Class: TextRank::CharFilter::UndoContractions

Inherits:

Object

• Object
• TextRank::CharFilter::UndoContractions

Defined in:

lib/text_rank/char_filter/undo_contractions.rb

Overview

Character filter to convert English contractions into their expanded form.

Example

UndoContractions.new.filter!("You're a bitter man. That's because I've lived.")
=> "You are a bitter man. That is because I have lived."

Constant Summary

CONTRACTIONS =

List of English contractions to undo

{
  "ain't"            => "am not",
  "amn't"            => "am not",
  "aren't"           => "are not",
  "can't"            => "can not",
  "could've"         => "could have",
  "couldn't"         => "could not",
  "couldn't've"      => "could not have",
  "didn't"           => "did not",
  "doesn't"          => "does not",
  "don't"            => "do not",
  "gonna"            => "going to",
  "hadn't"           => "had not",
  "hadn't've"        => "had not have",
  "hasn't"           => "has not",
  "haven't"          => "have not",
  "he'd"             => "he had",
  "he'd've"          => "he would have",
  "he'll"            => "he shall",
  "he's"             => "he has",
  "he'sn't"          => "he has not",
  "how'd"            => "how did",
  "how'll"           => "how will",
  "how's"            => "how has",
  "i'd"              => "i had",
  "i'd've"           => "i would have",
  "i'll"             => "i shall",
  "i'm"              => "i am",
  "i've"             => "i have",
  "i'ven't"          => "i have not",
  "isn't"            => "is not",
  "it'd"             => "it had",
  "it'd've"          => "it would have",
  "it'll"            => "it shall",
  "it's"             => "it has",
  "it'sn't"          => "it has not",
  "let's"            => "let us",
  "ma'am"            => "madam",
  "mightn't"         => "might not",
  "mightn't've"      => "might not have",
  "might've"         => "might have",
  "mustn't"          => "must not",
  "must've"          => "must have",
  "needn't"          => "need not",
  "not've"           => "not have",
  "o'clock"          => "of the clock",
  "ol'"              => "old",
  "oughtn't"         => "ought not",
  "shan't"           => "shall not",
  "she'd"            => "she had",
  "she'd've"         => "she would have",
  "she'll"           => "she shall",
  "she's"            => "she has",
  "she'sn't"         => "she has not",
  "should've"        => "should have",
  "shouldn't"        => "should not",
  "shouldn't've"     => "should not have",
  "somebody'd"       => "somebody had",
  "somebody'd've"    => "somebody would have",
  "somebody'dn't've" => "somebody would not have",
  "somebody'll"      => "somebody shall",
  "somebody's"       => "somebody has",
  "someone'd"        => "someone had",
  "someone'd've"     => "someone would have",
  "someone'll"       => "someone shall",
  "someone's"        => "someone has",
  "something'd"      => "something had",
  "something'd've"   => "something would have",
  "something'll"     => "something shall",
  "something's"      => "something has",
  "'sup"             => "what's up",
  "that'll"          => "that will",
  "that's"           => "that has",
  "there'd"          => "there had",
  "there'd've"       => "there would have",
  "there're"         => "there are",
  "there's"          => "there has",
  "they'd"           => "they had",
  "they'dn't"        => "they would not",
  "they'dn't've"     => "they would not have",
  "they'd've"        => "they would have",
  "they'd'ven't"     => "they would have not",
  "they'll"          => "they shall",
  "they'lln't've"    => "they will not have",
  "they'll'ven't"    => "they will have not",
  "they're"          => "they are",
  "they've"          => "they have",
  "they'ven't"       => "they have not",
  "'tis"             => "it is",
  "'twas"            => "it was",
  "wanna"            => "want to",
  "wasn't"           => "was not",
  "we'd"             => "we had",
  "we'd've"          => "we would have",
  "we'dn't've"       => "we would not have",
  "we'll"            => "we will",
  "we'lln't've"      => "we will not have",
  "we're"            => "we are",
  "we've"            => "we have",
  "weren't"          => "were not",
  "what'll"          => "what shall",
  "what're"          => "what are",
  "what's"           => "what has",
  "what've"          => "what have",
  "when's"           => "when has",
  "where'd"          => "where did",
  "where's"          => "where has",
  "where've"         => "where have",
  "who'd"            => "who would",
  "who'd've"         => "who would have",
  "who'll"           => "who shall",
  "who're"           => "who are",
  "who's"            => "who has",
  "who've"           => "who have",
  "why'll"           => "why will",
  "why're"           => "why are",
  "why's"            => "why has",
  "won't"            => "will not",
  "won't've"         => "will not have",
  "would've"         => "would have",
  "wouldn't"         => "would not",
  "wouldn't've"      => "would not have",
  "y'all"            => "you all",
  "y'all'd've"       => "you all would have",
  "y'all'dn't've"    => "you all would not have",
  "y'all'll"         => "you all will",
  "y'all'lln't"      => "you all will not",
  "y'all'll've"      => "you all will have",
  "y'all'll'ven't"   => "you all will have not",
  "you'd"            => "you had",
  "you'd've"         => "you would have",
  "you'll"           => "you shall",
  "you're"           => "you are",
  "you'ren't"        => "you are not",
  "you've"           => "you have",
  "you'ven't"        => "you have not",
}

Instance Method Summary

• #filter!(text) ⇒ String

  Perform the filter.

Instance Method Details

#filter!(text) ⇒ String

Perform the filter

Parameters:

• text (String)

Returns:

• (String)

# File 'lib/text_rank/char_filter/undo_contractions.rb', line 155

def filter!(text)
  text.gsub!(/[a-z']+/) do |word|
    CONTRACTIONS[word] || word
  end
end