xref: /dports/www/awffull/awffull-3.10.2/sample.conf

/*
#   AWFFull - A Webalizer Fork, Full o' features
#
#   sample.conf
#       Sample configuration file
#
#   Copyright 1997-2000 by Bradford L. Barrett (brad@mrunix.net)
#   Copyright (C) 2004- 2008 by Stephen McInerney
#       (spm@stedee.id.au)
#
#   This file is part of AWFFull.
#
#   AWFFull is free software: you can redistribute it and/or modify
#   it under the terms of the GNU General Public License as published by
#   the Free Software Foundation, either version 3 of the License, or
#   (at your option) any later version.
#
#   AWFFull is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied warranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#   GNU General Public License for more details.
#
#   You should have received a copy of the GNU General Public License
#   along with AWFFull.  If not, see <http://www.gnu.org/licenses/>.
#
*/

# Sample AWFFull configuration file
#
# This is a sample configuration file for AWFFull (v3.8.1)
# Lines starting with pound signs '#' are comment lines and are
# ignored.  Blank lines are skipped as well.  Other lines are considered
# as configuration lines, and have the form "ConfigOption  Value" where
# ConfigOption is a valid configuration keyword, and Value is the value
# to assign that configuration option.  Invalid keyword/values are
# ignored, with appropriate warnings being displayed.  There must be
# at least one space or tab between the keyword and its value.
#
# AWFFull will look for a 'default' configuration file
# "/usr/local/etc/awffull.conf", and if found, use that.
# the '-c config.file' option can also be used to specify an alternate
# configuration file. Or multiple configuration files, with multiple -c's.


# LogFile defines the web server log file to use.  If not specified
# here or on on the command line, input will default to STDIN.  If
# the log filename ends in '.gz' (ie: a gzip compressed file), it will
# be decompressed on the fly as it is being read.

#LogFile        /var/lib/httpd/logs/access_log

# LogType defines the log type being processed.  Normally, AWFFull
# expects a CLF or Combined web server log as input.  Using this option,
# you can process ftp logs as well (xferlog as produced by wu-ftp and
# others), or Squid native logs.
# Values can be 'auto' 'clf', 'combined', 'ftp', 'domino' or 'squid', with
# 'auto' the default.
# The 'auto' value means that AWFFull will try and work out what log format
# you are sending to it. If no joy, AWFFull will immediately exit.

#LogType        auto

# OutputDir is where you want to put the output files.  This should
# should be a full path name, however relative ones might work as well.
# If no output directory is specified, the current directory will be used.

#OutputDir      .

# HistoryName allows you to specify the name of the history file produced
# by AWFFull.  The history file keeps the data for up to 12 months
# worth of logs, used for generating the main HTML page (index.html).
# The default is a file named "awffull.hist", stored in the specified
# output directory.  If you specify just the filename (without a path),
# it will be kept in the specified output directory.  Otherwise, the path
# is relative to the output directory, unless absolute (leading /).

#HistoryName    awffull.hist

# Incremental processing allows multiple partial log files to be used
# instead of one huge one.  Useful for large sites that have to rotate
# their log files more than once a month.  AWFFull will save its
# internal state before exiting, and restore it the next time run, in
# order to continue processing where it left off.  This mode also causes
# AWFFull to scan for and ignore duplicate records (records already
# processed by a previous run).  See the README file for additional
# information.  The value may be 'yes' or 'no', with a default of 'no'.
# The file 'awffull.current' is used to store the current state data,
# and is located in the output directory of the program (unless changed
# with the IncrementalName option below).  Please read at least the section
# on Incremental processing in the README file before you enable this option.

#Incremental    no

# IncrementalName allows you to specify the filename for saving the
# incremental data in.  It is similar to the HistoryName option where the
# name is relative to the specified output directory, unless an absolute
# filename is specified.  The default is a file named "awffull.current"
# kept in the normal output directory.  If you don't specify "Incremental"
# as 'yes' then this option has no meaning.

#IncrementalName        awffull.current

# ReportTitle is the text to display as the title.  The hostname
# (unless blank) is appended to the end of this string (separated with
# a space) to generate the final full title string.
# Default is (for English) "Usage Statistics for".

