Class: Corenlp::Punctuation

Inherits:
Token
  • Object
show all
Defined in:
lib/corenlp/punctuation.rb

Constant Summary collapse

CURRENCY_SYMBOLS =
%W(\u0024 \u00A2 \u00A3 \u00A4 \u00A5 \u20AC)
DASH_SYMBOLS =
%W(\u2010 \u2011 \u2012 \u2013 \u2014)
OPENING_SYMBOLS =
%W(\u201C \u2018 \u00A1 \u00BF \( [ {)

Constants inherited from Token

Token::Enclitics, Token::IGNORED_ENTITIES, Token::NumberRegexp, Token::PunctRegexp, Token::STANFORD_TEXT_REPLACEMENTS, Token::WebsiteRegexp, Token::WordRegexp

Instance Attribute Summary

Attributes inherited from Token

#index, #ner, #penn_treebank_tag, #stanford_lemma, #text, #type

Instance Method Summary collapse

Methods inherited from Token

#==, clean_stanford_text, #content?, #ignored_entity?, #initialize, token_subclass_from_text, #top_level_penn_treebank_category, #website_text?

Constructor Details

This class inherits a constructor from Corenlp::Token

Instance Method Details

#currency?Boolean

Returns:

  • (Boolean)


8
9
10
# File 'lib/corenlp/punctuation.rb', line 8

def currency?
  CURRENCY_SYMBOLS.include?(text)
end

#dash?Boolean

Returns:

  • (Boolean)


12
13
14
# File 'lib/corenlp/punctuation.rb', line 12

def dash?
  DASH_SYMBOLS.include?(text)
end

#opening?Boolean

Returns:

  • (Boolean)


16
17
18
# File 'lib/corenlp/punctuation.rb', line 16

def opening?
  OPENING_SYMBOLS.include?(text)
end