wordy_number 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: fe333cd990b7fcfb3bb2d85652f668abec088e7f
+  data.tar.gz: bc8188687754c1c1966bbb8871c2f8e315f6738f
+SHA512:
+  metadata.gz: 35da8b5480e10b28421431680feadcca0a30685b7ea9f056b4c6c3b855659a6fbeba025b443e7c6ee4b980b96803cd02a5affdf9187017a5bb3e973bf551ec7d
+  data.tar.gz: 2ead7c0f8b42228e875036c8b7402ae5c06b2038b8f5b76e83c41cedce23371ddda56b6f37d295104735885e35c694b95245f38525ceee3332cbed22d3e4eb28

data/.gitignore

@@ -0,0 +1,3 @@
+**/*.swp
+/tags
+.byebug_history

data/.rspec

@@ -0,0 +1,3 @@
+--color
+--format documentation
+--require spec_helper

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,49 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, ethnicity, age, religion, or nationality.
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery
+* Personal attacks
+* Trolling or insulting/derogatory comments
+* Public or private harassment
+* Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+* Other unethical or unprofessional conduct
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+By adopting this Code of Conduct, project maintainers commit themselves to
+fairly and consistently applying these principles to every aspect of managing
+this project. Project maintainers who do not follow or enforce the Code of
+Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting a project maintainer at munish.goyal@universumglobal.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. Maintainers are
+obligated to maintain confidentiality with regard to the reporter of an
+incident.
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.3.0, available at
+[http://contributor-covenant.org/version/1/3/0/][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/3/0/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in wordy_number.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Munish Goyal
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,73 @@
+# WordyNumber
+
+Along with being a gem, WordyNumber is a command line application that reads from files specified as command-line arguments or STDIN when no files are given. Each line of the file is suppose to contain a single phone number.
+
+For every phone number read, the gem outputs all possible word replacements from a dictionary. It tries to replace every digit of the provided phone number with a letter from a dictionary word; however, if no match can be made, a single digit will be left as is at that point. No two consecutive digits will remain unchanged and the program skips over a number (producing on output) if a match cannot be made.
+
+All punctuations and whitespaces are ignored in both phone numbers and the dictionary file. Also, the program is not case sensitive.
+
+Output is in capital letters with words and digits separated with a single dash (-).
+
+For example, if the program is fed the number:
+
+    2255.63
+
+One possible line of output is:
+
+    CALL-ME
+
+According to the default dictionary.
+
+The number encoding on the phone, the program uses is:
+
+| Digit    | CHARACTERS |
+|:---------|:-----------|
+| 2        | A,B,C      |
+| 3        | D,E,F      |
+| 4        | G,H,I      |
+| 5        | J,K,L      |
+| 6        | M,N,O      |
+| 7        | P,Q,R,S    |
+| 8        | T,U,V      |
+| 9        | W,X,Y,Z    |
+
+WordList Sources:
+
+http://www-01.sil.org/linguistics/wordlists/english/
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'wordy_number'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install wordy_number
+
+## Usage
+
+    > sub = WordyNumber::WordyMatch.new
+    > sub.display_matches num_list: [2255,225563,8587071016]
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/wordy_number. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "wordy_number"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/wordy_number/dict_word.rb

@@ -0,0 +1,64 @@
+module WordyNumber
+  class DictWord
+    attr_accessor :word_form, :numeric_form
+
+    DIGIT_CHARACTER_MAP = {
+      :A => 2,
+      :B => 2,
+      :C => 2,
+      :D => 3,
+      :E => 3,
+      :F => 3,
+      :G => 4,
+      :H => 4,
+      :I => 4,
+      :J => 5,
+      :K => 5,
+      :L => 5,
+      :M => 6,
+      :N => 6,
+      :O => 6,
+      :P => 7,
+      :Q => 7,
+      :R => 7,
+      :S => 7,
+      :T => 8,
+      :U => 8,
+      :V => 8,
+      :W => 9,
+      :X => 9,
+      :Y => 9,
+      :Z => 9,
+    }
+
+    def initialize(word)
+      @word_form = word
+      sanitize_word!
+      word_to_numeric_string!
+    end
+
+    def to_s
+      "#{word_form}: #{numeric_form}"
+    end
+
+    private
+
+    def sanitize_word!
+      word = word_form
+      word.strip!
+      word.upcase!
+      word.gsub!(/[^A-Z]/, "")
+      self.word_form = word
+    end
+
+    def word_to_numeric_string!
+      numeric_string = ""
+      word_form.split("").each do |c|
+        numeric_string << DIGIT_CHARACTER_MAP[c.capitalize.to_sym].to_s
+      end
+
+      self.numeric_form = numeric_string
+    end
+  end
+end
+

data/lib/wordy_number/version.rb

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

data/lib/wordy_number/wordy_match.rb

@@ -0,0 +1,241 @@
+require_relative 'dict_word'
+
+module WordyNumber
+  class WordyMatch
+
+    # Dictioary hash structures looks like following
+    # dict_hash = {
+    # 1 => [{:word_form=>"a", :numeric_form=>"2"}],
+    # ,...,
+    # 23 => [{:word_form=>"disestablismentarianism", :numeric_form=>"34737822547636827426476"},
+    #        {:word_form=>"electroencephalographic", :numeric_form=>"35328763623742564727442"}],
+    # }
+
+    PUBLIC_DIR = File.expand_path("../../public", File.dirname(__FILE__))
+    DEFAULT_DICT_FILE_NAME = "wordsEn.txt"
+    DEFAULT_DICT_FILE_PATH = File.expand_path(DEFAULT_DICT_FILE_NAME, PUBLIC_DIR)
+    DEFAULT_DICT_FACTS = {
+      number_of_keys: 25,
+      number_of_words: 109582,
+    }
+    DEFAULT_SEPARATOR = "-"
+
+    attr_accessor :dict
+    attr_accessor :num, :num_patterns, :num_filtered_patterns
+
+    # dictionary is expected to have one word per line
+    def initialize(user_dictionary=DEFAULT_DICT_FILE_PATH)
+      @dict = user_dictionary
+      scan_dict!(dict)
+    end
+
+    def num=(user_number)
+      @num = user_number.to_s
+      @num.strip!
+      @num.gsub!(/\D/, "")
+
+      @num
+    end
+
+    def dict_hash
+      @dict_hash = {} unless @dict_hash
+
+      @dict_hash
+    end
+
+    def display_dict_stats
+      dh = dict_hash
+      dh.keys.each{ |key| puts "#{key} -> #{dh[key].size}" }
+    end
+
+    # sub = WordyMatch.new
+    # sub.display_matches num_file: "my_nums.txt"
+    # sub.display_matches num_list: [2255, 225563]
+    def display_matches(args = {num_file: nil, num_list: nil})
+      # get user inputs
+      num_file = args[:num_file]
+      num_list = args[:num_list]
+      num_file_path = File.expand_path(num_file, PUBLIC_DIR) if num_file
+      results = {}
+
+      # form numbers array
+      numbers = []
+      if num_file_path
+        File.open(num_file_path, "r") do |file|
+          file.each_line do |line|
+            numbers << line
+          end
+        end
+      elsif num_list.class == Array
+        numbers = num_list
+      else
+       # user hasn't provide num_file, so ask him/her explicitly
+        puts "Comma-separated list of numbers: "
+        numbers = gets.strip.split(",")
+      end
+
+      # get output
+      numbers.each do |number|
+        puts "---------------------------------------"
+        puts "Matches for #{number.to_s}"
+        matches = set_num_and_find_matches(number)
+        results[number.to_s] = matches
+        if matches.size > 0
+          matches.each do |match|
+            puts match
+          end
+        else
+          puts "No matches"
+        end
+      end
+
+      results
+    end
+
+    def set_num_and_find_matches(user_number)
+      set_num(user_number)
+
+      # find matches and filter them
+      split_arnd_0_1_n_find_matches
+      filtered_list
+    end
+
+    def self.concat_array_of_lists_of_strings(array_of_lists, separator=DEFAULT_SEPARATOR)
+      # remove empty elements
+      array_of_lists.each do |list|
+        list.delete_if{ |elem| elem.length == 0 }
+      end
+      # remove empty lists
+      array_of_lists.select!{ |list| list.size > 0 }
+
+      # calculate product
+      result = if array_of_lists.size > 1
+        array_of_lists[0].product(*array_of_lists[1..-1]).map{ |elem| elem.join(separator) }
+      elsif array_of_lists.size == 1
+        array_of_lists[0]
+      else
+        # array_of_lists.size == 0
+        []
+      end
+
+      result
+    end
+
+    def self.join_numbers_together_in_str(num_str, separator=DEFAULT_SEPARATOR)
+      res_str = num_str.gsub(/(\d)#{DEFAULT_SEPARATOR}+(\d)/, '\1\2')
+      if res_str != num_str
+        return join_numbers_together_in_str(res_str)
+      else
+        return res_str
+      end
+    end
+
+    private
+
+    # set_num() is kind of alias to num=(), but helps in chaining
+    def set_num(user_number)
+      self.num = user_number
+
+      self
+    end
