Class: Google::Cloud::Language::Annotation::Token

Inherits:
Object
  • Object
show all
Defined in:
lib/google/cloud/language/annotation.rb

Overview

Represents the smallest syntactic building block of the text. Returned by syntactic analysis.

Examples:

require "google/cloud/language"

language = Google::Cloud::Language.new

content = "Darth Vader is the best villain in Star Wars."
document = language.document content
annotation = document.annotate

annotation.tokens.count #=> 10
token = annotation.tokens.first

token.text_span.text #=> "Darth"
token.text_span.offset #=> 0
token.part_of_speech #=> :NOUN
token.head_token_index #=> 1
token.label #=> :NN
token.lemma #=> "Darth"

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(text_span, part_of_speech, head_token_index, label, lemma) ⇒ Token

Returns a new instance of Token.



283
284
285
286
287
288
289
290
 
# File 'lib/google/cloud/language/annotation.rb', line 283

def initialize text_span, part_of_speech, head_token_index, label,
               lemma
  @text_span        = text_span
  @part_of_speech   = part_of_speech
  @head_token_index = head_token_index
  @label            = label
  @lemma            = lemma
end

Instance Attribute Details

#head_token_index ⇒ Integer (readonly)

Represents the head of this token in the dependency tree. This is the index of the token which has an arc going to this token. The index is the position of the token in the array of tokens returned by the API method. If this token is a root token, then the headTokenIndex is its own index.

Returns:

  • (Integer) —

    the current value of head_token_index



277
278
279
 
# File 'lib/google/cloud/language/annotation.rb', line 277

def head_token_index
  @head_token_index
end

#label ⇒ Symbol (readonly)

The parse label for the token.

Returns:

  • (Symbol) —

    the current value of label



277
278
279
 
# File 'lib/google/cloud/language/annotation.rb', line 277

def label
  @label
end

#lemma ⇒ String (readonly)

[Lemma](en.wikipedia.org/wiki/Lemma_(morphology)) of the token.

Returns:

  • (String) —

    the current value of lemma



277
278
279
 
# File 'lib/google/cloud/language/annotation.rb', line 277

def lemma
  @lemma
end

#part_of_speech ⇒ Symbol (readonly)

Represents part of speech information for a token.

Returns:

  • (Symbol) —

    the current value of part_of_speech



277
278
279
 
# File 'lib/google/cloud/language/annotation.rb', line 277

def part_of_speech
  @part_of_speech
end

#text_span ⇒ TextSpan (readonly)

The token text.

Returns:

  • (TextSpan) —

    the current value of text_span



277
278
279
 
# File 'lib/google/cloud/language/annotation.rb', line 277

def text_span
  @text_span
end

Class Method Details

.from_grpc(grpc) ⇒ Object 



304
305
306
307
308
309
 
# File 'lib/google/cloud/language/annotation.rb', line 304

def self.from_grpc grpc
  text_span = TextSpan.from_grpc grpc.text
  new text_span, grpc.part_of_speech.tag,
      grpc.dependency_edge.head_token_index,
      grpc.dependency_edge.label, grpc.lemma
end

Instance Method Details

#offset ⇒ Object Also known as: begin_offset 



297
298
299
 
# File 'lib/google/cloud/language/annotation.rb', line 297

def offset
  @text_span.offset
end

#text ⇒ Object Also known as: content 



292
293
294
 
# File 'lib/google/cloud/language/annotation.rb', line 292

def text
  @text_span.text
end