files/0.5.4/webdruid.conf

webdruid.conf (text/plain), 24.70 KB, created by Niko on 2005-10-12 14:59:00 UTC

#
# Sample WebDruid configuration file
# Copyright 2003, 2004 by Fabien Chevalier <[e-mail]>
#
# Distributed under the GNU General Public License.  See the
# files "Copyright" and "COPYING" provided with the webalizer
# distribution for additional information.
#
# This is a sample configuration file for the WebDruid (ver 0.5.0)
# 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.
#
# The WebDruid will look for a 'default' configuration
# file named "webdruid.conf" in the current directory, and if not found
# there, will look for "/etc/webdruid/webdruid.conf".


# LogFile defines the web server log(s) file(s) to use.
# To use multiple logs files (for instance to generate statistics for
# a cluster of Apache servers), you can use the directive LogFile more
# than oncee.
# If no 'LogFile' is specified
# here or 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/log/apache/access_log

# LogType defines the log type being processed.  Normally, the WebDruid
# expects a CLF or Combined web server log as input.  Using this option,
# you can process w3c logs (IIS) as well.  Values can
# be 'clf' or 'w3c', with 'clf' the default.

#LogType	clf

# 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      DIR

######################################################################
# Development Area
# These options will be part of a future release of the WebDruid
# DO NOT EDIT
######################################################################

# Turns on new XML output engine.
# This is used for development tests.
# Defaults to no.

#XMLOutput yes

# Many people are only interested in a subset of WebDruid's statistics,
# or do not like the way output is done.
# So The WebDruid has the ability to support more than one output format.
# They are called 'Skins', as some popular music playing software ;-)
# Currently only one skin is shipped with, the 'classic' skin.
# You can also totally disable human readable output support, by
# setting 'Skin' to 'null'. You will then have to deal manually with raw
# XML files.

#Skin null

######################################################################

# 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.  The WebDruid 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
# The WebDruid 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 'incremental.1' is used to store the current state data,
# and is located in the output directory of the program. Please read at
# least the section on Incremental processing in the README file before
# you enable this option.

#Incremental	no

# FontFace is the True Type font face name. This font is used for
# drawing text inside charts. This is NOT the file name,
# this is the name that you would use in your favourite word processor
# when selecting this font. True Type fonts are searched in the path
# defined by the GDFONTPATH environment variable if it is set.
# If GDFONTPATH is not set, The WebDruid will look for fonts in the
# following directories:
#   - /usr/share/fonts/truetype/freefont
#   - /usr/share/fonts/truetype
# The default fontname is "FreeSerif". It is part of the FreeFonts package,
# available at http://savannah.nongnu.org/projects/freefont/ .

#FontFace FreeSerif

# ReportTitle is the text to display as the title.  The hostname
# (unless blank) is appended to the end of this string (seperated 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, webalizer 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 embeded pages).

#HTMLExtension  html

# PageType lets you tell the WebDruid 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*','php*', 'cgi' and HTMLExtension
# if different for web logs).

PageType	htm*
PageType	cgi
#PageType	phtml
#PageType	php3
#PageType	pl
#PageType	jsp

# 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

# DNSCache specifies the DNS cache filename to use for reverse DNS lookups.
# This file must be specified if you wish to perform name lookups on any IP
# addresses found in the log file.  If an absolute path is not given as
# part of the filename (ie: starts with a leading '/'), then the name is
# relative to the default output directory.  See the DNS.README file for
# additional information.

#DNSCache	dns_cache.db

# DNSChildren allows you to specify how many "children" processes are
# run to perform DNS lookups to create or update the DNS cache file.
# If a number is specified, the DNS cache file will be created/updated
# each time the WebDruid is run, immediately prior to normal processing,
# by running the specified number of "children" processes to perform
# DNS lookups.  If used, the DNS cache filename MUST be specified as
# well.  The default value is zero (0), which disables DNS cache file
# creation/updates at run time.  The number of children processes to
# run may be anywhere from 1 to 100, however a large number may effect
# normal system operations.  Reasonable values should be between 5 and
# 20.  See the DNS.README file for additional information.

#DNSChildren	0

# 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="The WebDruid">

# 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 apperance.
# 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
# alligned with the page.  Max string size is 80 characters.

#HTMLTail <IMG SRC="msfree.png" ALT="100% Micro$oft free!">

# 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>

# The Quiet option suppresses output messages... Useful when run
# as a cron job to prevent bogus e-mails.  Values can be either
# "yes" or "no".  Default is "no".  Note: this does not suppress
# warnings and errors (which are printed to stderr).

#Quiet		no

# ReallyQuiet will supress all messages including errors and
# warnings.  Values can be 'yes' or 'no' with 'no' being the
# default.  If 'yes' is used here, it cannot be overriden from
# the command line, so use with caution.  A value of 'no' has
# no effect.

#ReallyQuiet	no

# 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

# Debug prints additional information for error messages.  This
# will cause webalizer to dump bad records/fields instead of just
# telling you it found a bad one.   As usual, the value can be
# either "yes" or "no".  The default is "no".  It shouldn't be
# needed unless you start getting a lot of Warning or Error
# messages and want to see why.  (Note: warning and error messages
# are printed to stderr, not stdout like normal messages).

#Debug		no

# FoldSeqErr forces the WebDruid to ignore sequence errors.
# This is useful for Netscape and other web servers that cache
# the writing of log records and do not guarentee 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 usefull in certain situations.  If the
# history file is ignored, the main "index.html" file will only
# report on the current log files contents.  Usefull only when you
# want to reproduce the reports from scratch.  USE WITH CAUTION!
# Valid values are "yes" or "no".  Default is "no".

#IgnoreHist	no

#This keyword is used to either enable or disable the creation
#and display of the path graph. Path is...really a path, i mean
#a list of pages the user went to. What is displayed is only
#paths that were taken more than once. The drawback of this
#criteria is that if 200 users follow exactly the same path
#in your site, except for the last pages, they won't appear
#here because their path was different at the end. If anyone
#has an good algorithm to solve this issue, he should drop me
#a note. Another issue is because of client side and proxy
#caching. You can never know when a user goes back in your site.
#Default is "yes".

#PathGraph no

#This keyword is used to limit the number of path displayed by
#the path graph. Indicating here an inapropriate value will
#create a graph difficult to read, and dot will spend a lot
#CPU to create it.  Default is 10.

#PathGraphMaxPaths 10

#This keyword is used to either enable or disable the creation
#and display of the users flow graph. This graph tries to show
#you the flows of the users in your web site.
#Each node represents a page, and each edge is balanced by the
#number of hits from a page to another page. Default is "yes".

#UsersFlow no

#This keyword is used to limit the number of edges displayed by
#the users flow graph. Indicating here an inapropriate value will
#create a graph difficult to read, and dot will spend a lot
#CPU to create it.  Default is 30.

#UsersFlowMaxEdges 30

#Full path to dot utility location. Useful only if PathGraph or
#UsersFlow is set to yes. Default is /usr/bin/dot

#DotLocation /usr/local/bin/dot

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

#CountryGraph	yes

# 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

# 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.
# I personally am not crazy about them, but a lot of people requested
# them and they weren't a big deal to add.  The number represents the
# number of lines you want displayed.  Default is 2, you can disable
# the lines by using a value of zero ('0').  [max is 20]
# Note, due to rounding errors, some values don't work quite right.
# The lower the better, with 1,2,3,4,6 and 10 producing nice results.

#GraphLines	2

# 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 usernames default to 20.  Tables may be disabled
# by using zero (0) for the value.

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

# The All* keywords allow the display of all URL's, Sites, Referrers
# User Agents, Search Strings and Usernames.  If enabled, a seperate
# 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 visable, 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 seperate
# pages are generated for each month, which can consume quite a lot
# of disk space depending on the traffic to your site.

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

# The WebDruid 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 The WebDruid, 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 Hide*, Group* and Ignore* and Include* keywords allow you to
# change the way Sites, URL's, Referrers, User Agents and Usernames
# are manipulated.  The Ignore* keywords will cause The WebDruid 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 seperated 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 username
#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...)

#GroupAgent	MSIE		Micro$oft Internet Exploder
#HideAgent	MSIE
#GroupAgent	Mozilla		Netscape
#HideAgent	Mozilla
#GroupAgent	Lynx*		Lynx
#HideAgent	Lynx*

# 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 hostnames
# 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 diferentiate 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

# The Ignore* keywords allow you to completely ignore log records based
# on hostname, URL, user agent, referrer or username.  I hessitated in
# adding these, since the WebDruid 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 username.  They take
# precidence over the Ignore* keywords.  Note: Using Ignore/Include
# combinations to selectivly process parts of a web site is _extremely
# inefficent_!!! Avoid doing so if possible (ie: grep the records to a
# seperate 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 username
#IgnoreUser     *
#IncludeUser    someuser

# The MangleAgents allows you to specify how much, if any, The WebDruid
# 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
# supression.  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 Dump* keywords allow the dumping of Sites, URL's, Referrers
# User Agents, Usernames and Search strings to seperate 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/log/apache

# 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 pickey 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

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