Class: TextStat

Inherits:
Object
  • Object
show all
Defined in:
lib/textstat.rb,
lib/textstat/version.rb

Constant Summary collapse

GEM_PATH = 
File.dirname(File.dirname(__FILE__))
VERSION = 
"0.1.9"

Class Method Summary collapse

Class Method Details

.automated_readability_index(text) ⇒ Object 



113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/textstat.rb', line 113

def self.automated_readability_index(text)
  chars = char_count(text)
  words = lexicon_count(text)
  sentences = sentence_count(text)
  begin
    a = chars.to_f / words
    b = words.to_f / sentences

    readability = 4.71 * a + 0.5 * b - 21.43
    readability.round(1)
  rescue ZeroDivisionError
    0.0
  end
end

.avg_letter_per_word(text) ⇒ Object 



53
54
55
56
57
58
 
# File 'lib/textstat.rb', line 53

def self.avg_letter_per_word(text)
  letters_per_word = char_count(text).to_f / lexicon_count(text)
  letters_per_word.round(2)
rescue ZeroDivisionError
  0.0
end

.avg_sentence_length(text) ⇒ Object 



35
36
37
38
39
40
 
# File 'lib/textstat.rb', line 35

def self.avg_sentence_length(text)
  asl = lexicon_count(text).to_f / sentence_count(text)
  asl.round(1)
rescue ZeroDivisionError
  0.0
end

.avg_sentence_per_word(text) ⇒ Object 



60
61
62
63
64
65
 
# File 'lib/textstat.rb', line 60

def self.avg_sentence_per_word(text)
  sentence_per_word = sentence_count(text).to_f / lexicon_count(text)
  sentence_per_word.round(2)
rescue ZeroDivisionError
  0.0
end

.avg_syllables_per_word(text, language = 'en_us') ⇒ Object 



42
43
44
45
46
47
48
49
50
51
 
# File 'lib/textstat.rb', line 42

def self.avg_syllables_per_word(text, language = 'en_us')
  syllable = syllable_count(text, language)
  words    = lexicon_count(text)
  begin
    syllables_per_word = syllable.to_f / words
    syllables_per_word.round(1)
  rescue ZeroDivisionError
    0.0
  end
end

.char_count(text, ignore_spaces = true) ⇒ Object 



6
7
8
9
 
# File 'lib/textstat.rb', line 6

def self.char_count(text, ignore_spaces = true)
  text = text.delete(' ') if ignore_spaces
  text.length
end

.coleman_liau_index(text) ⇒ Object 



106
107
108
109
110
111
 
# File 'lib/textstat.rb', line 106

def self.coleman_liau_index(text)
  letters = (avg_letter_per_word(text) * 100).round(2)
  sentences = (avg_sentence_per_word(text) * 100).round(2)
  coleman = 0.0588 * letters - 0.296 * sentences - 15.8
  coleman.round(2)
end

.dale_chall_readability_score(text, language = 'en_us') ⇒ Object 



169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
# File 'lib/textstat.rb', line 169

def self.dale_chall_readability_score(text, language = 'en_us')
  word_count = lexicon_count(text)
  count = word_count - difficult_words(text, language)

  begin
    per = 100.0 * count / word_count
  rescue ZeroDivisionError
    return 0.0
  end

  difficult_words = 100 - per
  score = 0.1579 * difficult_words + 0.0496 * avg_sentence_length(text)
  score += 3.6365 if difficult_words > 5

  score.round(2)
end

.dictionary_path ⇒ Object 



310
311
312
 
# File 'lib/textstat.rb', line 310

def self.dictionary_path
  @dictionary_path ||= File.join(TextStat::GEM_PATH, 'lib', 'dictionaries')
end

.dictionary_path=(path) ⇒ Object 



306
307
308
 
# File 'lib/textstat.rb', line 306

def self.dictionary_path=(path)
  @dictionary_path = path
end

.difficult_words(text, language = 'en_us', return_words = false) ⇒ Object 



148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
 
# File 'lib/textstat.rb', line 148

def self.difficult_words(text, language = 'en_us', return_words = false)
  require 'set'
  easy_words = Set.new
  File.read(File.join(dictionary_path, "#{language}.txt")).each_line do |line|
    easy_words << line.chop
  end

  text_list = text.downcase.gsub(/[^0-9a-z ]/i, '').split(' ')
  diff_words_set = Set.new
  text_list.each do |value|
    next if easy_words.include? value

    diff_words_set.add(value) if syllable_count(value, language) > 1
  end
  if return_words
    diff_words_set
  else
    diff_words_set.length
  end
end

.flesch_kincaid_grade(text, language = 'en_us') ⇒ Object 



74
75
76
77
78
79
 
# File 'lib/textstat.rb', line 74

def self.flesch_kincaid_grade(text, language = 'en_us')
  sentence_length = avg_sentence_length(text)
  syllables_per_word = avg_syllables_per_word(text, language)
  flesch = 0.39 * sentence_length + 11.8 * syllables_per_word - 15.59
  flesch.round(1)
end

.flesch_reading_ease(text, language = 'en_us') ⇒ Object 



67
68
69
70
71
72
 
# File 'lib/textstat.rb', line 67

def self.flesch_reading_ease(text, language = 'en_us')
  sentence_length    = avg_sentence_length(text)
  syllables_per_word = avg_syllables_per_word(text, language)
  flesch = 206.835 - 1.015 * sentence_length - 84.6 * syllables_per_word
  flesch.round(2)
end

.forcast(text, language = 'en_us') ⇒ Object 



207
208
209
210
211
212
213
214
 
# File 'lib/textstat.rb', line 207

def self.forcast(text, language = 'en_us')
  words = text.split(' ')[0..149]
  words_with_one_syllabe = words.count {
    |word| syllable_count(word, language) == 1
  }
  forcast = 20 - (words_with_one_syllabe / 10)
  forcast
end

.gunning_fog(text, language = 'en_us') ⇒ Object 



186
187
188
189
190
191
192
193
 
# File 'lib/textstat.rb', line 186

def self.gunning_fog(text, language = 'en_us')
  per_diff_words = 100.0 * difficult_words(text, language) / lexicon_count(text) + 5
  grade = 0.4 * (avg_sentence_length(text) + per_diff_words)

  grade.round(2)
rescue ZeroDivisionError
  0.0
end

.lexicon_count(text, remove_punctuation = true) ⇒ Object 



11
12
13
14
15
 
# File 'lib/textstat.rb', line 11

def self.lexicon_count(text, remove_punctuation = true)
  text  = text.gsub(/[^a-zA-Z\s]/, '').squeeze(' ') if remove_punctuation
  count = text.split(' ').count
  count
end

.linsear_write_formula(text, language = 'en_us') ⇒ Object 



128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
 
# File 'lib/textstat.rb', line 128

def self.linsear_write_formula(text, language = 'en_us')
  easy_word = 0
  difficult_word = 0
  text_list = text.split(' ')[0..100]

  text_list.each do |word|
    if syllable_count(word, language) < 3
      easy_word += 1
    else
      difficult_word += 1
    end
  end

  text = text_list.join(' ')

  number = (easy_word * 1 + difficult_word * 3).to_f / sentence_count(text)
  number -= 2 if number <= 20
  number / 2
end

.lix(text) ⇒ Object 



195
196
197
198
199
200
201
202
203
204
205
 
# File 'lib/textstat.rb', line 195

def self.lix(text)
  words = text.split(' ')
  words_length = words.length
  long_words = words.count { |word| word.length > 6 }

  per_long_words = 100.0 * long_words / words_length
  asl = avg_sentence_length(text)
  lix = asl + per_long_words

  lix.round(2)
end

.polysyllab_count(text, language = 'en_us') ⇒ Object 



81
82
83
84
85
86
87
88
 
# File 'lib/textstat.rb', line 81

def self.polysyllab_count(text, language = 'en_us')
  count = 0
  text.split(' ').each do |word|
    w = syllable_count(word, language)
    count += 1 if w >= 3
  end
  count
end

.powers_sumner_kearl(text, language = 'en_us') ⇒ Object 



216
217
218
219
 
# File 'lib/textstat.rb', line 216

def self.powers_sumner_kearl(text, language = 'en_us')
  grade = 0.0778 * avg_sentence_length(text) + 0.0455 * syllable_count(text, language) - 2.2029
  grade.round(2)
end

.sentence_count(text) ⇒ Object 



31
32
33
 
# File 'lib/textstat.rb', line 31

def self.sentence_count(text)
  text.scan(/[\.\?!][\'\\)\]]*[ |\n][A-Z]/).map(&:strip).count + 1
end

.smog_index(text, language = 'en_us') ⇒ Object 



90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/textstat.rb', line 90

def self.smog_index(text, language = 'en_us')
  sentences = sentence_count(text)

  if sentences >= 3
    begin
      polysyllab = polysyllab_count(text, language)
      smog = 1.043 * Math.sqrt(30.0 * polysyllab / sentences) + 3.1291
      smog.round(1)
    rescue ZeroDivisionError
      0.0
    end
  else
    0.0
  end
end

.spache(text, language = 'en_us') ⇒ Object 



221
222
223
224
225
226
 
# File 'lib/textstat.rb', line 221

def self.spache(text, language = 'en_us')
  words = text.split(' ').count
  unfamiliar_words = difficult_words(text, language) / words
  grade = (0.141 * avg_sentence_length(text)) + (0.086 * unfamiliar_words) + 0.839
  grade.round(2)
end

.syllable_count(text, language = 'en_us') ⇒ Object 



17
18
19
20
21
22
23
24
25
26
27
28
29
 
# File 'lib/textstat.rb', line 17

def self.syllable_count(text, language = 'en_us')
  return 0 if text.empty?

  text = text.downcase
  text.gsub(/[^a-zA-Z\s]/, '').squeeze(' ')
  dictionary = Text::Hyphen.new(language: language, left: 0, right: 0)
  count = 0
  text.split(' ').each do |word|
    word_hyphenated = dictionary.visualise(word)
    count += word_hyphenated.count('-') + 1
  end
  count
end

.text_standard(text, float_output = nil) ⇒ Object 



228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
 
# File 'lib/textstat.rb', line 228

def self.text_standard(text, float_output=nil)
  grade = []

  lower = flesch_kincaid_grade(text).round
  upper = flesch_kincaid_grade(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Appending Flesch Reading Easy
  score = flesch_reading_ease(text)
  if score < 100 && score >= 90
    grade.append(5)
  elsif score < 90 && score >= 80
    grade.append(6)
  elsif score < 80 && score >= 70
    grade.append(7)
  elsif score < 70 && score >= 60
    grade.append(8)
    grade.append(9)
  elsif score < 60 && score >= 50
    grade.append(10)
  elsif score < 50 && score >= 40
    grade.append(11)
  elsif score < 40 && score >= 30
    grade.append(12)
  else
    grade.append(13)
  end

  # Appending SMOG Index
  lower = smog_index(text).round
  upper = smog_index(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Appending Coleman_Liau_Index
  lower = coleman_liau_index(text).round
  upper = coleman_liau_index(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Appending Automated_Readability_Index
  lower = automated_readability_index(text).round
  upper = automated_readability_index(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Appending Dale_Chall_Readability_Score
  lower = dale_chall_readability_score(text).round
  upper = dale_chall_readability_score(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Appending Linsear_Write_Formula
  lower = linsear_write_formula(text).round
  upper = linsear_write_formula(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Appending Gunning Fog Index
  lower = gunning_fog(text).round
  upper = gunning_fog(text).ceil
  grade.append(lower.to_i)
  grade.append(upper.to_i)

  # Finding the Readability Consensus based upon all the above tests
  require 'counter'
  d = Counter.new(grade)
  final_grade = d.most_common(1)
  score = final_grade[0][0]

  if float_output
    score.to_f
  else
    "#{score.to_i - 1}th and #{score.to_i}th grade"
  end
end