Lab2 mapper.py

mapper.py

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

import sys
from time import time
import happybase

MY_N = 138

connection = happybase.Connection('172.31.25.248')
table = connection.table('mikhail.klimin')

# input comes from STDIN (standard input)
for line in sys.stdin:
    # remove leading and trailing whitespace
    if not line.strip():
        # skip blank lines
        continue

    # split the line into tuple
    uid, timestamp, url  = line.split("\t")


    # convert uid (currently a string) to int
    # skip blank url
    try:
        uid = int(uid)
        timestamp = float(timestamp)
        if not url.strip():
            raise ValueError

    except ValueError:
        # uid was not a integer, so silently
        # ignore/discard this line
        continue


    # write the results to STDOUT (standard output);
    # tab-delimited
    if uid % 256 == MY_N:
        # print '{0}\t{1}\t{2}'.format(str(uid), int(timestamp*1000), url)
        table.put(str(uid), {'data:url': url}, timestamp=int(timestamp*1000))