+
+    def find_all_matches(num_str=self.num, original_call=true, pattern_length=num_str.length)
+      patterns = []
+      if num_str.size == 0  # first deal with the edge cases
+        return patterns
+      end
+      if pattern_length == 1  # first deal with the edge cases
+        if dict_hash[pattern_length]
+          times = 0
+          dict_hash[pattern_length].each do |dict_word|
+            if num_str == dict_word
+              times += 1
+              patterns << dict_word.word_form
+            end
+          end
+          if times == 0
+            patterns << num_str
+          end
+        end
+      elsif pattern_length > 0  # general case
+        if dict_hash[pattern_length]
+          dict_hash[pattern_length].each do |dict_word|
+            matched_index = num_str =~ /#{dict_word.numeric_form}/
+            if matched_index
+              str1 = matched_index > 0 ? num_str[0..(matched_index - 1)] : ""
+              str2 = dict_word.word_form  # it has word_form, but str1 and str3 still have numeric_form
+              str3 = num_str[(matched_index + pattern_length)..-1]
+              patterns += self.class.concat_array_of_lists_of_strings([find_all_matches(str1, false), [str2], find_all_matches(str3, false)])
+            end
+          end
+        end
+        patterns += find_all_matches(num_str, false, pattern_length-1)
+      else
+        raise NonReachableCodeError
+      end
+      patterns.uniq!
+
+      if original_call
+        self.num_patterns = patterns
+      end
+
+      return patterns
+    end
+
+    # filter out patterns with consecutive digits
+    def filtered_list(list_of_num_strs=self.num_patterns.clone)
+      unless list_of_num_strs
+        raise InvalidInputError
+      end
+      list_of_num_strs.delete_if{ |pattern| pattern.split(DEFAULT_SEPARATOR).join("") =~ /\d{2}/ }
+      self.num_filtered_patterns = list_of_num_strs
+
+      self.num_filtered_patterns
+    end
+
+    # it enhances the performance of long numbers carrying 1s or 0s
+    def split_arnd_0_1_n_find_matches(num_str=self.num)
+      # split given number_string at 0's and 1's
+      splits = num_str.gsub(/[^01]/, "").split("")
+      split_num_str = num_str.split(/[01]/)
+      # obtain patterns for each sub_number_string
+      split_results = split_num_str.map do |sub_num_str|
+        find_all_matches(sub_num_str)
+      end
+      # obtain combined result
+      combined_splits_and_split_results = []
+      split_results.each_index do |index|
+        combined_splits_and_split_results << split_results[index]
+        combined_splits_and_split_results << [splits[index]] if index <= splits.length - 1
+      end
+      combined_splits_and_split_results.select!{ |x| x.length > 0 }
+      results = self.class.concat_array_of_lists_of_strings(combined_splits_and_split_results)
+      # join numbers togeter in each results element
+      results.map!{ |str| self.class.join_numbers_together_in_str(str) }
+      # set num_patterns
+      self.num_patterns = results
+
+      results
+    end
+
+    def scan_dict!(dict_file_path)
+      dict_file_path = dict_file_path || dict || DEFAULT_DICT_FILE_PATH
+
+      # reset dict_hash
+      dh = dict_hash
+      dh.clear
+
+      # load dictionary
+      File.open(dict_file_path, "r") do |file|
+        file.each_line do |line|
+          dw = DictWord.new(line)
+          dh[dw.word_form.length] = [] unless dh[dw.word_form.length]  # `dw.word` is sanitized but `line` is not
+          dh[dw.word_form.length] << DictWord.new(line)
+        end
+      end
+
+      dh
+    end
+  end
+end
+

data/lib/wordy_number.rb

@@ -0,0 +1,16 @@
+require "wordy_number/version"
+require "wordy_number/dict_word"
+require "wordy_number/wordy_match"
+
+module WordyNumber
+  # custom Exceptions
+  class Error < StandardError;end
+
+  class StartsWithNonRepeatableRomanUnitError < Error;end
+
+  class NonReachableCodeError < Error;end
+
+  class InvalidInputError < Error;end
+
+end
+

data/public/my_nums.txt

@@ -0,0 +1,3 @@
+2255
+225563
+8587071016