unipept 0.7.1 → 0.8.0

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unipept
 version: !ruby/object:Gem::Version
-  version: 0.7.1
+  version: 0.8.0
 platform: ruby
 authors:
 - Toon Willems
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-05-20 00:00:00.000000000 Z
+date: 2015-06-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cri
@@ -41,75 +41,75 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.6'
 - !ruby/object:Gem::Dependency
-  name: shoulda
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: rdoc
+  name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: jeweler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: simplecov
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '0'
 description: |2
     Command line interface to the Unipept (http://unipept.ugent.be) web services
     (pept2lca, taxa2lca, pept2taxa and taxonomy) and some utility commands for
@@ -126,6 +126,8 @@ extra_rdoc_files:
 - README.md
 files:
 - ".document"
+- ".rubocop.yml"
+- ".travis.yml"
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -136,20 +138,40 @@ files:
 - bin/prot2pept
 - bin/unipept
 - bin/uniprot
-- lib/unipept.rb
-- lib/unipept/batch_order.rb
-- lib/unipept/commands.rb
-- lib/unipept/commands/api_runner.rb
-- lib/unipept/commands/pept2lca.rb
-- lib/unipept/commands/pept2prot.rb
-- lib/unipept/commands/pept2taxa.rb
-- lib/unipept/commands/taxa2lca.rb
-- lib/unipept/commands/taxonomy.rb
-- lib/unipept/configuration.rb
-- lib/unipept/formatters.rb
-- lib/unipept/version.rb
+- lib/batch_iterator.rb
+- lib/batch_order.rb
+- lib/commands.rb
+- lib/commands/peptfilter.rb
+- lib/commands/prot2pept.rb
+- lib/commands/unipept.rb
+- lib/commands/unipept/api_runner.rb
+- lib/commands/unipept/config.rb
+- lib/commands/unipept/pept2lca.rb
+- lib/commands/unipept/pept2prot.rb
+- lib/commands/unipept/pept2taxa.rb
+- lib/commands/unipept/taxa2lca.rb
+- lib/commands/unipept/taxonomy.rb
+- lib/commands/uniprot.rb
+- lib/configuration.rb
+- lib/formatters.rb
+- lib/version.rb
+- test/commands/test_peptfilter.rb
+- test/commands/test_prot2pept.rb
+- test/commands/test_unipept.rb
+- test/commands/test_uniprot.rb
+- test/commands/unipept/test_api_runner.rb
+- test/commands/unipept/test_config.rb
+- test/commands/unipept/test_pept2lca.rb
+- test/commands/unipept/test_pept2prot.rb
+- test/commands/unipept/test_pept2taxa.rb
+- test/commands/unipept/test_taxa2lca.rb
+- test/commands/unipept/test_taxonomy.rb
 - test/helper.rb
-- test/test_unipept.rb
+- test/test_bach_order.rb
+- test/test_base.rb
+- test/test_batch_iterator.rb
+- test/test_configuration.rb
+- test/test_formatters.rb
 - unipept.gemspec
 homepage: https://github.com/unipept/unipept-cli/
 licenses:
@@ -171,7 +193,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.1.11
 signing_key: 
 specification_version: 4
 summary: Command line interface to Unipept web services.

data/lib/unipept/batch_order.rb

@@ -1,28 +0,0 @@
-module Unipept
-
-  class BatchOrder
-
-    attr_reader :order
-
-    def initialize
-      @order = {}
-      @current = 0
-    end
-
-    def wait(i, &block)
-      if i == @current
-        # start writing + those who have been waiting as well
-        block.call
-        @current += 1
-        while order[@current]
-          order.delete(@current).call
-          @current += 1
-        end
-      else
-        @order[i] = block
-      end
-    end
-
-  end
-
-end

data/lib/unipept/commands/api_runner.rb

@@ -1,239 +0,0 @@
-require 'set'
-
-module Unipept::Commands
-  class ApiRunner < Cri::CommandRunner
-    def initialize(args, opts, cmd)
-      super
-      @configuration = Unipept::Configuration.new
-      set_configuration
-
-      @user_agent = 'Unipept CLI - unipept ' + Unipept::VERSION
-
-      @url = "#{@host}/api/v1/#{cmd.name}.json"
-      @message_url = "#{@host}/api/v1/messages.json"
-    end
-
-    def set_configuration
-      # find host in opts first
-      if options[:host]
-        host = options[:host]
-      else
-        host = @configuration['host']
-      end
-
-      # No host has been set?
-      if host.nil? || host.empty?
-        puts 'WARNING: no host has been set, you can set the host with `unipept config host http://localhost:3000/`'
-        exit 1
-      end
-      unless host.start_with? 'http://'
-        host = "http://#{host}"
-      end
-
-      @host = host
-    end
-
-    def input_iterator
-      # Argument over file input over stdin
-      if !arguments.empty?
-        arguments.each
-      else
-        if options[:input]
-          IO.foreach(options[:input])
-        else
-          STDIN.each_line
-        end
-      end
-    end
-
-    def batch_size
-      100
-    end
-
-    def url_options(sub_part)
-      filter = options[:select] ? options[:select] : []
-      if filter.empty?
-        names = true
-      else
-        names = filter.any? { |f| /.*name.*/.match f }
-      end
-      { input: sub_part,
-        equate_il: options[:equate],
-        extra: options[:all],
-        names: names
-      }
-    end
-
-    def get_server_message
-      return if options[:quiet]
-      return unless STDOUT.tty?
-      last_fetched = @configuration['last_fetch_date']
-      if last_fetched.nil? || (last_fetched + 60 * 60 * 24) < Time.now
-        version = Unipept::VERSION
-        resp = Typhoeus.get(@message_url, params: { version: version })
-        puts resp.body unless resp.body.chomp.empty?
-        @configuration['last_fetch_date'] = Time.now
-        @configuration.save
-      end
-    end
-
-    def run
-      get_server_message
-
-      formatter = Unipept::Formatter.new_for_format(options[:format])
-      peptides = input_iterator
-
-      filter_list = options[:select] ? options[:select] : []
-      # Parse filter list: convert to regex and split on commas
-      filter_list = filter_list.map { |f| f.include?(',') ? f.split(',') : f }.flatten.map { |f| glob_to_regex(f) }
-
-      batch_order = Unipept::BatchOrder.new
-
-      printed_header = false
-      result = []
-
-      hydra = Typhoeus::Hydra.new(max_concurrency: 10)
-      num_req = 0
-
-      peptide_iterator(peptides) do |sub_division, i, fasta_input|
-        request = Typhoeus::Request.new(
-          @url,
-          method: :post,
-          body: url_options(sub_division),
-          accept_encoding: 'gzip',
-          headers: { 'User-Agent' => @user_agent }
-        )
-        request.on_complete do |resp|
-          if resp.success?
-            # if JSON parsing goes wrong
-            sub_result = JSON[resp.response_body] rescue []
-            sub_result = [sub_result] unless sub_result.is_a? Array
-
-            sub_result.map! { |r| r.select! { |k, _v| filter_list.any? { |f| f.match k } } } unless filter_list.empty?
-
-            if options[:xml]
-              result << sub_result
-            end
-
-            # wait till it's our turn to write
-            batch_order.wait(i) do
-              unless sub_result.empty?
-                unless printed_header
-                  write_to_output formatter.header(sub_result, fasta_input)
-                  printed_header = true
-                end
-                write_to_output formatter.format(sub_result, fasta_input)
-              end
-            end
-
-          elsif resp.timed_out?
-
-            batch_order.wait(i) do
-              $stderr.puts 'request timed out, continuing anyway, but results might be incomplete'
-              save_error('request timed out, continuing anyway, but results might be incomplete')
-            end
-
-          elsif resp.code == 0
-
-            batch_order.wait(i) do
-              $stderr.puts 'could not get an http response, continuing anyway, but results might be incomplete'
-              save_error(resp.return_message)
-            end
-
-          else
-
-            batch_order.wait(i) do
-              $stderr.puts "received a non-successful http response #{resp.code}, continuing anyway, but results might be incomplete"
-              save_error("Got #{resp.code}: #{resp.response_body}\nRequest headers: #{resp.request.options}\nRequest body:\n#{resp.request.encoded_body}\n\n")
-            end
-
-          end
-        end
-
-        hydra.queue request
-
-        num_req += 1
-        if num_req % 200 == 0
-          hydra.run
-        end
-      end
-
-      hydra.run
-
-      begin
-        download_xml(result)
-      rescue
-        STDERR.puts 'Something went wrong while downloading xml information! please check the output'
-      end
-    end
-
-    def save_error(message)
-      path = File.expand_path(File.join(Dir.home, '.unipept', "unipept-#{Time.now.strftime('%F-%T')}.log"))
-      FileUtils.mkdir_p File.dirname(path)
-      File.open(path, 'w') do |f|
-        f.write message
-      end
-      $stderr.puts "API request failed! log can be found in #{path}"
-    end
-
-    def write_to_output(string)
-      if options[:output]
-        File.open(options[:output], 'a') do |f|
-          f.write string
-        end
-      else
-        puts string
-      end
-    end
-
-    def download_xml(result)
-      if options[:xml]
-        File.open(options[:xml] + '.xml', 'wb') do |f|
-          f.write Typhoeus.get("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=taxonomy&id=#{result.first.map { |h| h['taxon_id'] }.join(',')}&retmode=xml").response_body
-        end
-      end
-    end
-
-    def peptide_iterator(peptides, &block)
-      first = peptides.next rescue return
-      if first.start_with? '>'
-        # FASTA MODE ENGAGED
-        fasta_header = first.chomp
-        peptides.each_slice(batch_size).with_index do |sub, i|
-          fasta_input = []
-          # Use a set so we don't ask data twice
-          newsub = Set.new
-
-          # Iterate to find fasta headers
-          sub.each do |s|
-            s.chomp!
-            if s.start_with? '>'
-              # Save the FASTA header when found
-              fasta_header = s
-            else
-              # Add the input pair to our input list
-              fasta_input << [fasta_header, s]
-              newsub << s
-            end
-          end
-
-          block.call(newsub.to_a, i, fasta_input)
-        end
-      else
-        # shame we have to be this explicit, but it appears to be the only way
-        Enumerator.new do |y|
-          y << first
-          loop do
-            y << peptides.next
-          end
-        end.each_slice(batch_size).with_index(&block)
-      end
-    end
-
-    private
-
-    def glob_to_regex(string)
-      /^#{string.gsub('*', '.*')}$/
-    end
-  end
-end

data/lib/unipept/commands/pept2lca.rb

@@ -1,6 +0,0 @@
-require_relative 'api_runner'
-module Unipept::Commands
-  class Pept2lca < ApiRunner
-  end
-end
-

data/lib/unipept/commands/pept2prot.rb

@@ -1,20 +0,0 @@
-require_relative 'api_runner'
-
-module Unipept::Commands
-  class Pept2prot < ApiRunner
-    def download_xml(result)
-      if options[:xml]
-        FileUtils.mkdir_p(options[:xml])
-        result.first.each do |prot|
-          File.open(options[:xml] + "/#{prot['uniprot_id']}.xml", "wb") do |f|
-            f.write Typhoeus.get("http://www.uniprot.org/uniprot/#{prot['uniprot_id']}.xml").response_body
-          end
-        end
-      end
-    end
-
-    def batch_size
-      10
-    end
-  end
-end

data/lib/unipept/commands/taxa2lca.rb

@@ -1,12 +0,0 @@
-require_relative 'api_runner'
-module Unipept::Commands
-  class Taxa2lca < ApiRunner
-    def peptide_iterator(peptides, &block)
-      block.call(peptides.to_a, 0)
-    end
-
-    def batch_size
-      raise "NOT NEEDED FOR TAXA2LCA"
-    end
-  end
-end

data/lib/unipept/commands.rb

@@ -1,7 +0,0 @@
-['pept2lca','pept2taxa','pept2prot','taxa2lca','taxonomy'].each do |cmd|
-  require_relative File.join('commands',cmd)
-end
-module Unipept
-  module Commands
-  end
-end

data/lib/unipept/configuration.rb

@@ -1,29 +0,0 @@
-module Unipept
-  class Configuration
-
-    attr_reader :config
-    attr_reader :file_name
-
-    def initialize
-      @file_name = File.join(Dir.home, ".unipeptrc")
-      if !File.exists? file_name
-        @config = {}
-      else
-        @config = YAML.load_file file_name
-      end
-    end
-
-    def save
-      File.open(file_name, 'w') { |f| f.write config.to_yaml }
-    end
-
-    def [](*args)
-      config.[](*args)
-    end
-
-    def []=(*args)
-      config.[]=(*args)
-    end
-
-  end
-end

data/lib/unipept/formatters.rb

@@ -1,135 +0,0 @@
-module Unipept
-  class Formatter
-
-    def self.formatters
-      @@formatters ||= {}
-    end
-
-    def self.new_for_format(format)
-      begin
-        formatters[format].new
-      rescue
-        formatters[self.default].new
-      end
-    end
-
-    def self.register(format)
-      self.formatters[format.to_s] = self
-    end
-
-    def self.available
-      self.formatters.keys
-    end
-
-    def self.default
-      'csv'
-    end
-
-    def header(sample_data, fasta_mapper = nil)
-      ""
-    end
-
-    # JSON formatted data goes in, something other comes out
-    def format(data, fasta_mapper = nil)
-      data
-    end
-  end
-
-  class JSONFormatter < Formatter
-    require 'json'
-    register :json
-
-    def format(data, fasta_mapper = nil)
-      # TODO: add fasta header based on fasta_mapper information
-      data.to_json
-    end
-
-  end
-  class CSVFormatter < Formatter
-    require 'csv'
-
-    register :csv
-
-    def header(data, fasta_input = nil)
-      CSV.generate do |csv|
-        first = data.first
-        if first.kind_of? Array
-          first = first.first
-        end
-        if fasta_input
-          csv << (['fasta_header'] + first.keys).map(&:to_s) if first
-        else
-          csv << first.keys.map(&:to_s) if first
-        end
-      end
-    end
-
-    def format(data, fasta_input = nil)
-      CSV.generate do |csv|
-
-        if fasta_input
-          # Process the output from {key1: value1, key2: value2, ...}
-          # to {value => {key1: value1, key2: value2, ...}}
-          data_dict = {}
-          data.each do |d|
-            data_dict[d.values.first.to_s] ||= []
-            data_dict[d.values.first.to_s] << d
-          end
-
-          # Iterate over the input
-          fasta_input.each do |input_pair|
-            fasta_header, id = input_pair
-
-            # Retrieve the corresponding API result (if any)
-            unless data_dict[id].nil?
-              data_dict[id].each do |r|
-                csv << ([fasta_header] + r.values).map { |v| v == "" ? nil : v }
-              end
-            end
-          end
-
-        else
-
-          data.each do |o|
-            csv << o.values.map { |v| v == ""  ? nil : v }
-          end
-
-        end
-      end
-    end
-  end
-
-  class XMLFormatter < Formatter
-
-    # Monkey patch (do as to_xml, but saner)
-
-    class ::Object
-      def to_xml(name = nil)
-        name ? %{<#{name}>#{self.to_s}</#{name}>} : self.to_s
-      end
-    end
-
-    class ::Array
-      def to_xml(array_name = :array, item_name = :item)
-        %|<#{array_name} size="#{self.size}">| + self.map{|n|n.to_xml( :item )}.join+"</#{array_name}>"
-      end
-    end
-
-    class ::Hash
-      def to_xml(name = nil)
-        data = to_a.map{|k,v|v.to_xml(k)}.join
-        name ? "<#{name}>#{data}</#{name}>" : data
-      end
-    end
-
-    register :xml
-
-    def format(data, fasta_mapper = nil)
-      # TODO: add fasta header based on fasta_mapper information
-      data.to_xml
-    end
-
-  end
-
-
-end

data/lib/unipept/version.rb

@@ -1,3 +0,0 @@
-module Unipept
-  VERSION = File.read(File.join(File.dirname(__FILE__), '..', '..', 'VERSION')).strip
-end

data/lib/unipept.rb

@@ -1,8 +0,0 @@
-require_relative 'unipept/formatters'
-require_relative 'unipept/configuration'
-require_relative 'unipept/batch_order'
-require_relative 'unipept/commands'
-require_relative 'unipept/version'
-
-module Unipept
-end

data/test/test_unipept.rb

@@ -1,7 +0,0 @@
-require 'helper'
-
-class TestUnipept < Test::Unit::TestCase
-  should "probably rename this file and start testing for real" do
-    flunk "hey buddy, you should probably rename this file and start testing for real"
-  end
-end