docuvator 0.1.0

data/bin/docuvator

@@ -0,0 +1,9 @@
+#!/usr/bin/env ruby
+
+$:.unshift File.expand_path("../../lib", __FILE__)
+require 'docuvator'
+
+docuvator = Docuvator::CLI.new
+ARGV.each do |file|
+  docuvator.process(Dir.pwd + File::SEPARATOR + file)
+end

data/lib/docuvator.rb

@@ -0,0 +1,44 @@
+require 'docuvator/initialize'
+
+module Docuvator
+  class CLI
+    attr_reader :options
+    def initialize
+      @options = OpenStruct.new(
+        verbose: false,
+        debug: false,
+      )
+      parse_options
+      determine_log_level
+    end
+
+    def process(file)
+      Log.info "Processing #{file}"
+      Splitter.new(file).split
+    end
+
+    def parse_options
+      OptionParser.new do |opt|
+        opt.version = VERSION
+        opt.on "-v", "--verbose", "Verbose output (shows INFO level log statements)" do
+          options.verbose = true
+        end
+        opt.on "-d", "--debug", "Debug output (shows DEBUG level log statements)" do
+          options.debug = true
+        end
+      end.parse!
+    end
+
+    private
+
+    def determine_log_level
+      if options.debug
+        Log.level = Logger::DEBUG
+        Log.use_debug
+      elsif options.verbose
+        Log.level = Logger::INFO
+      end
+    end
+
+  end
+end

data/lib/docuvator/initialize.rb

@@ -0,0 +1,5 @@
+require 'pathname'
+require 'ostruct'
+require 'optparse'
+
+Dir.glob(File.dirname(__FILE__) + '/**/*.rb') { |file| require file }

data/lib/docuvator/log.rb

@@ -0,0 +1,59 @@
+require 'logger'
+require 'singleton'
+
+module Docuvator
+  class Log
+    include Singleton
+
+    attr_accessor :logger, :base_directory, :debugging
+
+    def initialize
+      @base_directory = File.expand_path("../..", __FILE__) + "/"
+      @debugging = false
+      @logger = Logger.new(STDOUT)
+      @logger.level = Logger::ERROR
+      @logger.formatter = proc do |sev, datetime, progname, msg|
+        "#{msg}\n"
+      end
+    end
+
+    def self.use_debug
+      instance.debugging = true
+      instance.logger.formatter = proc do |sev, datetime, progname, msg|
+        "#{sev} [#{progname}]: #{msg}\n"
+      end
+    end
+
+    # Determine the file, method, line number of the caller
+    def self.parse_caller(message)
+      if /^(?<file>.+?):(?<line>\d+)(?::in `(?<method>.*)')?/ =~ message
+        file = Regexp.last_match[:file]
+        line = Regexp.last_match[:line]
+        method = Regexp.last_match[:method]
+        "#{file.sub(instance.base_directory, "")}:#{line}"
+      end
+    end
+
+    def self.method_missing(method, *args, &blk)
+      if valid_method? method
+        instance.logger.progname = parse_caller(caller(1).first) if instance.debugging
+        instance.logger.send(method, *args, &blk)
+      else
+        super
+      end
+    end
+
+    def self.respond_to_missing?(method, include_all=false)
+      if valid_method? method
+        true
+      else
+        super
+      end
+    end
+
+    def self.valid_method?(method)
+      instance.logger.respond_to? method
+    end
+
+  end
+end

data/lib/docuvator/splitter.rb

@@ -0,0 +1,71 @@
+module Docuvator
+  class Splitter
+    attr_accessor :paragraphs, :sentences, :word_frequency
+    attr_reader :file
+
+    # Sentence ignore set
+    IGNORE_SET = ['Mr', 'Mrs', 'Ms', 'Jr', 'Dr', 'Prof', 'Sr']
+
+    REGEX_NEWLINE = Regexp.new(/\n+/)
+    REGEX_SPACES = Regexp.new(/\s+/)
+    REGEX_PUNCTUATION = Regexp.new(/[.!?,:;\[\]\(\)]+/)
+    REGEX_SENTENCES = Regexp.new(/(?<=[.!?]|[.!?][\'"])(?<! #{IGNORE_SET.join('\\.| ') + '\\.|'} \s[A-Z]\.)\s+/ix)
+=begin
+Regex to split up sentences - http://stackoverflow.com/a/5844564/583592
+
+(?<=                # Begin positive lookbehind.
+  [.!?]             # Either an end of sentence punct,
+| [.!?][\'"]        # or end of sentence punct and quote.
+)                   # End positive lookbehind.
+(?<!                # Begin negative lookbehind.
+  Mr\.              # Skip either "Mr."
+| Mrs\.             # or "Mrs.",
+| Ms\.              # or "Ms.",
+| Jr\.              # or "Jr.",
+| Dr\.              # or "Dr.",
+| Prof\.            # or "Prof.",
+| Sr\.              # or "Sr.",
+| \s[A-Z]\.         # or initials ex: "George W. Bush",
+)                   # End negative lookbehind.
+\s+                 # Split on whitespace between sentences.
+/ix
+
+=end
+
+    def initialize(file)
+      if File.exist? file
+        @file = file
+      else
+        Log.error "Cannot split #{file} as it does not exist"
+        exit 1
+      end
+    end
+
+    def split
+      # Split up text into paragraphs
+      @paragraphs = File.open(@file).read.split(REGEX_NEWLINE).map { |s|
+        s = s.gsub(REGEX_SPACES, ' ').strip
+      }
+      Log.info "Number of paragraphs: #{@paragraphs.size}"
+
+      # Split up paragraphs into sentences
+      @sentences = []
+      @paragraphs.each do |paragraph|
+        paragraph.split(REGEX_SENTENCES).each do |sentence|
+          @sentences << sentence
+        end
+      end
+      Log.info "Number of sentences: #{@sentences.size}"
+
+      @word_frequency = Hash.new(0)
+      @sentences.each do |sentence|
+        sentence.split.map { |s|
+          s = s.gsub(REGEX_PUNCTUATION, '').downcase
+          @word_frequency[s] += 1
+          s
+        }
+      end
+      Log.info "Unique words: #{@word_frequency.size}"
+    end
+  end
+end

data/lib/docuvator/version.rb

@@ -0,0 +1,3 @@
+module Docuvator
+  VERSION = "0.1.0"
+end

data/spec/log_spec.rb

@@ -0,0 +1,54 @@
+require 'spec_helper'
+
+include Docuvator
+
+describe Log do
+
+  let(:log) { Class.new(Log) }
+
+  context "initializes instance" do
+    it "should acts as singleton" do
+      log.instance.should == log.instance
+    end
+
+    it "should have a logger" do
+      log.instance.logger.should be_a Logger
+    end
+
+    it "should be a Log (FakeLog)" do
+      log.class.should eq Log.class
+    end
+
+    it "should react to Logger methods" do
+      Logger.public_instance_methods.each do |method|
+        log.valid_method?(method).should be_true
+      end
+    end
+  end
+
+  context "#use_debug" do
+    it "logger's progname before" do
+      log.progname.should be_nil
+    end
+
+    it "logger's progname after" do
+      log.use_debug
+      log.progname.should_not be_nil
+    end
+  end
+
+  context "#parse_caller" do
+    context "with nothing" do
+      it { log.parse_caller(nil).should be_nil }
+    end
+
+    context "with jumble (random text)" do
+      it { log.parse_caller("asdaacsdc").should be_nil }
+    end
+
+    context "with valid caller" do
+      it { log.parse_caller("docuvator/lib/docuvator.rb:45:in `respond_to_missing?'").should eq "docuvator/lib/docuvator.rb:45" }
+    end
+  end
+
+end

data/spec/splitter_spec.rb

@@ -0,0 +1,47 @@
+require 'spec_helper'
+
+include Docuvator
+
+describe Splitter do
+  let(:splitter) { Splitter.new(file) }
+
+  context "initializes instance" do
+    context "with valid file" do
+      let(:file) { fixture('lorem_ipsum.txt') }
+      it { splitter.file.should eq file }
+    end
+    context "with invalid file" do
+      let(:file) { fixture('invalid.txt') }
+      it { lambda { splitter }.should raise_error SystemExit }
+    end
+  end
+
+  describe "#split" do
+    context "valid file" do
+      let(:file) { fixture('lorem_ipsum.txt') }
+      let(:splitter) {
+        splitter = Splitter.new(file)
+        splitter.split
+        splitter
+      }
+
+      it { splitter.paragraphs.size.should eq 3 }
+      it { splitter.sentences.size.should eq 39 }
+      it { splitter.word_frequency.size.should eq 124 }
+    end
+
+    context "valid file (idempotence)" do
+      let(:file) { fixture('lorem_ipsum.txt') }
+      let(:splitter) {
+        splitter = Splitter.new(file)
+        splitter.split
+        splitter.split
+        splitter
+      }
+
+      it { splitter.paragraphs.size.should eq 3 }
+      it { splitter.sentences.size.should eq 39 }
+      it { splitter.word_frequency.size.should eq 124 }
+    end
+  end
+end

metadata

@@ -0,0 +1,56 @@
+--- !ruby/object:Gem::Specification
+name: docuvator
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- Kevin Jalbert
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-07-13 00:00:00.000000000 Z
+dependencies: []
+description: Gem which extracts document statistics and information
+email:
+- kevin.j.jalbert@gmail.com
+executables:
+- docuvator
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/docuvator/initialize.rb
+- lib/docuvator/log.rb
+- lib/docuvator/splitter.rb
+- lib/docuvator/version.rb
+- lib/docuvator.rb
+- spec/log_spec.rb
+- spec/splitter_spec.rb
+- bin/docuvator
+homepage: https://github.com/kevinjalbert/docuvator
+licenses: []
+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: 1.8.25
+signing_key: 
+specification_version: 3
+summary: Gem which extracts document statistics and information
+test_files:
+- spec/log_spec.rb
+- spec/splitter_spec.rb