demystify 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6401829101cacafbc3bbd667bbc6f7003fd9e1df
+  data.tar.gz: 8558b8f978dcc94dd685acf04e5b62ccbfd90ebe
+SHA512:
+  metadata.gz: aa98c469ade8a8ebaa75b6cbe74a6c4fbb822f1822ba8be580eff1a90f58ca20039c6cff0076a306a32eca9858a9028f22851dc94a128c27a668a0176c6d2009
+  data.tar.gz: 0b1a2840b3e6564d777890959f016ab4cee51fdaff444e91e1ef962f296b4c1e475322c889ba6636c6e6ceba2d3802abf4238a8cc146108f0439a6f4f5e1a342

data/.gitignore

@@ -0,0 +1,4 @@
+Gemfile.lock
+.byebug_history
+Rakefile
+bin/

data/Gemfile

@@ -0,0 +1,4 @@
+source "https://rubygems.org"
+
+gem 'rspec', "~> 3.1.0"
+gem 'byebug'

data/lib/demystify.rb

@@ -0,0 +1,106 @@
+require 'byebug'
+module Demystify
+
+  #From wikipedia
+  Punctuation = ['[', ']', '(', ')', '{', '}', '⟨', '⟩', ':', ',', '،',
+                 '、', '‒', '–', '—', '―', '…', '!', '.', '‹', '›', '«',
+                 '»', '‐', '-', '?', "‘", "’", "“", "”", "'", "\""]
+
+  Symbols = ['&', '*', '@', '\\', '/', '•', '^', '†', '‡', '°', '″', '¡', '¿',
+            '※', '#', '№', '÷', '×', 'º', 'ª', '%', '‰', '+', '−', '=',
+            '‱', '¶', '′', '″', '‴', '§', '~', '_', '|', '‖', '¦', '⁂',
+            '❧', '☞', '‽', '⸮', '◊', '⁀']
+
+  Intellectual_property = ['©', '℗', '®', '℠', '™']
+
+  # Currency = ["¤", "₳",​ "฿", "₵", "¢", "₡", "₢", "$", "₫", "₯", "₠", "€",
+  #             "ƒ", "₣", "₲", "₴", "₭", "₺", "ℳ", "₥", "₦", "₧", "₱", "₰",
+  #             ​"£", "៛", "₨", "₪", "৳", ​"₮", "₩", "¥"]
+
+  class Text
+
+    attr_accessor :content, :chars
+
+    def initialize(file)
+      @content = open(file).read
+      @chars = @content.split("")
+    end
+
+    def char_count
+      @chars.length
+    end
+
+    def spaces_count
+      count = 0
+      @chars.each do |char|
+        count += 1 if char == " "
+      end
+      count
+    end
+
+    def new_line_count
+      count = 0
+      @chars.each do |char|
+        count += 1 if char == "\n"
+      end
+      count
+    end
+
+    def non_whitespace_char_count
+      char_count - (spaces_count + new_line_count)
+    end
+
+    def punctuation_count
+      count = 0
+      @chars.each do |char|
+        count += 1 if Punctuation.include?(char)
+      end
+      count
+    end
+
+    def symbol_count
+      count = 0
+      @chars.each do |char|
+        count += 1 if Symbols.include?(char)
+      end
+      count
+    end
+
+    def intellectual_property_count
+      count = 0
+      @chars.each do |char|
+        count += 1 if Intellectual_property.include?(char)
+      end
+      count
+    end
+
+    def non_letter_count
+      punctuation_count + symbol_count + intellectual_property_count
+    end
+
+    def letter_count
+      char_count - (spaces_count + new_line_count + symbol_count + intellectual_property_count)
+    end
+
+    def sequence_count(sequence)
+      count = 0
+      i = 0
+      while i < (@chars.length - sequence.length)
+        # puts @chars[i...sequence.length].join("")
+        if @chars[i...(i+sequence.length)].join("") == sequence
+          count += 1
+        end
+        i += 1
+      end
+      count
+    end
+
+    def word_count
+      @content.split(/[^[[:word:]]]+/)
+    end
+
+  end
+
+end
+
+something = Demystify::Text.new(File.join( File.dirname(__FILE__), '../sample1.txt'))

data/sample1.txt

@@ -0,0 +1,4 @@
+Hello!
+This s.sd
+is some textsadkjflksj, .dsf./a .a..a
+asdf sdf

metadata

@@ -0,0 +1,76 @@
+--- !ruby/object:Gem::Specification
+name: demystify
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- DouglasTGordon
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-12-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: Demystify allows you to extract relevant information from text for easier
+  analysis.
+email:
+- douglastgordon@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- lib/demystify.rb
+- sample1.txt
+homepage: https://github.com/douglastgordon/Demystify
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Tools for text analysis and NLP.
+test_files: []