# -*- coding: utf-8 -*-
import os, sys, re

def main():

    pattern = re.compile(r"<<(.+?)>>")

    from collections import defaultdict
    frequency = defaultdict(int)/Users/it/home_dl/chainer_rnn/result/op_line_filter_hira_correct_spm_4k_unit=2000/log

    with open(sys.argv[1]) as f:
        for line in f:
            line = line.strip()

            match = re.search(pattern, line)
            if match is None:
                pass
            else:
                before = match.group(1)

                frequency[before] += 1

    for k, v in sorted(frequency.items(), key=lambda x:x[1],reverse=True):
        print (k, v)

main()

# Python 正規表現でマッチした箇所を利用して置換する
# ラムダ式を使う。

import re

text = 'あいうえお'
regex_pattern = re.compile('(。|？|\?|\n)')
sentence = re.sub(regex_pattern, lambda m:str(m.group() + '###') , text)
# 'あ###いうえ###お'


# 半角スペース区切りのテキストを入力し要素ごとの頻度を出力する。

import sys

from collections import defaultdict
frequency = defaultdict(int)

with open(sys.argv[1]) as f:
    lines = f.readlines()

    for line in lines:
            line = line.strip()
            morphs = line.split(" ")

            for morph in morphs:
                frequency[morph] += 1

for k, v in sorted(frequency.items(), key=lambda x:x[1], reverse=True):
    print(k, v)


# pythonの正規表現でのマッチ部分捕捉

import sys, re

# pn_ja.dic
# 優れる:すぐれる:動詞:1
pattern = re.compile(r"^(\S+?)\:(\S+?)\:(\S+?)\:(\S+)$")



with open(sys.argv[1]) as f:
    for line in f:
        line = line.strip()

        if line is None:
            pass
        else:
            match = re.search(pattern, line)
            if match is None:
                print('Not match')
            else:
                term = match.group(1)
                yomi = match.group(2)
                klass = match.group(3)
                pn_score = match.group(4)

                print(term, yomi, klass, pn_score)