name-spotter 0.0.7 → 0.1.0

data/Gemfile

@@ -12,9 +12,10 @@ gem "json"
 # Include everything needed to run rake, tests, features, etc.
 group :development do
   gem "rspec", "~> 2.3.0"
+  gem "rspec-expectations"
   gem "cucumber", ">= 0"
   gem "capybara"
-  gem "bundler", "~> 1.0.0"
+  gem "bundler"
   gem "jeweler", "~> 1.6.4"
   gem "rcov", ">= 0"
   gem "ruby-debug19"

data/Gemfile.lock

@@ -74,7 +74,7 @@ PLATFORMS
 
 DEPENDENCIES
   builder
-  bundler (~> 1.0.0)
+  bundler
   capybara
   cucumber
   jeweler (~> 1.6.4)
@@ -83,4 +83,5 @@ DEPENDENCIES
   rcov
   rest-client
   rspec (~> 2.3.0)
+  rspec-expectations
   ruby-debug19

data/VERSION

@@ -1 +1 @@
-0.0.7
+0.1.0

data/lib/name-spotter/taxon_finder_client.rb

@@ -8,19 +8,16 @@ class NameSpotter
       @document = ""
     end
 
-    def socket
-      @socket ||= TCPSocket.open @host, @port
-    end
-
     def find(str, from_web_form=false)
       @names = []
+      @document_verbatim = str
       return [] if str.nil? || str.empty?
 
       # These are for the data-send-back that happens in TaxonFinder
       @current_string = ''
       @current_string_state = ''
       @word_list_matches = 0
-
+      @empty_count = 0
       words = str.split(/\s/)
       words.each do |word|
         # Since we split on whitespace, this addition of a " " char
@@ -36,6 +33,12 @@ class NameSpotter
       @document = ""
       @names
     end
+    
+    private
+
+    def socket
+      @socket ||= TCPSocket.open @host, @port
+    end
 
     def taxon_find(word)
       input = "#{word}|#{@current_string}|#{@current_string_state}|#{@word_list_matches}|0"
@@ -45,16 +48,12 @@ class NameSpotter
         return if not response
 
         unless response.return_string.blank?
-          response.return_string.force_encoding('utf-8')
-          verbatim_string = response.return_string.sub(/\[.*\]/, '.')
-          scientific_string = response.return_string
-          add_name NameSpotter::ScientificName.new(verbatim_string, :start_position => @document.rindex(verbatim_string), :scientific_name => scientific_string)
+          verbatim_string, scientific_string, start_position = process_response(response.return_string)
+          add_name NameSpotter::ScientificName.new(verbatim_string, :start_position => start_position, :scientific_name => scientific_string)
         end
         unless response.return_string_2.blank?
-          response.return_string_2.force_encoding('utf-8')
-          verbatim_string = response.return_string_2.sub(/\[.*\]/, '.')
-          scientific_string = response.return_string_2
-          add_name NameSpotter::ScientificName.new(verbatim_string, :start_position => @document.rindex(verbatim_string), :scientific_name => scientific_string)
+          verbatim_string, scientific_string, start_position = process_response(response.return_string_2)
+          add_name NameSpotter::ScientificName.new(verbatim_string, :start_position => start_position, :scientific_name => scientific_string)
         end
       end
     end
@@ -77,5 +76,16 @@ class NameSpotter
         false
       end
     end
+
+    def process_response(str)
+      str.force_encoding('utf-8')
+      verbatim_string = str.sub(/\[.*\]/, '.')
+      verbatim_regex = Regexp.new(verbatim_string.split(/\s/).join('\s+'), true)
+      start_position = @document.rindex(verbatim_regex)
+      verbatim_string = @document_verbatim[start_position..-1].match(verbatim_regex)[0] if start_position
+      scientific_string = str
+      [verbatim_string, scientific_string, start_position]
+    end
+
   end
 end

data/name-spotter.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "name-spotter"
-  s.version = "0.0.7"
+  s.version = "0.1.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Anthony Goddard", "Chuck Ha", "Dmitry Mozzherin"]
-  s.date = "2012-05-04"
+  s.date = "2012-06-04"
   s.description = "The gem searches for scientific names in texts using socket servers running TaxonFinder (by Patrick Leary) and NetiNeti (by Lakshmi Manohar Akella)"
   s.email = "dmozzherin@gmail.com"
   s.extra_rdoc_files = [
@@ -36,6 +36,7 @@ Gem::Specification.new do |s|
     "lib/name-spotter/scientific_name.rb",
     "lib/name-spotter/taxon_finder_client.rb",
     "name-spotter.gemspec",
+    "spec/files/journalofentomol13pomo_0018.txt",
     "spec/name-spotter_spec.rb",
     "spec/scientific_name_spec.rb",
     "spec/spec_helper.rb"
@@ -43,7 +44,7 @@ Gem::Specification.new do |s|
   s.homepage = "http://github.com/GlobalNamesArchitecture/name-spotter"
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.10"
+  s.rubygems_version = "1.8.24"
   s.summary = "Scientific names finder"
 
   if s.respond_to? :specification_version then
@@ -55,9 +56,10 @@ Gem::Specification.new do |s|
       s.add_runtime_dependency(%q<builder>, [">= 0"])
       s.add_runtime_dependency(%q<json>, [">= 0"])
       s.add_development_dependency(%q<rspec>, ["~> 2.3.0"])
+      s.add_development_dependency(%q<rspec-expectations>, [">= 0"])
       s.add_development_dependency(%q<cucumber>, [">= 0"])
       s.add_development_dependency(%q<capybara>, [">= 0"])
-      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_development_dependency(%q<bundler>, [">= 0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
       s.add_development_dependency(%q<rcov>, [">= 0"])
       s.add_development_dependency(%q<ruby-debug19>, [">= 0"])
@@ -67,9 +69,10 @@ Gem::Specification.new do |s|
       s.add_dependency(%q<builder>, [">= 0"])
       s.add_dependency(%q<json>, [">= 0"])
       s.add_dependency(%q<rspec>, ["~> 2.3.0"])
+      s.add_dependency(%q<rspec-expectations>, [">= 0"])
       s.add_dependency(%q<cucumber>, [">= 0"])
       s.add_dependency(%q<capybara>, [">= 0"])
-      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_dependency(%q<bundler>, [">= 0"])
       s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
       s.add_dependency(%q<rcov>, [">= 0"])
       s.add_dependency(%q<ruby-debug19>, [">= 0"])
@@ -80,9 +83,10 @@ Gem::Specification.new do |s|
     s.add_dependency(%q<builder>, [">= 0"])
     s.add_dependency(%q<json>, [">= 0"])
     s.add_dependency(%q<rspec>, ["~> 2.3.0"])
+    s.add_dependency(%q<rspec-expectations>, [">= 0"])
     s.add_dependency(%q<cucumber>, [">= 0"])
     s.add_dependency(%q<capybara>, [">= 0"])
-    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+    s.add_dependency(%q<bundler>, [">= 0"])
     s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
     s.add_dependency(%q<rcov>, [">= 0"])
     s.add_dependency(%q<ruby-debug19>, [">= 0"])

data/spec/files/journalofentomol13pomo_0018.txt

@@ -0,0 +1,39 @@
+A List of California Arachnida 
+
+This list is compiled from already published but scattered papers. Many of these 
+ are local records of specimens and new species collected by many students through a 
+ number of years and determined for us for the most part by Banks and Chamberlin. 
+ As numerous earlier papers in this Journal have taken up the distribution of local 
+ forms only a hint of this will be given. There are included in this list records other 
+ than local. If the distribution is general some indication is given. A few hints as to 
+ characteristic features are given when possible. The family characteristics are com- 
+ piled by the aid of the works of Banks, Ewing, Comstock and several others. In 
+ order to save space the literature references are given in abbreviated form at the end 
+ of each section, especially as there are a number of papers and lists already published 
+ which give this material in great detail. 
+
+I. PSEUDOSCORPIONIDA 
+ M. Moles and W. Moore 
+
+Cheliferid..\e. Evidences of segmentation of thorax in some species. Serrula 
+ attached all its length to finger of chelicera. Spinneret long and slender. Flagellum 
+ absent. Tarsi of legs one-jointed. Tarsal claws short and thick, split on some of 
+ the feet. 
+
+Chelifer cancroides Linn, about buildings, oak, sycamore trees, Claeremont, mts. 
+
+C. fuscipes Bks. Calif. 
+
+C. scabrisciilus Simon. N. Calif, to Claremont. 
+
+Chelanops ohlongus Say. Palm springs. Brown's flats. 
+
+C. validus Bks. From Lake Tahoe. 
+
+f^i;^ 
+
+C. pallipes Bks., luuler stones Claremont, l,(is Angeles. 
+ C. dorsalis Bks., Lake Tahoe and San Francisco. 
+ C. acuminatus Sim. Maraposa, Claremont, Laguna Beach. 
+ C. lagunae Moles, Two eye spots. Claremont. 
+

data/spec/name-spotter_spec.rb

@@ -42,8 +42,8 @@ describe "NameSpotter" do
     text = "Some text that has Betula\n alba and Mus musculus and \neven B. alba and even M. mus-\nculus and unicoded name Aranea röselii. Also it has name unknown before: Varanus bitatawa species"
     res = @neti.find(text)[:names].map { |n| n[:scientificName] } 
     res.should == ["Betula alba", "Mus musculus", "B. alba", "Aranea röselii", "Varanus bitatawa"]
-    res = @tf.find(text)[:names].map { |n| n[:scientificName] } 
-
+    tf_res = @tf.find(text)
+    res = tf_res[:names].map { |n| n[:scientificName] } 
     res.should == ["Betula alba", "Mus musculus", "B[etula] alba", "Aranea röselii", "Varanus"]
   end
 
@@ -71,4 +71,12 @@ describe "NameSpotter" do
     end
   end
 
+  it "should be able to return offsets for all names found by taxonfinder" do
+    text = "We have to be sure that Betula\n alba and PSEUDOSCORPIONIDA and Aranea röselii and capitalized ARANEA RÖSELII and Pardosa\n moesta f. moesta Banks, 1892 all get their offsets"
+    res = @neti.find(text)
+    res.should == {:names=>[{:verbatim=>"Betula\n alba", :scientificName=>"Betula alba", :offsetStart=>24, :offsetEnd=>35}, {:verbatim=>"Aranea röselii", :scientificName=>"Aranea röselii", :offsetStart=>63, :offsetEnd=>76}, {:verbatim=>"Pardosa\n moesta", :scientificName=>"Pardosa moesta", :offsetStart=>113, :offsetEnd=>127}]}
+    tf_res = @tf.find(text)
+    tf_res.should == {:names=>[{:verbatim=>"Betula\n alba", :scientificName=>"Betula alba", :offsetStart=>24, :offsetEnd=>35}, {:verbatim=>"PSEUDOSCORPIONIDA", :scientificName=>"Pseudoscorpionida", :offsetStart=>41, :offsetEnd=>57}, {:verbatim=>"Aranea röselii", :scientificName=>"Aranea röselii", :offsetStart=>63, :offsetEnd=>76}, {:verbatim=>"ARANEA", :scientificName=>"Aranea", :offsetStart=>94, :offsetEnd=>99}, {:verbatim=>"Pardosa\n moesta f. moesta", :scientificName=>"Pardosa moesta f. moesta", :offsetStart=>113, :offsetEnd=>137}]}
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: name-spotter
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -11,11 +11,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-04 00:00:00.000000000Z
+date: 2012-06-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &70202321843640 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -23,10 +23,15 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70202321843640
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rest-client
-  requirement: &70202321842880 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -34,10 +39,15 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70202321842880
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: builder
-  requirement: &70202321841860 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -45,10 +55,15 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70202321841860
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: json
-  requirement: &70202321840740 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -56,10 +71,15 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70202321840740
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &70202321839600 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -67,10 +87,31 @@ dependencies:
         version: 2.3.0
   type: :development
   prerelease: false
-  version_requirements: *70202321839600
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.3.0
+- !ruby/object:Gem::Dependency
+  name: rspec-expectations
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: cucumber
-  requirement: &70202321838920 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -78,10 +119,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70202321838920
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: capybara
-  requirement: &70202321838220 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -89,21 +135,31 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70202321838220
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &70202321837480 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ~>
+    - - ! '>='
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70202321837480
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &70202321836820 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -111,10 +167,15 @@ dependencies:
         version: 1.6.4
   type: :development
   prerelease: false
-  version_requirements: *70202321836820
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.4
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &70202321836060 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -122,10 +183,15 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70202321836060
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: ruby-debug19
-  requirement: &70202321835280 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -133,7 +199,12 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70202321835280
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: The gem searches for scientific names in texts using socket servers running
   TaxonFinder (by Patrick Leary) and NetiNeti (by Lakshmi Manohar Akella)
 email: dmozzherin@gmail.com
@@ -162,6 +233,7 @@ files:
 - lib/name-spotter/scientific_name.rb
 - lib/name-spotter/taxon_finder_client.rb
 - name-spotter.gemspec
+- spec/files/journalofentomol13pomo_0018.txt
 - spec/name-spotter_spec.rb
 - spec/scientific_name_spec.rb
 - spec/spec_helper.rb
@@ -180,7 +252,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 2095636295522729544
+      hash: 4382720522777082124
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -189,7 +261,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.10
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Scientific names finder