rbbt-text 0.5.0 → 0.6.0

data/lib/rbbt/ner/annotations/annotated.rb

@@ -1,15 +0,0 @@
-require 'rbbt/ner/annotations'
-module Annotated
-  attr_accessor :annotations
-  def self.annotate(string, annotations = nil)
-    string.extend Annotated
-    string.annotations = annotations || []
-    string
-  end
-
-  def split_segments(skip_segments = false)
-    Segment.split(self, @annotations, skip_segments)
-  end
-end
-
-

data/lib/rbbt/ner/annotations/relations.rb

@@ -1,25 +0,0 @@
-require 'rbbt/ner/annotations'
-
-module Relationship
-  attr_accessor :terms, :segment_types
-  include Segment
-  def self.annotate(string, offset = nil, terms = nil)
-    string.extend PPI
-    string.offset = offset unless offset.nil?
-    string.terms = terms unless terms.nil?
-    string
-  end
-
-  def html
-    text = <<-EOF
-<span class='Relationship'\
->#{ self }</span>
-    EOF
-    text.chomp
-  end
-
-  def html_with_entities(*types)
-    annotations.values_at(*types).each do |segments|
-    end
-  end
-end

data/lib/rbbt/ner/annotations/token.rb

@@ -1,28 +0,0 @@
-require 'rbbt/ner/annotations'
-
-module Token
-  include Segment
-  attr_accessor :original
-  def self.annotate(string, offset = nil, original = nil)
-    string.extend Token
-    string.offset   = offset unless offset.nil?
-    string.original = original || string.dup
-    string
-  end
-
-  def self.tokenize(text, split_at = /\s|(\(|\)|[-."':,])/, start = 0)
-
-    tokens = []
-    while matchdata = text.match(split_at)
-      tokens << Token.annotate(matchdata.pre_match, start) unless matchdata.pre_match.empty?
-      tokens << Token.annotate(matchdata.captures.first, start + matchdata.begin(1)) if matchdata.captures.any? and not matchdata.captures.first.empty?
-      start += matchdata.end(0)
-      text = matchdata.post_match
-    end
-
-    tokens << Token.annotate(text, start) unless text.empty?
-
-    tokens
-  end
-end
-

data/test/rbbt/ner/annotations/test_named_entity.rb

@@ -1,14 +0,0 @@
-require File.join(File.expand_path(File.dirname(__FILE__)), '../../..', 'test_helper.rb')
-require 'rbbt/ner/annotations'
-require 'rbbt/ner/annotations/named_entity'
-require 'rbbt/ner/annotations/transformed'
-
-class TestClass < Test::Unit::TestCase
-  def test_info
-    a = "test"
-    a.extend NamedEntity
-    assert(! a.info.keys.include?("offset"))
-    a.offset = 10
-    assert a.info.keys.include? "offset"
-  end
-end

data/test/rbbt/ner/test_annotations.rb

@@ -1,70 +0,0 @@
-require File.join(File.expand_path(File.dirname(__FILE__)), '../..', 'test_helper.rb')
-require 'rbbt/ner/annotations'
-require 'rbbt/ner/annotations/named_entity'
-require 'rbbt/ner/annotations/transformed'
-
-class TestClass < Test::Unit::TestCase
-  def test_info
-    a = "test"
-    a.extend NamedEntity
-    a.type = "type"
-    assert a.info.keys.include? "type"
-  end
-
-  def test_segment_type
-    a = "test"
-    a.extend NamedEntity
-    assert a.segment_types.include? "NamedEntity"
-  end
-
-  def test_align
-    text =<<-EOF
-Atypical teratoid/rhabdoid tumors (AT/RTs) are highly aggressive brain tumors of early childhood poorly responding to therapy.
-    EOF
-
-    parts = text.split(/\W/)
-    Segment.align(text, parts)
-
-    assert_equal "Atypical teratoid/".length, parts.select{|s| s == "rhabdoid"}.first.offset
-  end
-
-  def test_sort
-    a = "This sentence mentions the TP53 gene and the CDK5R1 protein"
-
-    gene1 = "TP53"
-    gene1.extend NamedEntity
-    gene1.offset = a.index gene1
-    gene1.type = "Gene"
-
-    gene2 = "CDK5R1"
-    gene2.extend NamedEntity
-    gene2.offset = a.index gene2
-    gene2.type = "Gene"
-
-    assert_equal [gene1,gene2], Segment.sort([gene2,gene1])
-
-  end
-
-  def test_clean_sort
-    a = "This sentence mentions the TP53 gene and the CDK5R1 protein"
-
-    gene1 = "TP53"
-    gene1.extend NamedEntity
-    gene1.offset = a.index gene1
-    gene1.type = "Gene"
-
-    gene2 = "CDK5R1"
-    gene2.extend NamedEntity
-    gene2.offset = a.index gene2
-    gene2.type = "Gene"
-
-    gene3 = "TP53 gene"
-    gene3.extend NamedEntity
-    gene3.offset = a.index gene3
-    gene3.type = "Gene"
-
-    assert_equal [gene3,gene2], Segment.clean_sort([gene2,gene1,gene3])
-
-  end
-end
-