#ReportTitle    Usage Statistics for

# HostName defines the hostname for the report.  This is used in
# the title, and is prepended to the URL table items.  This allows
# clicking on URL's in the report to go to the proper location in
# the event you are running the report on a 'virtual' web server,
# or for a server different than the one the report resides on.
# If not specified here, or on the command line, awffull will
# try to get the hostname via a uname system call.  If that fails,
# it will default to "localhost".

#HostName       localhost

# HTMLExtension allows you to specify the filename extension to use
# for generated HTML pages.  Normally, this defaults to "html", but
# can be changed for sites who need it (like for PHP embedded pages).

#HTMLExtension  html

# PageType lets you tell AWFFull what types of URL's you
# consider a 'page'.  Most people consider html and cgi documents
# as pages, while not images and audio files.  If no types are
# specified, defaults will be used ('htm', 'html', 'cgi' and HTMLExtension
# if different for web logs, 'txt' for ftp logs).
# Putting the more likely page types first in the list should increase the
# speed of a run.
# Do Not Use Wildcards Here. It will not work.

PageType        htm
PageType        html
PageType        php
#PageType       pl
#PageType       cfm
#PageType       pdf
#PageType       txt
#PageType       cgi

# NotPageType is the direct and incompatible opposite of PageType.
# You can use one set or the other, but not both.
# PageType specifies what *is* a Page, NotPageType specifies what
# *isn't*, and hence by implication, everything else is a page.
# Neither method is more or lessor correct than the other. It's more
# what is more accurate for *your* site.
# Do not add the "." or use any wildcards. As a general rule.
# There are some assumed internal optimisations that may otherwise
# break.
# Those who understand pcre's would do well to examine the source
# of parser.c if they wish to extract greater flexibility from the
# below.

#NotPageType     gif
#NotPageType     css
#NotPageType     js
#NotPageType     jpg
#NotPageType     ico
#NotPageType     png

# CSSFilename is used to set the name of the CSS file to use in conjunction
# with the generated html. An existing file is *not* overwritten, so feel free
# to make you own changes to the default file.

#CSSFilename	awffull.css

# UseHTTPS should be used if the analysis is being run on a
# secure server, and links to urls should use 'https://' instead
# of the default 'http://'.  If you need this, set it to 'yes'.
# Default is 'no'.  This only changes the behaviour of the 'Top
# URL's' table.

#UseHTTPS       no

# HTMLPre defines HTML code to insert at the very beginning of the
# file.  Default is the DOCTYPE line shown below.  Max line length
# is 80 characters, so use multiple HTMLPre lines if you need more.

#HTMLPre <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">

# HTMLHead defines HTML code to insert within the <HEAD></HEAD>
# block, immediately after the <TITLE> line.  Maximum line length
# is 80 characters, so use multiple lines if needed.

#HTMLHead <META NAME="author" CONTENT="AWFFull">

# HTMLBody defined the HTML code to be inserted, starting with the
# <BODY> tag.  If not specified, the default is shown below.  If
# used, you MUST include your own <BODY> tag as the first line.
# Maximum line length is 80 char, use multiple lines if needed.

#HTMLBody <BODY BGCOLOR="#E8E8E8" TEXT="#000000" LINK="#0000FF" VLINK="#FF0000">

# HTMLPost defines the HTML code to insert immediately before the
# first <HR> on the document, which is just after the title and
# "summary period"-"Generated on:" lines.  If anything, this should
# be used to clean up in case an image was inserted with HTMLBody.
# As with HTMLHead, you can define as many of these as you want and
# they will be inserted in the output stream in order of appearance.
# Max string size is 80 characters.  Use multiple lines if you need to.

#HTMLPost       <BR CLEAR="all">

# HTMLTail defines the HTML code to insert at the bottom of each
# HTML document, usually to include a link back to your home
# page or insert a small graphic.  It is inserted as a table
# data element (ie: <TD> your code here </TD>) and is right
# aligned with the page.  Max string size is 80 characters.

#HTMLTail <IMG SRC="yourlogo.png" ALT="Company XYZ!">

# HTMLEnd defines the HTML code to add at the very end of the
# generated files.  It defaults to what is shown below.  If
# used, you MUST specify the </BODY> and </HTML> closing tags
# as the last lines.  Max string length is 80 characters.

#HTMLEnd </BODY></HTML>

# TimeMe allows you to force the display of timing information
# at the end of processing.  A value of 'yes' will force the
# timing information to be displayed.  A value of 'no' has no
# effect.

#TimeMe         no

# GMTTime allows reports to show GMT (UTC) time instead of local
# time.  Default is to display the time the report was generated
# in the timezone of the local machine, such as EDT or PST.  This
# keyword allows you to have times displayed in UTC instead.  Use
# only if you really have a good reason, since it will probably
# screw up the reporting periods by however many hours your local
# time zone is off of GMT.

#GMTTime        no

# FoldSeqErr forces AWFFull to ignore sequence errors.
# This is useful for Netscape and other web servers that cache
# the writing of log records and do not guarantee that they
# will be in chronological order.  The use of the FoldSeqErr
# option will cause out of sequence log records to be treated
# as if they had the same time stamp as the last valid record.
# Default is to ignore out of sequence log records.

#FoldSeqErr     no

# VisitTimeout allows you to set the default timeout for a visit
# (sometimes called a 'session').  The default is 30 minutes,
# which should be fine for most sites.
# Visits are determined by looking at the time of the current
# request, and the time of the last request from the site.  If
# the time difference is greater than the VisitTimeout value, it
# is considered a new visit, and visit totals are incremented.
# Value is the number of seconds to timeout (default=1800=30min)

#VisitTimeout   1800

# IgnoreHist shouldn't be used in a config file, but it is here
# just because it might be useful in certain situations.  If the
# history file is ignored, the main "index.html" file will only
# report on the current log files contents.  Useful only when you
# want to reproduce the reports from scratch.  USE WITH CAUTION!
# Valid values are "yes" or "no".  Default is "no".

#IgnoreHist     no

# TrackPartialRequests is used to track 206 codes. This gives two
# additional columns in the Top URLs tables.
# The first to "Hits" counts the number of partial requests
# The second to "Volume" counts the volume in partial requests
# This option is more of use to those with lots of PDF's.

#TrackPartialRequests    no

# CountryGraph allows the usage by country graph to be disabled.
# Values can be 'yes' or 'no', default is 'yes'.

#CountryGraph   yes

# GeoIP enables or disables the use of the GeoIP capability for more
# accurate detection of countries. Default is 'no'.
# NOTE! Do not enable GeoIP if you analyse files that have had the IP Address
# translated to a Fully Qualified Host Name.
# Use either raw IP Addresses and GeoIP, or Names and disable GeoIP.
# ie. Don't use GeoIP AND DNSHistory.

#GeoIP          no

# GeoIPDatabase is the location of the GeoIP database file. Default is
# '/usr/local/share/GeoIP/GeoIP.dat', which is where a default GeoIP
# install will put it. Note that the database is updated monthly.
# For the details see: http://www.maxmind.com/app/geoip_country

#GeoIPDatabase   /usr/local/share/GeoIP/GeoIP.dat

# FlagsLocation will enable the display of country flags in the country
# table. The path is that for a webserver, not file system. Can be
# relative or complete. The trailing slash is not necessary.

#FlagsLocation		flags

# DailyGraph and DailyStats allows the daily statistics graph
# and statistics table to be disabled (not displayed).  Values
# may be "yes" or "no". Default is "yes".

#DailyGraph     yes
#DailyStats     yes

# HourlyGraph and HourlyStats allows the hourly statistics graph
# and statistics table to be disabled (not displayed).  Values
# may be "yes" or "no". Default is "yes".

#HourlyGraph    yes
#HourlyStats    yes

# TopURLsbyHITsGraph - Display a pie chart of the top URLs by HITS
#TopURLsbyHitsGraph      yes
#TopURLsbyVolGraph       yes

# TopExitPagesGraph - Display Top Exit Pages Pie Chart
#   no     for don't display
#   hits   for by hits
#   visits for by visits
#TopExitPagesGraph    visits

# TopEntryPagesGraph - Display Top Entry Pages Pie Chart
#   no     for don't display
#   hits   for by hits
#   visits for by visits
#TopEntryPagesGraph    visits

# TopSitesbyPagesGraph - Display a pie chart of the Top Sites by Page Impressions
#TopSitesbyPagesGraph    yes

# TopSitesbyVolGraph - Display a pie chart of the Top Sites by Page Impressions
#TopSitesbyVolGraph    yes

# TopAgentsGraph - Display a pie chart of the Top User Agents (by pages)
#TopAgentsGraph         yes

# GraphLegend allows the color coded legends to be turned on or off
# in the graphs.  The default is for them to be displayed.  This only
# toggles the color coded legends, the other legends are not changed.
# If you think they are hideous and ugly, say 'no' here :)

#GraphLegend    yes

# GraphLines allows you to have index lines drawn behind the graphs.
# Anything other than "no" will enable the lines.

#GraphLines     yes

# YearlySubtotals will display the subtotal for a given year in the main
# page. This is in addition to the Grand Total of all years.

#YearlySubtotals         no

# The "Top" options below define the number of entries for each table.
# Defaults are Sites=30, URL's=30, Referrers=30 and Agents=15, and
# Countries=30. TopKSites and TopKURLs (by KByte tables) both default
# to 10, as do the top entry/exit tables (TopEntry/TopExit).  The top
# search strings and user names default to 20.  Tables may be disabled
# by using zero (0) for the value.
# Top404Errors, displays a table of error requests, and the corresponding
# referring URL.

#TopSites        30
#TopKSites       10
#TopURLs         30
#TopKURLs        10
#TopReferrers    30
#TopAgents       15
#TopCountries    30
#TopEntry        10
#TopExit         10
#TopSearch       20
#TopUsers        20
#Top404Errors    0

# The All* keywords allow the display of all URL's, Sites, Referrers
# User Agents, Search Strings and User names.  If enabled, a separate
# HTML page will be created, and a link will be added to the bottom
# of the appropriate "Top" table.  There are a couple of conditions
# for this to occur..  First, there must be more items than will fit
# in the "Top" table (otherwise it would just be duplicating what is
# already displayed).  Second, the listing will only show those items
# that are normally visible, which means it will not show any hidden
# items.  Grouped entries will be listed first, followed by individual
# items.  The value for these keywords can be either 'yes' or 'no',
# with the default being 'no'.  Please be aware that these pages can
# be quite large in size, particularly the sites page,  and separate
# pages are generated for each month, which can consume quite a lot
# of disk space depending on the traffic to your site.
# All404Errors displays a table of error requests, and the corresponding
# referring URL.

#AllSites       no
#AllURLs        no
#AllReferrers   no
#AllAgents      no
#AllSearchStr   no
#AllUsers       no
#All404Errors   no

# AWFFull normally strips the string 'index.' off the end of
# URL's in order to consolidate URL totals.  For example, the URL
# /somedir/index.html is turned into /somedir/ which is really the
# same URL.  This option allows you to specify additional strings
# to treat in the same way.  You don't need to specify 'index.' as
# it is always scanned for by AWFFull, this option is just to
# specify _additional_ strings if needed.  If you don't need any,
# don't specify any as each string will be scanned for in EVERY
# log record... A bunch of them will degrade performance.  Also,
# the string is scanned for anywhere in the URL, so a string of
# 'home' would turn the URL /somedir/homepages/brad/home.html into
# just /somedir/ which is probably not what was intended.

#IndexAlias     home.htm
#IndexAlias     homepage.htm

# The opposite (in a way) of IndexAlias is IgnoreIndexAlias.
# This will STOP any URL variable stripping, as well as ignoring the
# default "index." setting, or any that you set above.

#IgnoreIndexAlias no


# The Hide*, Group* and Ignore* and Include* keywords allow you to
# change the way Sites, URL's, Referrers, User Agents and User names
# are manipulated.  The Ignore* keywords will cause AWFFull to
# completely ignore records as if they didn't exist (and thus not
# counted in the main site totals).  The Hide* keywords will prevent
# things from being displayed in the 'Top' tables, but will still be
# counted in the main totals.  The Group* keywords allow grouping
# similar objects as if they were one.  Grouped records are displayed
# in the 'Top' tables and can optionally be displayed in BOLD and/or
# shaded. Groups cannot be hidden, and are not counted in the main
# totals. The Group* options do not, by default, hide all the items
# that it matches.  If you want to hide the records that match (so just
# the grouping record is displayed), follow with an identical Hide*
# keyword with the same value.  (see example below)  In addition,
# Group* keywords may have an optional label which will be displayed
# instead of the keywords value.  The label should be separated from
# the value by at least one 'white-space' character, such as a space
# or tab.
#
# The value can have either a leading or trailing '*' wildcard
# character.  If no wildcard is found, a match can occur anywhere
# in the string. Given a string "www.yourmama.com", the values "your",
# "*mama.com" and "www.your*" will all match.

# Your own site should be hidden
#HideSite       *mrunix.net
#HideSite       localhost

# Your own site gives most referrals
#HideReferrer   mrunix.net/

# This one hides non-referrers ("-" Direct requests)
#HideReferrer   Direct Request

# Usually you want to hide these
HideURL         *.gif
HideURL         *.GIF
HideURL         *.jpg
HideURL         *.JPG
HideURL         *.png
HideURL         *.PNG
HideURL         *.ra

# Hiding agents is kind of futile
#HideAgent      RealPlayer

# You can also hide based on authenticated user name
#HideUser       root
#HideUser       admin

# Grouping options
#GroupURL       /cgi-bin/*      CGI Scripts
#GroupURL       /images/*       Images

#GroupSite      *.aol.com
#GroupSite      *.compuserve.com

#GroupReferrer  yahoo.com/      Yahoo!
#GroupReferrer  excite.com/     Excite
#GroupReferrer  infoseek.com/   InfoSeek
#GroupReferrer  webcrawler.com/ WebCrawler

#GroupUser      root            Admin users
#GroupUser      admin           Admin users
#GroupUser      wheel           Admin users

# The following is a great way to get an overall total
# for browsers, and not display all the detail records.
# (You should use MangleAgent to refine further...)
#
# Simplified browser list for Webalizer. Copy & paste in awffull.conf,
#    replacing the original list.
#
# Longer version in http://griho.udl.es/webalizer/groupagent.txt
# Full version in http://griho.udl.es/webalizer/webalizer.conf.txt
#
# Version: 1.1 14/May/2005
#

# GroupAndHideAgent is equivalent to the two lines of a GroupAgent, then a HideAgent
GroupAndHideAgent       Googlebot                       Spider: Googlebot
GroupAndHideAgent       msnbot*                         Spider: MSNBot

GroupAndHideAgent       AppleWebKit/            Browser: Safari (OSX)
GroupAndHideAgent       Camino                  Browser: Camino (OSX)
GroupAndHideAgent       Epiphany                Browser: Epiphany (Gentoo)
GroupAndHideAgent       Firebird/               Browser: Firebird
GroupAndHideAgent       Firefox/                Browser: Firefox
GroupAndHideAgent       Galeon/                 Browser: Galeon
GroupAndHideAgent       Konqueror/              Browser: Konqueror
GroupAndHideAgent       Netscape6/              Browser: Netscape 6
GroupAndHideAgent       Netscape/7              Browser: Netscape 7
GroupAndHideAgent       Netscape/8              Browser: Netscape 8
GroupAndHideAgent       rv:1.                   Browser: Mozilla 1.x
GroupAndHideAgent       Opera                   Browser: Opera
GroupAndHideAgent       Mozilla/1               Browser: Netscape v1.xx
GroupAndHideAgent       Mozilla/2               Browser: Netscape v2.xx
GroupAndHideAgent       Mozilla/3.04Gold        Browser: Netscape 3.04 Gold
GroupAndHideAgent       Mozilla/3               Browser: Netscape v3.xx
GroupAndHideAgent       Mozilla/4.03            Browser: Netscape 4.03
GroupAndHideAgent       Mozilla/4.04            Browser: Netscape 4.04
GroupAndHideAgent       Mozilla/4.05            Browser: Netscape 4.05
GroupAndHideAgent       Mozilla/4.06            Browser: Netscape 4.06
GroupAndHideAgent       Mozilla/4.08            Browser: Netscape 4.08
GroupAndHideAgent       Mozilla/4.5             Browser: Netscape 4.5
GroupAndHideAgent       Mozilla/4.61            Browser: Netscape 4.6 (Mac/WinNT)
GroupAndHideAgent       Mozilla/4.6             Browser: Netscape 4.6 (Win95/Win98)
GroupAndHideAgent       Mozilla/4.72            Browser: Netscape 4.72
GroupAndHideAgent       Mozilla/4.73            Browser: Netscape 4.73
GroupAndHideAgent       Mozilla/4.75            Browser: Netscape 4.75
GroupAndHideAgent       Mozilla/4.76            Browser: Netscape 4.76
GroupAndHideAgent       Mozilla/4.77            Browser: Netscape 4.77
GroupAndHideAgent       Mozilla/4.78            Browser: Netscape 4.78
GroupAndHideAgent       Mozilla/4.79            Browser: Netscape 4.79
GroupAndHideAgent       Mozilla/4.7             Browser: Netscape 4.7
GroupAndHideAgent       Mozilla/4.8             Browser: Netscape 4.8
GroupAndHideAgent       Mozilla/5.0             Browser: Netscape 4.8
GroupAndHideAgent       "compatible; MSIE 6.0"  Browser: Internet Explorer 6.0 (Win)
GroupAndHideAgent       "compatible; MSIE 7.01" Spambot: Pretends to be MSIE 7.01
GroupAndHideAgent       "compatible; MSIE 7.0"  Browser: Internet Explorer 7.0 (Win)
GroupAndHideAgent       "compatible; MSIE 5.5"  Browser: Internet Explorer 5.5 (Win)
GroupAndHideAgent       "compatible; MSIE 5.01" Browser: Internet Explorer 5.01
# this 4.0 entry is matching Mozilla/4.0 which applies for every MSIE in the net, leave it commented
##GroupAgent    4.0                     Browser: Internet Explorer 4.0
##HideAgent     4.0
GroupAndHideAgent       4.5                     Browser: Internet Explorer 4.5
GroupAndHideAgent       5.0                     Browser: Internet Explorer 5.0
GroupAndHideAgent       5.12                    Browser: Internet Explorer 5.12 (Mac)
GroupAndHideAgent       5.13                    Browser: Internet Explorer 5.13 (Mac)
GroupAndHideAgent       5.14                    Browser: Internet Explorer 5.14 (Mac)
GroupAndHideAgent       5.15                    Browser: Internet Explorer 5.15 (Mac)
GroupAndHideAgent       5.16                    Browser: Internet Explorer 5.16 (Mac)
GroupAndHideAgent       5.17                    Browser: Internet Explorer 5.17 (Mac)
GroupAndHideAgent       5.21                    Browser: Internet Explorer 5.21 (Mac)
GroupAndHideAgent       5.22                    Browser: Internet Explorer 5.22 (Mac)
GroupAndHideAgent       5.23                    Browser: Internet Explorer 5.23 (Mac)
GroupAndHideAgent       "compatible; MSIE 5.0"  Browser: Internet Explorer 5.0
GroupAndHideAgent       "compatible; MSIE 4.5"  Browser: Internet Explorer 4.5
GroupAndHideAgent       3.0                     Browser: Internet Explorer 3.0  (win95)
GroupAndHideAgent       3.0B                    Browser: Internet Explorer 3.0B (win95)
GroupAndHideAgent       3.01                    Browser: Internet Explorer 3.01 (win95)
GroupAndHideAgent       4.01                    Browser: Internet Explorer 4.01

# we comment MSIE because many agents use it in their name to disguise as Internet Explorer
#####GroupAgent MSIE            Browser: Internet Explorer (unknown version)
#####HideAgent  MSIE


# HideAllSites allows forcing individual sites to be hidden in the
# report.  This is particularly useful when used in conjunction
# with the "GroupDomain" feature, but could be useful in other
# situations as well, such as when you only want to display grouped
# sites (with the GroupSite keywords...).  The value for this
# keyword can be either 'yes' or 'no', with 'no' the default,
# allowing individual sites to be displayed.

#HideAllSites   no


# The GroupDomains keyword allows you to group individual host names
# into their respective domains.  The value specifies the level of
# grouping to perform, and can be thought of as 'the number of dots'
# that will be displayed.  For example, if a visiting host is named
# cust1.tnt.mia.uu.net, a domain grouping of 1 will result in just
# "uu.net" being displayed, while a 2 will result in "mia.uu.net".
# The default value of zero disable this feature.  Domains will only
# be grouped if they do not match any existing "GroupSite" records,
# which allows overriding this feature with your own if desired.

#GroupDomains   0

# The GroupShading allows grouped rows to be shaded in the report.
# Useful if you have lots of groups and individual records that
# intermingle in the report, and you want to differentiate the group
# records a little more.  Value can be 'yes' or 'no', with 'yes'
# being the default.

#GroupShading   yes

# GroupHighlight allows the group record to be displayed in BOLD.
# Can be either 'yes' or 'no' with the default 'yes'.

#GroupHighlight yes


# Segmenting - segXXX
# Segmenting is a bit like the Ignore* and Include* keywords. Where it
# differs is in "remembering". Such that, as a "session" moves away from
# the original condition, that session is still tracked.
# So if you segment on a referral from Google, only sessions that were
# referred to the site from Google will be tracked. Even as they access
# other pages within the site.
# eg. Google -> Site Page 1 -> Site Page 2 -> Site Page 3
# Whereas Ignore/Include would only filter the first interaction.
# eg. Google -> Site Page 1
#
# By "session" it is meant that the time limitation of a session (typically
# 30 minutes timeout) will impact. So in the above example from Google, if
# the last step (from Page 2 to Page 3) occurred 31+ minutes after the Page 1
# to Page 2 transition, then this final step would NOT be included. The trail
# would be:
#   Google -> Site Page 1 -> Site Page 2
#
# Please do be aware that currently AWFFull uses IP Addresses to determine
# the continuation of a given session. This will be most flawed if you have
# a user population that sits behind corporate firewalls, or ISP Proxies.
# To mention two major problem areas.
#
# Why do Segmenting?
# http://judah.webanalyticsdemystified.com/2007/11/a-few-tips-on-web-analytics-segmentation.html
#  "Segment analysis will tell you different things about your audience than
#    you will realize from studying overall population metrics."
#  "The goal of segmentation is to maximize future value of that segment by
#    optimizing your marketing mix."
# With apologies to Judah for mixing his phrase order around. :-)

# Segment by Country
# Only track sessions that come from the following countries.
# This will be determined by:
# 1. Use of AssignToCountry overrides
# 2. GeoIP lookups if so configured and enabled
# 3. Hostname TLD. eg .au
# The third option is generally going to be the worst for accuracy.
# We have plenty of Australian IP addresses that are .com or .net etc.
# It is strongly advised to enable GeoIP if you wish to use this option.
#SegCountry AU
#SegCountry US
#SegCountry BR

# Segment by Referer
# Only track sessions that originated from the following referrers.
# NOTE!!!! SegReferer only works against the HOST name. Not the full URL.
#SegReferer *google.com.au
#SegReferer *yahoo.com.au
#SegReferer ninemsn


# The Ignore* keywords allow you to completely ignore log records based
# on hostname, URL, user agent, referrer or user name.  I hesitated in
# adding these, since the Webalizer was designed to generate _accurate_
# statistics about a web servers performance.  By choosing to ignore
# records, the accuracy of reports become skewed, negating why I wrote
# this program in the first place.  However, due to popular demand, here
# they are.  Use the same as the Hide* keywords, where the value can have
# a leading or trailing wildcard '*'.  Use at your own risk ;)

#IgnoreSite     bad.site.net
#IgnoreURL      /test*
#IgnoreReferrer file:/*
#IgnoreAgent    RealPlayer
#IgnoreUser     root


# The Include* keywords allow you to force the inclusion of log records
# based on hostname, URL, user agent, referrer or user name.  They take
# precedence over the Ignore* keywords.  Note: Using Ignore/Include
# combinations to selectively process parts of a web site is _extremely
# inefficient_!!! Avoid doing so if possible (ie: grep the records to a
# separate file if you really want that kind of report).

# Example: Only show stats on Joe User's pages...
#IgnoreURL      *
#IncludeURL     ~joeuser*

# Or based on an authenticated user name
#IgnoreUser     *
#IncludeUser    someuser


# The MangleAgents allows you to specify how much, if any, AWFFull
# should mangle user agent names.  This allows several levels of detail
# to be produced when reporting user agent statistics.  There are six
# levels that can be specified, which define different levels of detail
# suppression.  Level 5 shows only the browser name (MSIE or Mozilla)
# and the major version number.  Level 4 adds the minor version number
# (single decimal place).  Level 3 displays the minor version to two
# decimal places.  Level 2 will add any sub-level designation (such
# as Mozilla/3.01Gold or MSIE 3.0b).  Level 1 will attempt to also add
# the system type if it is specified.  The default Level 0 displays the
# full user agent field without modification and produces the greatest
# amount of detail.  User agent names that can't be mangled will be
# left unmodified.

#MangleAgents    0

# The SearchEngine keywords allow specification of search engines and
# their query strings on the URL.  These are used to locate and report
# what search strings are used to find your site.  The first word is
# a substring to match in the referrer field that identifies the search
# engine, and the second is the URL variable used by that search engine
# to define it's search terms.

SearchEngine    google.         q=
SearchEngine    yahoo.          p=
SearchEngine    msn.            q=
SearchEngine    search.aol      query=
SearchEngine    altavista.      q=
SearchEngine    lycos.          query=
SearchEngine    hotbot.         query=
SearchEngine    alltheweb.      query=
SearchEngine    infoseek.       qt=
SearchEngine    webcrawler      searchText=
SearchEngine    excite          search=
SearchEngine    netscape.       query=
SearchEngine    ask.com         q=
SearchEngine    webwombat.      ix=
SearchEngine    earthlink.      q=
SearchEngine    search.comcast. q=
SearchEngine    search.mywebsearch.     searchfor=
SearchEngine    reference.com   q=
SearchEngine    mamma.com       query=
# Last attempt catch all
SearchEngine    search.         q=


# AssignToCountry allows a form of override to force given domains
# to a specified country. Use the standard 2 letter country codes.
# Can also use org, com, net and so on, if more appropriate.
# With judicious use of the AllSites, GroupSite and 'whois', this
# can fairly easily cover all your majority users with not too much
# effort.

#AssignToCountry  *.bigpond.com           au
#AssignToCountry  *.internode.on.net      au
#AssignToCountry  203.36.*                au

#AssignToCountry  *.ntli.net              uk
#AssignToCountry  *.btcentralplus.com     uk


# The Dump* keywords allow the dumping of Sites, URL's, Referrers
# User Agents, User names and Search strings to separate tab delimited
# text files, suitable for import into most database or spreadsheet
# programs.
# DumpPath specifies the path to dump the files.  If not specified,
# it will default to the current output directory.  Do not use a
# trailing slash ('/').

#DumpPath       /var/lib/httpd/logs

# The DumpHeader keyword specifies if a header record should be
# written to the file.  A header record is the first record of the
# file, and contains the labels for each field written.  Normally,
# files that are intended to be imported into a database system
# will not need a header record, while spreadsheets usually do.
# Value can be either 'yes' or 'no', with 'no' being the default.

#DumpHeader     no

# DumpExtension allow you to specify the dump filename extension
# to use.  The default is "tab", but some programs are picky about
# the filenames they use, so you may change it here (for example,
# some people may prefer to use "csv").

#DumpExtension  tab

# These control the dumping of each individual table.  The value
# can be either 'yes' or 'no'.. the default is 'no'.

#DumpSites      no
#DumpURLs       no
#DumpReferrers  no
#DumpAgents     no
#DumpUsers      no
#DumpSearchStr  no
#DumpEntryPages no
#DumpExitPages  no
#DumpCountries  no


# This option controls how many years worth of data to display on the
# front summary page. In months.
#   eg: Display the last 5 years: 5 x 12 = 60
# IndexMonths     60


# The following Graph????X or Y options are used to modify the sizes of the
# created charts.
# The default settings are shown. The defaults are also the minimum settings.

# The main chart on the front page. Summary of all Months.
#GraphIndexX    512
#GraphIndexY    256

# The Day by Day Summary graph at the start of each Months Summary.
#GraphDailyX  512
#GraphDailyY  400

# The Hourly Average graph within each Months Summary.
#GraphHourlyX    512
#GraphHourlyY    256

# All pie charts are the same size.
#GraphPieX      512
#GraphPieY      300


# The custom  bar graph  and pie Colors are defined here.
# Declare them in the standard hexadecimal way (as HTML, but without the '#')
# If none are given, you will get the standard Webalizer colors.

#ColorHit       00805c
#ColorFile      0000ff
#ColorSite      ff8000
#ColorKbyte     ff0000
#ColorPage      00c0ff
#ColorVisit     ffff00

#PieColor1      800080
#PieColor2      80ffc0
#PieColor3      ff00ff
#PieColor4      ffc480

# End of configuration file...  Have a nice day!