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

# The directory where crawling data is kept temporarily before sending it to
# Solr. Contents are deleted after successful crawling. Make sure that this
# directory has plenty of free space for temporary use. REQUIRED!
 
#temp.dir = /opt/arch-1.41/temp

# Address of Solr server that will be installed with Arch

solr.url = http://localhost:8080/arch

#===============================================================================
#                                   Crawling
#===============================================================================


# Parallel indexing. If off, areas are crawled sequentially, one at a time. The
# sequential mode is recommended for troubleshooting a new installation or after
# a new site has been added. In this mode, if indexing fails, you can fix the
# problem and restart indexing. It will skip areas that have been processed
# successfully in the previous run. The parallel mode may significantly decrease
# the time of indexing. Note that bookmarks areas will be processed
# sequentially even if parallel processing is switched on.

parallel.indexing = on


# Default crawling depth. Defines how many crawling iterations to do by default
# when indexing an area. Each area can overwrite this parameter, if indexed
# sequentially. After deploying Arch, it is recommended to do a trial crawl with
# a shallow depth, e.g. 2. If everything works, run the bin/clean script, set the
# depth to a desired value and do a production crawl.

depth = 50


# Default crawling depth for links found in log files. This parameter is only used
# when sequential processing is done and can be overwritten in loglinks areas
# configurations. After indexing all areas of a site, links that are found in the
# site logs, but have not been crawled yet, are used as starting points for another
# round of crawling. It is not recommended that this parameter is set to higher than
# 2 because in this case too many URLs that have already been crawled in previous stages
# will be re-crawled and create duplicated entries in the index. If your site has too
# many isolated areas which are discovered only via log links, the parallel crawling
# mode is the recommended option. In parallel crawling, all pre-configured crawling
# roots together with all links found in logs are used as starting points of crawling
# with no risk of creating many duplicates because they are crawled together and Nutch
# is making sure that no link is fetched twice.

depth.loglinks = 2


# 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

max.urls = 10000


# Number of concurrent threads to use for crawling

threads = 10 


# Switches on and off removing duplicate entries from the index. They can result,
# for example, from indexing URLs aliases.

remove.duplicates = on 


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

# Database plugin module to use. This parameter must match database attribute
# (defined in plugin.xml file) of a database interface plugin. A MySQL  and
# Apache Derby based plugins are included with Arch, but any other relational
# database plugin can be used if available. For a reference implementation,
# please see the MySQL plugin. Apache Derby can be used in embedded mode, with
# minimal configuration, if you don't need the automatic site map function
# which is not available in this mode. The client-server Derby mode has not been
# tested.

database = MySQL

# To use Apche Derby:
# database = Derby

# 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. To use Apche Derby in embedded mode, this parameter can be dropped.

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

# For embedded Derby:
# target.db = jdbc:derby:myDB;create=true;user=<user name>;password=<password> 

# DB driver to use 

db.driver = com.mysql.jdbc.Driver

# For embedded Derby: 
# db.driver = org.apache.derby.jdbc.EmbeddedDriver

#===============================================================================
#                                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 


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

# 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. 

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


# The number of latest IP addresses to remember for a URL. This is needed
# to catch and filter repeated accesses from same source. 

history.size = 10


# Max counted accesses to a single page per day. The rest are ignored.  

max.hits.day = 5000


# Max hits counted per IP per URL per day. A filter to block impact on
# document scores caused by repeated accesses from the same IP. Should
# be used with care as there may be multiple users behind one IP address.

max.hits.ip.day = 5

# Max document weight value to use for final weight normalisation in the DB.
# All document weights are normalised to take values between 1 and max.score.
# Later Arch scoring filter uses these weights to boost indexed documents.

max.score = 5 


# Max size of URLs cache. This cache is used when counting document accesses.
# A bigger cache speeds up access counting, but requires more memory.

max.url.cache = 100000


# 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

# 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

#===============================================================================
#                            IP filtering (for log processing)
#===============================================================================

# Hits/IP/URL/day beyond which the IP is placed on the list to ignore.
# Should be used carefuly because some pages, e.g. home pages may be
# requested often in normal use

max.hits.norm = 1000

# This interval is used when identifying IP addresses (of crawlers) to ignore.
# If more hits than a certain threshold has come from an IP address in a time
# interval shorter than capture.interval (in seconds), this IP address is
# considered belonging to a crawler and put on a list to ignore. 

capture.interval = 300


# If IP address generates more than this number of hits per the interval, it is
# considered a search engine. In this example, IP address is blocked if there
# are more than 30 accesses to text documents in a 5 minutes interval.

hits.threshold = 30


# 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


# Max size of IP address cache. This cache is used when computing a list of
# ignored IP addresses with aim to count only accesses generated by human
# readers and exclude accesses generated by search engine crawlers. A bigger
# cache speeds up ignored IPs list generation, but requires more memory.

max.ip.cache = 100000  


# Ignore log records where file names have these extensions.

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


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

# These are used by the reference authenticator included with Arch. You can
# replace it with your own module and use different configuration method(s).

# Security switch. It is recommended to keep security disabled until you get
# your search working as expected. Else it may get in the way and it will be
# harder to tell what is causing problems.

security.enabled = false 

# Optional BLACK list of blocked IP addresses. All requests coming fro these
# addresses are rejected. Please note that regular expressions depend on whether
# IPv4 or IPv6 is used. The examples below are valid for  IPv4.

#blocked.ip.addresses = ^130\.155\.201\.106

# Optional WHITE list of privileged IP addresses. Requests coming from these
# addresses are let through, unless authentication is explicitly requested.
# allowed.users, allowed.groups, allowed.sites and allowed.areas are automatically
# assigned to unauthenticated requests from IP addresses on the WHITE list.
# Please note that regular expressions depend on whether IPv4 or IPv6 is used.
 
#allowed.ip.addresses = ^130\.155\.17[6-9]\..+ ^130\.155\.18[6-9]\..+
#allowed.ip.addresses = ^130\.155\.19[6-9]\..+ ^130\.155\.21[6-9]\..+

# Optional list of user names assigned to unauthenticated requests coming from
# IP addresses on the WHITE list.
# Use "all" or comment out to allow all user names.

#allowed.users = admin guest

# Optional list of group names assigned to unauthenticated requests coming from
# IP addresses on the WHITE list.
# Use "all" or comment out to allow all groups.

#allowed.groups = staff public

# Optional list of visible sites assigned to requests passed without authentication
# Use "all" or comment out to disble site filter.

#allowed.sites = all

# Optional list of visible areas assigned to requests passed without authentication
# Use "all" or comment out to disble area filter.

#allowed.areas = all

# Optional list of user names assigned to unauthenticated requests coming from 
# IP addresses NOT matching the white or black lists.
# Use "all" or comment out to allow all user names.

default.users = guest

# Optional list of group names assigned to requests matvh
# Use "all" or comment out to allow all groups.

default.groups = public

# Optional list of visible sites assigned to requests passed without authentication
# Use "all" or comment out to disble site filter.

default.sites = all

# Optional list of visible areas assigned to requests passed without authentication
# Use "all" or comment out to disble area filter.

default.areas = all

# Optional. A list of IP address to allow admin access to Solr server from. Clients
# from these addresses will have full unfiltered access to Solr server and will
# be able to updade and delete the contents there. Note that if distributed crawling
# is performed, addresses of all computers in the cluster have to be on this list.
# Leave this parameter commented out to allow admin access from any IP address.

# A GENERAL ADVICE: for trial runs, turn off security measures so that they do
# not cause problems. Else you may experience problems and spend a long time looking
# for the cause just to find out that, for example, you've indexed everything
# correctly, but your queries do not return anything just becuase your access
# permissions are too strict.

#admin.ip.addresses = ^127.0.0.1



#=========================== PHP front-end configuration ======================

# NOTE: UNLESS PARAMETER DOMAIN IS SENT WITH REQUEST, front-end 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.

# NOTE: frontent.profile parameter is expected by the 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.

# Users and groups files 
auth.passwords.file = /opt/arch-1.4/conf/arch/testPasswords.txt
auth.groups.file = /opt/arch-1.4/conf/arch/testGroups.txt

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

# This set of parameters controls email notofications. They can be redefined in 
# sites config files to send separate email messages for each site that requires
# it.

# Level of details in mail messages:
# DEBUG, INFO, WARN, ERROR, 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. Required.

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. Required.
# If it is not defined, email messages are not sent.
# "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

