name-spotter 0.1.0 → 0.1.1

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.1.1

data/lib/name-spotter/neti_neti_client.rb

@@ -8,9 +8,10 @@ class NameSpotter
       # the form does not get sent if text is nil or empty
       return [] if text.nil? || text.empty?
       response = RestClient.post("http://#{@host}:#{@port}", data: text)
-
       response.body.split("|").collect do |info|
-        name, offset_start = info.split(',')
+        res = info.split(",")
+        name = res[0...-2].join(",")
+        offset_start = res[-2]
         name.force_encoding('utf-8')
         normalized_name = NameSpotter::ScientificName.normalize(name)
         NameSpotter::ScientificName.new(name, :scientific_name => normalized_name, :start_position => offset_start.to_i)

data/lib/name-spotter/scientific_name.rb

@@ -3,7 +3,8 @@ class NameSpotter
     attr_reader :verbatim, :scientific, :start_pos, :end_pos, :score
 
     def self.normalize(name)
-      name.gsub(/\s+/, ' ')
+      name = name.gsub(",", " ") 
+      name.gsub(/\s+/, " ")
     end
 
     def initialize(verbatim_name, options={})

data/name-spotter.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "name-spotter"
-  s.version = "0.1.0"
+  s.version = "0.1.1"
 
   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 = "2012-06-04"
+  s.date = "2012-06-05"
   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 = [
@@ -37,6 +37,7 @@ Gem::Specification.new do |s|
     "lib/name-spotter/taxon_finder_client.rb",
     "name-spotter.gemspec",
     "spec/files/journalofentomol13pomo_0018.txt",
+    "spec/files/journalofentomol13pomo_0063.txt",
     "spec/name-spotter_spec.rb",
     "spec/scientific_name_spec.rb",
     "spec/spec_helper.rb"

data/spec/files/journalofentomol13pomo_0063.txt

@@ -0,0 +1,91 @@
+FLAT WORMS 45 
+
+1898 The Regeneration of the Nervous System of Planaria torva and 
+ the Anatomy of the Nervous System of Double-headed forms. 
+ Jour. Morph. vol. 14, no. 2, pp. 337-344, pi. 28. 
+
+Goto, S. , , , -..v T 
+
+1895 Studies on the Ectoparasitic Trematodes of Japan. Ihe Jour, 
+ of the Coll. Sc. Imp. Univ. Japan, vol. 8, pp. 1-273, pi. 1-27. 
+
+Graff, L. v. , ^, ^ V. . rr.- 
+
+191'^-1914 Turbellaria. Bearbeitet von Dr. L. v. Graff. Bronn s lier- 
+ Reiehs. Vierter Bd. Wurmer, pp. 2601-2960, pi. 24-47, text figs. 
+ 1-95. Nervous system, pi. 52-54. 
+
+Haswell, W. A. a. . j r> t 
+
+1887 On Temnocephala, an aberrant MonoKenttic Trematode. q. Jour. 
+ Mic. Sc. n. s. v. 28, pp. 279-302, pi. 20-22. 
+
+Hallez, P. ,. . 1 r, , r 4. 
+
+1873 Observations sur le Prostmum hneare. Arch. Zool. txper. et 
+ Gen. t. ii, pp. 559-585, pi. 20-22. 
+
+Hamann, O. . ^ , ^ j- /-. i. 
+
+1885. Taenia lineata Goeze, eine Taline mit flaschenstandigen Oesch. 
+ lechtsoffnungen. Zeit. f. wiss. Zool, Bd. 34. 
+
+Havert, J. „ ^ . r>- ^ 
+
+1900 Contribution a I'etude du Systeme des Trematodes. Distomum 
+ hepaticum. La Cellule, vol. 17, pp. 353-380, pi, 1-4. 
+
+Heath, H. /-> ir » e d «« 
+
+1902. The Anatomy of Epidella squamula sp. nov. Calif. Ac. be. free. 
+
+3d sec. Zool. vol. 3. 
+
+Heath, H., and McGregor, E. A. 
+
+1912. New Polyclads from Monterey Bay, Calif. Proc. Phila. .\c. be. 
+ v. Ixiv, pp. 453-488, pi. 12-18, 12 text figs. 
+
+Hesse, R. , , • , c j u • 
+
+1897. Untersuchungen ueber die Organe der Lichtemsfindung bei 
+
+niederen Thieren. Zeit. f. wiss. Zool. Bd. 62, pp. .527-582. Taf. 
+ 27-38, 3 text figs. 
+
+liiama, I. „ . , , ■.■ i_j. j 
+
+1884. Untersuchungen uber den Bau und Entwicklungsgeschichte der 
+ Susswasser Dendrocoelen (ticliden). Zeit. f. wjfs. Zool. Bd. 11, 
+ pp. 359-464, Taf. 20-23, 3 wood cuts. 
+
+Jiinichen, E. ,, . . r, ■. r ■ 
+
+1896 Beitrage ziir Kenntnis des Turbellarien Auges. Zeit. f. wiss. 
+ Zool. Bd. 62, pp. 250-288. 
+
+Joseph, V. AT 
+
+1886. Uber Centialnervensystem der Bandwurmer. Auszug in tag- 
+ bladt 59. Naturf. u. Arzte in Berlin. 
+
+Kahne, Z. „ . t^ i ■ j 
+
+1885. Anatomie von Taienia perfohata, als Beitrag zur Kenntniss der 
+ Cestoden. Zeit. f. wiss. Zool. Bd. 34. 
+
+Kepner. W. A. and Foshee. A. M. ,„,_■. 
+
+1917. Effects of light and darkness on the eye of Prorhynchus ap- 
+ planatus Kennel. Jour. Exp. Zool., vol. 30, pp. 465-473. 
+
+Kepner. W. A. and Rich A. .,,■•,.• t i:- 
+
+1918 Reactions of the probiscis of Planaria albissima vej. Jour. t>xp. 
+ Zool., vol. 26, pp. 83-100, 10 figs. 
+
+Kepner, W. A., and Lawrence, J. S. „ , , ^ „ . on 
+
+1918. The eye of Polycystis geettei (Bresslau). Jour. Morph. v. M). 
+ no. 2. ■ 
+

data/spec/name-spotter_spec.rb

@@ -79,4 +79,12 @@ describe "NameSpotter" do
     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
 
+  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
+    res = @neti.find(text)
+    offsets = res[:names].map {|n| n[:offsetStart]}
+    offsets.sort.should == offsets
+    offsets[0].should == 67
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: name-spotter
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
   prerelease: 
 platform: ruby
 authors:
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-04 00:00:00.000000000 Z
+date: 2012-06-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -234,6 +234,7 @@ files:
 - lib/name-spotter/taxon_finder_client.rb
 - name-spotter.gemspec
 - spec/files/journalofentomol13pomo_0018.txt
+- spec/files/journalofentomol13pomo_0063.txt
 - spec/name-spotter_spec.rb
 - spec/scientific_name_spec.rb
 - spec/spec_helper.rb
@@ -252,7 +253,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 4382720522777082124
+      hash: 4453341733111217314
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: