bio-publisci 0.0.1

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.rspec

@@ -0,0 +1 @@
+--color

data/.travis.yml

@@ -0,0 +1,13 @@
+language: ruby
+rvm:
+  - 1.9.2
+  - 1.9.3
+  - jruby-19mode # JRuby in 1.9 mode
+
+# - rbx-19mode
+#  - 1.8.7
+#  - jruby-18mode # JRuby in 1.8 mode
+#  - rbx-18mode
+#
+# uncomment this line if your project needs to run something other than `rake`:
+# script: bundle exec rspec spec

data/Gemfile

@@ -0,0 +1,24 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "rspec", "~> 2.8.0"
+  gem "rdoc", "~> 3.12"
+  gem "cucumber", ">= 0"
+  gem "jeweler", "~> 1.8.4", :git => "https://github.com/technicalpickles/jeweler.git"
+  gem "bundler", ">= 1.0.21"
+  gem "bio", ">= 1.4.2"
+  gem "rdoc", "~> 3.12"
+end
+
+group :production do
+  gem 'rdf'
+  gem 'rdf-4store'
+  gem 'rdf-turtle'
+  gem 'rserve-client'
+  gem 'sparql'
+end

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2013 wstrinz
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,47 @@
+# bio-publisci
+
+[![Build Status](https://secure.travis-ci.org/wstrinz/bioruby-publisci.png)](http://travis-ci.org/wstrinz/bioruby-publisci)
+
+Full description goes here
+
+Note: this software is under active development!
+
+## Installation
+
+```sh
+gem install bio-publisci
+```
+
+## Usage
+
+```ruby
+require 'bio-publisci'
+```
+
+The API doc is online. For more code examples see the test files in
+the source tree.
+        
+## Project home page
+
+Information on the source tree, documentation, examples, issues and
+how to contribute, see
+
+  http://github.com/wstrinz/bioruby-publisci
+
+The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
+
+## Cite
+
+If you use this software, please cite one of
+  
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+
+## Biogems.info
+
+This Biogem is published at (http://biogems.info/index.html#bio-publisci)
+
+## Copyright
+
+Copyright (c) 2013 wstrinz. See LICENSE.txt for further details.
+

data/README.rdoc

@@ -0,0 +1,48 @@
+= bio-publisci
+
+{<img
+src="https://secure.travis-ci.org/wstrinz/bioruby-publisci.png"
+/>}[http://travis-ci.org/#!/wstrinz/bioruby-publisci]
+
+Full description goes here
+
+Note: this software is under active development!
+
+== Installation
+
+        gem install bio-publisci
+
+== Usage
+
+== Developers
+
+To use the library 
+
+        require 'bio-publisci'
+
+The API doc is online. For more code examples see also the test files in
+the source tree.
+        
+== Project home page
+
+Information on the source tree, documentation, issues and how to contribute, see
+
+  http://github.com/wstrinz/bioruby-publisci
+
+The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
+
+== Cite
+
+  If you use this software, please cite one of
+ 
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+
+== Biogems.info
+
+This Biogem is published at http://biogems.info/index.html#bio-publisci
+
+== Copyright
+
+Copyright (c) 2013 wstrinz. See LICENSE.txt for further details.
+

data/Rakefile

@@ -0,0 +1,70 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "bio-publisci"
+  gem.homepage = "http://github.com/wstrinz/bioruby-publisci"
+  gem.license = "MIT"
+  gem.summary = %Q{Publish science data using semantic web ontologies}
+  gem.description = %Q{A toolkit for publishing scientific results and datasets using RDF and related technologies }
+  gem.email = "wstrinz@gmail.com"
+  gem.authors = ["wstrinz"]
+  gem.version = "0.0.1"
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+
+require 'cucumber/rake/task'
+Cucumber::Rake::Task.new(:features)
+
+# task :default => :spec
+
+task :default => [] do
+  begin   
+    Rake::Task[:spec].invoke
+  rescue
+  end
+  Rake::Task[:features].invoke
+end
+
+task :test => [] do
+  begin   
+    Rake::Task[:spec].invoke
+  rescue
+  end
+  Rake::Task[:features].invoke
+end
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : "0.0.1"
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "bio-publisci #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/bin/bio-publisci

@@ -0,0 +1,83 @@
+#!/usr/bin/env ruby
+#
+# BioRuby bio-publisci Plugin BioPublisci
+# Author:: wstrinz
+# Copyright:: 2013
+
+USAGE = "Describe bio-publisci"
+
+gempath = File.dirname(File.dirname(__FILE__))
+$: << File.join(gempath,'lib')
+
+VERSION_FILENAME=File.join(gempath,'VERSION')
+version = File.new(VERSION_FILENAME).read.chomp
+
+# print banner
+print "bio-publisci #{version} by wstrinz 2013\n"
+
+if ARGV.size == 0
+  print USAGE
+end
+
+require 'bio-publisci'
+require 'optparse'
+
+# Uncomment when using the bio-logger 
+# require 'bio-logger'
+# Bio::Log::CLI.logger('stderr')
+# Bio::Log::CLI.trace('info')
+
+options = {:example_switch=>false,:show_help=>false}
+opts = OptionParser.new do |o|
+  o.banner = "Usage: #{File.basename($0)} [options] reponame\ne.g. #{File.basename($0)} the-perfect-gem"
+
+  o.on('--example_parameter [EXAMPLE_PARAMETER]', 'TODO: put a description for the PARAMETER') do |example_parameter|
+    # TODO: your logic here, below an example
+    options[:example_parameter] = 'this is a parameter'
+  end
+  
+  o.separator ""
+  o.on("--switch-example", 'TODO: put a description for the SWITCH') do
+    # TODO: your logic here, below an example
+    self[:example_switch] = true
+  end
+
+  # Uncomment the following when using the bio-logger 
+  # o.separator ""
+  # o.on("--logger filename",String,"Log to file (default stderr)") do | name |
+  #   Bio::Log::CLI.logger(name)
+  # end
+  #
+  # o.on("--trace options",String,"Set log level (default INFO, see bio-logger)") do | s |
+  #   Bio::Log::CLI.trace(s)
+  # end
+  # 
+  # o.on("-q", "--quiet", "Run quietly") do |q|
+  #   Bio::Log::CLI.trace('error')
+  # end
+  # 
+  # o.on("-v", "--verbose", "Run verbosely") do |v|
+  #   Bio::Log::CLI.trace('info')
+  # end
+  # 
+  # o.on("--debug", "Show debug messages") do |v|
+  #   Bio::Log::CLI.trace('debug')
+  # end
+
+  o.separator ""
+  o.on_tail('-h', '--help', 'display this help and exit') do
+    options[:show_help] = true
+  end
+end
+
+begin
+  opts.parse!(ARGV)
+
+  # Uncomment the following when using the bio-logger 
+  # Bio::Log::CLI.configure('bio-publisci')
+
+  # TODO: your code here
+  # use options for your logic
+rescue OptionParser::InvalidOption => e
+  options[:invalid_argument] = e.message
+end

data/features/create_generator.feature

@@ -0,0 +1,25 @@
+Feature: create generators
+
+	In order to check that objects conform to a common interface
+	I want to be able to call a generate method on various classes 
+
+	Scenario: create a Dataframe generator
+		Given a Dataframe generator
+		Then I should be able to call its generate_n3 method
+
+	Scenario: create a CSV generator
+		Given a CSV generator
+		Then I should be able to call its generate_n3 method	
+
+	Scenario: create a RMatrix generator
+		Given a RMatrix generator
+		Then I should be able to call its generate_n3 method
+
+	Scenario: create a Cross generator
+		Given a Cross generator
+		Then I should be able to call its generate_n3 method	
+
+	Scenario: create a BigCross generator
+		Given a BigCross generator
+		Then I should be able to call its generate_n3 method	
+

data/features/integration.feature

@@ -0,0 +1,12 @@
+Feature: Integrate with other GSOC projects
+
+  In order to leverage the data sharing and comprehension power of RDF
+  I want to integrate my code with that of other GSOC students
+
+  Scenario: Integrate with Ruby Mining
+    Given a CSV generator
+    When I provide the reference file spec/csv/moar_bacon.csv and the label "moar_bacon" and the options {dimensions:["producer","pricerange"]}
+    And generate a turtle string from it
+    Given a ARFF writer
+    When I call its from_turtle method on the turtle string
+    Then I should be able to cluster the result and print statistics

data/features/integration_steps.rb

@@ -0,0 +1,10 @@
+Then(/^I should be able to cluster the result and print statistics$/) do
+  require 'ruby_mining'
+  f=Tempfile.open('arff'); f.write @result; f.close
+  clustering = Weka::Clusterer::SimpleKMeans::Base
+  clustering.set_options "-N 5"
+  clustering.set_data(Core::Parser::parse_ARFF(f.path))
+  f.unlink
+  clustered = clustering.new
+  puts clustered
+end

data/features/orm.feature

@@ -0,0 +1,60 @@
+Feature: generate data using ORM
+	
+	In order to make the generator simpler and more accessible to ruby users
+	I want to implement an ORM (OTM? OGM?) to assist creation of datacube objects
+
+	Scenario: build data cube and export turtle
+		Given an ORM::DataCube entitled "cats"
+		When I add a "size" dimension
+		And I add a "breed" dimension
+		And I add a "fluffiness" measure
+		And I add the observation {size: "big", breed: "American Shorthair", fluffiness: 100}
+		And I add the observation {size: "huge", breed: "Maine Coon", fluffiness: 9001}
+		And I add the observation {size: "little", breed: "American Shorthair", fluffiness: 15}
+    Then the to_n3 method should return a string
+
+  Scenario: load from turtle string
+  	Given a turtle string from file spec/turtle/bacon
+  	When I call the ORM::DataCube class method load on it
+  	Then I should receive an ORM::DataCube object
+    And the to_n3 method should return a string
+
+  Scenario: load from endpoint
+  	Given the URI string "http://localhost:8080"
+  	When I call the ORM::DataCube class method load on it
+  	Then I should receive an ORM::DataCube object
+    And the to_n3 method should return a string
+
+  Scenario: raise error when unknown components are used
+    Given an ORM::DataCube entitled "animals"
+    When I add a "robustness" dimension
+    And I add a "species" measure
+    And I add the observation {species: "Balaenoptera musculus", robustness: 25}
+    And I add the observation {species: "Hypsibius dujardini", robustness: 9001}
+    Then the to_n3 method should return a string
+    When I add the observation {species: "Deinococcus radiodurans", robustness: 350, chunkiness: 9}
+    Then the to_n3 method should raise error UnknownProperty ["chunkiness"]
+
+  Scenario: raise error when components are missing
+    Given an ORM::DataCube entitled "animals"
+    When I add a "robustness" dimension
+    And I add a "species" measure
+    And I add the observation {species: "Felis catus"}
+    Then the to_n3 method should raise error MissingValues for ["robustness"]
+
+  Scenario: raise error when components are missing
+    Given an ORM::DataCube entitled "animals" with the following options: 
+    | key | value |
+    | :validate_each | true |
+    When I add a "robustness" dimension
+    And I add a "species" measure
+    Then adding the observation {species: "Caenorhabditis elegans"} should raise error MissingValues for ["robustness"]
+
+  Scenario: add metadata
+    Given an ORM::DataCube entitled "meta"
+    When I add a "robustness" dimension
+    And I add a "species" measure
+    And I add the observation {species: "Hypsibius dujardini", robustness: 9001}
+    And I call the cubes add_publisher method with the arguments "Moss Piglets Unlimited", "http://mosspiglet.org/"
+		Then the to_n3 method should return a string with a "dct:publisher"
+

