Small example for conversion of file with kanji strings to csv file with corresponding readings in katakana, hiragana and romaji.

Gemfile

# A sample Gemfile
source "https://rubygems.org"

gem "natto"
gem "romaji"

kanji2csv.rb

#!/usr/bin/env ruby

require 'nkf'
require 'optparse'
require 'csv'
require 'bundler/setup'
require 'natto'
require 'romaji'
require 'romaji/core_ext/string'

$nm = Natto::MeCab.new

# Takes kanji string and converts to its equivalent in katakana
# 
def to_katakana(s)
	arr =[]

	$nm.parse(s) do |n|
		if n.char_type==2
			yomi = n.feature.split(',')[-2]
			arr << yomi
		else
			arr << n.surface
		end
	end

	arr.join
end

# Takes string in katakana and converts it to hiragana
#
def to_hiragana(s)
	NKF.nkf('-h1 -w', s)
end

# Parse options entered by user
#
options = {}
opt_parser =OptionParser.new do |opts|
	opts.banner = "Usage: kanji2csv.rb [options]"

	opts.on("-f", "--file FILENAME", String, "File with new line separated list of kanji") do |f|
		options[:file] = f
	end

	opts.on("-h", "--help", "Show help") do |h|
		options[:help] = h
		puts opt_parser
		exit
	end
end

begin
	opt_parser.parse!

	if (options[:file])
		if File.exists?(options[:file]) && File.file?(options[:file])
			srcfile		=options[:file]
			basename	=File.basename(srcfile)
			ext		="." << basename.split('.').last
			csvfile		=File.join(File.dirname(srcfile), "#{File.basename(basename, ext)}.csv")

			CSV.open(csvfile, "wb") do |csv|
				File.open(srcfile, "r").each_line do |line|
					kanji_str	=line.chomp!
					katakana_str	=to_katakana(kanji_str)
					hiragana_str	=to_hiragana(katakana_str)
					romaji_str	=katakana_str.romaji

					csv << [kanji_str, katakana_str, hiragana_str, romaji_str]
				end
			end
		else
			puts "File #{options[:file]} not found!"
			exit
		end
	else
		puts opt_parser
		exit
	end

rescue OptionParser::InvalidOption, OptionParser::MissingArgument
	puts $!.to_s
	puts opt_parser
	exit
end

Requirements

• Mecab with dictionaries

On OS X it can be installed with homebrew

brew install mecab mecab-ipadic

Installing

bundle install

Usage

Suppose we have file with the following text in kanji ( with filename kanji.txt ):

面白
目黒
岡田
無論
外国
漠然

We can use the script like follows

kanji2csv.rb -f kanji.txt

This will produce the following output

面白,オモシロ,おもしろ,omoshiro
目黒,メグロ,めぐろ,meguro
岡田,オカダ,おかだ,okada
無論,ムロン,むろん,muron
外国,ガイコク,がいこく,gaikoku
漠然,バクゼン,ばくぜん,bakuzen