Class: ChatCorrect::CorrectionsHash

Inherits:
Object
  • Object
show all
Defined in:
lib/chat_correct/corrections_hash.rb

Constant Summary collapse

PUNCTUATION_SYMBOLS = 
['∯', '∬', '∫', '∮']

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(original_sentence_info_hash:, corrected_sentence_info_hash:) ⇒ CorrectionsHash

Returns a new instance of CorrectionsHash.



5
6
7
8
9
10
 
# File 'lib/chat_correct/corrections_hash.rb', line 5

def initialize(original_sentence_info_hash:, corrected_sentence_info_hash:)
  @original_sentence_info_hash = original_sentence_info_hash
  @corrected_sentence_info_hash = corrected_sentence_info_hash
  @combined_hash = {}
  @final_matched_array = []
end

Instance Attribute Details

#corrected_sentence_info_hash ⇒ Object (readonly)

Returns the value of attribute corrected_sentence_info_hash.



4
5
6
 
# File 'lib/chat_correct/corrections_hash.rb', line 4

def corrected_sentence_info_hash
  @corrected_sentence_info_hash
end

#original_sentence_info_hash ⇒ Object (readonly)

Returns the value of attribute original_sentence_info_hash.



4
5
6
 
# File 'lib/chat_correct/corrections_hash.rb', line 4

def original_sentence_info_hash
  @original_sentence_info_hash
end

Instance Method Details

#create ⇒ Object 



12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
 
# File 'lib/chat_correct/corrections_hash.rb', line 12

def create
  @j = 0
  @i = 0
  while @i < corrected_sentence_info_hash.length do
    @correct_info = {}
    @mistake_info = {}
    if @j >= original_sentence_info_hash.length
      if corrected_sentence_info_hash[@i]['token'].gsub(/[[:punct:]]/, '').eql?('')
        @correct_info[corrected_sentence_info_hash[@i]['token']] = 'missing_punctuation_correction'
        @combined_hash[@combined_hash.length] = @correct_info
      else
        @correct_info[corrected_sentence_info_hash[@i]['token']] = 'missing_word_mistake'
        @combined_hash[@combined_hash.length] = @correct_info
      end
      @i +=1
    else
      case
      when original_sentence_info_hash[@j]['match_id'].to_s[0].eql?('c') && original_sentence_info_hash[@j]['match_id'].to_s[1..original_sentence_info_hash[@j]['match_id'].to_s.length].eql?(@i.to_s)
        matching_ids_error_analysis(original_sentence_info_hash[@j], corrected_sentence_info_hash[@i])
      when original_sentence_info_hash[@j]['match_id'].to_s[0].eql?('c') && original_sentence_info_hash[@j]['match_id'].to_s[1..original_sentence_info_hash[@j]['match_id'].to_s.length] != @i.to_s
        unmatched_ids_error_analysis
      when original_sentence_info_hash[@j]['match_id'].to_s[0].eql?('s')
        special_error_analysis
      when original_sentence_info_hash[@j]['match_id'].to_s[0].eql?('d')
        duplicate_error_analysis
      end
    end
  end
  original_sentence_info_hash.each do |k, v|
    if v['match_id'].to_s[0].eql?('s') && !@final_matched_array.include?(v['match_id'].to_s)
      if v['token'].gsub(/[[:punct:]]/, '').eql?('') || PUNCTUATION_SYMBOLS.include?(v['token'])
        @mistake_info = {}
        @mistake_info[v['token']] = 'punctuation_mistake'
        @combined_hash[@combined_hash.length] = @mistake_info
        @final_matched_array << v['match_id'].to_s
      else
        @mistake_info = {}
        @mistake_info[v['token']] = 'unnecessary_word_mistake'
        @combined_hash[@combined_hash.length] = @mistake_info
        @final_matched_array << v['match_id'].to_s
      end
    end
  end
  @combined_hash.each do |k, v|
    v.each do |k1, v1|
      next unless k1.include?('ƪ')
      case
      when v1.include?('missing_word_mistake') && @combined_hash[k - 1].to_s.include?('unnecessary_word_mistake') && @combined_hash[k - 2].to_s.include?('unnecessary_word_mistake')
        next if !ChatCorrect::Contraction.new(token_a: @combined_hash[k - 2].key('unnecessary_word_mistake').to_s, token_b: @combined_hash[k - 1].key('unnecessary_word_mistake').to_s, contraction: k1.to_s).contraction?
        @combined_hash[k][k1] = 'stylistic_choice_correction'
        @combined_hash[k - 1][@combined_hash[k - 1].key('unnecessary_word_mistake')] = 'stylistic_choice'
        @combined_hash[k - 2][@combined_hash[k - 2].key('unnecessary_word_mistake')] = 'stylistic_choice'
      when v1.include?('missing_word_mistake') && @combined_hash[k + 1].to_s.include?('unnecessary_word_mistake') && @combined_hash[k + 2].to_s.include?('unnecessary_word_mistake')
        next if !ChatCorrect::Contraction.new(token_a: @combined_hash[k + 2].key('unnecessary_word_mistake').to_s, token_b: @combined_hash[k + 1].key('unnecessary_word_mistake').to_s, contraction: k1.to_s).contraction?
        @combined_hash[k][k1] = 'stylistic_choice_correction'
        @combined_hash[k + 1][@combined_hash[k + 1].key('unnecessary_word_mistake')] = 'stylistic_choice'
        @combined_hash[k + 2][@combined_hash[k + 2].key('unnecessary_word_mistake')] = 'stylistic_choice'
      when v1.include?('unnecessary_word_mistake') && @combined_hash[k + 1].to_s.include?('missing_word_mistake') && @combined_hash[k + 2].to_s.include?('missing_word_mistake')
        next if !ChatCorrect::Contraction.new(token_a: @combined_hash[k + 1].key('missing_word_mistake').to_s, token_b: @combined_hash[k + 2].key('missing_word_mistake').to_s,  contraction: k1.to_s).contraction?
        @combined_hash[k][k1] = 'stylistic_choice'
        @combined_hash[k + 1][@combined_hash[k + 1].key('missing_word_mistake')] = 'stylistic_choice_correction'
        @combined_hash[k + 2][@combined_hash[k + 2].key('missing_word_mistake')] = 'stylistic_choice_correction'
      when v1.include?('unnecessary_word_mistake') && @combined_hash[k - 1].to_s.include?('missing_word_mistake') && @combined_hash[k - 2].to_s.include?('missing_word_mistake')
        next if !ChatCorrect::Contraction.new(token_a: @combined_hash[k - 2].key('missing_word_mistake').to_s, token_b: @combined_hash[k - 1].key('missing_word_mistake').to_s,  contraction: k1.to_s).contraction?
        @combined_hash[k][k1] = 'stylistic_choice'
        @combined_hash[k - 1][@combined_hash[k - 1].key('missing_word_mistake')] = 'stylistic_choice_correction'
        @combined_hash[k - 2][@combined_hash[k - 2].key('missing_word_mistake')] = 'stylistic_choice_correction'
      when v1.include?('verb_mistake') && @combined_hash[k + 1].to_s.include?('verb_mistake_correction')
        next if !ChatCorrect::Contraction.new(token_a: @combined_hash[k + 1].key('verb_mistake_correction').to_s.split[0].to_s, token_b: @combined_hash[k + 1].key('verb_mistake_correction').to_s.split[1].to_s,  contraction: k1.gsub(/ƪ/o, "'").split[0].to_s.gsub(/'/o, 'ƪ')).contraction?
        @combined_hash[k][k1] = 'stylistic_choice'
        @combined_hash[k + 1][@combined_hash[k + 1].key('verb_mistake_correction')] = 'stylistic_choice_correction'
      when v1.include?('verb_mistake_correction') && @combined_hash[k - 1].to_s.include?('verb_mistake')
        next if !ChatCorrect::Contraction.new(token_a: @combined_hash[k - 1].key('verb_mistake').to_s.split[0].to_s, token_b: @combined_hash[k - 1].key('verb_mistake').to_s.split[1].to_s,  contraction: k1.gsub(/ƪ/o, "'").split[0].to_s.gsub(/'/o, 'ƪ')).contraction?
        @combined_hash[k][k1] = 'stylistic_choice_correction'
        @combined_hash[k - 1][@combined_hash[k - 1].key('verb_mistake')] = 'stylistic_choice'
      end
    end
  end
  @combined_hash
end