name-spotter 0.2.0 → 0.2.1

data/VERSION

@@ -1 +1 @@
-0.2.0
+0.2.1

data/lib/name-spotter/taxon_finder_client.rb

@@ -14,17 +14,20 @@ class NameSpotter
       @current_string = ''
       @current_string_state = ''
       @word_list_matches = 0
-      @cursor = 8.times.inject([]) { |res| res << ['',-1] }
+      @cursor = 8.times.inject([]) { |res| res << ['',0, 0] }
       @current_index = nil
       words = str.split(/\s/)
       words.each do |word|
         if word.empty?
-          @cursor[-1][0] << " "
+          @cursor[-1][2] = @cursor[-1][2] + 1
         else
-          cursor_entry = [word, 1 + @cursor[-1][0].size + @cursor[-1][-1]]
-          @cursor.shift
-          @cursor << cursor_entry
-          taxon_find(word)
+          abbr_no_space =  word.match(/^([A-Z][a-z]?\.)([a-z|\p{Latin}]+)/)
+          if abbr_no_space
+            process_word(abbr_no_space[1], 0)
+            process_word(word[abbr_no_space[1].size..-1], 1)
+          else
+            process_word(word, 1)
+          end
         end
       end
       socket.close
@@ -34,6 +37,13 @@ class NameSpotter
     
     private
 
+    def process_word(word, word_separator_size)
+      cursor_entry = [word, @cursor[-1][0].size + @cursor[-1][1] + @cursor[-1][2], word_separator_size]
+      @cursor.shift
+      @cursor << cursor_entry
+      taxon_find(word)
+    end
+
     def socket
       @socket ||= TCPSocket.open @host, @port
     end
@@ -51,7 +61,7 @@ class NameSpotter
           next if scientific_string.empty?
           add_name NameSpotter::ScientificName.new(verbatim_string, :start_position => start_position, :scientific_name => scientific_string)
         end
-        @current_index = @current_string.empty? ? nil : @cursor[-1][-1]
+        @current_index = @current_string.empty? ? nil : @cursor[-1][1]
       end
     end
 
@@ -62,7 +72,7 @@ class NameSpotter
       @word_list_matches = word_list_matches
       @return_score = return_score
       if !@current_index && @current_string.size > 0
-          @current_index = @cursor[-1][-1]
+          @current_index = @cursor[-1][1]
       end
       if not return_string.blank? or not return_string_2.blank? 
         OpenStruct.new( { :current_string       => current_string,
@@ -83,11 +93,14 @@ class NameSpotter
       str.force_encoding('utf-8')
       start_position = verbatim_string = nil
       if @current_index
-        start_position = is_return_string2 ? @cursor[-1][-1] : @current_index
-        words, indices = @cursor.transpose
-        verbatim_string = (str.include?("[") || is_return_string2) ? words[indices.index(start_position)..-1].join(" ") : words[indices.index(start_position)...-1].join(" ")
+        start_position = is_return_string2 ? @cursor[-1][1] : @current_index
+        indices = @cursor.map { |item| item[1] }
+        verbatim_components = @cursor[indices.rindex(start_position)..-1]
+        sci_name_items_num = str.split(" ").size
+        verbatim_components = verbatim_components[0...sci_name_items_num]
+        verbatim_string = verbatim_components.map {|w| w[0] + (" " * w[2])}.join("").gsub(/[\.\,\!\;]*\s*$/, '')
       else
-        verbatim_string, start_position = @cursor[-1]
+        verbatim_string, start_position, space_size = @cursor[-1]
       end
       scientific_string = str
       [verbatim_string, scientific_string, start_position]

data/name-spotter.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "name-spotter"
-  s.version = "0.2.0"
+  s.version = "0.2.1"
 
   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 = "2012-06-18"
+  s.date = "2012-07-11"
   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 = [

data/spec/name-spotter_spec.rb

@@ -82,7 +82,7 @@ describe "NameSpotter" do
   it "should properly handle abbreviated names found by taxonfinder" do
     text = "Pardosa moesta Banks, 1892 is one spider, Schizocosa ocreata Keyserling, 1887 is a second and a third is Schizocosa saltatrix borealis. The abbreviations are P. moesta, S. ocreata, and S. saltatrix borealis is the third."
     tf_res = @tf.find(text)
-    tf_res.should == {:names=>[{:verbatim=>"Pardosa moesta", :scientificName=>"Pardosa moesta", :offsetStart=>0, :offsetEnd=>13}, {:verbatim=>"Schizocosa ocreata", :scientificName=>"Schizocosa ocreata", :offsetStart=>42, :offsetEnd=>59}, {:verbatim=>"Schizocosa saltatrix borealis.", :scientificName=>"Schizocosa saltatrix borealis", :offsetStart=>105, :offsetEnd=>134}, {:verbatim=>"P. moesta,", :scientificName=>"P[ardosa] moesta", :offsetStart=>158, :offsetEnd=>167}, {:verbatim=>"S. ocreata,", :scientificName=>"S[chizocosa] ocreata", :offsetStart=>169, :offsetEnd=>179}, {:verbatim=>"S. saltatrix borealis is", :scientificName=>"S[chizocosa] saltatrix borealis", :offsetStart=>185, :offsetEnd=>208}]}
+    tf_res.should == {:names=>[{:verbatim=>"Pardosa moesta", :scientificName=>"Pardosa moesta", :offsetStart=>0, :offsetEnd=>13}, {:verbatim=>"Schizocosa ocreata", :scientificName=>"Schizocosa ocreata", :offsetStart=>42, :offsetEnd=>59}, {:verbatim=>"Schizocosa saltatrix borealis", :scientificName=>"Schizocosa saltatrix borealis", :offsetStart=>105, :offsetEnd=>133}, {:verbatim=>"P. moesta", :scientificName=>"P[ardosa] moesta", :offsetStart=>158, :offsetEnd=>166}, {:verbatim=>"S. ocreata", :scientificName=>"S[chizocosa] ocreata", :offsetStart=>169, :offsetEnd=>178}, {:verbatim=>"S. saltatrix borealis", :scientificName=>"S[chizocosa] saltatrix borealis", :offsetStart=>185, :offsetEnd=>205}]}
   end
 
   it "should not make unsequential offsets on a page when using NetiNeti" do
@@ -111,6 +111,17 @@ describe "NameSpotter" do
     res = @tf.find(text)
     res.should == {:names=>[{:verbatim=>"Plantago major", :scientificName=>"Plantago major", :offsetStart=>16, :offsetEnd=>29}, {:verbatim=>"Plantago quercus quercus quercus quercus quercus", :scientificName=>"Plantago quercus quercus quercus quercus quercus", :offsetStart=>225, :offsetEnd=>272}, {:verbatim=>"Pardosa moesta var. moesta f. moesta", :scientificName=>"Pardosa moesta var. moesta f. moesta", :offsetStart=>340, :offsetEnd=>375}]}
   end
+
+  it "should be able to recognize names like P.moesta by TaxonFinder" do
+    text = "Pardosa moesta! If we encounter Pardosa moesta and then P.modica another name I know is Xenopus laevis and also P.moesta. Again without space TaxonFinder should find both. And Plantago major foreva"
+    res = @tf.find(text)
+    res.should == {:names=>[{:verbatim=>"Pardosa moesta", :scientificName=>"Pardosa moesta", :offsetStart=>0, :offsetEnd=>13}, {:verbatim=>"Pardosa moesta", :scientificName=>"Pardosa moesta", :offsetStart=>32, :offsetEnd=>45}, {:verbatim=>"P.modica", :scientificName=>"P[ardosa] modica", :offsetStart=>56, :offsetEnd=>63}, {:verbatim=>"Xenopus laevis", :scientificName=>"Xenopus laevis", :offsetStart=>88, :offsetEnd=>101}, {:verbatim=>"P.moesta", :scientificName=>"P[ardosa] moesta", :offsetStart=>112, :offsetEnd=>119}, {:verbatim=>"Plantago major", :scientificName=>"Plantago major", :offsetStart=>176, :offsetEnd=>189}]}
+    res[:names].map do |name|
+      verbatim = name[:verbatim]
+      found_name = text[name[:offsetStart]..name[:offsetEnd]]
+      found_name.should == verbatim
+    end
+ end
   
   it "should register situations where new name started and prev name is finished in the same cycle in TF" do
     text = "What  happens another called Pardosa moesta (Araneae: Lycosidae) is the species?"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: name-spotter
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
   prerelease: 
 platform: ruby
 authors:
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-18 00:00:00.000000000 Z
+date: 2012-07-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -270,7 +270,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 2125020200384233400
+      hash: 1101945023410070648
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: