#
# WWWOFFLE - World Wide Web Offline Explorer - Version 2.6d.
#
# WWWOFFLE Configuration file //etc/wwwoffle.conf
#
# Example configuration file Copyright 1997,98,99,2000,01 Andrew M. Bishop.
# They may be distributed under the GNU Public License, version 2, or
# any higher version.  See section COPYING of the GNU Public license
# for conditions under which this file may be redistributed.
#


#
# The configuration file (wwwoffle.conf) specifies all of the parameters that
# control the operation of the proxy server.  The file is split into sections
# each containing a series of parameters as described below.  The file
# CHANGES.CONF explains the changes in the configuration file between this
# version of the program and previous ones.
# 
# The file is split into sections, each of which can be empty or contain one or
# more lines of configuration information.  The sections are named and the order
# that they appear in the file is not important.
# 
# The general format of each of the sections is the same.  The name of the
# section is on a line by itself to mark the start.  The contents of the section
# are enclosed between a pair of lines containing only the '{' and '}'
# characters or the '[' and ']' characters.  When the '{' and '}' characters are
# used the lines between contain configuration information.  When the '[' and
# ']' characters are used the there must only be a single non-empty line between
# them that contains the name of a file (in the same directory) containing the
# configuration information for the section.
# 
# Comments are marked by a '#' character at the start of the line and they are
# ignored.  Blank lines are also allowed and ignored.
# 
# The phrases URL-SPECIFICATION (or URL-SPEC for short) and WILDCARD have
# specific meanings in the configuration file and are described at the end.  Any
# item enclosed in '(' and ')' in the descriptions means that it is a parameter
# supplied by the user, anything enclosed in '[' and ']' is optional, the '|'
# symbol is used to denote alternate choices.  Some options apply to specific
# URLs only, this is indicated by having a URL-SPECIFICATION enclosed between
# '<' & '>' in the option, the first URL-SPECIFICATION to match is used.  If no
# URL-SPECIFICATION is given then it matches all URLs.
#


#
# StartUp
# -------
# 
# This contains the parameters that are used when the program starts, changes to
# these are ignored if the configuration file is re-read while the program is
# running.
# 
# bind-ipv4 = (hostname) | (ip-address) | none
#         Specify the hostname or IP address to bind the HTTP proxy and WWWOFFLE
#         control port sockets to using IPv4 (default='0.0.0.0').  If 'none' is
#         specified then no IPv4 socket is bound.
#
# bind-ipv6 = (hostname) | (ip-address) | none
#         Specify the hostname or IP address to bind the HTTP proxy and WWWOFFLE
#         control port sockets to using IPv6 (default='::').  If 'none' is
#         specified then no IPv6 socket is bound.  This requires the IPv6
#         compilation option.
#
# http-port = (port)
#         An integer specifying the port number for the HTTP proxy to use
#         (default=8080).
# 
# wwwoffle-port = (port)
#         An integer specifying the port number for the WWWOFFLE control
#         connections to use (default=8081).
# 
# spool-dir = (dir)
#         The full pathname of the top level cache directory (spool directory)
#         (default=/var/spool/wwwoffle).
# 
# run-uid = (user) | (uid)
#         The username or numeric uid to change to when the WWWOFFLE server is
#         started (default=none).  This option is not applicable to win32
#         and only works if the server is started by root on UNIX.
# 
# run-gid = (group) | (gid)
#         The groupname or numeric gid to change to when the WWWOFFLE server is
#         started (default=none).  This option is not applicable to win32
#         and only works if the server is started by root on UNIX.
# 
# use-syslog = yes | no
#         Whether to use the syslog facility for messages or not (default=yes).
# 
# password = (word)
#         The password used for authentication of the control pages, for
#         deleting cached pages etc (default=none).  For the password to be
#         secure the configuration file must be set so that only authorised
#         users can read it.
# 
# max-servers = (integer)
#         The maximum number of server processes that are started for online and
#         automatic fetching (default=8).
# 
# max-fetch-servers = (integer)
#         The maximum number of server processes that are started to fetch pages
#         that were marked in offline mode (default=4).  This value must be less
#         than max-servers or you will not be able to use WWWOFFLE interactively
#         online while fetching.
# 

StartUp
{
 bind-ipv4         = 0.0.0.0
#bind-ipv6         = ::

 http-port         = 8080
 wwwoffle-port     = 8081

 spool-dir         = /var/spool/wwwoffle

#run-uid           = daemon
#run-gid           = daemon

 use-syslog        = yes

 password          = none

 max-servers       = 8
 max-fetch-servers = 4
}


#
# Options
# -------
# 
# Options that control how the program works.
# 
# log-level = debug | info | important | warning | fatal
#         The minimum log level for messages in syslog or stderr
#         (default=important).
# 
# socket-timeout = (time)
#         The time in seconds that WWWOFFLE will wait for data on a socket
#         connection before giving up (default=120).
# 
# dns-timeout = (time)
#         The time in seconds that WWWOFFLE will wait for a DNS (Domain Name
#         Service) lookup before giving up (default=60).
# 
# connect-timeout = (time)
#         The time in seconds that WWWOFFLE will wait for the socket connection
#         to be made before giving up (default=30).
# 
# connect-retry = yes | no
#         If a connection cannot be made to a remote server then WWWOFFLE should
#         try again after a short delay (default=no).
# 
# ssl-allow-port = (integer)
#         A port number that is allowed to be proxied for Secure Socket Layer
#         (SSL) connections, e.g. https.  This option should be set to 443 to
#         allow https, there can be more than one ssl-port entry for other ports
#         as required.
# 
# dir-perm = (octal int)
#         The directory permissions to use when creating spool directories
#         (default=0755).  This option overrides the umask of the user and must
#         be in octal starting with a '0'.
# 
# file-perm = (octal int)
#         The file permissions to use when creating spool files (default=0644).
#         This option overrides the umask of the user and must be in octal
#         starting with a '0'.
# 
# run-online = (filename)
#         The name of a program to run when WWWOFFLE is switched to online mode
#         (default=none).  The program is started with a single parameter set to
#         the current mode name "online".
# 
# run-offline = (filename)
#         The name of a program to run when WWWOFFLE is switched to offline mode
#         (default=none).  The program is started with a single parameter set to
#         the current mode name "offline".
# 
# run-autodial = (filename)
#         The name of a program to run when WWWOFFLE is switched to autodial
#         mode (default=none).  The program is started with a single parameter
#         set to the current mode name "autodial".
#
# run-fetch = (filename)
#         The name of a program to run when a WWWOFFLE fetch starts or stops
#         (default=none).  The program is started with two parameters, the first
#         is the word "fetch" and the second is "start" or "stop".
#
# lock-files = yes | no
#         Enable the use of lock files to stop more than one WWWOFFLE process
#         from downloading the same URL at the same time (default=no).
#
# reply-compressed-data = yes | no
#         If the replies that are made to the browser are to contain compressed
#         data when requested (default=no).  Requires zlib compilation option.
#

Options
{
 log-level             = important

 socket-timeout        = 120
 dns-timeout           = 60
 connect-timeout       = 30

 connect-retry         = no

 ssl-allow-port        = 443

 dir-perm              = 0755
 file-perm             = 0644

 lock-files            = no

 reply-compressed-data = no
}


#
# OnlineOptions
# -------------
# 
# Options that control how WWWOFFLE behaves when it is online.
# 
# [<URL-SPEC>] request-changed = (time)
#         While online pages will only be fetched if the cached version is older
#         than this specified time in seconds (default=600).  Setting this value
#         negative will indicate that cached pages are always used while online.
#         Longer times can be specified with a 'm', 'h', 'd' or 'w' suffix for
#         minutes, hours, days or weeks (e.g. 10m=600).
# 
# [<URL-SPEC>] request-changed-once = yes | no
#         While online pages will only be fetched if the cached version has not
#         already been fetched once this session online (default=yes).  This
#         option takes precedence over the request-changed option.
# 
# [<URL-SPEC>] request-expired = yes | no
#         While online pages that have expired will always be requested again
#         (default=no).  This option takes precedence over the request-changed
#         and request-changed-once options.
# 
# [<URL-SPEC>] request-no-cache = yes | no
#         While online pages that ask not to be cached will always be requested
#         again (default=no).  This option takes precedence over the
#         request-changed and request-changed-once options.
# 
# [<URL-SPEC>] try-without-password = yes | no
#         If a request is made for a page that contains a username and password
#         then a request is made for the same page without a username and
#         password specified (default=yes).  This allows for requests for the
#         page without a password to re-direct the browser to the passworded
#         version.
# 
# [<URL-SPEC>] intr-download-keep = yes | no
#         If the browser closes the connection while online the currently
#         downloaded incomplete page should be kept (default=no).
# 
# [<URL-SPEC>] intr-download-size = (integer)
#         If the browser closes the connection while online the page should
#         continue to download if it is smaller than this size in kB
#         (default=1).
# 
# [<URL-SPEC>] intr-download-percent = (integer)
#         If the browser closes the connection while online the page should
#         continue to download if it is more than this percentage complete
#         (default=80).
# 
# [<URL-SPEC>] timeout-download-keep = yes | no
#         If the server connection times out while reading then the currently
#         downloaded incomplete page should be kept (default=no).
#
# [<URL-SPEC>] request-compressed-data = yes | no
#         If the requests that are made to the server are to request compressed
#         data (default=yes).  Requires zlib compilation option.
#

OnlineOptions
{
 request-changed       = 10m

 request-changed-once  = yes

 request-expired       = no

 request-no-cache      = no

 try-without-password  = yes

 intr-download-keep    = no
 intr-download-size    = 1
 intr-download-percent = 80

 timeout-download-keep = no

 request-compressed-data = yes
}


#
# OfflineOptions
# --------------
# 
# [<URL-SPEC>] pragma-no-cache = yes | no
#         Whether to request a new copy of a page if the request from the
#         browser has 'Pragma: no-cache' (default=yes).  This option option
#         should be set to 'no' if when browsing offline all pages are
#         re-requested by a 'broken' browser.
# 
# [<URL-SPEC>] confirm-requests = yes | no
#         Whether to return a page requiring user confirmation instead of
#         automatically recording requests made while offline (default=no).
# 
# [<URL-SPEC>] dont-request = yes | no
#         Do not request any URLs that match this when offline (default=no).
# 

OfflineOptions
{
 pragma-no-cache  = yes

 confirm-requests = no

#### Example ####
# Dont request any URLs at all when offline.
# <*://*/*> dont-request = yes
}


#
# FetchOptions
# ------------
# 
# Options that control what is downloaded when fetching pages that were
# requested while offline.
# 
# stylesheets = yes | no
#         If style sheets are to be fetched (default=no).
# 
# images = yes | no
#         If images are to be fetched (default=no).
# 
# webbug-images = yes | no
#         If images that are 1 pixel square are also to be fetched, requires
#         the images option to also be selected. (default=yes).
#         This option is intended to be used in conjunction with the
#         replace-webbug-images option in the ModifyHTML section.
#
# frames = yes | no
#         If frames are to be fetched (default=no).
# 
# scripts = yes | no
#         If scripts (e.g. Javascript) are to be fetched (default=no).
# 
# objects = yes | no
#         If objects (e.g. Java class files) are to be fetched (default=no).
#

FetchOptions
{
 stylesheets = yes

 images      = yes

 frames      = yes

 scripts     = no

 objects     = no
}


#
# IndexOptions
# ------------
# 
# Options that control what is displayed in the indexes.
# 
# no-lasttime-index = yes | no
#         Disables creation of the lasttime/prevtime indexes (default=no).
# 
# <URL-SPEC> list-outgoing = yes | no
#         Choose if the URL is to be listed in the outgoing index (default=yes).
# 
# <URL-SPEC> list-latest = yes | no
#         Choose if the URL is to be listed in the lasttime/prevtime and
#         lastout/prevout indexes (default=yes).
# 
# <URL-SPEC> list-monitor = yes | no
#         Choose if the URL is to be listed in the monitor index (default=yes).
# 
# <URL-SPEC> list-host = yes | no
#         Choose if the URL is to be listed in the host indexes (default=yes).
# 
# <URL-SPEC> list-any = yes | no
#         Choose if the URL is to be listed in any of the indexes (default=yes).
#

IndexOptions
{
 no-lasttime-index    = no

#### Example ####
# Don't index any hosts in the barfoo.com domain.
# <*://*.barfoo.com/> list-any = no
# Don't index any gif or jpg files in the lasttime index.
# <*://*/*.gif> list-latest = no
# <*://*/*.jpg> list-latest = no
}


#
# ModifyHTML
# ----------
# 
# Options that control how the HTML that is provided from the cache is modified.
# 
# [<URL-SPEC>] enable-modify-html = yes | no
#         Enable the HTML modifications in this section (default=no).  With this
#         option disabled the following HTML options will not have any effect.
#         With this option enabled there is a small speed penalty.
# 
# [<URL-SPEC>] enable-modify-online = yes | no
#         Enable the modifications in this section to take place when online as
#         well as when offline (default=no).  This will cause the HTML or GIF
#         to not appear in the browser until WWWOFFLE has processed it all.
#         This still does not apply to pages that are not cached.
#
# [<URL-SPEC>] add-cache-info = yes | no
#         At the bottom of all of the spooled pages the date that the page was
#         cached and some navigation buttons are to be added (default=no).
# 
# [<URL-SPEC>] anchor-cached-begin = (HTML code)
#         Anchors (links) in the spooled page that are in the cache are to have
#         the specified HTML inserted at the beginning (default="").
# 
# [<URL-SPEC>] anchor-cached-end = (HTML code)
#         Anchors (links) in the spooled page that are in the cache are to have
#         the specified HTML inserted at the end (default="").
# 
# [<URL-SPEC>] anchor-requested-begin = (HTML code)
#         Anchors (links) in the spooled page that have been requested for
#         download are to have the specified HTML inserted at the beginning
#         (default="").
# 
# [<URL-SPEC>] anchor-requested-end = (HTML code)
#         Anchors (links) in the spooled page that have been requested for
#         download are to have the specified HTML inserted at the end
#         (default="").
# 
# [<URL-SPEC>] anchor-not-cached-begin = (HTML code)
#         Anchors (links) in the spooled page that are not in the cache or
#         requested are to have the specified HTML inserted at the beginning
#         (default="").
# 
# [<URL-SPEC>] anchor-not-cached-end = (HTML code)
#         Anchors (links) in the spooled page that are not in the cache or
#         requested are to have the specified HTML inserted at the end
#         (default="").
# 
# [<URL-SPEC>] disable-script = yes | no
#         Removes all scripts and scripted events (default=no).
# 
# [<URL-SPEC>] disable-applet = yes | no
#         Removes all Java applets (default=no).
# 
# [<URL-SPEC>] disable-style = yes | no
#         Removes all stylesheets and style references (default=no).
#
# [<URL-SPEC>] disable-blink = yes | no
#         Removes the <blink> tag (default=no).
# 
# [<URL-SPEC>] disable-meta-refresh = yes | no
#         Removes any meta tags in the HTML header that re-direct the browser to
#         change to another page after an optional delay (default=no).
# 
# [<URL-SPEC>] disable-meta-refresh-self = yes | no
#         Removes any meta tags in the HTML header that re-direct the browser to
#         reload the same page after a delay (default=no).
# 
# [<URL-SPEC>] disable-dontget-links  = yes | no
#         Disables any links to URLs that are in the DontGet section of the
#         configuration file (default=no).
#
# [<URL-SPEC>] replace-dontget-images = yes | no
#         Replaces image URLs that are in the DontGet section of the
#         configuration file with a static URL (default=no).
#
# [<URL-SPEC>] replacement-dontget-image = (URL)
#         The replacement image to use for URLs that are in the DontGet section of
#         the configuration file (default=/local/dontget/replacement.gif).
#
# [<URL-SPEC>] replace-webbug-images = yes | no
#         Replaces image URLs that are 1 pixel square with a static URL
#         (default=no).
#         This option is intended to be used in conjunction with the
#         webbug-images option in the FetchOptions section.
#
# [<URL-SPEC>] replacement-webbug-image = (URL)
#         The replacement image to use for images that are 1 pixel square
#         (default=/local/dontget/replacement.gif).
#
# [<URL-SPEC>] demoronise-ms-chars = yes | no
#         Replaces strange characters that some Microsoft Applications put into
#         HTML with character equivalents that most browsers can display
#         (default=no).  The idea for this comes from the public domain
#         Demoroniser perl script.
# 
# [<URL-SPEC>] disable-animated-gif = yes | no
#         Disables the animation in animated GIF files (default=no).
#

ModifyHTML
{
 enable-modify-html        = no

 enable-modify-online      = no

 add-cache-info            = no

#anchor-cached-begin       = <font color="#00B000">
#anchor-cached-end         = </font>
#anchor-requested-begin    = <font color="#B0B000">
#anchor-requested-end      = </font>
#anchor-not-cached-begin   = <font color="#B00000">
#anchor-not-cached-end     = </font>

 disable-script            = no
 disable-applet            = no

 disable-style             = no

 disable-blink             = no

 disable-meta-refresh      = no
 disable-meta-refresh-self = no

 disable-dontget-links     = no
 replace-dontget-images    = no
 replacement-dontget-image = /local/dontget/replacement.gif

 replace-webbug-images     = no
 replacement-webbug-image  = /local/dontget/replacement.gif

 demoronise-ms-chars       = no

 disable-animated-gif      = no
}


#
# LocalHost
# ---------
# 
# A list of hostnames that the host running the WWWOFFLE server may be known by.
# This is so that the proxy does not need to contact itself if the request has a
# different name for the same server.
# 
# (host)
#         A hostname or IP address that in connection with the port number (in
#         the StartUp section) specifies the WWWOFFLE proxy HTTP server.  The
#         hostnames must match exactly, it is not a WILDCARD match.  The first
#         named host is used as the server name for several features so must be
#         a name that will work from any client host on the network.  None of
#         the hosts named here are cached or fetched via a proxy.
#

LocalHost
{
 localhost
 127.0.0.1

#### Example ####
# The server is on www.foo.com, with IP address 11.22.33.44.
# www.foo.com
# 11.22.33.44
}


#
# LocalNet
# --------
# 
# A list of hostnames whose web servers are always accessible even when offline
# and are not to be cached by WWWOFFLE because they are on a local network.
# 
# (host)
#         A hostname or IP address that is always available and is not to be
#         cached by WWWOFFLE.  The host name matching uses WILDCARDs.  A host
#         can be excluded by appending a '!' to the start of the name, all
#         possible aliases and IP addresses for the host are also required.  All
#         entries here are assumed to be reachable even when offline.  None of
#         the hosts named here are cached or fetched via a proxy.
#

LocalNet
{

#### Example ####
# The local domain is foo.com so don't cache any hosts in it.
# *.foo.com
}


#
# AllowedConnectHosts
# -------------------
# 
# A list of client hostnames that are allowed to connect to the server.
# 
# (host)
#         A hostname or IP address that is allowed to connect to the server.
#         The host name matching uses WILDCARDs.  A host can be excluded by
#         appending a '!' to the start of the name, all possible aliases and IP
#         addresses for the host are also required.  All of the hosts named in
#         LocalHost are also allowed to connect.
#

AllowedConnectHosts
{

#### Example ####
# Only allow connections from hosts in the foo.com domain.
# *.foo.com
}


#
# AllowedConnectUsers
# -------------------
# 
# A list of the users that are allowed to connect to the server and their
# passwords.
# 
# (username):(password)
#         The username and password of the users that are allowed to connect to
#         the server.  If this section is left empty then no user authentication
#         is done.  The username and password are both stored in plaintext
#         format.  This requires the use of browsers that handle the HTTP/1.1
#         proxy authentication standard.
#

AllowedConnectUsers
{

#### Example ####
# Only allow connections from this one user.
# andrew:password
}


#
# DontCache
# ---------
# 
# A list of URLs that are not to be cached by WWWOFFLE.
# 
# [!]URL-SPECIFICATION
#         Do not cache any URLs that match this.  The URL-SPECIFICATION can be
#         negated to allow matches to be cached.  The URLs will not be requested
#         if offline.
#

DontCache
{

#### Example ####
# Don't cache any hosts in the barfoo.com domain.
# *://*.barfoo.com/
# Don't cache any gzipped or tar files.
# *://*/*.gz
# *://*/*.tar
# Don't cache any files from /volatile in the foo.com domain.
# *://*.foo.com/volatile/*
}


#
# DontGet
# -------
# 
# A list of URLs that are not to be got by WWWOFFLE (because they contain only
# junk adverts for example).
# 
# [!]URL-SPECIFICATION
#         Do not get any URLs that match this.  The URL-SPECIFICATION can be
#         negated to allow matches to be got.
# 
# [<URL-SPEC>] replacement = (URL)
#         The URL to use to replace any URLs that match the URL-SPECIFICATIONs
#         instead of using the standard error message (default=none).  The URLs
#         in /local/dontget/ are suggested replacements (e.g. replacement.gif or
#         replacement.png which are 1x1 pixel transparent images or
#         replacement.js which is an empty javascript file).
# 
# <URL-SPEC> get-recursive = yes | no
#         Choose whether to get URLs that match this when doing a recursive
#         fetch (default=yes).
#
# <URL-SPEC> location-error = yes | no
#         When a URL reply contains a 'Location' header that redirects to a URL
#         that is not got (specified in this section) then the reply is modified
#         to be an error message instead (default=no).  This will stop ISP
#         proxies from redirecting users to adverts if the advert URLs are
#         in this section.
#

DontGet
{

# <*://*/*.gif> replacement = /local/dontget/replacement.gif
# <*://*/*.png> replacement = /local/dontget/replacement.png
# <*://*/*.js>  replacement = /local/dontget/replacement.js
# replacement = /local/dontget/replacement.gif

#### Example ####
# Don't get from any hosts in the barfoo.com domain.
# *://*.barfoo.com/
# Don't get any gzipped or tar files.
# *://*/*.gz
# *://*/*.tar
# Don't get any files from /adverts in the foo.com domain.
# *://*.foo.com/adverts*
# Dont get any gzipped or tar files when getting recursively.
# <*://*/*.gz>  get-recursive = no
# <*://*/*.tar> get-recursive = no
}


#
# DontCompress
# ------------
#
# A list of MIME types and file extensions that are not to be compressed by
# WWWOFFLE (because they are already compressed or not not worth compressing).
# Requires zlib compilation option.
#
# mime-type = (mime-type)/(subtype)
#         The MIME type of a URL that is not to be compressed in the cache or when
#         providing compressed pages to browsers.
#
# file-ext = .(file-ext)
#         The file extension of a URL that is not to be requested compressed from
#         a server.
#

DontCompress
{
 mime-type = image/gif
 mime-type = image/jpeg
 mime-type = image/png
 mime-type = image/tiff

 mime-type = video/x-msvideo
 mime-type = video/quicktime
 mime-type = video/mpeg

 mime-type = audio/basic
 mime-type = audio/x-wav

 mime-type = application/x-dvi
 mime-type = application/pdf
 mime-type = application/zip

 mime-type = application/x-ns-proxy-autoconfig

 file-ext = .gz
 file-ext = .bz
 file-ext = .bz2
 file-ext = .Z

 file-ext = .zip
 file-ext = .tgz

 file-ext = .rpm
 file-ext = .deb

 file-ext = .gif
 file-ext = .GIF
 file-ext = .jpg
 file-ext = .JPG
 file-ext = .jpeg
 file-ext = .JPEG
 file-ext = .png
 file-ext = .PNG
}


#
# CensorHeader
# ------------
# 
# A list of HTTP header lines that are to be removed from the requests sent to
# web servers and the replies that come back from them.
# 
# [<URL-SPEC>] (header) = yes | no | (string)
#         A header field name (e.g. From, Cookie, Set-Cookie, User-Agent) and
#         the string to replace the header value with (default=no).  The header
#         is case sensitive, and does not have a ':' at the end.  The value of
#         "no" means that the header is unmodified, "yes" or no string can be
#         used to remove the header or a string can be used to replace the
#         header.  This only replaces headers it finds, it does not add any new
#         ones.
# 
# [<URL-SPEC>] referer-self = yes | no
#         Sets the Referer header to the same as the URL being requested
#         (default = no).
# 
# [<URL-SPEC>] referer-self-dir = yes | no
#         Sets the Referer header to the directory name of the URL being
#         requested (default = no).  This option takes precedence over
#         referer-self.
#

CensorHeader
{

### Example ###
# Don't send the username.
# From = yes
# Don't accept Cookies
# Set-Cookie = yes
# Don't send Cookies back
# Cookie = yes
# Lie about the Browser type.
# User-Agent = WWWOFFLE/2.6
}


#
# FTPOptions
# ----------
# 
# Options to use when fetching files using the ftp protocol.
# 
# anon-username = (string)
#         The username to use for anonymous ftp (default=anonymous).
# 
# anon-password = (string)
#         The password to use for anonymous ftp (default determined at run
#         time).  If using a firewall then this may contain a value that is not
#         valid to the FTP server and may need to be set to a different value.
# 
# <URL-SPEC> auth-username = (string)
#         The username to use on a host instead of the default anonymous
#         username.
# 
# <URL-SPEC> auth-password = (string)
#         The password to use on a host instead of the default anonymous
#         password.
#

FTPOptions
{
 anon-username = anonymous
#anon-password = 
}


#
# MIMETypes
# ---------
# 
# MIME Types to use when serving files that were not fetched using HTTP or for
# files on the built-in web-server.
# 
# default = (mime-type)/(subtype)
#         The default MIME type (default=text/plain).
# 
# .(file-ext) = (mime-type)/(subtype)
#         The MIME type to associate with a file extension.  The '.' must be
#         included in the file extension.  If more than one extension matches
#         then the longest one is used.
#

MIMETypes
{
 default  = text/plain

 .Z       = application/x-compress
 .au      = audio/basic
 .avi     = video/x-msvideo
 .class   = application/java
 .cpio    = application/x-cpio
 .css     = text/css
 .deb     = application/octet-stream
 .dtd     = application/xml
 .dvi     = application/x-dvi
 .eps     = application/postscript
 .gif     = image/gif
 .gz      = application/x-gzip
 .htm     = text/html
 .html    = text/html
 .jpeg    = image/jpeg
 .jpg     = image/jpeg
 .js      = application/x-javascript
 .latex   = application/x-latex
 .man     = application/x-troff-man
 .me      = application/x-troff-me
 .mov     = video/quicktime
 .mpeg    = video/mpeg
 .mpg     = video/mpeg
 .ms      = application/x-troff-ms
 .pac     = application/x-ns-proxy-autoconfig
 .pbm     = image/x-portable-bitmap
 .pdf     = application/pdf
 .pgm     = image/x-portable-graymap
 .png     = image/png
 .pnm     = image/x-portable-anymap
 .ppm     = image/x-portable-pixmap
 .ps      = application/postscript
 .ras     = image/x-cmu-raster
 .rgb     = image/x-rgb
 .rpm     = application/octet-stream
 .rtf     = application/rtf
 .snd     = audio/basic
 .tar     = application/x-tar
 .tcl     = application/x-tcl
 .tex     = application/x-tex
 .texi    = application/x-texinfo
 .texinfo = application/x-texinfo
 .tif     = image/tiff
 .tiff    = image/tiff
 .tr      = application/x-troff
 .txt     = text/plain
 .vr      = model/vrml
 .wav     = audio/x-wav
 .wrl     = model/vrml
 .xbm     = image/x-xbitmap
 .xml     = application/xml
 .xpm     = image/x-xpixmap
 .xwd     = image/x-xwindowdump
 .zip     = application/zip
}


#
# Proxy
# -----
# 
# This contains the names of the HTTP (or other) proxies to use external to the
# WWWOFFLE server machine.
# 
# [<URL-SPEC>] proxy = (host[:port])
#         The hostname and port on it to use as the proxy.
# 
# <URL-SPEC> auth-username = (string)
#         The username to use on a proxy host to authenticate WWWOFFLE to it.
#         The URL-SPEC in this case refers to the proxy and not the URL being
#         retrieved.
# 
# <URL-SPEC> auth-password = (string)
#         The password to use on a proxy host to authenticate WWWOFFLE to it.
#         The URL-SPEC in this case refers to the proxy and not the URL being
#         retrieved.
# 
# [<URL-SPEC>] ssl = (host[:port])
#         A proxy server that should be used for Secure Socket Layer (SSL)
#         connections e.g. https.  Note that for the <URL-SPEC> that only the host
#         is checked and that the other parts must be '*' WILDCARDs.
#

Proxy
{
 <http://*> proxy = none

#### Example ####
# Use www.foo.com as a default http proxy server on port 8080
# Except for the foo.com domain which has no proxy.
# <http://*>    proxy = www.foo.com:8080
# <*://foo.com> proxy = none
}


#
# Alias
# -----
# 
# A list of aliases that are used to replace the server name and path with
# another server name and path.  Also for servers known by two names.
# 
# URL-SPECIFICATION = URL-SPECIFICATION
#         Any requests that match the first URL-SPECIFICATION are replaced by
#         the second URL-SPECIFICATION.  The URL-SPECIFICATIONs must match
#         exactly, it is not a WILDCARD match, the URL arguments are ignored.
#

Alias
{

#### Example ####
# The http server www.bar.com is mirrored locally at www.bar-mirror.foo.com
# http://www.bar.com/ = http://www.bar-mirror.foo.com/
# The wwwoffle homepage can be aliased
# http://wwwoffle/ = http://www.gedanken.demon.co.uk/wwwoffle/
}


#
# Purge
# -----
# 
# The method to determine which pages to purge, the default age the host
# specific maximum age of the pages in days, and the maximum cache size.
# 
# use-mtime = yes | no
#         The method to use to decide which files to purge, last access time
#         (atime) or last modification time (mtime) (default=no).
# 
# max-size = (size)
#         The maximum size for the cache in MB after purging (default=0).  A
#         maximum cache size of 0 means there is no limit to the size.  If this
#         and the min-free options are both used the smaller cache size is
#         chosen.  This option take into account the URLs that are never purged
#         when measuring the cache size but will not purge them.
# 
# min-free = (size)
#         The minimum amount of free disk space in MB after purging (default=0).
#         A minimum disk free of 0 means there is no limit to the free space.
#         If this and the max-size options are both used the smaller cache size
#         is chosen.  This option take into account the URLs that are never
#         purged when measuring the cache size but will not purge them.
# 
# use-url = yes | no
#         If true then use the URL to decide on the purge age, otherwise use the
#         protocol and host only (default=no).
# 
# del-dontget = yes | no
#         If true then delete the URLs that match the entries in the DontGet
#         section (default=no).
# 
# del-dontcache = yes | no
#         If true then delete the URLs that match the entries in the DontCache
#         section (default=no).
# 
# [<URL-SPEC>] age = (age)
#         The maximum age in the cache for URLs that match this (default=14).
#         An age of zero means not to keep, negative not to delete.  The
#         URL-SPECIFICATION matches only the protocol and host unless use-url is
#         set to true. Longer times can be specified with a 'w', 'm' or 'y'
#         suffix for weeks, months or years (e.g. 2w=14).
#
# [<URL-SPEC>] compress-age = (age)
#         The maximum age in the cache for URLs that match this to be stored
#         uncompressed (default=-1).  Requires zlib compilation option.  The age
#         that is specified has the same meaning as for the age option.
# 

Purge
{
 use-mtime     = no

 max-size      = 0
 min-free      = 0

 use-url       = no

 del-dontget   = yes
 del-dontcache = yes

 age           = 4w

 compress-age  = -1

#### Example ####
# Expire hosts in the domain foo.com at 1 week except bar.foo.com at 2 weeks.
# <*://foo.com/>     age = 1w
# <*://bar.foo.com/> age = 2w
# Never keep anything in the domain bar.com except foo.bar.com is always kept.
# <*://bar.com/>     age = 0
# <*://foo.bar.com/> age = -1
#
# Keep ftp files for 7 days and http for 14.
# <ftp://*>  age = 7
# <http://*> age = 14
#
# Purge files to keep the cache below 100 MB
# max-size = 100
}


#
# WILDCARD
# --------
# 
# A WILDCARD match is one that uses the '*' character to represent any group of
# characters.
# 
# This is basically the same as the command line file matching expressions in
# DOS or the UNIX shell, except that the '*' can match the '/' character.  A
# maximum of 2 '*' characters can be used in any WILDCARD.
# 
# For example
# 
# *.gif      matches  foo.gif and bar.gif
# *.foo.com  matches  www.foo.com and ftp.foo.com
# /foo/*     matches  /foo/bar.html and /foo/bar/foobar.html
#
#
# URL-SPECIFICATION
# -----------------
# 
# When specifying a host and protocol and pathname in many of the sections a
# URL-SPECIFICATION can be used, this is a way of recognising a URL.
# 
# For the purposes of this explanation a URL is considered to be made up of five
# parts.
# 
# proto          The protocol that is used (e.g. 'http', 'ftp')
# host           The server hostname (e.g. 'www.gedanken.demon.co.uk').
# port           The port number on the host (e.g. default of 80 for HTTP).
# path           The pathname on the host (e.g. '/bar.html') or a directory name
#                (e.g. '/foo/').
# args           Optional arguments with the URL used for CGI scripts etc.
#                (e.g. 'search=foo').
# 
# For example the WWWOFFLE homepage: http://www.gedanken.demon.co.uk/wwwoffle/
# The protocol is 'http', the host is 'www.gedanken.demon.co.uk', the port is
# the default (in this case 80), and the pathname is '/wwwoffle/'.
# 
# In general this is written as (proto)://(host)[:(port)]/(path)[?(args)]
# 
# Where [] indicates an optional feature, and () indicate a user supplied name
# or number.
# 
# Some example URL-SPECIFICATION options are the following:
# 
# *://*              Any protocol, Any host, Any port, Any path, Any args
#                    (This is that same as saying 'default').
# 
# *://*/(path)       Any protocol, Any host, Any port, Named path, Any args
# 
# *://*/*.(ext)      Any protocol, Any host, Any port, Named path, Any args
# 
# *://*/*?           Any protocol, Any host, Any port, Any path, No args
# 
# *://(path)?*       Any protocol, Any host, Any port, Named path, Any args
# 
# *://(host)         Any protocol, Named host, Any port, Any path, Any args
# 
# (proto)://         Named protocol, Any host, Any port, Any path, Any args
# 
# (proto)://(host)   Named protocol, Named host, Any port, Any path, Any args
# 
# (proto)://(host):  Named protocol, Named host, Default port, Any path Any args
# 
# *://(host):(port)  Any protocol, Named host, Named port, Any path, Any args
# 
# The matching of the host, the path and the args use the WILDCARD matching that
# is described above.
# 
# 
# In some sections that accept URL-SPECIFICATIONs they can be negated by
# inserting the '!' character before it.  This will mean that the comparison
# of a URL with the URL-SPECIFICATION will return the logically opposite value
# to what would be returned without the '!'.  If all of the URL-SPECIFICATIONs
# in a section are negated and '*://*/*' is added to the end then the sense of
# the whole section is negated.
#