rundown 0.0.1 → 0.0.2

data/Gemfile

@@ -1,3 +1,5 @@
 source 'https://rubygems.org'
 
 gemspec
+
+gem 'nickel', github: 'modsognir/nickel'

data/README.md

@@ -1,7 +1,47 @@
 Rundown
 =======
 
-[![Build Status](https://travis-ci.org/modsognir/rundown.png)](https://travis-ci.org/modsognir/rundown)
+[![Gem Version](https://badge.fury.io/rb/rundown.png)](http://badge.fury.io/rb/rundown) [![Build Status](https://travis-ci.org/modsognir/rundown.png)](https://travis-ci.org/modsognir/rundown)
+
+Rundown is a simple Natural Language Processor built with Ruby, inspired by [Knwl.js](https://github.com/loadfive/Knwl.js). Rundown scans through text, user data, or just about anything for likely data of interest, phone numbers, dates, locations, emails, times, as well as likelyhood of spam and overall emotion.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'sentiment_parser'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install sentiment_parser
+
+## Usage
+
+    rd = Rundown.parse("I'll see you on the 18th, give me a ring on 07912 345 678. - Jerertt, me@example.com")
+    
+    rd.emails
+    => ["me@example.com"]
+
+    rd.phones
+    => ["07912 345 678"]
+
+    rd.sentiment
+    => -0.5333
+
+    rd.dates
+    => [#<Date: 2013-12-18>]
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request
 
 ###Known Issues
 

data/lib/rundown.rb

@@ -4,13 +4,17 @@ require 'phony'
 require 'nickel'
 require 'sentiment_parser'
 
+require 'rundown/parser'
 require 'rundown/processor'
-require 'rundown/words'
-require 'rundown/email_processor'
-require 'rundown/date_processor'
-require 'rundown/phone_processor'
-require 'rundown/sentiment_processor'
+require 'rundown/processors/email'
+require 'rundown/processors/dates'
+require 'rundown/processors/phone'
+require 'rundown/processors/sentiment'
 
 module Rundown
   module_function
+
+  def parse(text)
+    Parser.new(text)
+  end
 end

data/lib/rundown/parser.rb

@@ -0,0 +1,34 @@
+module Rundown
+  class Parser
+    attr_accessor :text
+    
+    def initialize(text)
+      @text = text
+    end
+
+    # def processors
+    #   [
+    #     ,
+    #     Processors::Email,
+    #     Processors::Phone,
+    #     Processors::Sentiment
+    #   ]
+    # end
+
+    def dates
+      @dates ||= Processors::Dates.new(text).process
+    end
+
+    def emails
+      @email ||= Processors::Email.new(text).process
+    end
+
+    def phones
+      @phone ||= Processors::Phone.new(text).process
+    end
+
+    def sentiment
+      @sentiment ||= Processors::Sentiment.new(text).process
+    end
+  end
+end

data/lib/rundown/processor.rb

@@ -3,7 +3,7 @@ module Rundown
     attr_accessor :words
 
     def initialize(words)
-      @words = Array(words)
+      @words = words.to_s.split(/\s/)
     end
   end
 end

data/lib/rundown/processors/dates.rb

@@ -0,0 +1,17 @@
+module Rundown
+  module Processors
+    class Dates < Rundown::Processor
+      attr_accessor :text, :parser
+
+      def initialize(words, parser=Nickel)
+        @text = words
+        @parser = parser
+      end
+
+      def process
+        parser.parse(text).occurrences
+      end
+
+    end
+  end
+end

data/lib/rundown/processors/email.rb

@@ -0,0 +1,29 @@
+module Rundown
+  module Processors
+    class Email < Rundown::Processor
+      REGEX = /\A[^@\s]+@([^@\s]+\.)+[^@\s]+\z/
+
+      def cleanup_words
+        words = @words.map { |word|
+          word.gsub!(/\(|\)/, "")
+        }
+      end
+
+      def process
+        cleanup_words
+        words.select { |word|
+          Array(word.match(REGEX))[0]
+        }.reject(&:empty?).map {|word|
+          word.split('@')
+        }.reject { |words|
+          words.size < 2 
+        }.select { |words|
+          x = Array(words.last).last.to_s.split('.').last
+          x.length <= 4 && !x.match(/\d+/)
+        }.map { |words|
+          words.join("@")
+        }
+      end
+    end
+  end
+end

data/lib/rundown/processors/phone.rb

@@ -0,0 +1,20 @@
+module Rundown
+  module Processors
+    class Phone < Rundown::Processor
+      attr_accessor :validator, :text
+
+      def initialize(words, validator=Phony)
+        @text = words
+        @validator = validator
+      end
+
+      def plausible?(number)
+        validator.plausible?(number)
+      end
+
+      def process
+        text.scan(/(\+?(\(|\)|[0-9]|\s|-|\.){4,20})/).select {|e| plausible?(e) }
+      end
+    end
+  end
+end

data/lib/rundown/processors/sentiment.rb

@@ -0,0 +1,16 @@
+module Rundown
+  module Processors
+    class Sentiment < Rundown::Processor
+      attr_accessor :parser
+
+      def initialize(words, parser=SentimentParser)
+        @parser = parser
+        super(words)
+      end
+
+      def process
+        parser.parse(words.join(' '))
+      end
+    end
+  end
+end

data/lib/rundown/version.rb

@@ -1,3 +1,3 @@
 module Rundown
-  VERSION = '0.0.1'
+  VERSION = '0.0.2'
 end

data/rundown.gemspec

@@ -8,8 +8,8 @@ Gem::Specification.new do |spec|
   spec.version       = Rundown::VERSION
   spec.authors       = ["Jared Fraser"]
   spec.email         = ["dev@jsf.io"]
-  spec.description   = %q{knows things}
-  spec.summary       = %q{knows things}
+  spec.description   = %q{Extracts dates, phone numbers, sentiment and other items from naturally worded text.}
+  spec.summary       = %q{Natural Language Processor}
   spec.homepage      = ""
   spec.license       = "MIT"
 

data/spec/processors/dates_spec.rb

@@ -0,0 +1,18 @@
+require 'spec_helper'
+
+module Rundown
+  module Processors
+    describe Dates do
+      describe 'month' do
+        {
+          "I will see you on 12/15/2013" => Date.new(2013, 12, 15),
+          " the 28th of december." => Date.new(Time.now.year, 12, 28)
+        }.each do |input, expected|
+          it "parse '#{input}' to '#{expected}'" do
+            expect(Rundown::Processors::Dates.new(input).process.first.start_date.to_date).to eql(expected)
+          end
+        end
+      end
+    end
+  end
+end

data/spec/processors/email_spec.rb

@@ -0,0 +1,9 @@
+require 'spec_helper'
+
+module Rundown
+  module Processors
+    describe Email do
+      
+    end
+  end
+end

data/spec/processors/phone_spec.rb

@@ -0,0 +1,9 @@
+require 'spec_helper'
+
+module Rundown
+  module Processors
+    describe Phone do
+      
+    end
+  end
+end

data/spec/processors/sentiment_spec.rb

@@ -0,0 +1,9 @@
+require 'spec_helper'
+
+module Rundown
+  module Processors
+    describe Sentiment do
+      
+    end
+  end
+end

data/spec/rundown_spec.rb

@@ -5,24 +5,41 @@ describe Rundown do
     "I'm sorry, I'm extremely busy right now. I just looked at the clock, and it's 12:54 AM, I've still got a lot of work to do.  Don't worry about the event tomorrow, it's been moved ahead a week, the 28th of december. Remember though, you've got to call to get a ticket soon, their # is 1-212-323-1239. Their website says it costs $23 per person.
 If you've got enough time, they have some more information on their website, http://theevent.com.
 Regards,
-David (david32@gmail.com)".split(/\s/)
+David (david32@gmail.com)"
   }
 
   describe 'emails' do
-    it {  expect(Rundown::EmailProcessor.new(subject).process).to eql ["david32@gmail.com"]}
+    it {  expect(Rundown::Processors::Email.new(subject).process).to eql ["david32@gmail.com"]}
   end
 
   describe 'dates' do
     # FIXME: remove dependence on start date knowledge
-    it {  expect(Rundown::DateProcessor.new(subject).process.map(&:start_date).map(&:date)).to include "20131228"}
+    it {  expect(Rundown::Processors::Dates.new(subject).process.map(&:start_date).map(&:date)).to include "20131228"}
   end
 
   describe 'phones' do
-    it { pending; expect(Rundown::PhoneProcessor.new(subject).process).to eql ["212-323-1239"]}
+    it { pending; expect(Rundown::Processors::Phone.new(subject).process).to eql ["212-323-1239"]}
   end
 
   describe 'sentiment' do
-    it {  expect(Rundown::SentimentProcessor.new(subject).process.floor).to eql(2) }
+    it {  expect(Rundown::Processors::Sentiment.new(subject).process.floor).to eql(2) }
+  end
+
+  context 'basic string' do
+    subject { Rundown.parse("I'll see you on the 18th, give me a ring on 07912 345 678. - Jerertt, me@example.com") }
+
+    it 'extracts emails' do
+      expect(subject.emails).to eql(["me@example.com"])
+    end
+
+    it 'extracts phone numbers' do
+      pending
+      expect(subject.phones).to eql(["07912 345 678"])
+    end
+
+    it 'extracts sentiment' do
+      expect(subject.sentiment).to eql(0.791666666667)
+    end
   end
 
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rundown
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
   prerelease: 
 platform: ruby
 authors:
@@ -107,7 +107,8 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: knows things
+description: Extracts dates, phone numbers, sentiment and other items from naturally
+  worded text.
 email:
 - dev@jsf.io
 executables: []
@@ -121,14 +122,19 @@ files:
 - README.md
 - Rakefile
 - lib/rundown.rb
-- lib/rundown/date_processor.rb
-- lib/rundown/email_processor.rb
-- lib/rundown/phone_processor.rb
+- lib/rundown/parser.rb
 - lib/rundown/processor.rb
-- lib/rundown/sentiment_processor.rb
+- lib/rundown/processors/dates.rb
+- lib/rundown/processors/email.rb
+- lib/rundown/processors/phone.rb
+- lib/rundown/processors/sentiment.rb
 - lib/rundown/version.rb
 - lib/rundown/words.rb
 - rundown.gemspec
+- spec/processors/dates_spec.rb
+- spec/processors/email_spec.rb
+- spec/processors/phone_spec.rb
+- spec/processors/sentiment_spec.rb
 - spec/rundown_spec.rb
 - spec/spec_helper.rb
 homepage: ''
@@ -146,7 +152,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2506835466625535810
+      hash: -3027207295298503492
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -155,13 +161,17 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -2506835466625535810
+      hash: -3027207295298503492
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.25
 signing_key: 
 specification_version: 3
-summary: knows things
+summary: Natural Language Processor
 test_files:
+- spec/processors/dates_spec.rb
+- spec/processors/email_spec.rb
+- spec/processors/phone_spec.rb
+- spec/processors/sentiment_spec.rb
 - spec/rundown_spec.rb
 - spec/spec_helper.rb

data/lib/rundown/date_processor.rb

@@ -1,15 +0,0 @@
-module Rundown
-  class DateProcessor < Processor
-    attr_accessor :text, :parser
-
-    def initialize(words, parser=Nickel)
-      @text = words.join(' ')
-      @parser = parser
-    end
-
-    def process
-      parser.parse(text).occurrences
-    end
-
-  end
-end

data/lib/rundown/email_processor.rb

@@ -1,27 +0,0 @@
-module Rundown
-  class EmailProcessor < Processor
-    REGEX = /\A[^@\s]+@([^@\s]+\.)+[^@\s]+\z/
-
-    def cleanup_words
-      words = @words.map { |word|
-        word.gsub!(/\(|\)/, "")
-      }
-    end
-
-    def process
-      cleanup_words
-      words.select { |word|
-        Array(word.match(REGEX))[0]
-      }.reject(&:empty?).map {|word|
-        word.split('@')
-      }.reject { |words|
-        words.size < 2 
-      }.select { |words|
-        x = Array(words.last).last.to_s.split('.').last
-        x.length <= 4 && !x.match(/\d+/)
-      }.map { |words|
-        words.join("@")
-      }
-    end
-  end
-end

data/lib/rundown/phone_processor.rb

@@ -1,18 +0,0 @@
-module Rundown
-  class PhoneProcessor < Processor
-    attr_accessor :validator, :text
-
-    def initialize(words, validator=Phony)
-      @text = words.join(' ')
-      @validator = validator
-    end
-
-    def plausible?(number)
-      validator.plausible?(number)
-    end
-
-    def process
-      text.scan(/(\+?(\(|\)|[0-9]|\s|-|\.){4,20})/).select {|e| plausible?(e) }
-    end
-  end
-end

data/lib/rundown/sentiment_processor.rb

@@ -1,14 +0,0 @@
-module Rundown
-  class SentimentProcessor < Processor
-    attr_accessor :parser
-
-    def initialize(words, parser=SentimentParser)
-      @parser = parser
-      super(words)
-    end
-
-    def process
-      parser.parse(words.join(' '))
-    end
-  end
-end