Created
March 16, 2012 08:01
-
-
Save komiya-atsushi/2049048 to your computer and use it in GitHub Desktop.
MeCab の Ruby バインディングに薄い皮をかぶせたもの。Ruby らしく each でループしたいがためだけに作りました。
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
# -*- coding: utf-8 -*- | |
require 'MeCab' | |
class MeCabTagger | |
class MeCabNode | |
def initialize(node, charset) | |
@node = node | |
@feature = node.feature.force_encoding(charset).split(',') | |
@charset = charset | |
end | |
def pos | |
return @feature[0] | |
end | |
def pos_detail1 | |
return @feature[1] | |
end | |
def pos_detail2 | |
return @feature[2] | |
end | |
def pos_detail3 | |
return @feature[3] | |
end | |
def basic_string | |
return @feature[6] | |
end | |
def surface | |
return @node.surface.force_encoding(@charset) | |
end | |
def word | |
if @feature[6] == "*" | |
return surface() | |
else | |
return @feature[6] | |
end | |
end | |
end | |
class MeCabResult | |
def initialize(head, charset) | |
@head = head | |
@charset = charset | |
end | |
def each | |
node = @head.next | |
while node.next != nil | |
yield MeCabNode.new(node, @charset) | |
node = node.next | |
end | |
end | |
end | |
def initialize(charset) | |
@tagger = MeCab::Tagger.new | |
@charset = charset | |
end | |
def parse(text) | |
return [] if text == nil || text.length == 0 | |
return MeCabResult.new(@tagger.parseToNode(text), @charset) | |
end | |
end | |
if __FILE__ == $0 | |
tagger = MeCabTagger.new('UTF-8') | |
tagger.parse('吾輩は猫である。名前はまだない。').each do |node| | |
puts "pos : #{node.pos}, word : #{node.word}" | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment