#
#   httpd.py
#   
#   Analyse Apache (httpd) server logs, including data transferred, requests,
#   clients, and errors. Note that Apache's logs can get filled up very quickly
#   with the default verbosity, leading to logparse taking a very long time to
#   analyse them. In general the default verbosity is good, but logs should be
#   cleared as soon as they are analysed (make sure 'rotate' is set to 'y'). 
#

import re

from ..formatting import *
from ..util import readlog, resolve
from .. import config

import logging
logger = logging.getLogger(__name__)

def parse_log():
    output = ''
    logger.debug("Starting httpd section")
    output += opentag('div', 1, 'httpd', 'section')
    accesslog = readlog(config['logs']['httpd'] + '/access.log')
    a = len(accesslog.split('\n'))
    errorlog = readlog(config['logs']['httpd'] + '/error.log')
    e = len(errorlog.split('\n'))
    data_b = 0
    ips = []
    files = []
    useragents = []
    errors = []
    notfound = []
    unprivileged = []

    logger.debug("Searching through access log")
    for line in accesslog.split('\n'):
        fields = re.search('^(\S*) .*GET (\/.*) HTTP/\d\.\d\" 200 (\d*) \"(.*)\".*\((.*)\;', line)
        try:
            ips.append(resolve(fields.group(1), fqdn=config.prefs['httpd']['resolve-domains']))
            files.append(fields.group(2))
            useragents.append(fields.group(5))
            data_b += int(fields.group(3))
        except Exception as error:
            if type(error) is AttributeError: # this line is not an access log
                pass
            else:
                logger.warning("Error processing httpd access log: " + str(error))
                traceback.print_exc()
    data_h = parsesize(data_b)
    output += writetitle("apache")

    logger.info("httpd has transferred " + str(data_b) + " bytes in response to " + str(a) + " requests with " + str(e) + " errors")
    if (a > 0):
        logger.debug("Parsing request statistics (this might take a while)")
        files = addtag(files, 'code')
        files = orderbyfreq(files)
        files = truncl(files, config.prefs['maxlist'])
        output += writedata(plural(" request", a), files)
    if (ips != None):
        logger.debug("Parsing client statistics")
        ips = addtag(ips, 'code')
        ips = orderbyfreq(ips)
        n_ip = str(len(ips))
        ips = truncl(ips, config.prefs['maxlist'])
        output += writedata(plural(" client", n_ip), ips)
    if (useragents != None):
        logger.debug("Parsing user agent statistics")
        useragents = addtag(useragents, 'code')
        useragents = orderbyfreq(useragents)
        n_ua = str(len(useragents))
        useragents = truncl(useragents, config.prefs['maxlist'])
        output += writedata(plural(" device", n_ua), useragents)

    output += writedata(data_h + " transferred")
    output += writedata(plural(" error", e))

    output += closetag('div', 1)
    logger.info("Finished httpd section")
    return output