#===============================================================================
#                                   General
#===============================================================================

# Base URL of this site. REQUIRED!

url = http://www.mysite.com/


#===============================================================================
#                                Database access
#===============================================================================

# These parameters are normally defined in the global configuration file, but
# each site can override them and keep its data in another database.

# Database plugin module to use. This parameter must match database attribute
# (defined in plugin.xml file) of a database interface plugin. A MySQL based
# plugin is included with Arch, but any other relational database plugin can be
# used as long as available. For a reference implementation, please see the MySQL
# plugin.

#database = MySQL


# Address of a database where to keep data. Note that DB related parameters
# can be re-defined for each site. Sites can store their data in different
# databases.

#target.db = jdbc:mysql://localhost/arch?user=<user name>&password=<password>


# DB driver to use 

#db.driver = com.mysql.jdbc.Driver

#===============================================================================
#                                Faceted search 
#===============================================================================

# To switch ON faceted search, just set at least one of the parameters below
# to true. Faceting parameters set for sites override root configuration if
# parameter "domain" is used in the request. Another method to  override faceting
# settings is to add facet=true and other Solr faceting parameters to the request.
# If Arch finds a "facet" field in request, it ignores configuration parameters.

facet.sites = true 
facet.areas = true 
facet.formats = true 


#===============================================================================
#                        Area configuration parameters                      
#===============================================================================

# THERE CAN BE AS MANY AREAS AS DESIRED, AS LONG AS NAMES ARE DIFFERENT


# Area name. Must be alphanumeric, up to 30 characters long.
# Use this name to define other area configuration parameters. 
# area = <area-name>

area = documentation


# Area status. Area can be either enabled or disabled. If disabled, it is not
# included in crawling and the index.
# enabled.<area-name> = {on,off}

enabled.documentation = on


# Roots - urls used as starting point to crawl the area. There is no practical
# limit on the number of roots, inclusions or exclusions per area.
# root.<area-name> = http://www.mysite.com/myarea/root-1
# root.<area-name> = http://www.mysite.com/myarea/root-2

root.documentation = http://www.mysite.com/myarea/root-1
root.documentation = http://www.mysite.com/myarea/root-2


# Inclusions - prefixes of urls to include in the area. Inclusions and
# exclusions combined define contents of the area.
# A url is included in the area if it is a root or matches (starts with) at
# least one inclusion and does not match any exclusions.
# include.<area-name> = http://www.mysite.com/myarea/include-1
# include.<area-name> = http://www.mysite.com/myarea/include-2

include.documentation = http://www.mysite.com/myarea/include-1
include.documentation = http://www.mysite.com/myarea/include-2


# Exclusions - prefixes of urls to exclude from the area.
# A url is excluded from the area if it matches (starts with) at elast 
# one exclusion. This allows to exclude certain subtrees of trees
# defined by includes.
# exclude.<area-name> = http://www.mysite.com/myarea/exclude-1
# exclude.<area-name> = http://www.mysite.com/myarea/exclude-2

exclude.documentation = http://www.mysite.com/myarea/include-1/exclude-1
exclude.documentation = http://www.mysite.com/myarea/include-1/exclude-2


# Re-indexing interval (days) with weekdays on which re-indexing is allowed.
# interval.<area-name> = NN [,sun][,mon][,tue][,wed][,thu][,fri][,sat]
# For example, to re-index area approx. every 20 days, but only on weekends:
# interval.<area-name> = 20, sat, sun

interval.documentation = 20, sat, sun


# Default crawling depth. Defines how many crawling iterations to do by default
# when indexing an area. Each area can overwrite this parameter. After deploying
# Arch, it is recommended to do a trial crawl with shallow depth, e.g. 2.
# If everything works, delete index directories, set the depth to a desired
# value and do a production crawl.
# A global value for this parameter can be defined in the global configuration
# file and re-defined for each area.
# NOTE: this parameter is ignored in parallel crawling (the global value is used)
# depth.<area-name> = 20

depth.documentation = 20


# Default max number of urls to fetch on each iteration. This is passed to Nutch
# as the topN parameter.
# Note: if defined, then the total size of an area index is limited to the depth 
# multiplied by max.urls
# A global value for this parameter can be defined in the global configuration
# file and re-defined for each area.
# NOTE: this parameter is ignored in parallel crawling (the global value is used)
# max.urls.<area-name> = -1

max.urls.documentation = -1


# Number of concurrent threads to use for crawling
# A global value for this parameter can be defined in the global configuration
# file and re-defined for each area.
# NOTE: this parameter is ignored in parallel crawling (the global value is used)
# threads.<area-name> = 10 

threads.documentation = 50 

#===============================================================================
#                  Loglinks area                    
#===============================================================================

# This area controls processing of links found in site logs, but not fetched
# by the crawler (e.g. isolated, orphan pages).

