#!/usr/bin/env python

def dictify_logline(line):
    '''return a dictionary of the pertinent pieces of an apache combined log file

    Currently, the only fields we are interested in are remote host and bytes sent,
    but we are putting status in there just for good measure.
    '''
    split_line = line.split()
    return {'remote_host': split_line[0], 
            'status': split_line[8],
            'bytes_sent': split_line[9],
    }

def generate_log_report(logfile):
    '''return a dictionary of format remote_host=>[list of bytes sent]
    
    This function takes a file object, iterates through all the lines in the file,
    and generates a report of the number of bytes transferred to each remote host
    for each hit on the webserver.
    '''
    report_dict = {}
    for line in logfile:
        line_dict = dictify_logline(line)
        host = line_dict['remote_host']
        #print line_dict
        try:
            bytes_sent = int(line_dict['bytes_sent'])
        except ValueError:
            ##totally disregard anything we don't understand
            continue
        report_dict[host] = report_dict.setdefault(host, 0) + bytes_sent
    return report_dict