Created
December 10, 2012 22:08
-
-
Save leejarvis/4253798 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
class Tag | |
class << self | |
attr_accessor :match | |
attr_accessor :children | |
end | |
self.children = [] | |
def self.inherited(klass) | |
Tag.children << klass | |
end | |
def self.matches(obj) | |
self.match = obj | |
end | |
def self.scan(token, value) | |
token.tags << self.new if matches?(value) | |
end | |
def self.matches?(value) | |
case self.match | |
when Regexp; self.match =~ value | |
when String, Numeric; self.match == value | |
when Array, Range; self.match.include?(value) | |
else | |
false | |
end | |
end | |
def to_s | |
self.class.to_s.gsub(/([a-z\d])([A-Z])/, '\1_\2').downcase | |
end | |
end | |
class Number < Tag | |
matches /\d+/ | |
end | |
class SingleNumber < Tag | |
matches '0'...'10' | |
end | |
class Token | |
attr_reader :value, :tags | |
def initialize(value) | |
@value = value | |
@tags = [] | |
Tag.children.each { |tagger| tagger.scan(self, value) } | |
end | |
end | |
class Tokenizer | |
def self.tokenize(text) | |
text.split(/\s+/).map { |token| Token.new(token) } | |
end | |
end | |
tokens = Tokenizer.tokenize(DATA.read) | |
p tokens.map { |t| [t.value, t.tags.map(&:to_s)] } | |
__END__ | |
foo bar 10 two 3 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment