery-platform.readthedocs.org/en/latest/administrator/setup.html>`_
 for more details, including information on how to configure Galaxy for this setup.

Vagrantfile

@@ -15,7 +15,8 @@ Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
   config.vm.network :private_network, ip: "192.168.50.50"
 
   config.vm.provider "virtualbox" do |v|
-    v.customize ["modifyvm", :id, "--memory", "1024"]
+    v.memory = 1024
+    v.cpus = 2
   end
 
   config.ssh.forward_agent = true  # to enable cloning from Github over SSH

deployment/manifests/default.pp

@@ -5,6 +5,12 @@
 $project_root = "/vagrant/refinery"
 $ui_app_root = "${project_root}/ui"
 
+# to make logs easier to read
+file { "/etc/timezone":
+  content => "US/Eastern",
+}
+
+# for better performance
 sysctl { 'vm.swappiness': value => '10' }
 
 file { "/home/${appuser}/.ssh/config":
@@ -27,6 +33,9 @@
 }
 class { 'postgresql::lib::devel':
 }
+postgresql::server::role { $appuser:
+  createdb => true,
+}
 postgresql::server::db { 'refinery':
   user => $appuser,
   password => '',
@@ -67,7 +76,7 @@
 
 package { 'virtualenvwrapper': }
 ->
-file_line {"virtualenvwrapper_config":
+file_line { "virtualenvwrapper_config":
   path => "/home/${appuser}/.profile",
   line => "source /etc/bash_completion.d/virtualenvwrapper",
   require => Python::Virtualenv[$virtualenv],
@@ -82,7 +91,10 @@
   group => $appgroup,
 }
 
-file { ["/vagrant/media", "/vagrant/static", "/vagrant/isa-tab" ]:
+file { ["/vagrant/media",
+        "/vagrant/static",
+        "/vagrant/isa-tab",
+        "/vagrant/import" ]:
   ensure => directory,
   owner => $appuser,
   group => $appgroup,

refinery/data_set_manager/management/commands/process_metadata_table.py

@@ -86,28 +86,31 @@ def handle(self, *args, **options):
         Description: main program; calls the parsing and insertion functions
 
         """
-        required = ['username', 'title', 'file_name', 'source_column_index', 'data_file_column']
+        required = ['username', 'title', 'file_name', 'source_column_index',
+                    'data_file_column']
         for arg in required:
             if not options[arg]:
-                raise CommandError('%s was not provided.' % arg)
+                raise CommandError('{} was not provided'.format(arg))
+        source_columns = \
+            [x.strip() for x in options['source_column_index'].split(",")]
         try:
-            source_columns = [int(x.strip()) for x in options['source_column_index'].split(",")]
-        except ValueError:
-            raise CommandError("source_column_index value(s) are invalid")
-        for column_index in source_columns:
-            if column_index < 0:
-                raise CommandError("source_column_index values can not be negative")
-        integer_values = ['data_file_column', 'auxiliary_file_column',
-                          'genome_build_column', 'annotation_column']
-        for arg in integer_values:
-            if options[arg] and options[arg] < 0:
-                raise CommandError("{} can not be negative".format(arg))
-        with open(options['file_name']) as metadata_file:
-            dataset_uuid = process_metadata_table(
-                options['username'], options['title'], metadata_file,
-                source_columns, options['data_file_column'],
-                options['data_file_permanent'], options['base_path'],
-                options['auxiliary_file_column'], options['species_column'],
-                options['genome_build_column'], options['annotation_column'],
-                options['slug'], options['is_public'])
+            with open(options['file_name']) as metadata_file:
+                dataset_uuid = process_metadata_table(
+                    username=options['username'], title=options['title'],
+                    metadata_file=metadata_file, source_columns=source_columns,
+                    data_file_column=options['data_file_column'],
+                    auxiliary_file_column=options['auxiliary_file_column'],
+                    base_path=options['base_path'],
+                    data_file_permanent=options['data_file_permanent'],
+                    species_column=options['species_column'],
+                    genome_build_column=options['genome_build_column'],
+                    annotation_column=options['annotation_column'],
+                    slug=options['slug'], is_public=options['is_public'])
+        except IOError as exc:
+            raise CommandError(
+                "Could not open file '{}': {}".format(
+                    options['file_name'], exc))
+        except ValueError as exc:
+            raise CommandError(exc)
+
         print("Created dataset with UUID '{}'".format(dataset_uuid))

refinery/data_set_manager/models.py

@@ -550,7 +550,7 @@ def _is_facet_attribute(attribute,study,assay):
 
     query = settings.REFINERY_SOLR_BASE_URL + "data_set_manager" + "/select?" + "q=django_ct:data_set_manager.node&wt=json&start=0&rows=1&fq=(study_uuid:" + study.uuid + "%20AND%20assay_uuid:" + assay.uuid + "%20AND%20is_annotation:false%20AND%20(type:%22Array%20Data%20File%22%20OR%20type:%22Derived%20Array%20Data%20File%22%20OR%20type:%22Raw%20Data%20File%22%20OR%20type:%20%22Derived%20Data%20File%22))&facet=true&facet.field=" + attribute + "&facet.sort=count&facet.limit=-1"
 
-    logger.debug( "Query for initialize_attribute_order: %s" % ( query, ) )
+    # logger.debug( "Query for initialize_attribute_order: %s" % ( query, ) )
 
     # proper url encoding                  
     query = urllib2.quote(query, safe="%/:=&?~#+!$,;'@()*[]")
@@ -586,7 +586,7 @@ def initialize_attribute_order( study, assay ):
 
     query = settings.REFINERY_SOLR_BASE_URL + "data_set_manager" + "/select?" + "q=django_ct:data_set_manager.node&wt=json&start=0&rows=1&fq=(study_uuid:" + study.uuid + "%20AND%20assay_uuid:" + assay.uuid + "%20AND%20is_annotation:false%20AND%20(type:%22Array%20Data%20File%22%20OR%20type:%22Derived%20Array%20Data%20File%22%20OR%20type:%22Raw%20Data%20File%22%20OR%20type:%20%22Derived%20Data%20File%22))&facet=true&facet.sort=count&facet.limit=-1"
 
-    logger.debug( "Query for initialize_attribute_order: %s" % ( query, ) )
+    # logger.debug( "Query for initialize_attribute_order: %s" % ( query, ) )
 
     # proper url encoding                  
     query = urllib2.quote(query, safe="%/:=&?~#+!$,;'@()*[]")