seed

#!/usr/bin/env python

# This tool will  radom select articles  from a wikipedia article select
# and radomly seed it with PII data

import random
import os
from faker import Factory



fake = Factory.create()

def dedupe(seq):
    seen = set()
    seen_add = seen.add
    return [ x for x in seq if not (x in seen or seen.add(x))]

def randomDocuments(rootFolder):
    folderlst = []
    for(dirpath, _, files) in os.walk(rootFolder):
        for filename in files:
            filepath = os.path.join(dirpath, filename)
            folderlst.append(filepath)


    return random.choice(folderlst)

def seedDocuments(rootFolder, count, piiFolder):

    if not os.path.exists(piiFolder):
        os.mkdir(piiFolder)

    filelst = []
    print('Randomizing {} Documents'.format(count))
    while len(filelst) < count:

        filelst.append(randomDocuments(rootFolder))
        dedupe(filelst)

        index = 0

    for each_doc in filelst:
        index += 1

        with open(each_doc, 'r') as seedread:
            filecontent = seedread.read()

            with open('{}/pii_{}.txt'.format(piiFolder, index), 'w+') as outfile:
                file_size = os.stat(each_doc)[6]
                outfile.write(filecontent)
                outfile.seek((outfile.tell()+random.randint(0, file_size-2))%file_size)
                piiproviders = [fake.credit_card_number(), fake.ssn()]
                outfile.write(' PII VECTOR ( {} ) '.format(random.choice(piiproviders)))
    print('Document creation complete,files are located in folder {}'.format(os.path.abspath(piiFolder)))

seedDocuments('data',10,'needle')