Created
February 12, 2014 03:49
-
-
Save ohnishiakira/8949780 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
#!/usr/bin/env ruby | |
# coding: utf-8 | |
require "forwardable" | |
require "csv" | |
require "MeCab" | |
class Mecab | |
def self.wakati | |
new "-O wakati" | |
end | |
def initialize(output) | |
@mecab = MeCab::Tagger.new output | |
end | |
def parse(str) | |
n = @mecab.parseToNode str | |
begin | |
yield Node.new n | |
end while n = n.next | |
end | |
class Node | |
extend Forwardable | |
def initialize(node) | |
@node = node | |
end | |
%i( | |
surface length rlength id rcAttr lcAttr | |
posid char_type stat isbest alpha beta | |
prob wcost cost | |
).each{|m| | |
def_delegator :@node, m | |
} | |
def feature | |
Hash[%w(品詞 品詞細分類1 品詞細分類2 品詞細分類3 活用形 活用型 原形 読み 発音).zip(CSV.parse_line(@node.feature))] | |
end | |
end | |
end | |
if $0 == __FILE__ | |
require "pp" | |
Mecab.wakati.parse("月が綺麗ですね"){|n| | |
puts [ | |
n.feature["品詞"], | |
n.surface, | |
n.cost | |
].join("\t") | |
# p n.surface if n.feature["品詞"] == "名詞" | |
# p %i( | |
# surface length rlength id rcAttr lcAttr | |
# posid char_type stat isbest alpha beta | |
# prob wcost cost | |
# ).map{|m| | |
# n.send(m) | |
# } | |
} | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment