rbbt-text 0.6.3 → 1.0.0

data/lib/rbbt/nlp/genia/sentence_splitter.rb

@@ -101,7 +101,7 @@ module NLP
           a, b, d, c = $1, $2, $3, $4
           events << eventCount.to_s  << "\t"
           events << returnFeatures(a, b, c)
-          (" " + a + b + "__" + eventCount.to_s + "____" + d + "__" + c + " ")
+          (" " << a << b << "__" << eventCount.to_s << "____" << d << "__" << c << " ")
         }
         eventCount += 1
       end
@@ -111,6 +111,27 @@ module NLP
     [events, marks]
   end
 
+  def self.event_extraction(text)
+    events = ""
+    marks = ""
+
+    eventCount = 0
+
+    pat = / ([^ ]+)([.!\?\)\]\"])( +)([^ ]+) /
+    for line in text.split(/\n/) do
+      while line.match(pat) do
+        a, b, d, c = $1, $2, $3, $4
+        events << eventCount.to_s  << "\t"
+        events << returnFeatures(a, b, c)
+        line = $` + (" " << a << b << "__" << eventCount.to_s << "____" << d << "__" << c << " ") << $'
+        eventCount += 1
+      end
+      marks << line
+    end
+
+    [events, marks]
+  end
+
   def self.process_labels(marked_text, labels)
     out = ""
 

data/lib/rbbt/nlp/open_nlp/sentence_splitter.rb

@@ -0,0 +1,74 @@
+require 'rbbt'
+require 'rjb'
+require 'rbbt/ner/segment'
+require 'rbbt/resource'
+
+module OpenNLP
+  Rbbt.claim Rbbt.software.opt.OpenNLP, :install, Rbbt.share.install.software.OpenNLP.find
+
+  Rbbt.claim Rbbt.software.opt.OpenNLP.models["da-sent.bin"], :url, "http://opennlp.sourceforge.net/models-1.5/de-sent.bin"
+
+  MAX = 5
+
+  @@FileInputStream = Rjb::import('java.io.FileInputStream')
+  @@SentenceModel = Rjb::import('opennlp.tools.sentdetect.SentenceModel')
+  @@SentenceDetectorME = Rjb::import('opennlp.tools.sentdetect.SentenceDetectorME')
+
+  def self.sentence_split_detector
+    @@sentence_split_detector ||= begin
+                                    modelIn = @@FileInputStream.new(Rbbt.software.opt.OpenNLP.models["da-sent.bin"].produce.find);
+
+                                    model = @@SentenceModel.new(modelIn);
+                                    modelIn.close()
+                                    model
+
+                                    @@SentenceDetectorME.new(model)
+                                  end
+  end
+
+  def self.sentence_splitter(text)
+    return [] if text.nil? or text.empty?
+
+    last = 0
+    begin
+      sentence_split_detector = self.sentence_split_detector
+      
+      sentences = nil
+      TmpFile.with_file do |tmpfile|
+        start_time = Time.now
+
+        begin
+          pid = Process.fork do
+            sent = sentence_split_detector.sentDetect(text)
+            Open.write(tmpfile, sent * "#OpenNLP:SENTENCE#")
+          end
+
+          while not Process.waitpid(pid)
+            if Time.now - start_time > MAX
+              Process.kill(9, pid)
+              raise "Taking to long (> #{MAX} seconds)"
+            end
+            sleep 0.1
+          end
+
+          begin
+            Process.waitpid(pid)
+          end
+        rescue Errno::ECHILD
+        end
+
+        sentences = Open.read(tmpfile).split("#OpenNLP:SENTENCE#")
+      end
+
+      sentences.collect{|sentence|
+        start = text.index(sentence, last)
+        Segment.setup sentence, start
+        last = start + sentence.length - 1
+        sentence
+      }
+    rescue Exception
+      raise $!
+      raise "Sentence splitter raised exception: #{$!.message}"
+    end
+  end
+end

data/share/install/software/Linnaeus

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+name='Linnaeus'
+url="http://sourceforge.net/projects/linnaeus/files/Linnaeus/linnaeus-2.0.tar.gz/download"
+species_url="http://sourceforge.net/projects/linnaeus/files/Entity_packs/species-proxy-1.2.tar.gz/download"
+
+install_src "$name" "$url"
+ln -s "$OPT_DIR/$name/bin/"*.jar "$OPT_JAR_DIR/$name.jar" 
+
+echo "GET SPECIES"  > /tmp/foo
+get_src "Linnaeus-species-proxy" "$species_url"
+pkg_dir="`opt_dir \"$name\"`"
+build_dir=`build_dir`
+echo $pkg_dir  >> /tmp/foo
+echo $build_dir  >> /tmp/foo
+mv "$build_dir" "$pkg_dir"
+tmp_file="/tmp/species-proxy-properties.tmp"
+cat  "$pkg_dir/species-proxy/properties.conf" |grep -v "^.dir =" >> $tmp_file
+echo "\$dir = $pkg_dir/species-proxy/" > "$pkg_dir/species-proxy/properties.conf"
+cat $tmp_file | grep -v "^#" >>  "$pkg_dir/species-proxy/properties.conf"
+

data/share/install/software/OpenNLP

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+name='OpenNLP'
+url="http://apache.rediris.es//incubator/opennlp/apache-opennlp-1.5.2-incubating-bin.tar.gz"
+
+get_src "$name" "$url"
+move_opt "$name" 
+
+
+ln -sf  "$OPT_DIR/$name/lib/"*.jar  "$OPT_JAR_DIR/"
+
+clean_build

data/share/rnorm/tokens_default

@@ -1,6 +1,5 @@
 require 'rbbt/util/misc'
 
-
 plural = Proc.new do |t| t.sub(/s$/,'') end
 
 tokens do
@@ -14,7 +13,7 @@ tokens do
 
   # Some words for removal 
   stopword     do |w|  $stopwords.include?( w.downcase_first)  end
-  gene         /genes?/i 
+  gene         /genes?/i
   dna
   cdna
   rna

data/test/rbbt/entity/test_document.rb

@@ -0,0 +1,66 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../../test_helper.rb')
+require 'rbbt/entity'
+require 'rbbt/entity/pmid'
+require 'rbbt/entity/document'
+require 'test/unit'
+
+require 'rbbt/workflow'
+
+Workflow.require_workflow "TextMining"
+
+module Document
+  self.corpus = Persist.open_tokyocabinet("/tmp/corpus", false, :string, "BDB")
+
+  property :banner => :single do |*args|
+    normalize, organism = args
+    TextMining.job(:gene_mention_recognition, "Factoid", :text => text, :method => :banner, :normalize => normalize, :organism => organism).exec.each{|e| SegmentWithDocid.setup(e, self.docid)}
+  end
+
+  property :abner => :single do |*args|
+    normalize, organism = args
+    TextMining.job(:gene_mention_recognition, "Factoid", :text => text, :method => :banner, :normalize => normalize, :organism => organism).exec.each{|e| SegmentWithDocid.setup(e, self.docid)}
+  end
+
+  persist :abner, :annotations, :dir => Rbbt.tmp.test.find(:user).entity_property
+end
+
+class TestDocument < Test::Unit::TestCase
+  def test_pmid
+    pmid = "21904853"
+    PMID.setup(pmid)
+
+    assert_match /^PMID/, pmid.id
+    assert_match /TET2/, pmid.text
+  end
+
+  def test_abner
+    pmid = "21904853"
+    PMID.setup(pmid)
+
+    genes = pmid.abner.reject{|ne| ne.offset.nil?}
+    genes.each do |ne|
+      orig = ne
+      orig_range = ne.range
+      ne.mask
+      assert ne.masked?
+      assert ne =~ /^MASKED/
+      assert_equal orig_range, ne.range
+      assert_equal ne, ne.unmask
+    end
+    assert pmid.abner.include? "TET2"
+  end
+
+  def test_free_text
+    text = "Free text including a mention to TET2."
+    Document.setup(text)
+
+    assert text.abner.include? "TET2"
+    
+    docid = text.docid
+    assert_match /TET2/, Document.setup(docid).text
+
+    assert Document.setup(docid).abner.include? "TET2"
+  end
+end
+
+

data/test/rbbt/ner/segment/test_transformed.rb

@@ -74,6 +74,16 @@ class TestClass < Test::Unit::TestCase
       assert_equal original.gsub(/TP53/, 'GN'), a
     end
 
+    Transformed.with_transform(a, [gene1], "GN") do 
+      Transformed.with_transform(a, [gene2], "LONG_GENE_PLACEHOLDER") do 
+        assert_equal original.gsub(/TP53/, 'GN').sub('CDK5R1', "LONG_GENE_PLACEHOLDER"), a
+      end
+      assert_equal original.gsub(/TP53/, 'GN'), a
+    end
+
+    assert_equal original, a
+
+
     assert_equal original, a
 
     exp1, exp2 = nil, nil

data/test/rbbt/ner/test_finder.rb

@@ -0,0 +1,34 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../../test_helper.rb')
+require 'rbbt/entity'
+require 'rbbt/ner/finder'
+require 'rbbt/ner/finder'
+require 'rbbt/sources/organism'
+require 'rbbt/sources/kegg'
+require 'rbbt/sources/NCI'
+
+class TestFinder < Test::Unit::TestCase
+
+  def _test_namespace_and_format
+    #f = Finder.new(CMD.cmd("head -n 1000", :in => Open.open(Organism.identifiers("Hsa/jun2011").find)))
+    f = Finder.new(KEGG.pathways, :grep => "^hsa")
+    assert_equal "Hsa/jun2011", f.instances.first.namespace
+    assert_equal "Ensembl Gene ID", f.instances.first.format
+  end
+
+  def _test_find
+    f = Finder.new(Organism.lexicon("Hsa/jun2011"), :grep => ["SF3B1"])
+
+    assert_equal "ENSG00000115524", f.find("SF3B1").first
+    if defined? Entity
+      ddd f.find("SF3B1").first.info
+      assert_equal "Ensembl Gene ID", f.find("SF3B1").first.format
+    end
+  end
+
+  def test_find
+    f = Finder.new(Organism.lexicon("Hsa/jun2011"), :grep => ["RASGRF2"])
+
+    ddd f.find("RAS").collect{|m| m.info}
+  end
+
+end

data/test/rbbt/ner/test_linnaeus.rb

@@ -0,0 +1,16 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../../test_helper.rb')
+require 'rbbt/ner/linnaeus'
+require 'test/unit'
+
+class TestLinnaeus < Test::Unit::TestCase
+
+  def test_match
+    begin
+      mentions = Linnaeus.match("Human HeLa cells and murine models")
+      ["Human", "HeLa cells", "murine"].each{|mention| 
+        assert(mentions.include? mention)
+      }
+    rescue
+    end
+  end
+end

data/test/rbbt/ner/test_ngram_prefix_dictionary.rb

@@ -3,6 +3,7 @@ require 'rbbt/ner/ngram_prefix_dictionary'
 require 'rbbt/util/tmpfile'
 
 class TestNGramPrefixDictionary < Test::Unit::TestCase
+
   def test_match
     lexicon =<<-EOF
 C1;aa;AA;bb b
@@ -17,6 +18,27 @@ C2;11;22;3 3;bb
     end
   end
 
+  def test_case_insensitive_match
+    lexicon =<<-EOF
+C1;aa
+C2;bb
+    EOF
+
+    TmpFile.with_file(lexicon) do |file|
+      index = NGramPrefixDictionary.new(TSV.open(file, :flat, :sep => ';'), "test", true)
+
+      matches = index.match('AA oo')
+      assert matches.select{|m| m.code.include? 'C1'}.any?
+      assert matches.include? 'AA'
+
+      matches = index.match('AA')
+      assert matches.select{|m| m.code.include? 'C1'}.any?
+      assert matches.include? 'AA'
+
+    end
+  end
+
+
   def test_stream
     lexicon =<<-EOF
 C1;aa;AA;bb b

data/test/rbbt/ner/test_oscar4.rb

@@ -8,9 +8,9 @@ class TestOSCAR4 < Test::Unit::TestCase
   def test_match
     begin
       ner = OSCAR4.new
-      str  = "Alternatively, rearrangement of O-(w-haloalkyl)esters 34 of 2-carboethoxy-N-hydroxypyridine-2-selone affords azonianaphthalenium halides 37 in 79% yield"
+      str  = "Alternatively, CO2 rearrangement of O-(w-haloalkyl)esters 34 of 2-carboethoxy-N-hydroxypyridine-2-selone affords azonianaphthalenium halides 37 in 79% yield"
 
-      mentions = ner.match(str, "CM", false)
+      mentions = ner.match(str, "CM")
       good_mentions = ["2-carboethoxy-N-hydroxypyridine-2-selone", "O-(w-haloalkyl)esters"]
 
       good_mentions.each{|mention| 
@@ -22,7 +22,7 @@ class TestOSCAR4 < Test::Unit::TestCase
     end
   end
 
-  def test_ranges
+  def _test_ranges
     begin
       ner = OSCAR4.new
       str =<<-EOF 

data/test/rbbt/ner/test_rnorm.rb

@@ -25,9 +25,9 @@ S000000376	AAA	GENE1	DDD
 
   def test_match
      assert_equal(["S000000029"], @norm.match("FUN21"))
-     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN"))
-     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN 2"))
-     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN 21")) 
+     assert_equal(["S000000030", "S000000029", "S000000031"].sort, @norm.match("FUN").sort)
+     assert_equal(["S000000030", "S000000029", "S000000031"].sort, @norm.match("FUN 2").sort)
+     assert_equal(["S000000030", "S000000029", "S000000031"].sort, @norm.match("FUN 21").sort) 
      assert_equal([], @norm.match("GER4"))
 
      @norm.match("FUN21")

data/test/rbbt/nlp/open_nlp/test_sentence_splitter.rb

@@ -0,0 +1,45 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../../..', 'test_helper.rb')
+require 'rbbt/nlp/open_nlp/sentence_splitter'
+require 'rbbt/ner/segment'
+
+$text=<<-EOF
+Atypical teratoid/rhabdoid tumors (AT/RTs) are highly aggressive brain tumors
+of early childhood poorly responding to therapy. The majority of cases show
+inactivation of SMARCB1 (INI1, hSNF5, BAF47), a core member of the adenosine
+triphosphate (ATP)-dependent SWI/SNF chromatin-remodeling complex. We here
+report the case of a supratentorial AT/RT in a 9-month-old boy, which showed
+retained SMARCB1 staining on immunohistochemistry and lacked genetic
+alterations of SMARCB1. Instead, the tumor showed loss of protein expression of
+another SWI/SNF chromatin-remodeling complex member, the ATPase subunit SMARCA4
+(BRG1) due to a homozygous SMARCA4 mutation [c.2032C>T (p.Q678X)].  Our
+findings highlight the role of SMARCA4 in the pathogenesis of SMARCB1-positive
+AT/RT and the usefulness of antibodies directed against SMARCA4 in this
+diagnostic setting.
+  EOF
+
+class TestClass < Test::Unit::TestCase
+
+  def test_sentences
+    text =<<-EOF
+This is a sentence.    
+A funky character ™ in a sentence.
+This is a sentence.    
+This is a 
+sentence. This is
+another sentence. 
+    EOF
+
+    assert_equal 5, OpenNLP.sentence_splitter(text).length
+    assert_equal "This is a \nsentence.", OpenNLP.sentence_splitter(text)[3]
+  end
+
+  def test_text_sentences
+    Misc.benchmark(100) do
+      OpenNLP.sentence_splitter($text).include? "Our
+findings highlight the role of SMARCA4 in the pathogenesis of SMARCB1-positive
+AT/RT and the usefulness of antibodies directed against SMARCA4 in this
+diagnostic setting."
+    end
+  end
+end
+ 

data/test/test_helper.rb

@@ -9,7 +9,7 @@ require 'rbbt/util/log'
 require 'rbbt/corpus/document_repo'
 
 class Test::Unit::TestCase
-  def test_datafile(file)
+  def get_test_datafile(file)
     File.join(File.dirname(__FILE__), 'data', file)
   end
 

metadata

@@ -1,103 +1,104 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: rbbt-text
-version: !ruby/object:Gem::Version 
-  hash: 1
+version: !ruby/object:Gem::Version
+  version: 1.0.0
   prerelease: 
-  segments: 
-  - 0
-  - 6
-  - 3
-  version: 0.6.3
 platform: ruby
-authors: 
+authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2012-02-09 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2012-12-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: rbbt-util
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 63
-        segments: 
-        - 4
-        - 0
-        - 0
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 4.0.0
   type: :runtime
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
-  name: stemmer
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 4.0.0
+- !ruby/object:Gem::Dependency
+  name: stemmer
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id002
-- !ruby/object:Gem::Dependency 
-  name: libxml-ruby
   prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: libxml-ruby
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id003
-- !ruby/object:Gem::Dependency 
-  name: json
   prerelease: false
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id004
-- !ruby/object:Gem::Dependency 
-  name: rjb
   prerelease: false
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rjb
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id005
-description: "Text mining tools: named entity recognition and normalization, document classification, bag-of-words, dictionaries, etc"
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: ! 'Text mining tools: named entity recognition and normalization, document
+  classification, bag-of-words, dictionaries, etc'
 email: miguel.vazquez@fdi.ucm.es
-executables: 
+executables:
 - get_ppis.rb
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
+files:
 - lib/rbbt/bow/bow.rb
 - lib/rbbt/bow/dictionary.rb
 - lib/rbbt/bow/misc.rb
@@ -110,6 +111,8 @@ files:
 - lib/rbbt/ner/abner.rb
 - lib/rbbt/ner/banner.rb
 - lib/rbbt/ner/chemical_tagger.rb
+- lib/rbbt/ner/finder.rb
+- lib/rbbt/ner/linnaeus.rb
 - lib/rbbt/ner/ngram_prefix_dictionary.rb
 - lib/rbbt/ner/oscar3.rb
 - lib/rbbt/ner/oscar4.rb
@@ -119,6 +122,7 @@ files:
 - lib/rbbt/ner/rnorm/cue_index.rb
 - lib/rbbt/ner/rnorm/tokens.rb
 - lib/rbbt/ner/segment.rb
+- lib/rbbt/ner/segment/docid.rb
 - lib/rbbt/ner/segment/named_entity.rb
 - lib/rbbt/ner/segment/relationship.rb
 - lib/rbbt/ner/segment/segmented.rb
@@ -127,13 +131,16 @@ files:
 - lib/rbbt/ner/token_trieNER.rb
 - lib/rbbt/nlp/genia/sentence_splitter.rb
 - lib/rbbt/nlp/nlp.rb
+- lib/rbbt/nlp/open_nlp/sentence_splitter.rb
 - share/install/software/ABNER
 - share/install/software/BANNER
 - share/install/software/ChemicalTagger
 - share/install/software/Gdep
 - share/install/software/Geniass
+- share/install/software/Linnaeus
 - share/install/software/OSCAR3
 - share/install/software/OSCAR4
+- share/install/software/OpenNLP
 - share/install/software/StanfordParser
 - share/patterns/drug_induce_disease
 - share/rnorm/cue_default
@@ -157,44 +164,37 @@ files:
 - test/rbbt/ner/test_oscar4.rb
 - test/rbbt/ner/test_chemical_tagger.rb
 - test/rbbt/ner/test_ngram_prefix_dictionary.rb
+- test/rbbt/ner/test_finder.rb
+- test/rbbt/ner/test_linnaeus.rb
+- test/rbbt/entity/test_document.rb
 - test/rbbt/nlp/test_nlp.rb
-- test/rbbt/corpus/test_corpus.rb
-- test/rbbt/corpus/test_document.rb
+- test/rbbt/nlp/open_nlp/test_sentence_splitter.rb
 - bin/get_ppis.rb
 homepage: http://github.com/mikisvaz/rbbt-util
 licenses: []
-
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.8.10
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Text mining tools for the Ruby Bioinformatics Toolkit (rbbt)
-test_files: 
+test_files:
 - test/test_helper.rb
 - test/rbbt/bow/test_bow.rb
 - test/rbbt/bow/test_dictionary.rb
@@ -213,6 +213,8 @@ test_files:
 - test/rbbt/ner/test_oscar4.rb
 - test/rbbt/ner/test_chemical_tagger.rb
 - test/rbbt/ner/test_ngram_prefix_dictionary.rb
+- test/rbbt/ner/test_finder.rb
+- test/rbbt/ner/test_linnaeus.rb
+- test/rbbt/entity/test_document.rb
 - test/rbbt/nlp/test_nlp.rb
-- test/rbbt/corpus/test_corpus.rb
-- test/rbbt/corpus/test_document.rb
+- test/rbbt/nlp/open_nlp/test_sentence_splitter.rb