nemupm

#!/usr/bin/perl

use strict;
use warnings;
use utf8;
use encoding 'utf8';
use MeCab;

my $model = new MeCab::Model(join " ", @ARGV);
my $c = $model->createTagger();

nemupm

#!/usr/bin/python
# -*- coding:utf-8 -*-

from unicodedata import normalize

def convert_str_to_regular_format(string):
    uni = normalize('NFKC', string.decode('utf-8')).lower()
    return uni.encode('utf-8')

f = open("jawiki-latest-all-titles-in-ns0","r")