stringfu 0.0.6 → 0.0.8

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ODk5OGY2ZmJkNDA0MmRiOTMyMWU3MGZmMzVmNDg0M2M4MDdlNzAyNA==
+  data.tar.gz: !binary |-
+    MjVlZTA1ZTI5MmE4YTY2YTZiMzY3NjliMjY5Nzg4YTQ3OGZhOGQ1Yw==
+SHA512:
+  metadata.gz: !binary |-
+    YjZkZTA3ZWNiNWIxN2ZiMDIxYTc3NWZkODJiNDcxYjE0ZmExM2IzNjk1OWQ4
+    NDI2OWM3NTZkYTJiZWNlYmJjNmM3ZjBmZmMxZTFlY2IzNWNlNzAzZTBlNzM5
+    YzA4OWU3ZTY0ODNkOTI2ZWQyOWQ2MzhlOTM4NTQ0MmYxYjIzMzM=
+  data.tar.gz: !binary |-
+    MTEyYWRmNmZlNjRhYzUwMzZjMmQyMWY0ODk2Yjg0ZTk0ODliZDY5ODNkNmRj
+    ZTY0M2VkMDI3OGIwYmFkNTNlZTgwNDMzNDNhOGQ1Y2VmODVhYTM5ZDBlODZm
+    OTRmOGU1OTNlYTRhZThjYjhkMDgyNjM1YzE0Nzk2Y2NlNjQ5NjA=

data/README.markdown

@@ -1,11 +1,17 @@
-# StringFu
+# stringfu
 
-StringFu are some simple methods to manipulate strings in order for them to be cleaned up for Natural Language Processing (NLP).
+stringfu is a ruby gem with some simple methods to manipulate strings in order for them to be cleaned up for Natural Language Processing (NLP).
 
-## Install StringFu
+## Install stringfu
 
     gem install stringfu
 
+### Dependencies
+
+UEA Stemmer for Porter Stemming: https://github.com/ealdent/uea-stemmer
+
+    gem install uea-stemmer
+
 ## Usage
 
     wtf = 'Charlie the Unicorn is a potty mouth. He\'ll say things like, @!@#% !@$%$[@#$^!)'
@@ -22,15 +28,40 @@ 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
+ngrams will generate ngrams (unigrams, bigrams, trigrams, four-grams, etc.) for any string and returns the max number of ngrams.
 
     ftw = "I choose Whoppie Goldberg for the Win!"
-    ftw.ngrams  # => [1, 2, 3, 4, 5, 6, 7]
+    ftw.ngrams  # => 7
+    
+    ftw.unigrams
+    ftw._1grams
+    # => ["I", "choose", "Whoppie", "Goldberg", "for", "the", "Win!"]
+    
+    ftw.bigrams
+    ftw._2grams
+    # => ["I choose", "choose Whoppie", "Whoppie Goldberg", "Goldberg for", "for the", "the Win!"]
     
-    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.trigrams
+    ftw._3grams
+    # => ["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]
+    ftw.ngrams 2, 7, 2..4   # => [2, 3, 4, 7]
+
+stemming a string will output an array of the Porter Stemmed words
+
+    "ZOMG! I hearted installing headlights into used decepticons".stem
+    # => ["zomg", "i", "heart", "instal", "headlight", "into", "use", "decepticon"]
+    
+## Todo
+
+* ngrams
+ * add option to make punctation it's own -gram
+ * add option to -gramify individual words into characters / syllables
+ * add parts of speech (POS) integration to drop types (noun, adj, verbs) from ngrams
+* stemming
+ * add pluralize and singularize methods
+ * add parts of speech (POS) integration so you can pluarlize and singularize just nouns (NN, NNS, NNP)

data/lib/stringfu.rb

@@ -41,7 +41,7 @@ module Stringfu
     if args.size == 0 
       args = [1..wordphrase.length]
     end
-  
+
     # Inspired by http://www.rubyquiz.com/quiz4.html
     args = args.map { |arg| Array(arg) }.flatten.uniq.sort
     args = args.select { |arg| arg <= wordphrase.length and arg > 0 }  
@@ -50,10 +50,10 @@ module Stringfu
       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(" ")
+      wordphrase.each_cons(num) do |words|
+        self.instance_variable_get("@#{prefix}grams")  << words.join(" ")
       end
+
       # Calls :attr_accessor to add new instance variable
       self.class.__send__(:attr_accessor, "#{prefix}grams".to_sym)
       self.instance_variable_get("@#{prefix}grams")

data/lib/stringfu/version.rb

@@ -1,3 +1,3 @@
 module Stringfu
-  VERSION = "0.0.6"
+  VERSION = "0.0.8"
 end

data/stringfu.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |s|
   s.email       = ["me@eywu.com"]
   s.homepage    = "http://stringfu.com"
   s.summary     = %q{Manipulating words like a grandmasta}
-  s.description = %q{Extending String with methods to stem, count, and clean words}
+  s.description = %q{Extending the String Class with methods to stem, count, and clean words}
 
   s.rubyforge_project = "stringfu"
 

metadata

@@ -1,17 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: stringfu
 version: !ruby/object:Gem::Version
-  version: 0.0.6
-  prerelease: 
+  version: 0.0.8
 platform: ruby
 authors:
 - Eric Wu
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-20 00:00:00.000000000Z
+date: 2013-09-30 00:00:00.000000000 Z
 dependencies: []
-description: Extending String with methods to stem, count, and clean words
+description: Extending the String Class with methods to stem, count, and clean words
 email:
 - me@eywu.com
 executables: []
@@ -28,26 +27,25 @@ files:
 - stringfu.gemspec
 homepage: http://stringfu.com
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: stringfu
-rubygems_version: 1.8.10
+rubygems_version: 2.1.5
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Manipulating words like a grandmasta
 test_files: []