# Area name. Always "loglinks".

area = loglinks

# Area status. Area can be either enabled or disabled. If disabled, it is not
# included in crawling and the index.
# enabled.<area-name> = {on,off}

enabled.loglinks = on

# Depth of crawling. Note that setting this parameter to more than 2 will lead
# to high ovelaps with the sets of URLs already crawled.

depth.loglinks = 1

# Crawling interval

interval.loglinks = 1
 
#===============================================================================
#                        Bookmarks configuration parameters                      
#===============================================================================

# Each site can have a bookmarks area. This is a set of heterogenious URLs.
# No filtering is done. All bookmarks receive equal scores. If fetching of a
# bookmark fails, no re-fetching is done until next crawl.

# Area name. Always "bookmarks".

area = bookmarks

# Area status. Area can be either enabled or disabled. If disabled, it is not
# included in crawling and the index.
# enabled.<area-name> = {on,off}

enabled.bookmarks = on

# Bookmark files - files containing bookmark URLs. Adding or removing files,
# or changing their names triggers re-indexing of bookmarks. If relative paths
# are used, they must be based on the directory where Arch is started.

file.bookmarks = /opt/arch/data/sites/mySite/documentUrls.txt

# Re-indexing interval (days) with weekdays on which re-indexing is allowed.
# interval.<area-name> = NN [,sun][,mon][,tue][,wed][,thu][,fri][,sat]
# For example, to re-index area approx. every 20 days, but only on weekends:
# interval.<area-name> = 20, sat, sun

interval.bookmarks = 1

# Number of concurrent threads to use for crawling
# A global value for this parameter can be defined in the global configuration
# file and re-defined for each area.
# threads.<area-name> = 10 

threads.bookmarks = 50

# Define who can read URLs indexed as bookmarks. See more about security in the
# security section below.

groupsread.bookmarks = staff public
usersread.bookmarks = me
 

#===============================================================================
#                                Log processing
#===============================================================================

# The parameters in this section can override the parameteres in the global
# configuration file.

# Log format name. This parameter must match format attribute (defined in
# plugin.xml) file of a log parser plugin that is able to process logs of this
# type. The default arch log parser works with logs in combined format. 
# A global value for this parameter can be defined in the global configuration
# file and re-defined for each site.

log.format = combined

# The log length to process, days. The latest log of this length will be taken
# if available. E.g. if we have logs for the last 10 years, but this parameter
# is 365 days, only the latest 365 days are used to compute document scores.

log.length = 365

# Attempt to identify and ignore search engines and abuse based on IP stats.
# All IP based filtering can be turned off by setting this parameter to off.
# This is not fatal, because robots accesses can still be filtered out based
# on the client type, if this information is in the logs and robots do not
# masquerade as browsers. 

ip.filter = on


# File names of index pages that will be served by the web server if there is
# no file name in the URL (e.g. http://www.mysite.com/) 

index.file.names = index.html index.htm home.html home.htm index.php home.php

# Ignore log records where file names have these extensions.

ignore.in.logs = jpg .gif .png .css .js

# A URL of file with pre-processed sitemap data that can be used as a
# substitute to log processing. See more in Arch deployment manual about
# generating, encrypting and making available sitemaps for remote sites. If
# this URL is provided, log files are ignored. If there are no log files in the
# defailt location, (arch_home/conf/arch/sites/site_name/logs), Arch will
# attempt to get a sitemap file from the default URL, as in the example below.

# sitemap.url = http://mySite.base.url/arch/sitemap.dat

# Delete log files after processing. Switching this on is convenient for setting
# up automatic log processing. All you have to do is keep copying the latest log
# files to the location where Arch expects them. Arch will find them, process and
# delete.

delete.logs = false 


#===============================================================================
#                                   Security
#===============================================================================

# Permissions. This parameter is used to set access permissions for a file or
# folder (and by default, its subfolders). These permissions make effect when
# covered documents are re-indexed.
# permissions = {f,d} | url | groups-R/O | groups-R/W | users-R/O | users-R/W |
# owners | {s,i}
# Here f or d stand for folder or document respectively;
# groups-R/O  a space separated list of user groups having R/O access;
# groups-R/W  a space separated list of user groups having R/W access;
# users-R/O  a space separated list of users having R/O access;
# users-R/W  a space separated list of users having R/W access;
# owners  a space separated list of users having administrator access;
# s or i stand for defined or inherited permissions mode respectively. If
# inherited mode is set, all user and group lists, including administrators,
# are inherited from the document/folder parent folder. 

permissions = d | http://www.atnf.csiro.au/internal/ | staff | staff | admin | admin | admin | s 


# Permissions are controlled a bit differently for bookmarks because bookmarks
# are a set of miscellaneous urls that do not have a hierarchical structure
# that a web site has.

# To give access to bookmarks to a limited set of users:

usersread.bookmarks = user1 user2

# To give access to bookmarks to a limited set of user groups:

groupsread.bookmarks = group1 group2 group3


# The permissions parameter is the only parameter that affects indexing.
# All other security parameters (below) are used on access stage.

# NOTE: UNLESS PARAMETER DOMAIN IS SENT WITH REQUEST, all authentication
# related parameters are taken from the global configuration file and must
# be declared there. If domain is sent in request, it must match name of a
# site. All authentication related parameters will be taken from that site
# configuration file and access will be limited to that site data only.

# Authentication scheme. This parameter helps to find a proper authentication
# plugin to use for authentication in JSP interface. Arch searches for a plugin
# that has an attribute scheme (declared in plugin.xml) matching the
# authentication.scheme parameter. If such plugin is found, it is used for 
# authentication.

authentication.scheme = file

# NOTE: frontent.profile parameter is expected by Arch reference authentication 
# plugin. It is very likely that you will want to replace it with a plugin 
# implementing authentication method used in your organization. Your plugin may 
# use a different configuration parameters set.
#
# Front-end search profile parameter defines front-end id, password, sites and
# areas that the front-end is allowed to search and users and groups that are
# allowed to do search via this front-end. The fields are separated by |. The 
# required parameters are the id and password. The rest can be left blank.  
# frontend.profile = id | password | site1 site2 | area1 area2 | group1 group2 | 
# user1 user2

frontend.profile = global | pass1

# Users and groups files. This is also a parameter required by Arch reference
# authentication plugin implementing Apache file based authentication scheme.

auth.passwords.file = /arch/data/testPasswords.txt
auth.groups.file = /arch/data/testGroups.txt

#===============================================================================
#                                Notifications
#===============================================================================

# This set of parameters may override parameters in the global config file. If
# they are present here, email messages related to this site are sent to address
# defined here and their text is not included in the combined message sent to the
# address configured in the global config file. To cause sending a separate email
# for this site, define at least mail.recipient parameter here. The rest are
# optional, as long as they are defined in the global config file.

# Level of details in emeail messages: DEBUG, INFO, WARN, ERROR or OFF.
# DEBUG level is most detailed, OFF switches email notifications OFF.
# Please note that email notifications are not designed to provide detailed reports.
# To get details, see log files. 

mail.level = INFO

# Mail protocol to use. Optional. The default value is smtp.

mail.transport.protocol = smtp 

# Mail server address. Has to be defined either here or in the global config file.

mail.host = mail.mycompany.com

# Mail user name, if mail server requires authentication.

mail.user = itsme

# Mail user password, if mail server requires authentication.

mail.pass = mypassword

# Email message subject to use. Optional. The default value is 
# Arch indexing report

mail.subject = My message from Arch

# Adresses of recipients. This parameter is required to switch per-site email ON.
# If it is not defined, email message body for this site is included in the
# "global" message sent in accordance with the global config file parameters.
# There can be multiple recipients separated by ';', ':' or ','.

mail.recipient = address1@mycompany.com; address2@anothercompany.com

