Created
November 21, 2019 19:18
-
-
Save rmarronnier/90aef3697ee7463a010b1196c632d8cc to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require "./stemmer" | |
module Cadmium | |
class PorterStemmer < Stemmer | |
include Tokenizer::StopWords | |
property stop_words : Set(String) | |
def initialize | |
add_stop_words_list(:en) | |
@stop_words : Set(String) = @@loaded_stop_words[:en] | |
end | |
def self.stem(token) | |
token | |
end | |
def self.tokenize_and_stem(text, keep_stops = false) | |
stemmed_tokens = [] of String | |
lowercase_text = text.downcase | |
tokens = Cadmium::Tokenizer::Aggressive.new.tokenize(lowercase_text) | |
if keep_stops | |
tokens.each { |token| stemmed_tokens.push(stem(token)) } | |
else | |
tokens.each { |token| stemmed_tokens.push(stem(token)) unless @stop_words.includes?(token) } | |
end | |
stemmed_tokens | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment