entrez 0.5.6 → 0.5.7

data/.rspec

@@ -0,0 +1 @@
+--colour

data/README.rdoc

@@ -54,9 +54,14 @@ args:
 
   Entrez.ESearch('genomeprj', {WORD: 'hapmap', SEQS: 'inprogress'}, retmode: :xml)
   #=> makes request to http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=genomeprj&term=hapmap[WORD]+AND+inprogress[SEQS]&retmode=xml.
-  #=> returns XML document with list of Ids of genome projects that match the searc term criteria.
+  #=> returns XML document with list of ids of genome projects that match the searc term criteria.
   #=> i.e. genome projects that have 'hapmap' in the description and whose sequencing status is 'inprogress'.
 
+The response has a convenience method to retrieve the parsed ids.
+
+  response = Entrez.ESearch('genomeprj', {WORD: 'hapmap', SEQS: 'inprogress'}, retmode: :xml)
+  response.ids #=> [1, 2, ...]
+
 ==== Customized Queries
 
 You can build your own customized queries if you have something more complex with ANDs and ORs.

data/entrez.gemspec

@@ -19,7 +19,10 @@ Gem::Specification.new do |s|
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
 
-  s.add_runtime_dependency 'httparty' # Written with version 0.7.3.
-  s.add_development_dependency 'rspec', '2.4.0'
+  s.add_runtime_dependency 'httparty' # Written with version 0.7.8.
+
+  s.add_development_dependency 'awesome_print'
+  s.add_development_dependency 'fakeweb', '1.3.0'
+  s.add_development_dependency 'rspec', '2.6.0'
 
 end

data/lib/entrez.rb

@@ -1,4 +1,5 @@
 require 'httparty'
+require 'httparty/response_ext'
 require 'query_string_normalizer'
 
 class Entrez
@@ -21,12 +22,10 @@ class Entrez
     end
 
     # E.g. Entrez.ESearch('genomeprj', {WORD: 'hapmap', SEQS: 'inprogress'}, retmode: :xml)
-    # returns response. For convenience, response.ids() returns array of ID integers from result set.
     # search_terms can also be string literal.
     def ESearch(db, search_terms = {}, params = {})
       params[:term] = search_terms.is_a?(Hash) ? convert_search_term_hash(search_terms) : search_terms
       response = perform '/esearch.fcgi', db, params
-      parse_ids_and_extend response if response[:retmode].nil? || response[:retmode] == :xml
       response
     end
 
@@ -58,15 +57,18 @@ class Entrez
 
     private
 
+    # NCBI does not allow more than 3 requests per second.
+    # Unless 3 requests ago was more than 1 second ago,
+    # sleep for enough time to honor limit.
     def respect_query_limit
       three_requests_ago = request_times[-3]
       return unless three_requests_ago
-      three_requests_ago = three_requests_ago.to_f
-      now = Time.now.to_f
-      enough_time_has_passed = now > three_requests_ago + 1
+      time_for_last_3_requeests = Time.now.to_f - three_requests_ago
+      enough_time_has_passed = time_for_last_3_requeests >= 1
       unless enough_time_has_passed
-        STDERR.puts "sleeping #{now - three_requests_ago}"
-        sleep(now - three_requests_ago)
+        sleep_time = 1 - time_for_last_3_requeests
+        STDERR.puts "sleeping #{sleep_time}"
+        sleep(sleep_time)
       end
     end
 
@@ -74,22 +76,6 @@ class Entrez
       @request_times ||= []
     end
 
-    # Define ids() method which will parse and return the IDs from the XML response.
-    def parse_ids_and_extend(response)
-      response.instance_eval do
-        def ids
-          return @ids if @ids
-          id_content = self['eSearchResult']['IdList']['Id']
-          # If there is only 1, Crack will parse it and return just the string.
-          # Need to always return array.
-          id_content = [id_content].flatten
-          @ids = id_content.map(&:to_i)
-        rescue ::NoMethodError
-          @ids = []
-        end
-      end
-    end
-
   end
 
   class UnknownOperator < StandardError

data/lib/entrez/version.rb

@@ -1,3 +1,3 @@
 module Entrez
-  VERSION = "0.5.6"
+  VERSION = "0.5.7"
 end

data/lib/httparty/response/ids.rb

@@ -0,0 +1,32 @@
+module HTTParty
+
+  module ResponseIds
+
+    # For ESearch, add convenience method that parses ids and converts to array of integers.
+    # Only works if either no retern mode specified or if it is :xml.
+    def ids
+      if parse_ids?
+        return @ids if @ids
+        id_list = parsed_response['eSearchResult']['IdList']
+        if id_list
+          id_content = id_list['Id']
+          id_content = [id_content].flatten
+          @ids = id_content.map(&:to_i)
+        else
+          @ids = []
+        end
+      end
+    end
+
+    private
+
+    # Parse only if this is an ESearch request and in xml format.
+    def parse_ids?
+      esearch_request? && (retmode.nil? || xml?)
+    end
+
+  end
+
+end
+
+HTTParty::Response.send :include, HTTParty::ResponseIds

data/lib/httparty/response_ext.rb

@@ -0,0 +1,22 @@
+require 'httparty/response/ids'
+
+module HTTParty
+  module ResponseExt
+
+    # Get the return mode from request.
+    def retmode
+      request.options[:query][:retmode]
+    end
+
+    def xml?
+      retmode == :xml
+    end
+
+    def esearch_request?
+      request.path.to_s.match /esearch/
+    end
+
+  end
+end
+
+HTTParty::Response.send :include, HTTParty::ResponseExt

data/spec/entrez_spec.rb

@@ -8,7 +8,7 @@ describe Entrez do
   end
 
   it '#EFetch retrieves results' do
-    response = Entrez.EFetch('taxonomy', id: 9606, retmode: :xml)
+    response = Entrez.EFetch('taxonomy', id: 9606)
     response.body.should include('Homo sapiens')
   end
 
@@ -18,39 +18,23 @@ describe Entrez do
   end
 
   it '#EInfo retrieves results' do
-    response = Entrez.EInfo('snp', retmode: :xml)
+    response = Entrez.EInfo('snp')
     response.body.should include('<Name>RS</Name>')
   end
 
   context '#ESearch' do
 
     it 'retrieves results' do
-      response = Entrez.ESearch('genomeprj', {WORD: 'hapmap', SEQS: 'inprogress'}, retmode: :xml)
+      response = Entrez.ESearch('genomeprj', {WORD: 'hapmap', SEQS: 'inprogress'})
       response.body.should include('28911')
     end
 
-    it 'response returns IDs for convenience' do
-      response = Entrez.ESearch('genomeprj', {WORD: 'hapmap', SEQS: 'inprogress'}, retmode: :xml)
-      response.ids.should == [60153, 29429, 28911, 48101, 59851, 59849, 59847, 59845, 59839, 59835, 59833, 59831, 51895, 59829, 59827, 60835, 59811, 60831, 60819, 33895]
-    end
-
-    it 'returns empty array if nothing found' do
-      response = Entrez.ESearch('genomeprj', {NON_EXISTENT_SEARCH_FIELD: 'does not exist even in oompaloompa land'}, retmode: :xml)
-      response.ids.should be_empty
-    end
-
-    it 'returns array even if only 1 id found' do
-      id = 60153
-      response = Entrez.ESearch('genomeprj', {uid: id}, retmode: :xml)
-      response.ids.should == [id]
-    end
-
     it 'accepts string as search_terms parameter' do
-      response = Entrez.ESearch('genomeprj', 'hapmap[WORD]', retmode: :xml)
+      response = Entrez.ESearch('genomeprj', 'hapmap[WORD]')
       response.ids.should include(60153)
     end
 
-    it 'can handle array of uids' do
+    it 'handles array of uids' do
       response = Entrez.ESearch('gene', {UID: [1, 2, 3]})
       response.ids.should =~ [1, 2, 3]
     end
@@ -58,8 +42,10 @@ describe Entrez do
   end
 
   it 'should respect query limit' do
-    requests = proc { 4.times { Entrez.EFetch('taxonomy', id: 9606) } }
-    requests.should take_longer_than(1.0)
+    fake_service :ESearch, 'esearch_empty.xml' do
+      requests = proc { 4.times { Entrez.ESearch('asdf') } }
+      requests.should take_longer_than(1.0)
+    end
   end
 
   it 'should convert search term hash into query string with AND operator by default' do

data/spec/response_ids_spec.rb

@@ -0,0 +1,26 @@
+require 'spec_helper'
+
+describe HTTParty::ResponseIds do
+
+  it 'parses body and returns IDs' do
+    fake_service :ESearch, 'esearch_1_2_3.xml' do
+      response = Entrez.ESearch('asdf')
+      response.ids.should == [1, 2, 3]
+    end
+  end
+
+  it 'returns empty array if nothing found' do
+    fake_service :ESearch, 'esearch_empty.xml' do
+      response = Entrez.ESearch('asdf')
+      response.ids.should be_empty
+    end
+  end
+
+  it 'returns array even if only 1 id found' do
+    fake_service :ESearch, 'esearch_1.xml' do
+      response = Entrez.ESearch('asdf')
+      response.ids.should == [1]
+    end
+  end
+
+end

data/spec/spec_helper.rb

@@ -1,10 +1,12 @@
+require 'awesome_print'
+require 'fakeweb'
 require 'pathname'
 
 require File.join(Pathname(__FILE__).dirname.expand_path, '../lib/entrez')
-
-# require support .rb files.
+Entrez.default_params(
+  retmode: :xml,
+)
 Dir[File.expand_path("../support/**/*.rb", __FILE__)].each {|f| require f}
-
 RSpec.configure do |config|
   config.include(Macros)
 end

data/spec/support/fixtures/esearch_1.xml

@@ -0,0 +1,5 @@
+<?xml version="1.0" ?>
+<!DOCTYPE eSearchResult PUBLIC "-//NLM//DTD eSearchResult, 11 May 2002//EN" "http://www.ncbi.nlm.nih.gov/entrez/query/DTD/eSearch_020511.dtd">
+<eSearchResult><Count>41</Count><RetMax>20</RetMax><RetStart>0</RetStart><IdList>
+		<Id>1</Id>
+	</IdList><TranslationSet/><TranslationStack>   <TermSet>    <Term>hapmap[WORD]</Term>    <Field>WORD</Field>    <Count>3</Count>    <Explode>Y</Explode>   </TermSet>   <TermSet>    <Term>inprogress[SEQS]</Term>    <Field>SEQS</Field>    <Count>3913</Count>    <Explode>Y</Explode>   </TermSet>   <OP>AND</OP>  </TranslationStack><QueryTranslation>hapmap[WORD] AND inprogress[SEQS]</QueryTranslation></eSearchResult>

data/spec/support/fixtures/esearch_1_2_3.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" ?>
+<!DOCTYPE eSearchResult PUBLIC "-//NLM//DTD eSearchResult, 11 May 2002//EN" "http://www.ncbi.nlm.nih.gov/entrez/query/DTD/eSearch_020511.dtd">
+<eSearchResult><Count>41</Count><RetMax>20</RetMax><RetStart>0</RetStart><IdList>
+		<Id>1</Id>
+		<Id>2</Id>
+		<Id>3</Id>
+	</IdList><TranslationSet/><TranslationStack>   <TermSet>    <Term>hapmap[WORD]</Term>    <Field>WORD</Field>    <Count>3</Count>    <Explode>Y</Explode>   </TermSet>   <TermSet>    <Term>inprogress[SEQS]</Term>    <Field>SEQS</Field>    <Count>3913</Count>    <Explode>Y</Explode>   </TermSet>   <OP>AND</OP>  </TranslationStack><QueryTranslation>hapmap[WORD] AND inprogress[SEQS]</QueryTranslation></eSearchResult>

data/spec/support/fixtures/esearch_empty.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" ?>
+<!DOCTYPE eSearchResult PUBLIC "-//NLM//DTD eSearchResult, 11 May 2002//EN" "http://www.ncbi.nlm.nih.gov/entrez/query/DTD/eSearch_020511.dtd">
+<eSearchResult><Count>41</Count><RetMax>20</RetMax><RetStart>0</RetStart><IdList>
+	</IdList><TranslationSet/><TranslationStack>   <TermSet>    <Term>hapmap[WORD]</Term>    <Field>WORD</Field>    <Count>3</Count>    <Explode>Y</Explode>   </TermSet>   <TermSet>    <Term>inprogress[SEQS]</Term>    <Field>SEQS</Field>    <Count>3913</Count>    <Explode>Y</Explode>   </TermSet>   <OP>AND</OP>  </TranslationStack><QueryTranslation>hapmap[WORD] AND inprogress[SEQS]</QueryTranslation></eSearchResult>

data/spec/support/macros.rb

@@ -1,7 +1,7 @@
 module Macros
 
-  def file_fixture(file_name)
-    File.open(File.join(File.dirname(__FILE__), 'fixtures/', file_name)).read
+  def fixture_file(file_name)
+    File.open(File.join(File.dirname(__FILE__), 'fixtures/', file_name))
   end
 
   # Return how long it takes to run block.
@@ -12,4 +12,16 @@ module Macros
     end_time - start_time
   end
 
+  # Use FakeWeb to simulate Entrez service with contents of fixture file.
+  # Since the generated URL is a bit difficult to capture,
+  # Faked uri will just match regular expression of service.
+  # When block ends, clean registry.
+  def fake_service(service, fixture_file_name)
+    file_contents = fixture_file(fixture_file_name).read
+    FakeWeb.register_uri(:get, Regexp.new(service.to_s.downcase), body: file_contents, content_type: 'text/xml')
+    yield
+  ensure
+    FakeWeb.clean_registry
+  end
+
 end

metadata

@@ -2,7 +2,7 @@
 name: entrez
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.5.6
+  version: 0.5.7
 platform: ruby
 authors: 
 - Jared Ning
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-20 00:00:00 -05:00
+date: 2011-08-15 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -25,16 +25,38 @@ dependencies:
   type: :runtime
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
-  name: rspec
+  name: awesome_print
   prerelease: false
   requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - "="
+    - - ">="
       - !ruby/object:Gem::Version 
-        version: 2.4.0
+        version: "0"
   type: :development
   version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: fakeweb
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - "="
+      - !ruby/object:Gem::Version 
+        version: 1.3.0
+  type: :development
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - "="
+      - !ruby/object:Gem::Version 
+        version: 2.6.0
+  type: :development
+  version_requirements: *id004
 description: Simple API for HTTP requests to Entrez E-utilities
 email: 
 - jared@redningja.com
@@ -47,6 +69,7 @@ extra_rdoc_files: []
 files: 
 - .gemtest
 - .gitignore
+- .rspec
 - .rvmrc
 - Gemfile
 - README.rdoc
@@ -54,10 +77,16 @@ files:
 - entrez.gemspec
 - lib/entrez.rb
 - lib/entrez/version.rb
+- lib/httparty/response/ids.rb
+- lib/httparty/response_ext.rb
 - lib/query_string_normalizer.rb
 - spec/entrez_spec.rb
 - spec/query_string_normalizer_spec.rb
+- spec/response_ids_spec.rb
 - spec/spec_helper.rb
+- spec/support/fixtures/esearch_1.xml
+- spec/support/fixtures/esearch_1_2_3.xml
+- spec/support/fixtures/esearch_empty.xml
 - spec/support/macros.rb
 - spec/support/matchers.rb
 has_rdoc: true
@@ -91,6 +120,10 @@ summary: HTTP requests to Entrez E-utilities
 test_files: 
 - spec/entrez_spec.rb
 - spec/query_string_normalizer_spec.rb
+- spec/response_ids_spec.rb
 - spec/spec_helper.rb
+- spec/support/fixtures/esearch_1.xml
+- spec/support/fixtures/esearch_1_2_3.xml
+- spec/support/fixtures/esearch_empty.xml
 - spec/support/macros.rb
 - spec/support/matchers.rb