100_questions_NLP_011

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

#Link: http://www.cl.ecei.tohoku.ac.jp/nlp100/

"""
hightemp.txt: http://www.cl.ecei.tohoku.ac.jp/nlp100/data/hightemp.txt
は，日本の最高気温の記録を「都道府県」「地点」「℃」「日」のタブ区切り形式で格納したファイルである．
以下の処理を行うプログラムを作成し，hightemp.txtを入力ファイルとして実行せよ．
Question 11:
11. タブをスペースに置換
タブ1文字につきスペース1文字に置換せよ．確認にはsedコマンド，trコマンド，もしくはexpandコマンドを用いよ．
"""
import subprocess
import requests
import os

def download(url, dir, params={}):
    dl = requests.get(url, params=params)
    with file(dir, "wb") as f:
        f.write(dl.content)

def readFile(path):
  answer = ""
  with file(path, "r") as f:
    for line in f.readlines():
      answer = answer + line
  return answer

def remove(path):
  if os.path.exists(path):
    os.remove(path)

def encloseByQuotation(sentence):
  if "'" in sentence:
    quotation = '"'
  else:
    quotation = "'"
  return quotation + sentence + quotation

def tr(path, before, after):
  before = encloseByQuotation(before)
  after = encloseByQuotation(after)
  cmd = "cat " + path + " | tr " + before + " " + after + " > ./tr.txt"
  subprocess.call(cmd, shell=True)
  answer = ""
  with file("./tr.txt", "r") as f:
    for line in f.readlines():
      answer = answer + line
    remove("./tr.txt")
  return answer


#download hightemp.txt
download("http://www.cl.ecei.tohoku.ac.jp/nlp100/data/hightemp.txt","./hightemp.txt") if not os.path.exists("./hightemp.txt") else None

content = readFile("./hightemp.txt")

print("original file: \n" + content)
print("Every tabs inside the file was replaced by a space: \n" + content.replace("\t"," "))
print("executed by tr: \n" + tr("./hightemp.txt","\t"," "))