tomereader 0.0.1

data/data/three_phrases.txt

@@ -0,0 +1,4 @@
+I see a narrow face, wide, round eyes, and a long, thin nose—I still look
+like a little girl, though sometime in the last few months I turned sixteen. The other factions celebrate birthdays, but we don’t. It
+would be self-indulgent.
+My older brother, Caleb, stands in the aisle, holding a railing above his head to keep himself steady. We don’t look alike.

data/lib/tomereader.rb

@@ -0,0 +1,13 @@
+require "logging"
+require 'em-synchrony'
+require 'tempfile'
+require "pdf/reader"
+require "tomereader/version"
+require "tomereader/settings"
+require "tomereader/parser"
+require "tomereader/index"
+require "tomereader/phrase"
+require "tomereader/word"
+
+module Tomereader
+end

data/lib/tomereader/index.rb

@@ -0,0 +1,79 @@
+# - розбиває контент книги на фрази та слова
+# - розміщує фрази та слова в індексі
+module Tomereader
+  class Index
+    #include Settings
+    def initialize
+      #raise ArgumentError, "Content must be a String - #{content.class} given instead" unless content.kind_of? String
+      #raise StandardError, "Content is empty" if content.empty?
+      #@logger = create_logger
+      @phrase_split_pattern = /[\.\;]/
+      @word_pattern = /[A-Za-z]([A-Za-z\'\-])*/
+      @word_storage = Hash.new
+      @total_words = []
+      @phrase_storage = []
+    end
+    def add(content)
+      raise ArgumentError, "Content must be a String - #{content.class} given instead" unless content.kind_of? String
+      raise StandardError, "Content is empty" if content.empty?
+      phrase_strings = split_into_phrases(content)
+      split(content)
+      self
+    end
+    def split_into_phrases(content)
+      content.split @phrase_split_pattern
+    end
+    def words
+      @word_storage
+    end
+    def phrases
+      @phrase_storage
+    end
+    def words_sorted_by_alphabet(count=nil)
+      words = self.words.sort_by{|key, value| key}
+      words = words.first(count) unless count.nil?
+      Hash[words]
+    end
+    def words_sorted_by_frequency(count=nil)
+      words = self.words.sort_by{|key, value| value.frequency}
+      words = words.first(count) unless count.nil?
+      Hash[words]
+    end
+    def to_s
+      {total: @total_words.count, unique_count: @word_storage.count, phrases: @phrase_storage.count}
+    end
+    # розбиває текст на фрази, витягує слова,
+    # встановлює звязки:  фраза -> слова, та слово -> фрази
+    def split(content)
+      split_into_phrases(content).map do |phrase_string|
+        phrase = Phrase.new(phrase_string)
+        phrase.split do |word_string, position|
+          @total_words << word_string
+          word = find_or_create(word_string)
+          word.add(phrase, position) if word.is_a? Word
+        end
+        @phrase_storage << phrase
+      end
+  end
+  # word word_storage
+  def suitable? word_string
+    word_string =~ @word_pattern
+  end
+  def find(word_string)
+    if @word_storage.has_key?(word_string)
+      @word_storage[word_string]
+    end
+  end
+  def create(word_string)
+    if check word_string
+      @word_storage[word_string] = Word.new(word_string)
+    end
+  end
+  def check(word_string)
+    word_string.kind_of?(String) && suitable?(word_string)
+  end
+  def find_or_create(word_string)
+    find(word_string) || create(word_string)
+  end
+end
+end

data/lib/tomereader/logger.rb

@@ -0,0 +1,2 @@
+module Tomereader
+end

data/lib/tomereader/parser.rb

@@ -0,0 +1,36 @@
+module Tomereader
+  class Parser
+    attr_reader :format_pattern, :filename, :reader
+    def initialize(filename)
+      raise ArgumentError, "Specify correct filename" if not filename and filename.empty?
+      raise StandardError, "File #{filename} not exists" unless File.exists? filename
+      @filename = filename
+      @format_pattern = /[a-z0-9_\-\.]+\.([a-z0-9]{3,4})$/
+    end
+    def format
+      @match = format_pattern.match(filename)
+      format = @match[1]
+      raise StandardError, "Format is undefined" unless @match && format
+      format
+    end
+    def read
+      case format
+      when 'pdf'
+        #TODO: check if pdftotext installed
+        open("|pdftotext #{filename} -").read() 
+      when 'txt'
+        File.read(filename)
+      else
+        temp_file = Tempfile.new([@match[0], '.txt'])
+        system("ebook-convert #{filename} #{temp_file.path}")
+        content = temp_file.read
+        temp_file.close
+        temp_file.unlink
+        content
+      end
+    end
+    def pages_count
+      reader.page_count
+    end
+  end
+end

data/lib/tomereader/phrase.rb

@@ -0,0 +1,32 @@
+module Tomereader
+  class Phrase
+    #include Settings
+    attr_reader :words
+    def initialize(phrase_string)
+      @phrase_string = phrase_string.strip
+      @word_pattern = /[\s,;\"\—]+/
+      @words = []
+      #@logger = create_logger
+    end
+    def to_s
+      @phrase_string
+    end
+    def word_strings
+      @phrase_string.split @word_pattern
+    end
+    # split phrase into words
+    # @return Array of words
+    def split
+      return false if words.count > 0
+      begin
+        word_strings.each_with_index do |word_string, position|
+          word = yield(word_string, position)
+          @words << word if word.is_a? Word
+        end
+        words.count
+      rescue => e
+        #@logger.warn e.message
+      end
+    end
+  end
+end

data/lib/tomereader/settings.rb

@@ -0,0 +1,10 @@
+ module Tomereader
+   module Settings
+     def create_logger(name=nil)
+      name ||= 'output'
+      logger = Logging.logger[self]
+      logger.add_appenders(Logging.appenders.file("log/#{name}.log"))
+      return logger
+    end
+  end
+end

data/lib/tomereader/version.rb

@@ -0,0 +1,3 @@
+module Tomereader
+  VERSION = "0.0.1"
+end

data/lib/tomereader/word.rb

@@ -0,0 +1,33 @@
+module Tomereader
+  class Word
+    attr_reader :name, :phrases
+    def initialize(word)
+      @name = word
+      @phrases = Hash.new
+    end
+    def add(phrase, position)
+      if @phrases.has_key? phrase
+        @phrases[phrase] << position
+      else
+        @phrases[phrase] = [position]
+      end
+      self
+    end
+    def frequency
+      @phrases.count
+    end
+    def phrase_format(phrase)
+      {source: phrase[0].to_s, positions: phrase[1]}
+    end
+    def phrases
+      if block_given?
+        @phrases.each {|phrase| yield phrase_format(phrase)}
+      else
+        @phrases.map{|phrase| phrase_format(phrase)}
+      end
+    end
+    def to_s
+      "#{name} : #{@phrases.count}"
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,87 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'tomereader'
+require 'logging'
+require 'rspec/logging_helper'
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause this
+# file to always be loaded, without a need to explicitly require it in any files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, make a
+# separate helper file that requires this one and then use it only in the specs
+# that actually need it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  include RSpec::LoggingHelper
+  config.capture_log_messages
+
+  #Logging.logger.root.appenders = Logging.appenders.file('log/output.log')
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # Enable only the newer, non-monkey-patching expect syntax.
+    # For more details, see:
+    #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+    expectations.syntax = :expect
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Enable only the newer, non-monkey-patching expect syntax.
+    # For more details, see:
+    #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+    mocks.syntax = :expect
+
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended.
+    mocks.verify_partial_doubles = true
+  end
+=end
+end

data/spec/tomereader_spec.rb

@@ -0,0 +1,76 @@
+require 'spec_helper'
+
+describe Tomereader do
+  before do
+    @path = File.expand_path(File.dirname(__FILE__) + "/../data")
+    filename = "three_phrases.txt"
+    @file = File.join(@path, filename)
+  end
+
+  let(:parser) { Tomereader::Parser.new(@file) }
+  context Tomereader::Parser do
+    it "has correct filename path" do
+      expect(File.exists? @file).to eq true
+    end
+    it "has content" do
+      expect(parser.read.length).to be > 0
+    end
+    it "converts pdf to txt and reads" do
+      filename = "evented-spec.pdf"
+      file = File.join(@path, filename)
+      expect(File.exists?(file)).to eq true
+      parser = Tomereader::Parser.new(file)
+      expect(parser.read.length).to be > 0
+    end
+    it "creates temp file" do
+      temp_file = Tempfile.new(["test", '.txt'])
+      expect(File.exists?(temp_file)).to eq true
+      temp_file.close
+      temp_file.unlink
+    end
+    it "converts fb2 to txt and reads" do
+      filename = "stormrage.fb2"
+      file = File.join(@path, filename)
+      expect(File.exists?(file)).to eq true
+      parser = Tomereader::Parser.new(file)
+      expect(parser.read.length).to be > 0
+    end
+  end
+  context Tomereader::Index do
+    let(:content) { parser.read }
+    let(:word) { "tomereader" }
+    let(:index) { Tomereader::Index.new}
+    let(:book_info) { {:total=>64, :phrases=>5} }
+    
+    before(:each){index.add(content)}
+
+    it "creates word in word storage" do
+      expect(index.create(word)).to be_a Tomereader::Word
+    end
+    it "finds word in word storage" do
+      index.create(word)
+      expect(index.find(word)).to be_a Tomereader::Word
+    end
+    it "empty word is not suitable for storage" do
+      expect(index.suitable? "").to_not eq true
+    end
+    it "split_into_phrases" do
+      expect(index.split_into_phrases(content).count).to eq book_info[:phrases]
+    end
+    it "#split" do
+      expect(index.to_s[:total]).to eq book_info[:total]
+    end
+    it "shows word's list of phrases" do
+      word = index.find('alike')
+      phrases = word.phrases
+      expect(phrases.count).to eq 1
+      expect(phrases[0][:source]).to eq "We don’t look alike"
+      expect(phrases[0][:positions]).to be_a_kind_of Array
+      expect(phrases[0][:positions][0]).to eq 3
+    end
+    it "shows word's list sorted by frequency" do
+      hash = index.words_sorted_by_frequency
+      expect(hash.first[0]).to eq "I"
+    end
+  end
+end

data/tomereader.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'tomereader/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "tomereader"
+  spec.version       = Tomereader::VERSION
+  spec.authors       = ["nychka"]
+  spec.email         = ["nychka93@gmail.com"]
+  spec.summary       = %q{Tomereader will help you to read English books}
+  spec.description   = %q{Tomereader will help you to learn English by reading your favourites books}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.5"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "pdf-reader", "~>1.3"
+  spec.add_development_dependency "rspec", "~>3.0"
+  spec.add_development_dependency "logging"
+  spec.add_development_dependency "em-synchrony"
+  spec.add_development_dependency "tempfile"
+end

metadata

@@ -0,0 +1,186 @@
+--- !ruby/object:Gem::Specification
+name: tomereader
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- nychka
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-09-07 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: logging
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: em-synchrony
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: tempfile
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Tomereader will help you to learn English by reading your favourites
+  books
+email:
+- nychka93@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .autotest
+- .gitignore
+- .rspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- data/content.txt
+- data/divergent.txt
+- data/divergent_1.pdf
+- data/divergent_1.txt
+- data/evented-spec.pdf
+- data/stormrage.fb2
+- data/three_phrases.txt
+- lib/tomereader.rb
+- lib/tomereader/index.rb
+- lib/tomereader/logger.rb
+- lib/tomereader/parser.rb
+- lib/tomereader/phrase.rb
+- lib/tomereader/settings.rb
+- lib/tomereader/version.rb
+- lib/tomereader/word.rb
+- spec/spec_helper.rb
+- spec/tomereader_spec.rb
+- tomereader.gemspec
+homepage: ''
+licenses:
+- MIT
+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: 
+rubygems_version: 1.8.29
+signing_key: 
+specification_version: 3
+summary: Tomereader will help you to read English books
+test_files:
+- spec/spec_helper.rb
+- spec/tomereader_spec.rb