part_of_speech 0.0.0 → 0.0.1

data/README.rdoc

@@ -9,6 +9,8 @@ I've just cleaned it up a little bit and packaged it into a gem.
   gem sources -a http://gemcutter.org
   sudo gem install part_of_speech
   
+You can download a lexicon list from http://github.com/downloads/reddavis/Part-Of-Speech/lexicon.txt
+  
 == How To Use
 
   require 'rubygems'
@@ -16,7 +18,7 @@ I've just cleaned it up a little bit and packaged it into a gem.
   
   text = "This is some text that I want analyzing"
   
-  PartOfSpeechTagger.analyze(text)
+  PartOfSpeechTagger.analyze(lexicon_path, text)
     #=> [["This", "DT"], ["is", "VBZ"], ["some", "DT"], ["text", "NN"], ["that", "IN"], ["I", "PRP"], ["want", "VBP"], ["analyzing", "VBG"]]
     
 == What Do These Letters Mean?

data/VERSION

@@ -1 +1 @@
-0.0.0
+0.0.1

data/lib/part_of_speech.rb

@@ -1,22 +1,22 @@
 class PartOfSpeech
   
   class << self
-    def analyze(text)
-      new.tag(text)
+    def analyze(lexicon_path, text)
+      new(lexicon_path).tag(text)
     end
   end
   
   # Place corpus into memory
-  def initialize
-    @lexicons = {}
-    File.open(corpus_path).each do |line|
+  def initialize(lexicon_path)
+    @lexicons = Hash.new {|hash, k| hash[k] = []}
+    File.open(lexicon_path, 'r').each do |line|
       line = line.split
       @lexicons[line.shift] = line
     end
   end
   
   def tag(text)
-    @text = text.split(/\s|\.|,|\:|\;|\'/)
+    @text = text.split(/ |,|\.|\:|\;|\'/)
     
     @pos = []
     @text.each do |word|
@@ -114,11 +114,11 @@ class PartOfSpeech
     ## rule 9: <noun> <noun 2> --> <noun> <verb> if <noun 2> can also be a verb
     return unless index > 0
 
-    if @pos[index-1] =~ /^NN/  && @pos[index] =~ /^NN/ 
-      if @lexicon[@text[index]].include?("VBN")
+    if @pos[index-1] =~ /^NN/  && @pos[index] =~ /^NN/
+      if @lexicons[@text[index]].include?("VBN")
         @pos[index] = "VBN"
       end
-      if @lexicon[@text[index]].include?("VBZ")
+      if @lexicons[@text[index]].include?("VBZ")
         @pos[index] = "VBZ"
       end
     end

data/part_of_speech.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{part_of_speech}
-  s.version = "0.0.0"
+  s.version = "0.0.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["reddavis"]
-  s.date = %q{2010-03-01}
+  s.date = %q{2010-03-02}
   s.description = %q{Part of speech tagger based off Mark Watsons code}
   s.email = %q{reddavis@gmail.com}
   s.extra_rdoc_files = [
@@ -23,9 +23,9 @@ Gem::Specification.new do |s|
      "README.rdoc",
      "Rakefile",
      "VERSION",
-     "lib/corpus/lexicon.txt",
      "lib/part_of_speech.rb",
      "part_of_speech.gemspec",
+     "spec/files/lexicon.txt",
      "spec/part_of_speech_spec.rb",
      "spec/spec.opts",
      "spec/spec_helper.rb"

data/spec/part_of_speech_spec.rb

@@ -2,9 +2,9 @@ require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
 describe "PartOfSpeech" do
   it "should properly tag 'the fast fox'" do
-    a = PartOfSpeech.analyze('the fast fox')
+    a = PartOfSpeech.analyze(lexicon_path, text_sample)
     a[0][1].should == "DT"
-    a[1][1].should == "RB"
+    a[1][1].should == "JJ"
     a[2][1].should == "NN"
   end
 end

data/spec/spec_helper.rb

@@ -4,6 +4,15 @@ require 'part_of_speech'
 require 'spec'
 require 'spec/autorun'
 
+def text_sample
+  "This regular expression is read in the following manner: Zero or more adjectives or nouns, followed by an option group of a noun and a preposition, followed again by zero or more adjectives or nouns, followed by a single noun. A sequence of tags matching this pattern ensures that the corresponding words make up a noun phrase.
+  In addition to simply pulling out the phrases, it is common to do some simple post processing to link variants together (For example, unpluralizing plural variants)."
+end
+
+def lexicon_path
+  File.expand_path(File.dirname(__FILE__) + '/files/lexicon.txt')
+end
+
 Spec::Runner.configure do |config|
   
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: part_of_speech
 version: !ruby/object:Gem::Version 
-  version: 0.0.0
+  version: 0.0.1
 platform: ruby
 authors: 
 - reddavis
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-03-01 00:00:00 +00:00
+date: 2010-03-02 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -38,9 +38,9 @@ files:
 - README.rdoc
 - Rakefile
 - VERSION
-- lib/corpus/lexicon.txt
 - lib/part_of_speech.rb
 - part_of_speech.gemspec
+- spec/files/lexicon.txt
 - spec/part_of_speech_spec.rb
 - spec/spec.opts
 - spec/spec_helper.rb