name-spotter 0.1.10 → 0.1.11

data/VERSION

@@ -1 +1 @@
-0.1.10
+0.1.11

data/lib/name-spotter/taxon_finder_client.rb

@@ -83,7 +83,7 @@ class NameSpotter
       if @current_index
         start_position = @current_index
         words, indices = @cursor.transpose
-        verbatim_string = words[indices.index(start_position)...-1].join(" ") rescue (require 'ruby-debug'; debugger)
+        verbatim_string = str.include?("[") ? words[indices.index(start_position)..-1].join(" ") : words[indices.index(start_position)...-1].join(" ")
       else
         verbatim_string, start_position = @cursor[-1]
       end

data/name-spotter.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "name-spotter"
-  s.version = "0.1.10"
+  s.version = "0.1.11"
 
   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 = "2012-06-12"
+  s.date = "2012-06-13"
   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

@@ -71,13 +71,19 @@ describe "NameSpotter" do
     end
   end
 
-  it "should be able to return offsets for all names found by taxonfinder" do
+  it "should be able to return offsets for all names" do
     text = "We have to be sure that Betula\n alba and PSEUDOSCORPIONIDA and ×Inkea which is not Passeriformes. We also have another hybrid Passiflora ×rosea 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=>"Passiflora ×rosea", :scientificName=>"Passiflora ×rosea", :offsetStart=>126, :offsetEnd=>142}, {:verbatim=>"Aranea röselii", :scientificName=>"Aranea röselii", :offsetStart=>148, :offsetEnd=>161}, {:verbatim=>"Pardosa\n moesta", :scientificName=>"Pardosa moesta", :offsetStart=>198, :offsetEnd=>212}]}
     tf_res = @tf.find(text)
     tf_res.should == {:names=>[{:verbatim=>"Betula  alba", :scientificName=>"Betula alba", :offsetStart=>24, :offsetEnd=>35}, {:verbatim=>"PSEUDOSCORPIONIDA", :scientificName=>"Pseudoscorpionida", :offsetStart=>41, :offsetEnd=>57}, {:verbatim=>"Passeriformes.", :scientificName=>"Passeriformes", :offsetStart=>83, :offsetEnd=>96}, {:verbatim=>"Passiflora ×rosea", :scientificName=>"Passiflora rosea", :offsetStart=>126, :offsetEnd=>142}, {:verbatim=>"Aranea röselii", :scientificName=>"Aranea röselii", :offsetStart=>148, :offsetEnd=>161}, {:verbatim=>"ARANEA", :scientificName=>"Aranea", :offsetStart=>179, :offsetEnd=>184}, {:verbatim=>"Pardosa  moesta f. moesta", :scientificName=>"Pardosa moesta f. moesta", :offsetStart=>198, :offsetEnd=>222}]} 
   end
+  
+  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}]}
+  end
 
   it "should not make unsequential offsets on a page when using NetiNeti" do
     text = open(File.join(File.dirname(__FILE__), 'files', 'journalofentomol13pomo_0063.txt'), 'r:utf-8').read

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: name-spotter
 version: !ruby/object:Gem::Version
-  version: 0.1.10
+  version: 0.1.11
   prerelease: 
 platform: ruby
 authors:
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-12 00:00:00.000000000 Z
+date: 2012-06-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -269,7 +269,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 1111528646489484932
+      hash: -2251568119704049389
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: