rbbt-text 1.0.0 → 1.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    OGU0NTNiMzRjZjZiOTkwMjg1ZmJlNTU0NGY1MTM4YzhkZmYwOTZmZg==
+  data.tar.gz: !binary |-
+    NTI2YmFhMzI3OWU1NjQ3ZjZhMDUzMzc0N2VkOTAwMjMyNzAxOWVmNQ==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    N2U5NGZmOWVjODdlYjY0N2NjMmVkNmVmODJhNTVjNzI1NTA3ZmYyY2E3ZWYx
+    MGU0MDlmOGNkODRiYjYyYmVlYzFjOTkwMGYyMTQ2NmIxMGExZmYxMWQxMjQy
+    OWM2MDZlZDQxZTRmOTJlMzMzMTk4MDlhM2YwOGNmYWQxNDAwY2E=
+  data.tar.gz: !binary |-
+    ZjQyYTg2YTIzMmQyMjE5NjhlYjExZTllZGJlNjQ3ZGU3NTVlNTEyMWE0NjRl
+    YWQzMTUxNDVjNzQ0NWQ0YWQ5MWY2ZGI4MzJlNjI2ZWQ5OWI1OTI0MjllYzBj
+    NDIwYmM3OTBhNDBhMWIwYzk1Mjc3MTU0Mzc1MWE3Yzk3MDgyN2Q=

data/lib/rbbt/entity/document.rb

@@ -8,8 +8,6 @@ module Document
     attr_accessor :corpus
   end
 
-  attr_accessor :docid
-
   property :docid => :single2array do |*args|
     @docid ||= if self =~ /^text:/
                  self
@@ -19,10 +17,6 @@ module Document
     @docid
   end
 
-  #property :annotation_id => :single2array do |*args|
-  #  docid(*args)
-  #end
-
   property :annotation_id => :both do |*args|
     if Array === self
       Misc.hash2md5(info.merge(:self => self))
@@ -43,42 +37,39 @@ module Document
       self._get_text(*args)
     else
 
-      Document.corpus.read if Document.corpus.respond_to? :read
-      self.each do |doc|
+      Document.corpus.read_and_close do
+        self.each do |doc|
+          id = doc.docid(*args)
+          case
+          when Document.corpus.include?(doc) 
+            article_text[doc] =  Document.corpus[doc] 
+          when Document.corpus.include?(id) 
+            article_text[doc] =  Document.corpus[id] 
+          else
+            missing << doc
+          end
 
-        case
-        when Document.corpus.include?(doc) 
-          article_text[doc] =  Document.corpus[doc] 
-        when Document.corpus.include?(doc.docid(*args)) 
-          article_text[doc] =  Document.corpus[doc.docid(*args)] 
-        else
-          missing << doc
         end
-
       end
-      Document.corpus.close if Document.corpus.respond_to? :close
 
       if missing.any?
         missing.first.annotate missing
         missing_text = Misc.process_to_hash(missing){|list| list._get_text(*args)}
 
         Misc.lock(Document.corpus.respond_to?(:persistence_path) ? Document.corpus.persistence_path : nil) do
-          Document.corpus.write if Document.corpus.respond_to? :write and not Document.corpus.write?
+          Document.corpus.write_and_close do
 
-          missing_text.each do |doc, doc_text|
-            doc = missing.first.annotate doc.dup
-            Document.corpus[doc.docid(*args)] = doc_text
-            article_text[doc] = doc_text
+            missing_text.each do |doc, doc_text|
+              doc = self.annotate doc.dup
+              Document.corpus[doc.docid(*args)] = doc_text
+              article_text[doc] = doc_text
+            end
           end
-
-          Document.corpus.close if Document.corpus.respond_to? :close
         end
-
       end
 
       article_text.values_at *self
     end
   end
-
 end
 

data/lib/rbbt/ner/abner.rb

@@ -33,6 +33,7 @@ class Abner < NER
   def match(text)
     return [] if text.nil? or text.empty?
 
+    text = text.encode('utf-8', 'binary', :invalid => :replace, :undef => :replace, :replace => '')
     res = @tagger.getEntities(text)
     types = res[1]
     strings = res[0]

data/lib/rbbt/ner/banner.rb

@@ -57,6 +57,7 @@ class Banner < NER
     text.gsub!(/\n/,' ')
     text.gsub!(/\|/,'/') # Character | gives an error
     return [] if text.strip.empty? 
+    text = text.encode('utf-8', 'binary', :invalid => :replace, :undef => :replace, :replace => '')
     sentence = @@Sentence.new(text)
 
     @tokenizer.tokenize(sentence)

data/lib/rbbt/ner/chemical_tagger.rb

@@ -8,6 +8,7 @@ class ChemicalTagger < NER
   Rbbt.claim Rbbt.software.opt.ChemicalTagger, :install, Rbbt.share.install.software.ChemicalTagger.find
 
   def self.init
+    ENV["CLASSPATH"] = ENV["CLASSPATH"].split(":").reverse * ":"
     Rjb::load(nil, jvmargs = ['-Xms1G','-Xmx2G']) unless Rjb.loaded?
     @@RbbtChemicalTagger ||= Rjb::import('RbbtChemicalTagger')
   end
@@ -21,6 +22,7 @@ class ChemicalTagger < NER
       matches = @@RbbtChemicalTagger.match(text)
     rescue
       Log.debug "ChemicalTagger Error: #{$!.message}"
+      ddd $!.backtrace
       return []
     end
 

data/lib/rbbt/ner/finder.rb

@@ -15,16 +15,17 @@ class Finder
   class Instance
     attr_accessor :namespace, :format, :normalizer
     def initialize(path, open_options = {})
-      if TSV === path
+      case path
+      when TSV 
         @namespace = path.namespace 
         @format = path.key_field
         @normalizer = Normalizer.new(path)
       else
         open_options = Misc.add_defaults open_options, :type => :flat
-        parser = TSV::Parser.new(Open.open(Path === path ? path.find : path), open_options)
-        @namespace = parser.namespace 
-        @format = parser.key_field
-        @normalizer = Normalizer.new(Path === path ? path.tsv(open_options) : TSV.open(path, open_options))
+        tsv = TSV.open(path, open_options)
+        @namespace = tsv.namespace 
+        @format = tsv.key_field
+        @normalizer = Normalizer.new(tsv)
       end
     end
 
@@ -55,6 +56,4 @@ class Finder
       acc += instance.find(name)
     end
   end
-
 end
-

data/lib/rbbt/ner/ngram_prefix_dictionary.rb

@@ -31,7 +31,7 @@ VALUE fast_start_with(VALUE str, VALUE cmp, int offset)
   int length_cmp = RSTRING_LEN(cmp);
   int length_str = RSTRING_LEN(str);
 
-  if (memcmp(RSTRING_PTR(str)+ offset, RSTRING_PTR(cmp), length_cmp) == 0){
+  if (memcmp(RSTRING_PTR(str) + offset, RSTRING_PTR(cmp), length_cmp) == 0){
     if (length_cmp - offset == length_str || is_stop_letter(RSTRING_PTR(str)[offset + length_cmp]))
       return Qtrue;
     else
@@ -87,25 +87,23 @@ VALUE fast_start_with(VALUE str, VALUE cmp, int offset)
     matches = []
 
     text_offset = 0
+    text_chars = text.chars.to_a
     text_length = text.length
     while (not text_offset.nil?) and text_offset < text_length
       if STOP_LETTER_CHAR_VALUES.include? text[text_offset]
         text_offset += 1 
         next
       end
-      ngram =  text[text_offset..text_offset + 2].strip
+      ngram =  text.slice(text_offset, 3).strip
+      text_byte_offset = text_offset == 0 ? 0 : text[0..text_offset-1].bytesize
 
       found = nil
       if index.include? ngram
-
         diff = text_length - text_offset
         # Match with entries
         index[ngram].each do |name, code|
           if name.length <= diff
-            #if piece.start_with? name and 
-            #  (text_offset + name.length == text_length or piece[name.length] == " "[0])
-
-            if fast_start_with(text, name, text_offset)
+            if fast_start_with(text, name, text_byte_offset)
               found = [name.dup, code, text_offset]
               break
             end

data/lib/rbbt/ner/oscar4.rb

@@ -9,6 +9,12 @@ class OSCAR4 < NER
   Rbbt.claim Rbbt.software.opt.OSCAR4, :install, Rbbt.share.install.software.OSCAR4.find
 
   def self.init
+
+    # There is an incompatibility between the OpenNLP version in OSCAR4 and the
+    # one used for other matters in Rbbt, which is the most recent. We remove
+    # the standalone jars from the CLASSPATH
+    ENV["CLASSPATH"] = ENV["CLASSPATH"].split(":").select{|p| p !~ /opennlp/} * ":"
+
     Rjb::load(nil, jvmargs = ['-Xms1G','-Xmx2G']) unless Rjb.loaded?
 
     @@OSCAR      ||= Rjb::import('uk.ac.cam.ch.wwmm.oscar.Oscar')
@@ -38,6 +44,8 @@ class OSCAR4 < NER
       #inchi = inchi.getValue() unless inchi.nil?
       inchi = nil
 
+      next unless entity.getType.toString == type unless type.nil?
+
       NamedEntity.setup mention, entity.getStart, entity.getType, inchi, entity.getConfidence
 
       result << mention

data/lib/rbbt/ner/segment/docid.rb

@@ -22,7 +22,7 @@ module SegmentWithDocid
   def unmasked_text
     return self unless masked?
     tag, length = self.split(":")
-    Document.setup(docid).text[offset..(offset+length.to_i-1)]
+    Document.setup(docid).text[offset.to_i..(offset.to_i+length.to_i-1)]
   end
 
   def unmask

data/lib/rbbt/ner/segment/named_entity.rb

@@ -27,5 +27,19 @@ Score: #{score.inspect}
     EOF
     text.chomp
   end
+
+  def entity(params = nil)
+    format, entity = code.split(":")
+    entity, format = format, nil if entity.nil?
+    
+    if defined? Entity and Entity.formats.include? type or Entity.formats.include? format
+      params ||= {}
+      params[:format] = format if format and params[:format].nil?
+      mod = (Entity.formats[type] || Entity.format[entity])
+      mod.setup(entity, params)
+    end
+
+    entity
+  end
 end
 

data/lib/rbbt/ner/segment/transformed.rb

@@ -69,16 +69,16 @@ module Transformed
       when (b.nil? or b.offset.nil?)
         +1
         # Non-overlap
-      when (a.end < b.offset or b.end < a.offset)
+      when (a.end < b.offset.to_i or b.end < a.offset.to_i)
         b.offset <=> a.offset
         # b includes a
-      when (a.offset >= b.offset and a.end <= b.end)
+      when (a.offset.to_i >= b.offset.to_i and a.end <= b.end)
         -1
         # b includes a
-      when (b.offset >= a.offset and b.end <= a.end)
+      when (b.offset.to_i >= a.offset.to_i and b.end <= a.end)
         +1
         # Overlap
-      when (a.offset > b.offset and a.end > b.end or b.offset < a.offset and b.end > a.end)
+      when (a.offset.to_i > b.offset.to_i and a.end > b.end or b.offset.to_i < a.offset.to_i and b.end > a.end)
         a.length <=> b.length
       else
         raise "Unexpected case in sort: #{a.range} - #{b.range}"
@@ -99,8 +99,8 @@ module Transformed
 
       shift_begin, shift_end = shift
 
-      text_offset = self.respond_to?(:offset)? self.offset : 0
-      updated_begin = segment.offset + shift_begin - text_offset
+      text_offset = self.respond_to?(:offset)? self.offset.to_i : 0
+      updated_begin = segment.offset.to_i + shift_begin - text_offset
       updated_end   = segment.range.last + shift_end - text_offset
 
       updated_range = (updated_begin..updated_end)
@@ -136,11 +136,11 @@ module Transformed
       # Before
     when segment.end < range.begin
       # After
-    when segment.offset > range.end + diff
-      segment.offset -= diff
+    when segment.offset.to_i > range.end + diff
+      segment.offset.to_i -= diff
       # Includes
-    when (segment.offset <= range.begin and segment.end >= range.end + diff)
-      segment.replace self[segment.offset..segment.end - diff]
+    when (segment.offset.to_i <= range.begin and segment.end >= range.end + diff)
+      segment.replace self[segment.offset.to_i..segment.end - diff]
     else
       raise "Segment Overlaps"
     end

data/lib/rbbt/ner/segment.rb

@@ -9,21 +9,24 @@ module Segment
     @offset = offset.nil? ? nil : offset.to_i
   end
 
-
   def segment_length
-    self.length
+    begin
+      super()
+    rescue
+      self.length
+    end
   end
 
   #{{{ Ranges
 
   def end
     return nil if offset.nil?
-    offset + segment_length - 1
+    offset.to_i + segment_length - 1
   end
 
   def range
     raise "No offset specified" if offset.nil?
-    (offset..self.end)
+    (offset.to_i..self.end)
   end
 
   def pull(offset)
@@ -68,6 +71,11 @@ module Segment
     end
   end
 
+  def includes?(segment)
+    (segment.offset.to_i >= self.offset.to_i) and
+    (segment.offset.to_i + segment.segment_length.to_i <= self.offset.to_i + self.segment_length.to_i)
+  end
+
   #{{{ Sorting
 
   def self.sort(segments, inline = true)
@@ -92,9 +100,9 @@ module Segment
   end
 
   def self.overlaps(sorted_segments)
-
     last = nil
     overlaped = []
+
     sorted_segments.reverse.each do |segment| 
       overlaped << segment if (not last.nil?) and segment.range.end > last 
       last = segment.range.begin

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

@@ -1,3 +1,4 @@
+require 'rbbt/nlp/nlp'
 require 'rbbt/ner/segment'
 module NLP
   def self.returnFeatures(prevWord, delimiter, nextWord)
@@ -168,6 +169,7 @@ module NLP
   end
 
   def self.geniass_sentence_splitter_extension(text)
+    Rbbt.software.opt.Geniass.produce
     require Rbbt.software.opt.Geniass.ruby["Geniass.so"].find
     geniass = Geniass.new
     if not geniass.geniass_is_loaded

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

@@ -29,6 +29,7 @@ module OpenNLP
   def self.sentence_splitter(text)
     return [] if text.nil? or text.empty?
 
+    text = Misc.to_utf8(text)
     last = 0
     begin
       sentence_split_detector = self.sentence_split_detector
@@ -61,6 +62,7 @@ module OpenNLP
       end
 
       sentences.collect{|sentence|
+        sentence = Misc.to_utf8(sentence)
         start = text.index(sentence, last)
         Segment.setup sentence, start
         last = start + sentence.length - 1

data/share/install/software/Geniass

@@ -5,7 +5,7 @@ RBBT_SOFTWARE_DIR="$2"
 source "$INSTALL_HELPER_FILE"
 
 name='Geniass'
-url="http://www-tsujii.is.s.u-tokyo.ac.jp/~y-matsu/geniass/geniass-1.00.tar.gz"
+url="http://www.nactem.ac.uk/y-matsu/geniass/geniass-1.00.tar.gz"
 
 
 get_pkg "$name" "$url"

data/share/install/software/OpenNLP

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 name='OpenNLP'
-url="http://apache.rediris.es//incubator/opennlp/apache-opennlp-1.5.2-incubating-bin.tar.gz"
+url="http://apache.rediris.es//opennlp/opennlp-1.5.3/apache-opennlp-1.5.3-bin.tar.gz"
 
 get_src "$name" "$url"
 move_opt "$name" 

data/test/rbbt/entity/test_document.rb

@@ -1,12 +1,15 @@
 require File.join(File.expand_path(File.dirname(__FILE__)), '../../test_helper.rb')
+
+require 'rbbt/workflow'
 require 'rbbt/entity'
+Workflow.require_workflow "Genomics"
+
+Workflow.require_workflow "TextMining"
+
 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")
@@ -18,14 +21,14 @@ module Document
 
   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)}
+    TextMining.job(:gene_mention_recognition, "Factoid", :text => text, :method => :abner, :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
+  def _test_pmid
     pmid = "21904853"
     PMID.setup(pmid)
 
@@ -33,7 +36,7 @@ class TestDocument < Test::Unit::TestCase
     assert_match /TET2/, pmid.text
   end
 
-  def test_abner
+  def _test_abner
     pmid = "21904853"
     PMID.setup(pmid)
 

data/test/rbbt/ner/test_finder.rb

@@ -8,14 +8,13 @@ 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
+  def test_namespace_and_format
+    f = Finder.new(CMD.cmd("head -n 1000", :in => Open.open(Organism.identifiers("Hsa/jun2011").produce.find)))
+    assert_equal "Hsa", f.instances.first.namespace
     assert_equal "Ensembl Gene ID", f.instances.first.format
   end
 
-  def _test_find
+  def test_find
     f = Finder.new(Organism.lexicon("Hsa/jun2011"), :grep => ["SF3B1"])
 
     assert_equal "ENSG00000115524", f.find("SF3B1").first
@@ -28,7 +27,7 @@ class TestFinder < Test::Unit::TestCase
   def test_find
     f = Finder.new(Organism.lexicon("Hsa/jun2011"), :grep => ["RASGRF2"])
 
-    ddd f.find("RAS").collect{|m| m.info}
+    assert f.find("RAS").include? "ENSG00000113319"
   end
 
 end

data/test/rbbt/ner/test_ngram_prefix_dictionary.rb

@@ -47,7 +47,6 @@ C2;11;22;3 3;bb
 
     TmpFile.with_file(lexicon.gsub(/;/,"\t")) do |file|
       index = NGramPrefixDictionary.new(file, "test")
-
       matches = index.match(' asdfa dsf asdf aa asdfasdf ')
       assert matches.select{|m| m.code.include? 'C1'}.any?
     end

data/test/rbbt/ner/test_oscar4.rb

@@ -22,7 +22,7 @@ class TestOSCAR4 < Test::Unit::TestCase
     end
   end
 
-  def _test_ranges
+  def test_ranges
     begin
       ner = OSCAR4.new
       str =<<-EOF 

metadata

@@ -1,20 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-text
 version: !ruby/object:Gem::Version
-  version: 1.0.0
-  prerelease: 
+  version: 1.1.0
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-12-21 00:00:00.000000000 Z
+date: 2013-10-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -22,7 +20,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -30,7 +27,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: stemmer
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -38,7 +34,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -46,7 +41,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: libxml-ruby
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -54,7 +48,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -62,7 +55,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: json
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -70,7 +62,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -78,7 +69,6 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: rjb
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -86,7 +76,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -146,75 +135,74 @@ files:
 - share/rnorm/cue_default
 - share/rnorm/tokens_default
 - share/wordlists/stopwords
-- test/test_helper.rb
+- test/rbbt/bow/test_misc.rb
 - test/rbbt/bow/test_bow.rb
 - test/rbbt/bow/test_dictionary.rb
-- test/rbbt/bow/test_misc.rb
-- test/rbbt/ner/test_regexpNER.rb
-- test/rbbt/ner/test_abner.rb
-- test/rbbt/ner/test_banner.rb
+- test/rbbt/ner/test_ngram_prefix_dictionary.rb
 - test/rbbt/ner/test_NER.rb
-- test/rbbt/ner/test_token_trieNER.rb
-- test/rbbt/ner/test_patterns.rb
 - test/rbbt/ner/segment/test_named_entity.rb
-- test/rbbt/ner/segment/test_segmented.rb
 - test/rbbt/ner/segment/test_transformed.rb
+- test/rbbt/ner/segment/test_segmented.rb
+- test/rbbt/ner/test_patterns.rb
 - test/rbbt/ner/test_segment.rb
-- test/rbbt/ner/test_rnorm.rb
-- 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_chemical_tagger.rb
+- test/rbbt/ner/test_token_trieNER.rb
+- test/rbbt/ner/test_oscar4.rb
+- test/rbbt/ner/test_abner.rb
+- test/rbbt/ner/test_regexpNER.rb
+- test/rbbt/ner/test_rnorm.rb
+- test/rbbt/ner/test_banner.rb
 - test/rbbt/ner/test_linnaeus.rb
-- test/rbbt/entity/test_document.rb
 - test/rbbt/nlp/test_nlp.rb
 - test/rbbt/nlp/open_nlp/test_sentence_splitter.rb
+- test/rbbt/entity/test_document.rb
+- test/test_helper.rb
 - bin/get_ppis.rb
 homepage: http://github.com/mikisvaz/rbbt-util
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Text mining tools for the Ruby Bioinformatics Toolkit (rbbt)
 test_files:
-- test/test_helper.rb
+- test/rbbt/bow/test_misc.rb
 - test/rbbt/bow/test_bow.rb
 - test/rbbt/bow/test_dictionary.rb
-- test/rbbt/bow/test_misc.rb
-- test/rbbt/ner/test_regexpNER.rb
-- test/rbbt/ner/test_abner.rb
-- test/rbbt/ner/test_banner.rb
+- test/rbbt/ner/test_ngram_prefix_dictionary.rb
 - test/rbbt/ner/test_NER.rb
-- test/rbbt/ner/test_token_trieNER.rb
-- test/rbbt/ner/test_patterns.rb
 - test/rbbt/ner/segment/test_named_entity.rb
-- test/rbbt/ner/segment/test_segmented.rb
 - test/rbbt/ner/segment/test_transformed.rb
+- test/rbbt/ner/segment/test_segmented.rb
+- test/rbbt/ner/test_patterns.rb
 - test/rbbt/ner/test_segment.rb
-- test/rbbt/ner/test_rnorm.rb
-- 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_chemical_tagger.rb
+- test/rbbt/ner/test_token_trieNER.rb
+- test/rbbt/ner/test_oscar4.rb
+- test/rbbt/ner/test_abner.rb
+- test/rbbt/ner/test_regexpNER.rb
+- test/rbbt/ner/test_rnorm.rb
+- test/rbbt/ner/test_banner.rb
 - test/rbbt/ner/test_linnaeus.rb
-- test/rbbt/entity/test_document.rb
 - test/rbbt/nlp/test_nlp.rb
 - test/rbbt/nlp/open_nlp/test_sentence_splitter.rb
+- test/rbbt/entity/test_document.rb
+- test/test_helper.rb