demystify 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6401829101cacafbc3bbd667bbc6f7003fd9e1df
-  data.tar.gz: 8558b8f978dcc94dd685acf04e5b62ccbfd90ebe
+  metadata.gz: 5971ce18068cb4b0be4e3089c81e8d1aeda25d93
+  data.tar.gz: bfc5e6fd91f9a7dd292384cdc2b6bb9ccf43212c
 SHA512:
-  metadata.gz: aa98c469ade8a8ebaa75b6cbe74a6c4fbb822f1822ba8be580eff1a90f58ca20039c6cff0076a306a32eca9858a9028f22851dc94a128c27a668a0176c6d2009
-  data.tar.gz: 0b1a2840b3e6564d777890959f016ab4cee51fdaff444e91e1ef962f296b4c1e475322c889ba6636c6e6ceba2d3802abf4238a8cc146108f0439a6f4f5e1a342
+  metadata.gz: 261f97b8e0274588b73844ce2aa17d8a0d64b377cdf9420ec76d3160326909f9188104d1b27b7256334e2385a046a64f6b13c94cd6ad5a42f7fbb6632be5a301
+  data.tar.gz: f6c8113b838cd63cddb2eaa265a394d5c15b05fcac98e7ebcac06fadfc56d1e34df58b64a159221514e9578a3d06c4840f72ea8f0b7b67dc83907716e3063343

data/.gitignore

@@ -2,3 +2,4 @@ Gemfile.lock
 .byebug_history
 Rakefile
 bin/
+.demystify-0.0.1.gem

data/README.md

@@ -0,0 +1 @@
+#Demystify

data/demystify.gemspec

@@ -0,0 +1,34 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'demystify/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "demystify"
+  spec.version       = Demystify::VERSION
+  spec.authors       = ["DouglasTGordon"]
+  spec.email         = ["douglastgordon@gmail.com"]
+
+  spec.summary       = %q{Tools for text analysis and NLP.}
+  spec.description   = %q{Demystify allows you to extract relevant information from text for easier analysis.}
+  spec.homepage      = "https://github.com/douglastgordon/Demystify"
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  # if spec.respond_to?(:metadata)
+  #   spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
+  # else
+  #   raise "RubyGems 2.0 or newer is required to protect against " \
+  #     "public gem pushes."
+  # end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.13"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/lib/demystify/version.rb

@@ -0,0 +1,3 @@
+module Demystify
+  VERSION = "0.0.2"
+end

data/lib/demystify.rb

@@ -1,4 +1,5 @@
 require 'byebug'
+
 module Demystify
 
   #From wikipedia
@@ -19,11 +20,15 @@ module Demystify
 
   class Text
 
-    attr_accessor :content, :chars
+    attr_accessor :content, :chars, :words
 
     def initialize(file)
       @content = open(file).read
       @chars = @content.split("")
+      @words = @content.split(/[^[[:word:]]]+/)
+
+      @sentences = make_sentences
+
     end
 
     def char_count
@@ -96,7 +101,36 @@ module Demystify
     end
 
     def word_count
-      @content.split(/[^[[:word:]]]+/)
+      @words.count
+    end
+
+    def sentence_count
+      @sentences.length
+    end
+
+    def first_words_of_sentences
+      first_words = []
+      @sentences.each do |sentence|
+        first_words << sentence.first
+      end
+      first_words
+    end
+
+    def last_words_of_sentences
+      last_words = []
+      @sentences.each do |sentence|
+        last_words << 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}
     end
 
   end

data/sample2.txt

@@ -0,0 +1 @@
+Whale is the common name for a widely distributed and diverse group of fully aquatic placental marine mammals. They are an informal grouping within the infraorder Cetacea, usually excluding dolphins and porpoises. Whales, dolphins and porpoises belong to the order Cetartiodactyla with even-toed ungulates and their closest living relatives are the hippopotamuses, having diverged about 40 million years ago. The two parvorders of whales, baleen whales (Mysticeti) and toothed whales (Odontoceti), are thought to have split apart around 34 million years ago. The whales comprise eight extant families: Balaenopteridae (the rorquals), Balaenidae (right whales), Cetotheriidae (the pygmy right whale), Eschrichtiidae (the gray whale), Monodontidae (belugas and narwhals), Physeteridae (the sperm whale), Kogiidae (the dwarf and pygmy sperm whale), and Ziphiidae (the beaked whales).

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: demystify
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - DouglasTGordon
@@ -48,8 +48,12 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - Gemfile
+- README.md
+- demystify.gemspec
 - lib/demystify.rb
+- lib/demystify/version.rb
 - sample1.txt
+- sample2.txt
 homepage: https://github.com/douglastgordon/Demystify
 licenses: []
 metadata: {}