#!/bin/bash

LOGFILE="access.log"
LIMIT=10

while getopts l:f: option
do
    case "${option}"
    in
        l) LIMIT=${OPTARG};;
        f) LOGFILE=${OPTARG};;
    esac
done

LOGFILE_GZ="$LOGFILE.*"
RESPONSE_CODE="200"

filters() {
    grep $RESPONSE_CODE
    #\
    #    | grep -v "\/rss\/" \
    #    | grep -v robots.txt \
    #    | grep -v "\.css" \
    #    | grep -v "\.jss*" \
    #    | grep -v "\.png" \
    #    | grep -v "\.ico"
}

filters_404() {
    grep "404"
}

request_ips() {
    awk '{print $1}'
}

request_method() {
    awk '{print $6}' | cut -d'"' -f2
}

wordcount() {
    sort | uniq -c
}

sort_desc() {
    sort -rn
}

return_kv() {
    awk '{print $1, $2}'
}

request_pages() {
    awk '{print $7}'
}

referer_pages() {
    awk '{print $11}'
}

return_top_ten() {
    head -$LIMIT
}

## actions
get_request_ips() {
    echo ""
    echo "Top $LIMIT Request IP's:"
    echo "===================="

    cat $LOGFILE \
        | filters \
        | request_ips \
        | wordcount \
        | sort_desc \
        | return_kv \
        | return_top_ten
    echo ""
}

get_request_methods() {
    echo "Top Request Methods:"
    echo "===================="
    cat $LOGFILE \
        | filters \
        | request_method \
        | wordcount \
        | return_kv
    echo ""
    }

get_request_pages_404() {
    echo "Top $LIMIT: 404 Page Responses:"
    echo "==========================="
    zgrep '-' $LOGFILE $LOGFILE_GZ\
        | filters_404 \
        | request_pages \
        | wordcount \
        | sort_desc \
        | return_kv \
        | return_top_ten
    echo ""
}

get_request_pages() {
    echo "Top $LIMIT Request Pages:"
    echo "====================="
    cat $LOGFILE \
        | filters \
        | request_pages \
        | wordcount \
        | sort_desc \
        | return_kv \
        | return_top_ten
    echo ""
}

get_referer_pages() {
    echo "Top $LIMIT Referer Pages:"
    echo "====================="
    cat $LOGFILE \
        | filters \
        | referer_pages \
        | wordcount \
        | sort_desc \
        | return_kv \
        | return_top_ten
    echo ""
}

get_request_pages_all() {
    echo "Top $LIMIT Request Pages from All Logs:"
    echo "==================================="
    zgrep '-' --no-filename $LOGFILE $LOGFILE_GZ \
        | filters \
        | request_pages \
        | wordcount \
        | sort_desc \
        | return_kv \
        | return_top_ten
    echo ""
}

get_referer_pages_all() {
    echo "Top $LIMIT Referer Pages from All Logs:"
    echo "==================================="
    zgrep '-' --no-filename $LOGFILE $LOGFILE_GZ \
        | filters \
        | referer_pages \
        | wordcount \
        | sort_desc \
        | return_kv \
        | return_top_ten
    echo ""
}

# executing
get_request_ips
get_request_methods
get_request_pages
get_referer_pages
get_request_pages_all
get_referer_pages_all
get_request_pages_404