text_parser 0.1.0

data/README.rdoc

@@ -0,0 +1,20 @@
+:title: Text Parser Ruby Gem
+=Arguments
+* :dictionary => nil,
+* :order => :word,
+* :order_direction => :asc,
+* :negative_dictionary => []
+
+=Usage
+  "Simple, simple test".parse # => [{:word => "simple", :hits => 2}, {:word => "test", :hits => 1}]
+  
+  my_text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Pellentesque pretium consectetur."
+  my_text.parse(:dictionary => ["dolor", "consectetur"])
+  # => [{:word => "consectetur", :hits => 2}, {:word => "dolor", :hits => 1}]
+  
+  my_text.parse(:dictionary => ["dolor", "consectetur"], :order => :word, :order_direction => :desc)
+  # => [{:word => "dolor", :hits => 1}, {:word => "consectetur", :hits => 2}]
+  
+  
+  
+  

data/Rakefile

@@ -0,0 +1,6 @@
+require "rake/testtask"
+ 
+Rake::TestTask.new do |t|
+  t.libs << "lib"
+  t.test_files = Dir["test/**/*_test.rb"]
+end

data/lib/string.rb

@@ -0,0 +1,5 @@
+require 'text_parser'
+
+class String
+  include TextParser
+end

data/lib/text_parser.rb

@@ -0,0 +1,27 @@
+module TextParser
+  def parse(args = {})
+    options = {
+      :dictionary => nil,
+      :order => :word,
+      :order_direction => :asc,
+      :negative_dictionary => []
+    }.merge(args)
+    result = []
+    text = process_text
+    options[:dictionary] = text.split(" ") unless options[:dictionary]
+    regex = Regexp.new(options[:dictionary].join("|"), Regexp::IGNORECASE)
+    match_result = text.scan(regex).map{|i| i.downcase}
+    match_result.each do |w|
+      result << {:hits => match_result.count(w), :word => w} unless result.select{|r| r[:word] == w}.shift unless options[:negative_dictionary].map{|i| i.downcase}.include?(w)
+    end 
+    result = result.sort_by{|i| i[options[:order]]}
+    result.reverse! if options[:order_direction] == :desc
+    result
+  end
+  
+  private
+  
+  def process_text
+    self.gsub(/[^\w\s\-]/, "")
+  end
+end

data/lib/text_parser/version.rb

@@ -0,0 +1,8 @@
+module TextParser
+  module Version
+    MAJOR = 0
+    MINOR = 1
+    PATCH = 0
+    STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
+  end
+end

data/test/text_parser_test.rb

@@ -0,0 +1,66 @@
+require "test/unit"
+require "string"
+require "text_parser"
+
+class TextParserTest < Test::Unit::TestCase
+
+  def test_should_have_method_parse
+    assert "some text".methods.select{|a| a=~/parse/}.count > 0
+  end
+  
+  def test_should_parse
+    text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Pellentesque pretium consectetur."
+    assert_equal text.parse(:dictionary => ["dolor", "consectetur"]), [{:word => "consectetur", :hits => 2}, {:word => "dolor", :hits => 1}]
+  end
+  
+  def test_should_parse_without_dictionary
+    text = "test test"
+    assert_equal text.parse, [{:word => "test", :hits => 2}]
+  end
+  
+  def test_should_remove_some_characters
+    text = "Test? Test. Yes, test!"
+    assert_equal text.parse, [{:word => "test", :hits => 3}, {:word => "yes", :hits => 1}]
+  end
+  
+  def test_should_return_an_empty_array
+    text = "test"
+    assert_equal text.parse(:dictionary => ['abc']), []
+  end
+
+  def test_should_order_by_word_asc
+    text = " beta omega gamma alpha gamma"
+    result = [{:word => "alpha",  :hits => 1}, 
+              {:word => "beta",   :hits => 1},
+              {:word => "gamma",  :hits => 2},
+              {:word => "omega",  :hits => 1}]
+    assert_equal text.parse, result
+    assert_equal text.parse(:order => :word), result
+    assert_equal text.parse(:order => :word, :order_direction => :asc), result
+  end
+  
+  def test_should_order_by_word_desc
+    assert_equal "aaa zzz".parse(:order => :word, :order_direction => :desc), [{:word => "zzz",  :hits => 1}, {:word => "aaa",  :hits => 1}]
+  end
+ 
+  def test_should_order_by_hits_asc
+    text = "gamma alpha gamma beta alpha gamma"
+    result = [{:word => "beta",  :hits => 1},
+              {:word => "alpha", :hits => 2},
+              {:word => "gamma", :hits => 3}]
+    assert_equal text.parse(:order => :hits), result
+    assert_equal text.parse(:order => :hits, :order_direction => :asc), result
+  end
+  
+  def test_should_order_by_hits_desc
+    text = "gamma alpha gamma beta alpha gamma"
+    assert_equal text.parse(:order => :hits, :order_direction => :desc), [{:word => "gamma",  :hits => 3},
+                                                                          {:word => "alpha",  :hits => 2},
+                                                                          {:word => "beta",   :hits => 1}]
+  end
+  
+  def test_should_ignore_negative_dictionary
+    text = "This is good"
+    assert_equal text.parse(:negative_dictionary => ["is", "this"]), [{:word => "good",  :hits => 1}]
+  end
+end

data/text_parser.gemspec

@@ -0,0 +1,7 @@
+Gem::Specification.new do |s|
+  s.name        = "text_parser"
+  s.version     = "0.1.0"
+  s.author      = "Frederico de Paula"
+  s.summary     = "A easy way to parse text."
+  s.files       = Dir["{lib/**/*.rb,README.rdoc,test/**/*.rb,Rakefile,*.gemspec}"]
+end

metadata

@@ -0,0 +1,73 @@
+--- !ruby/object:Gem::Specification 
+name: text_parser
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: 
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Frederico de Paula
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-12-01 00:00:00 -02:00
+default_executable: 
+dependencies: []
+
+description: 
+email: 
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/string.rb
+- lib/text_parser/version.rb
+- lib/text_parser.rb
+- README.rdoc
+- test/text_parser_test.rb
+- Rakefile
+- text_parser.gemspec
+has_rdoc: true
+homepage: 
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+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 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.4.2
+signing_key: 
+specification_version: 3
+summary: A easy way to parse text.
+test_files: []
+