demystify 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5971ce18068cb4b0be4e3089c81e8d1aeda25d93
-  data.tar.gz: bfc5e6fd91f9a7dd292384cdc2b6bb9ccf43212c
+  metadata.gz: 70032c0a2eaf6eeecedc921876cf1760e160c7fb
+  data.tar.gz: d855804fb3f43777a71cac79dd8a54b5bd990896
 SHA512:
-  metadata.gz: 261f97b8e0274588b73844ce2aa17d8a0d64b377cdf9420ec76d3160326909f9188104d1b27b7256334e2385a046a64f6b13c94cd6ad5a42f7fbb6632be5a301
-  data.tar.gz: f6c8113b838cd63cddb2eaa265a394d5c15b05fcac98e7ebcac06fadfc56d1e34df58b64a159221514e9578a3d06c4840f72ea8f0b7b67dc83907716e3063343
+  metadata.gz: 64e2cc110909035a29df6e05e46235a0bcc7db8faf4ea8c412a25149da1a03af1684bf887d7e995ea25afafbffacfd3ceedd6de469eb0cb7d77c8dfad3d2b607
+  data.tar.gz: 43d451c3267e88b6aa1bda6792310066a4d1666807fdb3bf5741eb138e299db508f23bd211a5c88a5cd7a7f3eb241e543ed6ca95ad2a87f789cc1fdb60f47192

data/README.md

@@ -1 +1,65 @@
 #Demystify
+
+Demystify is a gem to help you deal with text, for text analysis or NLP projects.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+  gem 'demystify'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install demystify
+
+##Usage
+
+Make a Text object using your text file.
+```ruby
+  text = Demystify::Text.new('./my_text_file.txt')
+```
+
+Get an array of all characters, words or sentences:
+```ruby
+  text.chars
+  text.words
+  text.sentences
+```
+
+Count the number of all characters, spaces, new lines, non-whitespace characters,
+punctuation, symbols, letters, non-letters, words and sentences:
+```ruby
+  text.char_count
+  text.spaces_count
+  text.new_line_count
+  text.non_whitespace_char_count
+  text.punctuation_count
+  text.symbol_count
+  text.letter_count
+  text.non_letter_count
+  text.word_count
+  text.sentence_count
+```
+
+Check for the number of occurrences of a particular sequence of characters:
+```ruby
+text.sequence_count(sequence)
+```
+
+Get the first word or last word of every sentence in an array:
+```ruby
+text.first_words
+text.last_words
+```
+
+Get a hash of every word in the text of pointing to an array of all of its following or preceding words in the text:
+```ruby
+text.forwards_probability_hash
+text.backwards_probability_hash
+```

data/lib/demystify/version.rb

@@ -1,3 +1,3 @@
 module Demystify
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/demystify.rb

@@ -20,15 +20,22 @@ module Demystify
 
   class Text
 
-    attr_accessor :content, :chars, :words
+    attr_accessor :content,
+                  :chars,
+                  :words,
+                  :sentences,
+                  :forwards_probability_hash,
+                  :backwards_probability_hash,
+                  :first_words,
+                  :last_words
 
     def initialize(file)
       @content = open(file).read
       @chars = @content.split("")
       @words = @content.split(/[^[[:word:]]]+/)
-
-      @sentences = make_sentences
-
+      make_sentences
+      make_probability_hashes
+      make_first_and_last_words
     end
 
     def char_count
@@ -108,33 +115,41 @@ module Demystify
       @sentences.length
     end
 
-    def first_words_of_sentences
-      first_words = []
-      @sentences.each do |sentence|
-        first_words << sentence.first
-      end
-      first_words
-    end
+    private
 
-    def last_words_of_sentences
-      last_words = []
+    def make_first_and_last_words
+      @first_words = []
+      @last_words = []
       @sentences.each do |sentence|
-        last_words << sentence.last
+        split_sentence = sentence.split(" ")
+        @first_words << split_sentence.first
+        @last_words << split_sentence.last
       end
-      last_words
     end
 
-    private
-
     def make_sentences
       sentence_regex = /((?<=[a-z0-9)][.?!])|(?<=[a-z0-9][.?!]"))\s+(?="?[A-Z])/
       sentences = @content.split(sentence_regex)
       sentences.select!{|sentence| sentence.length > 1}
-      sentences.map{|sentence| sentence.chomp}
+      @sentences = sentences.map{|sentence| sentence.chomp}
+    end
+
+    def make_probability_hashes
+      @forwards_probability_hash = Hash.new { |h, k| h[k] = [] }
+      @backwards_probability_hash = Hash.new { |h, k| h[k] = [] }
+      @sentences.each do |sentence|
+        sentence_array = sentence.split(" ")
+        sentence_array.each_with_index do |word, i|
+          unless i == sentence_array.length - 1
+            @forwards_probability_hash[word] << sentence_array[i+1]
+          end
+          unless i == 0
+            @backwards_probability_hash[word] << sentence_array[i-1]
+          end
+        end
+      end
     end
 
   end
 
 end
-
-something = Demystify::Text.new(File.join( File.dirname(__FILE__), '../sample1.txt'))

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: demystify
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - DouglasTGordon