data/features/orm_steps.rb

@@ -0,0 +1,74 @@
+require_relative '../lib/bio-publisci.rb'
+
+Given /^an ORM::DataCube entitled "(.*?)"$/ do |name|
+	@cube = R2RDF::Dataset::ORM::DataCube.new(name: name)
+end
+
+Given /^an ORM::DataCube entitled "(.*?)" with the following options:$/ do |name, opts|
+	options_hash = {name: name}
+	opts.hashes.map{|hash|
+		k = hash["key"]
+		k = k[1..-1].to_sym if k[0] == ":"
+
+		v = hash["value"]
+		v = v[1..-1].to_sym if k[0] == ":"
+		
+		v = true if v =="true"
+		v = false if v =="false"
+
+		options_hash[k] = v
+	}
+	@cube = R2RDF::Dataset::ORM::DataCube.new(options_hash)
+end
+
+Given(/^a turtle string from file (.*)$/) do |file|
+	@string = IO.read(file)
+end
+
+Given(/^the URI string "(.*?)"$/) do |uri|
+  @string = uri
+end
+
+When(/^I call the ORM::DataCube class method load on it$/) do
+  @cube = R2RDF::Dataset::ORM::DataCube.load(@string)
+end
+
+When /^I add a "(.*?)" dimension$/ do |dim|
+	@cube.add_dimension(dim)
+end
+
+When /^I add a "(.*?)" measure$/ do |meas|
+	@cube.add_measure(meas)
+end
+
+When /^I add the observation (.*)$/ do |obs|
+	data = eval(obs)
+	# obs.split(',').map{|entry| data[entry.chomp.strip.split(':')[0].to_s] = eval(entry.chomp.strip.split(':')[1])}
+	@cube.add_observation(data)
+end
+
+When /^adding the observation (.*) should raise error (.*)$/ do |obs,err|
+	data = eval(obs)
+	expect { @cube.add_observation(data) }.to raise_error(err)
+end
+
+When /^I call the cubes (.*) method with the arguments (.*)$/ do |method,args|
+  eval("args = #{args}")
+  @cube.send(method.to_sym, *args)
+end
+
+Then /^the to_n3 method should return a string$/ do
+	@cube.to_n3.is_a?(String).should be true
+end
+
+Then /^the to_n3 method should raise error (.*?)$/ do |err|
+	expect { @cube.to_n3 }.to raise_error(err)
+end
+
+Then /^the to_n3 method should return a string with a "(.*?)"$/ do |search|
+	@cube.to_n3[search].should_not be nil
+end
+
+Then(/^I should receive an ORM::DataCube object$/) do
+  @cube.is_a?(R2RDF::Dataset::ORM::DataCube).should == true
+end

data/features/reader.feature

@@ -0,0 +1,25 @@
+Feature: generate RDF
+
+	In order to test the generators
+	I want to be able to create turtle strings from various objects
+
+	Scenario: generate turtle RDF from a Dataframe
+		Given a Dataframe generator
+		When I provide an R dataframe and the label "mr"
+			And generate a turtle string from it 
+		Then the result should contain a "qb:dataSet"
+			And the result should contain some "qb:Observation"s
+
+	Scenario: generate turtle RDF from a CSV
+		Given a CSV generator
+		When I provide the reference file spec/csv/bacon.csv and the label "bacon"
+			And generate a turtle string from it 
+		Then the result should contain a "qb:dataSet"
+			And the result should contain some "qb:Observation"s
+
+	Scenario: generate turtle RDF from an ARFF file
+		Given a ARFF generator
+		When I provide the file resources/weather.numeric.arff
+			And generate a turtle string from it 
+		Then the result should contain a "qb:dataSet"
+			And the result should contain some "qb:Observation"s

data/features/reader_steps.rb

@@ -0,0 +1,60 @@
+require_relative '../lib/bio-publisci.rb'
+
+Given /^a (.*) generator$/ do |generator|
+	@generator = R2RDF::Reader.const_get(generator).new
+end
+
+When /^I ask for its methods$/ do
+	@methods = @generator.methods
+end
+
+When /^I provide an R (.*) and the label "(.*?)"$/ do |type, label|
+	if type == "dataframe"
+		r = Rserve::Connection.new
+		r.eval <<-EOF
+			library(qtl)
+			data(listeria)
+			mr = scanone(listeria,method="mr")
+EOF
+		rexp = r.eval 'mr'
+		@attr = rexp,label
+	else
+		raise "Unknown object #{type}"
+	end
+
+end
+
+When /^I provide the.* file (.*) and the label "(.*?)"$/ do |file, label|
+	raise "Cant find #{file}" unless File.exist? file
+	@attr = file,label
+end
+
+When /^I provide the.* file (.*) and the label "(.*?)" and the options (.*)$/ do |file, label, opts|
+  raise "Cant find #{file}" unless File.exist? file
+  @attr = file,label,eval(opts)
+end
+
+When /^I provide the.* file (\S+)$/ do |file|
+	raise "Cant find #{file}" unless File.exist? file
+	@attr = file
+end
+
+When /^generate a turtle string from it$/ do
+	@turtle_string = @generator.send :generate_n3, *@attr
+end
+
+Then /^I should have access to a (.*) method$/ do |method|
+	@methods.include?(method).should == true
+end
+
+Then /^I should be able to call its (.*) method$/ do |method|
+	@generator.methods.include?(:"#{method}").should == true
+end
+
+Then /^the result should contain a "(.*?)"$/ do |search|
+	@turtle_string[search].should_not be nil
+end
+
+Then /^the result should contain some "(.*?)"s$/ do |search|
+	@turtle_string[search].size.should > 1
+end

data/features/store.feature

@@ -0,0 +1,27 @@
+Feature: load triples into a store
+
+	In order to query and share data
+	I want to be able load the output into a variety of store 
+
+	Scenario: Use an RDF::Graph to store data
+		Given a store of type graph
+		When I call the stores add method with the turtle file spec/turtle/bacon and an RDF::Repository
+		Then I should recieve a non-empty graph
+
+	Scenario: Use 4store to store data
+		Given a store of type fourstore
+		When I call the stores add method with the turtle file spec/turtle/bacon and the graph name "test"
+		Then I should receive an info string
+
+	Scenario: Run queries on store
+		Given a store of type fourstore
+		When I call the query method using the text in file spec/queries/integrity/1.rq
+		Then I should receive 0 results
+		When I call the query method using the text in file resources/queries/test.rq
+		Then I should receive 10 results
+
+	Scenario: Run queries on graph based store
+		Given a store of type graph
+		When I call the stores add method with the turtle file spec/turtle/bacon and an RDF::Repository
+		Then calling the query method using the text in file spec/queries/integrity/1.rq should return 0 results
+		And calling the query method using the text in file resources/queries/test.rq should return 10 results

data/features/store_steps.rb

@@ -0,0 +1,42 @@
+require_relative '../lib/bio-publisci.rb'
+
+Given /a store of type (.*?)$/ do |type|
+	@store = R2RDF::Store.new(type: :"#{type}")
+end
+
+When /^I call the stores add method with the turtle file (.*?) and an RDF::(.*?)$/ do |file,graph|
+	graph = RDF.const_get(graph).new #rescue graph
+	@graph = @store.add(file,graph)
+end
+
+When /^I call the stores add method with the turtle file (.*?) and the graph name "(.*?)"$/ do |file,graph|
+	@graph = @store.add(file,graph)
+end
+
+
+When /^I call the query method using the text in file (.*)$/ do |file|
+	query_string = IO.read(file)
+	@query_result  = @store.query(query_string)
+end
+
+Then /^calling the query method using the text in file (.*) should return (.*) results$/ do |file, num|
+	query_string = IO.read(file)
+	@store.query(query_string) #.size.should == num
+end
+
+Then /^I should recieve a non-empty graph$/ do
+	@graph.is_a?(RDF::Repository).should be true
+	@graph.size.should > 0
+end
+
+Then /^I should receive an info string$/ do
+	@graph.is_a?(String).should be true
+end
+
+Then /^I should receive (.*) results$/ do |num|
+	@query_result.size.should == num.to_i
+end
+
+# Then /^raise the result$/ do
+# 	raise "got @graph"
+# end

data/features/support/env.rb

@@ -0,0 +1,13 @@
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+
+$LOAD_PATH.unshift(File.dirname(__FILE__) + '/../../lib')
+require 'bio-publisci'
+
+require 'rspec/expectations'