text_analyzer 0.0.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ZTMxNzI2NzkxZmI1ZjhlZWFmNjlhYjQ5ZDgwZjA0YTQyMDdlYTUzZA==
+  data.tar.gz: !binary |-
+    MjYwODdmODZhYjNhNGJjY2I2YmI4ZDA1NzBhYTA0MGQ5OWY1ZDdiNA==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    NGQ0OWM0NDM4MWQ3MGM5MjQyNjVhYjU2NmI4NmI1ZjZhNzUwM2MyODFiMzRh
+    MWE0NjQ3MjJlMzI0ZTZhZDk0ZDg3YjcwMGRmYmQwM2I0YzQxNmUwNzdiNjA4
+    MDYwNzdjMTg1NjA3NGU0YjU2ZTE5NWE3OTFlYTM0NDQ2YmY0MGE=
+  data.tar.gz: !binary |-
+    MzAxOWEzZDgxZjVhMWJkOTYzM2MyZjE1MTc4ZTFjODhhNTc5ZTM1MjllNGVh
+    MmUyODAyODg0NDRlZjQ1ODA3ZDYyNGIyMjQ1NzgzNDJlYTNlMTFjNzk3NDYx
+    YTZiYTZmNDM3YTFkMTNkMTAwNWY1NWQ5ZTE2YWRjOTliZTYzYzU=

data/lib/text_analyzer.rb

@@ -0,0 +1,112 @@
+class TextAnalyzer
+  attr_accessor :text
+  attr_reader :arr, :unique,:textaz, :zipped, :count
+  def initialize text
+    @text=text
+    @textaz
+    @arr
+    @unique
+    @zipped
+    @count
+    @hash
+    
+  end
+  def init
+    get_words
+    slice_to_symbols
+    count_occurrences
+    sort_words
+    to_h
+  end
+  def get_words 
+    @textaz=@text.downcase.gsub /[^a-z]/, ' ' #/[\.,\"]/, ' '
+  end
+  
+  def slice_to_symbols
+    @textaz||=get_words
+    @arr=@textaz.split(' ').map{|x| x.to_sym}
+    return true
+  end
+  
+  def count_occurrences 
+    @unique = @arr.uniq
+    @count=@unique.map {|x| arr.count x}
+  #  return @unique, @count
+    return true
+  end
+  def sort_words
+    @zipped = (@unique.zip @count).sort {|x, y| y[1]<=>x[1]}
+    @count = []
+    @unique = []
+    @zipped.each{|x| @unique << x[0] }
+    @zipped.each{|x| @count <<  x[1] }
+    #return @unique, @count, @zipped
+    return true
+  end
+  def to_h
+    @hash ||= Hash[@zipped]
+  end
+  def to_s
+    'done'
+  end
+  def == ob
+    @text==ob.text
+  end
+  
+  def values_from_list quantity
+    @hash.values_at *@unique[0...quantity]
+  end
+  
+  def quantity
+    @unique.length
+  end
+  
+  def length
+    @arr.length
+  end
+  
+  def percentage symbol
+    c = length
+    w = @hash[symbol]
+    return w.to_f/c
+  end
+  
+  def percentages
+    per = []
+    @unique.each{|x| per<< (percentage x)}
+    Hash[@unique.zip per]
+  end
+  
+  #adds 2 object and create new object
+  def + obj
+    
+      #@text=text
+      #@textaz
+      #@arr
+      #@unique
+      #@zipped
+      #@count
+      #@hash
+    
+    new=TextAnalyzer.new @text+"\n"+obj.text
+    new.instance_variable_set(:@textaz, @textaz+"\n"+obj.textaz)
+    
+    arr=@arr+obj.arr
+    new.instance_variable_set(:@arr, arr)
+    
+    
+    u=arr.uniq
+    c=u.map {|x| arr.count x}
+    zipped = (u.zip c).sort {|x, y| y[1]<=>x[1]}
+    u=c=[]
+    zipped.each{|x| u << x[0];c <<  x[1]  }
+    #zipped.each{|x| c <<  x[1] }
+    new.instance_variable_set(:@unique, u)
+    new.instance_variable_set(:@count, c)
+    new.instance_variable_set(:@zipped, zipped)
+    new.instance_variable_set(:@hash, Hash[zipped])
+    
+    
+    return new
+  end
+end

metadata

@@ -0,0 +1,44 @@
+--- !ruby/object:Gem::Specification
+name: text_analyzer
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Darek Nędza
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-07-11 00:00:00.000000000 Z
+dependencies: []
+description: This simple text analyzer. It aimed at simplicity and not too much dependencies.
+email: nedzadarek@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/text_analyzer.rb
+homepage: 
+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: 2.0.6
+signing_key: 
+specification_version: 4
+summary: A simple text analyzer
+test_files: []
+has_rdoc: