stringfu 0.0.3 → 0.0.4

data/Gemfile

@@ -2,3 +2,5 @@ source "http://rubygems.org"
 
 # Specify your gem's dependencies in stringfu.gemspec
 gemspec
+gem "uea-stemmer"
+

data/Gemfile.lock

@@ -0,0 +1,16 @@
+PATH
+  remote: .
+  specs:
+    stringfu (0.0.3)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    uea-stemmer (0.10.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  stringfu!
+  uea-stemmer

data/README.markdown

@@ -1,3 +1,36 @@
 # StringFu
 
 StringFu are some simple methods to manipulate strings in order for them to be cleaned up for Natural Language Processing (NLP).
+
+## Install StringFu
+
+    gem install stringfu
+
+## Usage
+
+    wtf = 'Charlie the Unicorn is a potty mouth. He\'ll say things like, @!@#% !@$%$[@#$^!)'
+
+punc_strip will strip away all standard punctation.
+  
+    wtf.punc_strip  # => "Charlie the Unicorn is a potty mouth He'll say things like  "
+
+punc_gsub will replace punctionation with spaces if given no arguments
+
+    wtf.punc_gsub   # => "Charlie the Unicorn is a potty mouth  He'll say things like                    "
+
+punc_gsub can also take arguments
+
+    wtf.punc_gsub "?"   # => "Charlie the Unicorn is a potty mouth? He'll say things like? ????? ????????????"
+
+ngrams will generate ngrams for any string and returns an array of numbers corresponding to the ngrams
+
+    ftw = "I choose Whoppie Goldberg for the Win!"
+    ftw.ngrams  # => [1, 2, 3, 4, 5, 6, 7]
+    
+    ftw.unigrams  # => ["I", "choose", "Whoppie", "Goldberg", "for", "the", "Win!"]
+    ftw.bigrams   # => ["I choose", "choose Whoppie", "Whoppie Goldberg", "Goldberg for", "for the", "the Win!"]
+    ftw.trigrams  # => ["I choose Whoppie", "choose Whoppie Goldberg", "Whoppie Goldberg for", "Goldberg for the", "for the Win!"]
+    ftw._4grams   # => ["I choose Whoppie Goldberg", "choose Whoppie Goldberg for", "Whoppie Goldberg for the", "Goldberg for the Win!"]
+
+    ftw.ngrams 3..6   # => [3, 4, 5, 6]
+    ftw.ngrams 2, 7, 3..4   # => [2, 3, 4, 7]

data/lib/stringfu/version.rb

@@ -1,3 +1,3 @@
 module Stringfu
-  VERSION = "0.0.3"
+  VERSION = "0.0.4"
 end

data/lib/stringfu.rb

@@ -1,4 +1,8 @@
-require "stringfu/version"
+require 'rubygems'
+require 'bundler/setup'
+
+require 'stringfu/version'
+require 'uea-stemmer'
 
 STOP = ["a", "able", "about", "across", "after", "all", "almost", "also", "am", "among", "an", "and", "any", "are", "as", "at", "be", "because", "been", "but", "by", "can", "cannot", "could", "dear", "did", "do", "does", "either", "else", "ever", "every", "for", "from", "get", "got", "had", "has", "have", "he", "her", "hers", "him", "his", "how", "however", "i", "if", "in", "into", "is", "it", "its", "just", "least", "let", "like", "likely", "may", "me", "might", "most", "must", "my", "neither", "no", "nor", "not", "of", "off", "often", "on", "only", "or", "other", "our", "own", "rather", "said", "say", "says", "she", "should", "since", "so", "some", "than", "that", "the", "their", "them", "then", "there", "these", "they", "this", "tis", "to", "too", "twas", "us", "wants", "was", "we", "were", "what", "when", "where", "which", "while", "who", "whom", "why", "will", "with", "would", "yet", "you", "your"]
 
@@ -45,6 +49,7 @@ module Stringfu
     args.each do |num| 
       prefix = latinfy num
       self.instance_variable_set "@#{prefix}grams", []
+
       rounds = wordphrase.length - num + 1
       rounds.times do |iter| 
         self.instance_variable_get("@#{prefix}grams") << wordphrase[iter...(iter+num)].join(" ")
@@ -52,10 +57,30 @@ module Stringfu
       # Calls :attr_accessor to add new instance variable
       self.class.__send__(:attr_accessor, "#{prefix}grams".to_sym)
       self.instance_variable_get("@#{prefix}grams")
+
+      self.class.__send__(:alias_method, "_#{num}grams", "#{prefix}grams") if num <= 3
+      self.class.__send__(:alias_method, "_#{num}grams=", "#{prefix}grams=") if num <= 3
     end
     args
   end
 
+  def stem
+    words = self.punc_strip.normalize.split
+
+    stemmer = UEAStemmer.new
+    words = words.map do |word|
+      stem = stemmer.stem word
+    end
+  end
+
+  def normalize
+    self.downcase.squeeze(" ").strip
+  end
+
+  def normalize!
+    replace(self.downcase.squeeze(" ").strip)
+  end
+
   private
   def latinfy num
     prefix = {1 => "uni", 2 => "bi", 3 => "tri"}

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: stringfu
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
   prerelease: 
 platform: ruby
 authors:
@@ -20,6 +20,7 @@ extra_rdoc_files: []
 files:
 - .gitignore
 - Gemfile
+- Gemfile.lock
 - README.markdown
 - Rakefile
 - lib/stringfu.rb