chat_correct 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 83347780fd13ba3682aa33265cca80906f4e2005
+  data.tar.gz: 170d4c280a553ae9c554ba8396594664be6ebf31
+SHA512:
+  metadata.gz: 001eba96eb826a38d918a83eff12673f5ba80e81f30ee9ddefe038ad1c187c84fa266508941633ea40d7c7f28b91f961a835bbd6c89f6c679725d4b2cec4090f
+  data.tar.gz: c33e23f38d08530f2472369d8af0edfd3c254aa7532665564785953b73a76da2d9c43ca4e07c293bbed79dcc247b56eddd353e01deddd16d71f3019eb1217fcb

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/.rspec

@@ -0,0 +1 @@
+--color

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - "2.1.5"
+  - "2.2.0"

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2015 Kevin S. Dias
+
+MIT License
+
+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 +1,208 @@
+# Chat Correct
+
+[![Gem Version](https://badge.fury.io/rb/chat_correct.svg)](http://badge.fury.io/rb/chat_correct) [![Build Status](https://travis-ci.org/diasks2/chat_correct.png)](https://travis-ci.org/diasks2/chat_correct) [![License](https://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat)](https://github.com/diasks2/chat_correct/blob/master/LICENSE.txt)
+
+A Ruby gem to help students improve their English. A teacher can correct a student's sentence and this gem will automatically provide information on the type of error (i.e. punctuation, spelling, etc.), the placement of the errors, and the number of errors.
+
+Live Demo: [Chat Correct chat room application](http://www.chat-correct.com)
+
+![](https://s3.amazonaws.com/tm-town-nlp-resources/chat_correct_screenshot.jpg)
+
+##Install  
+
+**Ruby**  
+*Supports Ruby 2.1.5 and above*  
+```
+gem install chat_correct
+```
+
+**Ruby on Rails**  
+Add this line to your application’s Gemfile:  
+```ruby 
+gem 'chat_correct'
+```
+
+## Usage
+
+#### Correct
+
+The correct method returns a hash of the original sentence interleaved with the corrected sentence. The idea is that you can use styling in your output progam to highlight the errors (color, **font weight**, ~~strikethrough~~, etc.).
+
+```ruby
+os = "is the, puncttuation are wrong."
+cs = "Is the punctuation wrong?"
+cc = ChatCorrect.new(original_sentence: os, corrected_sentence: cs)
+cc.correct
+
+# =>  {
+#       0 => {
+#        'token' => 'is',
+#        'type' => 'capitalization_mistake'
+#       },
+#       1 => {
+#        'token' => 'Is',
+#        'type' => 'capitalization_correction'
+#       },
+#       2 => {
+#        'token' => 'the',
+#        'type' => 'no_mistake'
+#       },
+#       3 => {
+#        'token' => ',',
+#        'type' => 'punctuation_mistake'
+#       },
+#       4 => {
+#        'token' => 'puncttuation',
+#        'type' => 'spelling_mistake'
+#       },
+#       5 => {
+#        'token' => 'punctuation',
+#        'type' => 'spelling_correction'
+#       },
+#       6 => {
+#        'token' => 'are',
+#        'type' => 'unnecessary_word_mistake'
+#       },
+#       7 => {
+#        'token' => 'wrong',
+#        'type' => 'no_mistake'
+#       },
+#       8 => {
+#        'token' => '.',
+#        'type' => 'punctuation_mistake'
+#       },
+#       9 => {
+#        'token' => '?',
+#        'type' => 'punctuation_correction'
+#       }
+#     }
+
+cc.correct[5]['token']
+# => 'punctuation'
+
+cc.correct[5]['type']
+# => 'spelling_correction'
+
+```
+
+#### Mistakes
+
+The mistakes method returns a hash of each mistake, ordered by its position in the sentence. For each mistake the method returns the `position`, `error_type`, `mistake`, and `correction`.
+
+```ruby
+os = "is the, puncttuation are wrong."
+cs = "Is the punctuation wrong?"
+cc = ChatCorrect.new(original_sentence: os, corrected_sentence: cs)
+cc.mistakes
+
+# =>  {
+#       0 => {
+#        'position' => 0,
+#        'error_type' => 'capitalization',
+#        'mistake' => 'is',
+#        'correction' => 'Is'
+#       },
+#       1 => {
+#        'position' => 3,
+#        'error_type' => 'punctuation',
+#        'mistake' => ',',
+#        'correction' => ''
+#       },
+#       2 => {
+#        'position' => 4,
+#        'error_type' => 'spelling',
+#        'mistake' => 'puncttuation',
+#        'correction' => 'punctuation'
+#       },
+#       3 => {
+#        'position' => 3,
+#        'error_type' => 'unnecessary_word',
+#        'mistake' => 'are',
+#        'correction' => ''
+#       },
+#       4 => {
+#        'position' => 3,
+#        'error_type' => 'punctuation',
+#        'mistake' => '.',
+#        'correction' => '?'
+#       }
+#     }
+
+cc.mistakes[4]['correction']
+# => '?'
+
+cc.mistakes[1]['mistake']
+# => ','
+```
+
+#### Mistake Report
+
+The mistake report method returns a hash containing the number of mistakes for each error type.
+
+```ruby
+os = "is the, puncttuation are wrong."
+cs = "Is the punctuation wrong?"
+cc = ChatCorrect.new(original_sentence: os, corrected_sentence: cs)
+cc.mistake_report
+# => { 
+#      'missing_word'     => 0, 
+#      'unnecessary_word' => 1,
+#      'spelling'         => 1,
+#      'verb'             => 0,
+#      'punctuation'      => 2,
+#      'word_order'       => 0,
+#      'capitalization'   => 1,
+#      'duplicate_word'   => 0,
+#      'word_choice'      => 0,
+#      'pluralization'    => 0,
+#      'possessive'       => 0,
+#      'stylistic_choice' => 0
+#    }
+
+cc.mistake_report['punctuation']
+# => 2
+```
+
+#### Number of Mistakes
+
+The number of mistakes method returns the total number of mistakes in the original sentence.
+
+```ruby
+os = "is the, puncttuation are wrong."
+cs = "Is the punctuation wrong?"
+cc = ChatCorrect.new(original_sentence: os, corrected_sentence: cs)
+cc.number_of_mistakes
+# => 5
+```
+
+## Contributing
+
+1. Fork it ( https://github.com/diasks2/chat_correct/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request
+
+## License
+
+The MIT License (MIT)
+
+Copyright (c) 2015 Kevin S. Dias
+
+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/Rakefile

@@ -0,0 +1,4 @@
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec)
+task :default => :spec

data/chat_correct.gemspec

@@ -0,0 +1,28 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'chat_correct/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "chat_correct"
+  spec.version       = ChatCorrect::VERSION
+  spec.authors       = ["Kevin S. Dias"]
+  spec.email         = ["diasks2@gmail.com"]
+  spec.summary       = %q{Returns the errors and error types when an incorrect English sentence is diffed with a correct English sentence.}
+  spec.description   = %q{A Ruby gem to help students improve their English. A teacher can correct a student's sentence and this gem will automatically provide information on the type of error (i.e. punctuation, spelling, etc.), the placement of the errors, and the number of errors.}
+  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", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec"
+  spec.add_runtime_dependency "levenshtein-ffi"
+  spec.add_runtime_dependency "linguistics", "~> 2.0.2"
+  spec.add_runtime_dependency "verbs"
+  spec.add_runtime_dependency "engtagger"
+end

data/lib/chat_correct/capitalization.rb

@@ -0,0 +1,13 @@
+module ChatCorrect
+  class Capitalization
+    attr_reader :token_a, :token_b
+    def initialize(token_a:, token_b:)
+      @token_a = token_a
+      @token_b = token_b
+    end
+
+    def capitalization_error?
+      token_a.downcase.eql?(token_b.downcase) && token_a != token_b
+    end
+  end
+end

data/lib/chat_correct/combine_multi_word_verbs.rb

@@ -0,0 +1,51 @@
+require 'engtagger'
+
+module ChatCorrect
+  class CombineMultiWordVerbs
+    TOKEN_ARRAY = ['are', 'am', 'was', 'were', 'have', 'has', 'had', 'will', 'would', 'could', 'did', 'arenƪt', 'wasnƪt', 'werenƪt', 'havenƪt', 'hasnƪt', 'hadnƪt', 'wouldnƪt', 'couldnƪt', 'didnƪt']
+    TOKEN_ARRAY_2 = ['are', 'am', 'was', 'were', 'have', 'has', 'had', 'will', 'would', 'did', 'could']
+    attr_reader :text
+    def initialize(text:)
+      @text = text
+    end
+
+    def combine
+      tgr = EngTagger.new
+      tokens = ChatCorrect::Tokenize.new(text: text).tokenize
+      sentence_tagged = tgr.add_tags(text).split
+      tokens_to_delete = []
+      tokens.each_with_index do |token, index|
+        case
+        when ((token.eql?('will') && tokens[index + 1].eql?('have')) || (token.eql?('would') && tokens[index + 1].eql?('have')) || (token.eql?('had') && tokens[index + 1].eql?('been'))) &&
+          sentence_tagged[index + 2].to_s.partition('>').first[1..-1][0].eql?('v')
+            tokens[index] = token + ' ' + tokens[index + 1] + ' ' + tokens[index + 2]
+            tokens_to_delete << tokens[index + 1].to_s
+            tokens_to_delete << tokens[index + 2].to_s
+        when TOKEN_ARRAY_2.include?(token) &&
+          tokens[index + 1].to_s.eql?('not') &&
+          sentence_tagged[index + 2].to_s[1].to_s.eql?('v')
+            tokens[index] = token + ' ' + tokens[index + 1] + ' ' + tokens[index + 2]
+            tokens_to_delete << tokens[index + 1].to_s
+            tokens_to_delete << tokens[index + 2].to_s
+        when TOKEN_ARRAY.include?(token) &&
+          (sentence_tagged[index + 1].to_s[1].to_s.eql?('v') ||
+          sentence_tagged[index + 1].to_s[1..2].to_s.eql?('rb')) &&
+          tokens[index - 1].exclude?(' ') &&
+          tokens[index + 1] != 'had'
+            tokens[index] = token + ' ' + tokens[index + 1]
+            tokens_to_delete << tokens[index + 1].to_s
+        end
+      end
+      delete_tokens_from_array(tokens, tokens_to_delete)
+    end
+
+    private
+
+    def delete_tokens_from_array(tokens, array)
+      array.each do |token_to_delete|
+        tokens.delete(token_to_delete) if tokens.include?(token_to_delete)
+      end
+      tokens
+    end
+  end
+end

data/lib/chat_correct/common_verb_mistake.rb

@@ -0,0 +1,62 @@
+module ChatCorrect
+  class CommonVerbMistake
+    COMMON_VERB_MISTAKES =
+      { "flied" => "flew",
+        "weared" => "wore",
+        "finded" => "found",
+        "fighted" => "fought",
+        "clinged" => "clung",
+        "bleeded" => "bled",
+        "bringed" => "brought",
+        "catched" => "caught",
+        "cutted" => "cut",
+        "feeled" => "felt",
+        "drived" => "drove",
+        "falled" => "fell",
+        "forgetted" => "forgot",
+        "freezed" => "froze",
+        "gived" => "gave",
+        "heared" => "heard",
+        "hurted" => "hurt",
+        "keeped" => "kept",
+        "knowed" => "knew",
+        "leaved" => "left",
+        "losed" => "lost",
+        "meaned" => "meant",
+        "quited" => "quit",
+        "quitted" => "quit",
+        "ridded" => "rode",
+        "runned" => "ran",
+        "rised" => "rose",
+        "seed" => "saw",
+        "singed" => "sang",
+        "sitted" => "sat",
+        "sited" => "sat",
+        "speaked" => "spoke",
+        "standed" => "stood",
+        "sweared" => "swore",
+        "swimmed" => "swam",
+        "thinked" => "thought",
+        "telled" => "told",
+        "taked" => "took",
+        "stringed" => "strung",
+        "teached" => "taught",
+        "waked" => "woke",
+        "weeped" => "wept",
+        "winned" => "won",
+        "writed" => "wrote",
+        "weaved" => "wove",
+        "gots" => "have"
+      }
+    attr_reader :token_a, :token_b
+    def initialize(token_a:, token_b:)
+      @token_a = token_a
+      @token_b = token_b
+    end
+
+    def exists?
+      COMMON_VERB_MISTAKES[token_a].eql?(token_b) ||
+      COMMON_VERB_MISTAKES[token_b].eql?(token_a)
+    end
+  end
+end

data/lib/chat_correct/contraction.rb

@@ -0,0 +1,103 @@
+module ChatCorrect
+  class Contraction
+    NOT_CONTRACTION = {
+      'am' => "ain't",
+      'do' => "don't",
+      'will' => "won't",
+      'shall' => "shan't",
+      'is' => "isn't"
+    }
+    IRREGULAR_CONTRACTION = {
+      ['is', 'not'] => "ain't",
+      ['madam', nil] => "ma'am",
+      ['never-do-well', nil] => "ne'er-do-well",
+      ['cat-of-nine-tails', nil] => "cat-o'-nine-tails",
+      ['jack-of-the-lantern', nil] => "jack-o'-lantern",
+      ['will-of-the-wisp', nil] => "will-o'-the-wisp"
+    }
+    attr_reader :token_a, :token_b, :contraction
+    def initialize(token_a:, token_b:, contraction:)
+      return false if token_a.nil? || contraction.nil?
+      @token_a = token_a.downcase
+      token_b ? @token_b = token_b.downcase : @token_b = token_b
+      @contraction = contraction.downcase.gsub(/ƪ/, "'")
+    end
+
+    def contraction?
+      !token_a.nil? && !contraction.nil? &&
+      (is_a_not_contraction? ||
+      is_an_irregular_contraction? ||
+      is_an_us_contraction? ||
+      is_an_am_contraction? ||
+      is_an_are_contraction? ||
+      is_an_is_does_has_contraction? ||
+      is_a_have_contraction? ||
+      is_a_had_did_would_contraction? ||
+      is_a_will_contraction? ||
+      is_an_of_contraction? ||
+      is_an_it_contraction? ||
+      is_a_them_contraction?)
+    end
+
+    private
+
+    def is_a_not_contraction?
+      token_b.eql?('not') && (NOT_CONTRACTION[token_a].eql?(contraction) ||
+        (contraction.partition("n't")[0].eql?(token_a)) &&
+        contraction.partition("n't")[2].empty?)
+    end
+
+    def is_an_irregular_contraction?
+      IRREGULAR_CONTRACTION[[token_a, token_b]].eql?(contraction)
+    end
+
+    def is_an_us_contraction?
+      token_b.eql?('us') && contraction.partition("'s")[0].eql?(token_a) &&
+      token_a.eql?('let') && contraction.partition("'s")[2].empty?
+    end
+
+    def is_an_am_contraction?
+      token_b.eql?("am") && contraction.partition("'m")[0].eql?(token_a) &&
+      token_a.eql?('i') && contraction.partition("'m")[2].empty?
+    end
+
+    def is_an_are_contraction?
+      token_b.eql?('are') && contraction.partition("'re")[0].eql?(token_a) &&
+      contraction.partition("'re")[2].empty?
+    end
+
+    def is_an_is_does_has_contraction?
+      (token_b.eql?('is') || token_b.eql?('does') || token_b.eql?('has')) &&
+        contraction.partition("'s")[0].eql?(token_a) && contraction.partition("'s")[2].empty?
+    end
+
+    def is_a_have_contraction?
+      token_b.eql?('have') && contraction.partition("'ve")[0].eql?(token_a) &&
+        contraction.partition("'ve")[2].empty?
+    end
+
+    def is_a_had_did_would_contraction?
+      (token_b.eql?('had') || token_b.eql?('did') || token_b.eql?('would')) &&
+        contraction.partition("'d")[0].eql?(token_a) &&
+        contraction.partition("'d")[2].empty?
+    end
+
+    def is_a_will_contraction?
+      token_b.eql?('will') && contraction.partition("'ll")[0].eql?(token_a) &&
+        contraction.partition("'ll")[2].empty?
+    end
+
+    def is_an_of_contraction?
+      token_a.eql?('of') && (contraction.eql?("o'") ||
+        contraction.partition("o' ")[-1].eql?(token_b))
+    end
+
+    def is_an_it_contraction?
+      token_a.eql?('it') && contraction.partition("'t")[-1].eql?(token_b)
+    end
+
+    def is_a_them_contraction?
+      token_b.eql?('them') && contraction.partition(" 'em")[0].eql?(token_a)
+    end
+  end
+end