ccls-ccls_engine 3.11.0

data/lib/tasks/application.rake

@@ -0,0 +1,286 @@
+namespace :ccls do
+
+	desc "Dump data to xml files"
+	task :export_to_xml => :environment do
+		outdir = if Rails.env == 'production'
+			"/my/ruby/xml"
+		else
+			"."
+		end
+		%w( project enrollment study_subject 
+				patient phone_number address addressing ).each do |model|
+			puts "Exporting #{model.pluralize} ..."
+			File.open("#{outdir}/#{model.pluralize}.xml",'w'){|f| 
+				f.puts model.camelize.constantize.all.to_xml }
+		end
+	end
+
+	desc "Report data counts in database"
+	task :data_report => :environment do
+		puts
+		puts "Report data counts in database"
+		puts
+		printf "%-25s %5d\n", "StudySubject.count:", StudySubject.count
+
+		StudySubject.all(:select => "subject_type_id, COUNT(*) AS count",
+				:group => :subject_type_id ).each do |e|
+			printf "%-25s %5d\n", "subject_type = #{e.subject_type}:", e.count
+		end
+
+		%w{ case_control_type childidwho hispanicity_id father_hispanicity_id
+				mother_hispanicity_id sex do_not_contact }.each do |field|
+			StudySubject.all(:select => "#{field}, COUNT(*) AS count",
+					:group => field ).each do |e|
+				printf "%-25s %5d\n", "#{field} = #{e.send(field)}:", e.count
+			end
+		end
+
+		printf "%-25s %5d\n", "Patient.count:", Patient.count
+		%w{ was_under_15_at_dx was_previously_treated was_ca_resident_at_diagnosis 
+			organization_id diagnosis_id
+		}.each do |field|
+			Patient.all(:select => "#{field}, COUNT(*) AS count",
+					:group => field ).each do |e|
+				printf "%-25s %5d\n", "#{field} = #{e.send(field)}:", e.count
+			end
+		end
+
+		printf "%-25s %5d\n", "Enrollment.count:", Enrollment.count
+		printf "%-25s %5d\n", "OperationalEvent.count:", OperationalEvent.count
+		%w{ operational_event_type_id }.each do |field|
+			OperationalEvent.all(:select => "#{field}, COUNT(*) AS count",
+					:group => field ).each do |e|
+				printf "%-25s %5d\n", "#{field} = #{e.send(field)}:", e.count
+			end
+		end
+
+		printf "%-25s %5d\n", "CCLS Enrollments.count:", Enrollment.count(
+			:conditions => { :project_id => Project['ccls'].id })
+		%w{ consented is_eligible refusal_reason_id document_version_id
+			ineligible_reason_id
+		}.each do |field|
+			Enrollment.all(:select => "#{field}, COUNT(*) AS count",
+					:conditions => { :project_id => Project['ccls'].id },
+					:group      => field ).each do |e|
+				printf "%-25s %5d\n", "#{field} = #{e.send(field)}:", e.count
+			end
+		end
+
+		printf "%-25s %5d\n", "IcfMasterId.count:", IcfMasterId.count
+		printf "%-25s %5d\n", "Used IcfMasterId.count:", IcfMasterId.count(
+			:conditions => [ 'study_subject_id IS NOT NULL' ])
+		printf "%-25s %5d\n", "Unused IcfMasterId.count:", IcfMasterId.count(
+			:conditions => [ 'study_subject_id IS NULL' ])
+
+		printf "%-25s %5d\n", "Subjects with icf_master_id:", StudySubject.count(
+			:conditions => [ 'icf_master_id IS NOT NULL' ])
+		printf "%-25s %5d\n", "Subjects without icf_master_id:", StudySubject.count(
+			:conditions => [ 'icf_master_id IS NULL' ])
+
+		printf "%-25s %5d\n", "Subjects with childid:", StudySubject.count(
+			:conditions => [ 'childid IS NOT NULL' ])
+		printf "%-25s %5d\n", "Subjects without childid:", StudySubject.count(
+			:conditions => [ 'childid IS NULL' ])
+
+		printf "%-25s %5d\n", "Subjects with patid:", StudySubject.count(
+			:conditions => [ 'patid IS NOT NULL' ])
+		printf "%-25s %5d\n", "Subjects without patid:", StudySubject.count(
+			:conditions => [ 'patid IS NULL' ])
+
+		printf "%-25s %5d\n", "Subjects with studyid:", StudySubject.count(
+			:conditions => [ 'studyid IS NOT NULL' ])
+		printf "%-25s %5d\n", "Subjects without studyid:", StudySubject.count(
+			:conditions => [ 'studyid IS NULL' ])
+
+		printf "%-25s %5d\n", "Subjects with subjectid:", StudySubject.count(
+			:conditions => [ 'subjectid IS NOT NULL' ])
+		printf "%-25s %5d\n", "Subjects without subjectid:", StudySubject.count(
+			:conditions => [ 'subjectid IS NULL' ])
+
+	end
+
+#	task :sync_subject_type => :environment do
+#		abort("Don't do this in production! Not unless you know exactly what you're doing anyway."
+#			) if Rails.env == 'production'
+#		Identifier.find(:all).each_with_index do |identifier,index|
+#			puts "Processing #{index}"
+#			study_subject = identifier.study_subject
+#			if study_subject.nil?
+#				puts "No study_subject on this identifier" 
+#				next
+#			end
+#			puts "case_control_type #{identifier.case_control_type}"
+#			puts "subject_type #{study_subject.subject_type}"
+#			if study_subject.subject_type.to_s == 'Case' and identifier.case_control_type != 'C'
+#				puts "subject_type == 'Case' and case_control_type != 'C'"
+#				study_subject.patient.destroy unless study_subject.patient.nil?
+#				study_subject.reload.subject_type = SubjectType['Control']
+#				study_subject.save!
+#				puts "NEW subject_type #{study_subject.reload.subject_type}"
+#			end
+#		end
+#	end
+
+	desc "Load some fixtures to database for application"
+	task :update => :environment do
+#			gift_cards
+		fixtures = %w(
+			address_types
+			contexts
+			context_data_sources
+			data_sources
+			diagnoses
+			document_types
+			document_versions
+			follow_up_types
+			hospitals
+			ineligible_reasons
+			instrument_versions
+			instruments
+			interview_methods
+			interview_outcomes
+			instrument_types
+			languages
+			organizations
+			operational_event_types
+			people
+			phone_types
+			projects
+			races
+			refusal_reasons
+			roles
+			sample_outcomes
+			sample_temperatures
+			sample_types
+			sections
+			states
+			subject_relationships
+			subject_types
+			tracing_statuses
+			units
+			vital_statuses 
+		)
+		ENV['FIXTURES'] = fixtures.join(',')
+		puts "Loading fixtures for #{ENV['FIXTURES']}"
+		Rake::Task["db:fixtures:load"].invoke
+		Rake::Task["db:fixtures:load"].reenable
+	end
+
+	task :full_update => :update do
+#
+#	We don't use this yet, plus it hasn't changed, so why keep updating it?
+#	It takes about 30 minutes.
+#
+#		#	the zip_codes.csv fixtures is too big and takes too long to
+#		#	load in testing, so I left a small one there and put
+#		#	the full version from http://www.populardata.com/zipcode_database.html
+		fixtures = %w(
+			zip_codes
+			counties
+		)
+#	Do not import icf_master_ids this way in production as these are real
+#	icf_master_ids and some may be assigned to real subjects already.
+#			icf_master_ids
+		ENV['FIXTURES'] = fixtures.join(',')
+		ENV['FIXTURES_PATH'] = 'production/fixtures'
+		puts "Loading production fixtures for #{ENV['FIXTURES']}"
+		Rake::Task["db:fixtures:load"].invoke
+		Rake::Task["db:fixtures:load"].reenable
+	end
+
+	desc "Add some expected users."
+	task :add_users => :environment do
+		puts "Adding users"
+		%w( 859908 228181 214766 180918 66458 768475 
+			10883 86094 769067 ).each do |uid|
+			puts " - Adding user with uid:#{uid}:"
+			User.find_create_and_update_by_uid(uid)
+		end
+	end
+
+	desc "Add user by UID"
+	task :add_user => :environment do
+		puts
+		if ENV['uid'].blank?
+			puts "User's CalNet UID required."
+			puts "Usage: rake #{$*} uid=INTEGER"
+			puts
+			exit
+		end
+		if !User.exists?(:uid => ENV['uid'])
+			puts "No user found with uid=#{ENV['uid']}. Adding..."
+			User.find_create_and_update_by_uid(ENV['uid'])
+		else
+			puts "User with uid #{ENV['uid']} already exists."
+		end
+		puts
+	end
+
+	desc "Deputize user by UID"
+	task :deputize => :environment do
+		puts
+		if ENV['uid'].blank?
+			puts "User's CalNet UID required."
+			puts "Usage: rake #{$*} uid=INTEGER"
+			puts
+			exit
+		end
+		if !User.exists?(:uid => ENV['uid'])
+			puts "No user found with uid=#{ENV['uid']}."
+			puts
+			exit
+		end
+		user = User.find(:first, :conditions => { :uid => ENV['uid'] })
+		puts "Found user #{user.displayname}.  Deputizing..."
+		user.deputize
+		puts "User deputized: #{user.is_administrator?}"
+		puts
+	end
+
+end
+
+
+__END__
+
+#	task :args_as_array do
+#		args = $*.dup.slice(1..-1)
+#		puts args.collect {|arg| "X:" << arg }.join("\n")
+#		exit
+#	end
+
+
+Another way to pass arguments to rake task as demonstrated by one of the sunspot gem's tasks
+...
+  # This task depends on the standard Rails file naming \
+  # conventions, in that the file name matches the defined class name. \
+  # By default the indexing system works in batches of 50 records, you can \
+  # set your own value for this by using the batch_size argument. You can \
+  # also optionally define a list of models to separated by a forward slash '/'
+  # 
+  # $ rake sunspot:reindex                # reindex all models
+  # $ rake sunspot:reindex[1000]          # reindex in batches of 1000
+  # $ rake sunspot:reindex[false]         # reindex without batching
+  # $ rake sunspot:reindex[,Post]         # reindex only the Post model
+  # $ rake sunspot:reindex[1000,Post]     # reindex only the Post model in
+  #                                       # batchs of 1000
+  # $ rake sunspot:reindex[,Post+Author]  # reindex Post and Author model
+  task :reindex, :batch_size, :models, :needs => :environment do |t, args|
+    reindex_options = {:batch_commit => false}
+    case args[:batch_size]
+    when 'false'
+      reindex_options[:batch_size] = nil
+    when /^\d+$/ 
+      reindex_options[:batch_size] = args[:batch_size].to_i if args[:batch_size].to_i > 0
+    end
+    unless args[:models]
+      all_files = Dir.glob(Rails.root.join('app', 'models', '*.rb'))
+      all_models = all_files.map { |path| File.basename(path, '.rb').camelize.constantize }
+      sunspot_models = all_models.select { |m| m < ActiveRecord::Base and m.searchable? }
+    else
+      sunspot_models = args[:models].split('+').map{|m| m.constantize}
+    end
+    sunspot_models.each do |model|
+      model.solr_reindex reindex_options
+    end
+  end
+

data/lib/tasks/calnet_authenticated.rake

@@ -0,0 +1,6 @@
+# From `script/generate calnet_authenticated` ...
+# condition added to allow clean 'rake gems:install'
+unless Gem.source_index.find_name('ccls-calnet_authenticated').empty?
+	gem 'ccls-calnet_authenticated'
+	require 'calnet_authenticated/test_tasks'
+end

data/lib/tasks/common_lib.rake

@@ -0,0 +1,7 @@
+# From `script/generate ccls_common_lib` ...
+# condition added to allow clean 'rake gems:install'
+unless Gem.source_index.find_name('ccls-common_lib').empty?
+	gem 'ccls-common_lib'
+	require 'common_lib/tasks'
+	require 'common_lib/test_tasks'
+end

data/lib/tasks/database.rake

@@ -0,0 +1,288 @@
+namespace :db do
+
+#	desc "Import subject and address data from CSV files"
+#	task :import_csv_data => [
+#		:destroy_csv_data,
+#		:import_subject_data,
+#		:import_matchingid_and_familyid,
+#		:import_address_data,
+#		:random_enrollments_data
+#	]
+
+	desc "Destroy subject and address data"
+	task :destroy_csv_data => :environment do
+		StudySubject.destroy_all
+		Enrollment.destroy_all
+		Addressing.destroy_all
+		Address.destroy_all
+		PhoneNumber.destroy_all
+		Interview.destroy_all
+#		Identifier.destroy_all
+		Patient.destroy_all
+#		Pii.destroy_all
+#		ResponseSet.destroy_all
+#		Response.destroy_all
+		Sample.destroy_all
+		SampleKit.destroy_all
+#		Package.destroy_all
+		HomexOutcome.destroy_all
+		InterviewOutcome.destroy_all
+		HomeExposureResponse.destroy_all
+		OperationalEvent.destroy_all
+		ProjectOutcome.destroy_all
+		SampleOutcome.destroy_all
+#		Track.destroy_all
+		Transfer.destroy_all
+#		SurveyInvitation.destroy_all
+	end
+
+	task :random_enrollments_data => :environment do 
+		p = Project.find_or_create_by_code({
+			:code => "HomeExposures",
+			:description => "HomeExposures"
+		})
+		StudySubject.all.each do |s|
+			puts s.id
+			#	2440000 is sometime in 1968
+			#	2455000 is sometime in 2009
+
+			options = {
+				:study_subject => s,
+				:project => p,
+				:is_candidate => true,
+				:able_to_locate => true
+			}
+			options[:is_eligible] = [nil,1,2,999][rand(4)]
+			if options[:is_eligible] == 2
+				ir = IneligibleReason.random()
+				options[:ineligible_reason_id] = ir.id
+				if ir.is_other?
+					options[:ineligible_reason_specify] = "Random reason ineligible"
+				end
+			end
+
+			options[:is_chosen] = [nil,1,2,999][rand(4)]
+			if options[:is_chosen] == 2
+				options[:reason_not_chosen] = "Random reason not chosen"
+			end
+
+			options[:consented] = [nil,1,2,999][rand(4)]
+			if options[:consented] == 1
+				options[:consented_on] = Date.jd(2440000+rand(15000))
+			elsif options[:consented] == 2
+				options[:consented_on] = Date.jd(2440000+rand(15000))
+				rr = RefusalReason.random()
+				options[:refusal_reason_id] = rr.id
+				if rr.is_other?
+					options[:other_refusal_reason] = "Random refusal reason"
+				end
+			end
+
+			options[:terminated_participation] = [nil,1,2,999][rand(4)]
+			if options[:terminated_participation] == 1
+				options[:terminated_reason] = "Random terminated reason"
+			end
+
+			options[:is_complete] = [nil,1,2,999][rand(4)]
+			if options[:is_complete] == 1
+				options[:completed_on] = Date.jd(2440000+rand(15000))
+			end
+			Enrollment.create!(options)
+
+
+			options = {
+				:interview_outcome => InterviewOutcome.random(),
+				:sample_outcome => SampleOutcome.random()
+			}
+			if options[:interview_outcome]
+				options[:interview_outcome_on] = Date.jd(2440000+rand(15000))
+			end
+			if options[:sample_outcome]
+				options[:sample_outcome_on] = Date.jd(2440000+rand(15000))
+			end
+			s.build_homex_outcome(options)
+			s.save!
+		end
+	end
+
+#	desc "Import subject data from CSV file"
+#	task :import_subjectid => :environment do
+#		require 'fastercsv'
+#		#	DO NOT COMMENT OUT THE HEADER LINE OR IT RAISES CRYPTIC ERROR
+#		(f=FasterCSV.open('misc/dummy_subject_pii_etc.csv', 'rb',{
+#			:headers => true })).each do |line|
+##	Childid,patID,Type,OrderNo,subjectID,sex,DOB,RefDate,InterviewDate,First_Name,Middle_Name,Last_Name,Mother_First_Name,Mother_Middle_Name,Mother_Maiden_Name,Mother_Last_Name,Father_First_Name,Father_Middle_Name,Father_Last_Name,Primary_Phone,Alternate_phone1,Alternate_phone2,Alternate_phone3
+#			puts "Processing line #{f.lineno}"
+#			puts line
+#
+#			#	due to padding it with zeros, NEED this to be an Integer
+#			#	doesn't work correctly in sqlite so just pad it before search
+#			identifier = Identifier.find_by_childid(
+#				sprintf("%06d",line['Childid'].to_i))
+#			raise ActiveRecord::RecordNotFound unless identifier
+#
+#			identifier.update_attributes!(:subjectid => line['subjectID'])
+#
+#		end
+#	end
+#
+#	desc "Import matchingid and familyid data from CSV file"
+#	task :import_matchingid_and_familyid => :environment do
+#		require 'fastercsv'
+#		#	DO NOT COMMENT OUT THE HEADER LINE OR IT RAISES CRYPTIC ERROR
+#		(f=FasterCSV.open('misc/subjectmatchingfamilyids_xref.csv', 'rb',{
+#			:headers => true })).each do |line|
+##	subjectID,matchingID,familyid
+#			puts "Processing line #{f.lineno}"
+#			puts line
+#			if line['subjectID'] =~ /^\s*#/
+#				puts "skipping as subjectid not found"
+#				next 
+#			end
+#
+#			#	due to padding it with zeros, NEED this to be an Integer
+#			#	doesn't work correctly in sqlite so just pad it before search
+#			identifier = Identifier.find_by_subjectid(
+#				sprintf("%06d",line['subjectID'].to_i))
+#			raise ActiveRecord::RecordNotFound unless identifier
+#
+#			identifier.update_attributes!(
+#				:matchingid => line['matchingID'],
+#				:familyid   => line['familyid']
+#			)
+#
+#		end
+#	end
+#
+#	desc "Import address data from CSV file"
+#	task :import_address_data => :environment do
+#		require 'fastercsv'
+#		#	DO NOT COMMENT OUT THE HEADER LINE OR IT RAISES CRYPTIC ERROR
+#		(f=FasterCSV.open('misc/dummy_addresses.csv', 'rb',{
+#			:headers => true })).each do |line|
+##	subjectID,Address_Type_ID,Address_Line1,Address_City,Address_State,Address_Zip
+#			puts "Processing line #{f.lineno}"
+#			puts line
+#
+#			#	due to padding it with zeros, NEED this to be an Integer
+#			#	doesn't work correctly in sqlite so just pad it before search
+#			study_subject = Identifier.find_by_subjectid(
+#				sprintf("%06d",line['subjectID'].to_i)).study_subject
+#			raise ActiveRecord::RecordNotFound unless study_subject
+#
+##			address_type = AddressType.find(line[1].to_s)
+##			address_type = AddressType.find_by_code(
+##				(line[1].to_s == '1')?'Home':'Mailing')
+##			raise ActiveRecord::RecordNotFound unless address_type
+#
+##			study_subject.addressings << Addressing.create!(
+##				:study_subject_id  => study_subject.id,
+#			study_subject.addressings.create!(
+#				:current_address => 1,		#	Yes
+#				:is_valid    => true,
+#				:is_verified => false,
+#				:address_attributes => {
+#					:address_type_id => line['Address_Type_ID'].to_i,
+#					:line_1 => line['Address_Line1']||"FAKE LINE 1",
+#					:city => line['Address_City']||"FAKE CITY",
+#					:state => line['Address_State']||"FAKE STATE",
+#					:zip => line['Address_Zip']||"12345-6789"
+#				}
+#			)
+#		end
+#	end
+#
+#	desc "Import subject data from CSV file"
+#	task :import_subject_data => :environment do
+#		require 'fastercsv'
+#		#	DO NOT COMMENT OUT THE HEADER LINE OR IT RAISES CRYPTIC ERROR
+#		(f=FasterCSV.open('misc/dummy_subject_pii_etc.csv', 'rb',{
+#			:headers => true })).each do |line|
+##	Childid,patID,Type,OrderNo,subjectID,sex,DOB,RefDate,InterviewDate,First_Name,Middle_Name,Last_Name,Mother_First_Name,Mother_Middle_Name,Mother_Maiden_Name,Mother_Last_Name,Father_First_Name,Father_Middle_Name,Father_Last_Name,Primary_Phone,Alternate_phone1,Alternate_phone2,Alternate_phone3
+#			puts "Processing line #{f.lineno}"
+#			puts line
+#
+##			subject_type = SubjectType['Case']
+#			subject_type = SubjectType.random()
+#
+#			#	TODO	(not included in csv)
+##			race = Race[1]
+#			race = Race.random()
+#
+#			dob = (line['DOB'].blank?)?'':Time.parse(line['DOB'])
+#			refdate = (line['RefDate'].blank?)?'':Time.parse(line['RefDate'])
+#			interview_date = (line['InterviewDate'].blank?)?'':Time.parse(line['InterviewDate'])
+#			study_subject = StudySubject.create!({
+##				:patient_attributes  => { },										#	TODO (patid)
+#				:pii_attributes => {
+#					:first_name  => line['First_Name'],
+#					:middle_name => line['Middle_Name'],
+#					:last_name   => line['Last_Name'],
+#					:father_first_name  => line['Father_First_Name'],
+#					:father_middle_name => line['Father_Middle_Name'],
+#					:father_last_name   => line['Father_Last_Name'],
+#					:mother_first_name  => line['Mother_First_Name'],
+#					:mother_middle_name => line['Mother_Middle_Name'],
+#					:mother_maiden_name => line['Mother_Maiden_Name'],
+#					:mother_last_name   => line['Mother_Last_Name'],
+#					:dob => dob
+#				},
+#				:identifier_attributes => {
+#					:state_id_no       => sprintf('%09d',line['Childid']),			#	TODO
+#					:subjectid         => line['subjectID'],
+#					:ssn               => sprintf('%09d',line['Childid']),							#	TODO
+#					:patid             => line['patID'],
+#					:case_control_type => line['Type'],
+#					:orderno           => line['OrderNo'],
+#					:childid           => line['Childid'] 
+#				},
+#				:subject_type => subject_type,
+#				:sex => line['sex'],
+#				:reference_date => refdate
+#			})
+#			study_subject.races = [race]
+#
+##			Identifier.create!({
+##					:study_subject_id        => study_subject.id,
+##					:state_id_no       => sprintf('%09d',line['Childid']),			#	TODO
+##					:subjectid         => line['subjectID'],
+##					:ssn               => sprintf('%09d',line['Childid']),							#	TODO
+##					:patid             => line['patID'],
+##					:case_control_type => line['Type'],
+##					:orderno           => line['OrderNo'],
+##					:childid           => line['Childid'] 
+##				})
+#
+#			(19..22).each do |i|
+##				PhoneNumber.create!({
+#				study_subject.phone_numbers.create!({
+##					:study_subject_id    => study_subject.id,
+#					:phone_type_id => 1,
+#					:phone_number  => line[i]
+#				}) unless line[i].blank?
+#			end
+#
+#			options = {
+##				:identifier_id => study_subject.identifier.id,
+#				:interview_method => InterviewMethod.random(),
+#				:interviewer => Person.random(),
+#				:language   => Language.random(),
+#				:instrument_version => InstrumentVersion.random(),
+#				:began_on   => interview_date,
+#				:ended_on   => interview_date
+#			}
+#			options[:subject_relationship] = SubjectRelationship.random()
+#			if options[:subject_relationship].is_other?
+#				options[:subject_relationship_other] = 'super unknown god buddy'
+#			end
+#			
+##			Interview.create!(options)
+#			study_subject.interviews.create!(options)
+#			
+##	use Time.parse to parse all dates (better than Date.parse)
+#
+##	need ssn, state_id_no in data (making it up now)
+#
+#		end
+#	end
+end