Chantier HN Triangle » NouvellesItaliennes19eme

#!/usr/bin/python

# -*- coding: utf-8 -*-

import os

import re

import unicodedata

import sys

import csv

import string

from os import listdir, rename

from os.path import isfile, join

## répertoire depuis lequel on lance le script

mypath = os.getcwd()

mypath_input_papers = sys.argv[1]

def prepareListPapers():

  papers_map = {}

  ##############################

  # PARSING du fichier CSV     #

  ##############################

  with open(mypath_input_papers) as csvfile:

    filereader = csv.reader(csvfile, delimiter='#')

    i = 0

    for row in filereader:

      paper_line = {}

      if i == 0:

        print "First line (and first column) : ",row[0]

      else : 

        name_paper = row[1]

        name_paper = name_paper.strip(" ")

        id_paper = row[0]

        id_paper = id_paper.translate(None, string.whitespace)

        paper_line = {"id": id_paper, "name": name_paper,"comment": row[2],"first_date": row[3],"last_date": row[4],"authors": row[5]}

        papers_map[name_paper] = paper_line

        print "PAPER : [",id_paper,"]"

      i = i + 1

  return papers_map

def findDuplicateNames(papers, paper_key):

  paper = papers[paper_key]

  name_paper = paper["name"]

  name_paper_2 = name_paper.strip(" ")

  name_paper_2 = name_paper_2[1:len(name_paper_2)-1]

  id_paper = paper["id"]

  for paper_other_key in papers.keys() :

    paper_other = papers[paper_other_key]

    name_other_paper = paper_other["name"]

    name_other_paper_2 = name_other_paper.strip(" ")

    name_other_paper_2 = name_other_paper_2[1:len(name_other_paper_2)-1]

    if name_other_paper_2 in name_paper_2:

      if name_other_paper_2 != name_paper_2:

        id_paper_other = paper_other["id"]

        print "#",id_paper,"#",name_paper_2,"#",id_paper_other,"#",name_other_paper_2

papers = prepareListPapers()

for paper in papers.keys() :

    findDuplicateNames(papers, paper)