Appendix B - infinite.configuration.properties.TEMPLATE (STANDALONE and AWS)

#-------------------------------------------------------------------------------
# 1.1] Basic Infinit.e Settings 
#-------------------------------------------------------------------------------
# Default admin and test user passwords
# CHANGE THIS:
admin.email=infinite_default@ikanow.com
admin.password=infinit.e!2012
# Test User : This is a dummy account for testing only so it doesn't matter what it is set to (default below)
# (or it can be changed as below, but cannot be the same email as the admin)
#test.email=test_user@ikanow.com
# CHANGE THIS:
test.user.password=infinit.e!2012

#-------------------------------------------------------------------------------
# 1.3] Amazon services properties
#-------------------------------------------------------------------------------
# This is the root s3 bucket name to be used for backups (use.aws=1 only):
# (The following names are used: mongo.<s3.url>, elasticsearch.<s3.url> .. daily backups in the same region
#  backup.mongo.<s3.url>, backup.elasticsearch.<s3.url> ... monthly backups in a different region
#  Note these dirs need to be set up manually)
s3.url=
#-------------------------------------------------------------------------------
# 2.3] Amazon services properties
#-------------------------------------------------------------------------------
# Values: 0=false, 1=true
# If deployed on an EC2 cluster set this to 1:
use.aws=0

#-------------------------------------------------------------------------------
# 1.4] EMail Server Settings
#-------------------------------------------------------------------------------
# The server to be used for mail transactions (eg smtp.google.com if Internet-enabled, contact your sysadmin if not):
mail.server=
# Base-64 encoded Jasypt encrpyion of username (using salt/"password" "infinit.e"):
mail.username=
# Base-64 encoded Jasypt encrpyion of password (using salt/"password" "infinit.e"):
mail.password=
# This URL is used as the base for links included in the 
# So should point to an accessible REST endpoint (eg the same as ui.end.point.url below)
# If this is left commented out, it defaults to the browser domain (ie location of GUI)
#url.root=http://MY_REST_ENDPOINT/api/

#-------------------------------------------------------------------------------
# 1.5] EMail Addresses for log files etc.
#-------------------------------------------------------------------------------
# All emails come from this user:
log.files.mail.from=
# System alert emails come from this user:
log.files.mail.to=

#-------------------------------------------------------------------------------

# 1.7] Amazon AWS Settings
#-------------------------------------------------------------------------------
# AWS keys (only needed if use.aws=1)
aws.access.key=
aws.secret.key=

#-------------------------------------------------------------------------------
# 1.8] MongoDB Properties
#-------------------------------------------------------------------------------
# MongoDB config server or servers (must be 1 or 3 comma separated IPs/hosts), non-EC2/AWS installations only
# (Can be used in AWS mode for legacy clusters only, to hardwire server order)
db.config.servers=
# Replica set configuration (non-EC2/AWS installations only): comma-separated list of either all IPs or all hostnames within a replica set, semi-colon-separated for multiple replica sets
# (eg "A,B;C,D" where A-D are IP addresses or hostnames would create 2 shards with 2 hosts each "A,B;A,B" would create 2 shards both on the same replica set, etc)
db.replica.sets=
#----------------------------------------------
# db.cluster.subnet - used for non-EC2/AWS only installations to help mongodb configurations
# identify proper host ip addresses, e.g. 127.0.0. - these are compared against the IPs in db.replica.sets
# Can also be one of the following: if blank then assumes that the db.replica.sets will be a list of short hostnames - if "FQDN" then assumes that the db.replica.sets will be a list of fully qualified hostnames
db.cluster.subnet=

#-------------------------------------------------------------------------------
# 1.9] UI settings
#-------------------------------------------------------------------------------
# The passphrase for the SSL keystore (not needed unless HTTPS is being used)
ssl.passphrase=

#-------------------------------------------------------------------------------
# 1.10] Elasticsearch Properties
#-------------------------------------------------------------------------------
# Cluster name 
# Any unique name within the EC2 cluster/subnet: 
elastic.cluster=
#----------------------------------------------
# ES nodes, e.g.: elastic.search.nodes=['NODE1:9300','NODE2:9300','NODE3:9300']
# Needed if discovery.mode=zen (not EC2/AWS), a set of IPs to try (>= 1 must be running elasticsearch)
elastic.search.nodes=
# If any node sees less than this number of connections it will take itself down
# For a single node, should be 0 (default), for a 2-node system, should be 1, for large clusters
# ideally would be CLUSTER_SIZE - #REPLICAS (and >=2), but 2 is workable if the size is not fixed
# (if this is set too low then split brain situations may not be detected)
elastic.search.min_peers=0

#-------------------------------------------------------------------------------
# 1.12] Hadoop properties
#-------------------------------------------------------------------------------
# This limits the number of jobs that can be concurrently submitted to the Hadoop cluster
# by the custom processing engine (other jobs remain at pending until a slot is available)
# There is no default, 10 is recommended as a sensible value until the size of your cluster is known.
hadoop.max_concurrent=10
# If this is set to true then custom (Hadoop) plugins will run locally on this node, without 
# a Hadoop cluster needing to be set up (which is complicated to do) - the downside of course is that
# jobs will not scale across many nodes. Set this to true for single-node clusters and before Hadoop
# has been installed.
hadoop.local_mode=false

#-------------------------------------------------------------------------------
# 1.13] Entity Extractor Properties
#-------------------------------------------------------------------------------
# Alchemy and Open Calais Keys:
# (Obtain from alchemyapi.com or opencalais.com)
# (can't be blank so set to DUMMY if not in use)
extractor.key.alchemyapi=DUMMY
extractor.key.opencalais=DUMMY
#----------------------------------------------
# Entity extraction type selection: opencalais or alchemyapi or none
# ("opencalais" has a much higher limit than "alchemyapi" (1000/day) so is recommended for free use
#  "alchemyapi" extracts sentiment, "opencalais" extracts entity associations Note this can be overridden per source)
extractor.entity.default=
# Text extraction type selection: boilerpipe or alchemyapi or none
# ("alchemyapi" is much better, but has the limit discussed above. Note this can be overridden per source)
extractor.text.default=

#-------------------------------------------------------------------------------
# 1.14] Interface Related Properties for the AppConstants.js file found in:
#       /mnt/opt/infinite-tomcat/interface-engine/webapps/ROOT/
#-------------------------------------------------------------------------------
# The REST end point of the server (or a DNS/AWS load balancer across multiple rest end points):
# (Will normally end "/api/") 
ui.end.point.url=http://MY_REST_ENDPOINT/api/
#You can use this to set a different logo
#ui.logo.url=

#-------------------------------------------------------------------------------
# 2.2] Software as a service (SAAS) settings
#-------------------------------------------------------------------------------
# If true, allows admin requests that come from trusted sources to have admin privileges: 
app.saas=false
# A list of trusted DNS/IP addresses (eg from CMS):
app.saas.trusted.dns=

#-------------------------------------------------------------------------------
# 2.6] API Settings
#-------------------------------------------------------------------------------
# API Search Test Terms and Expected Results
# List of terms formatted like: "*" "something" "something":
# (The continuous testing randomly selects one of these for querying the API)
api.search.test.terms="*"
# The expected results (max 100), if a different number comes back, the system alerts:
api.search.expected.results=0
# For smaller clusters with many documents, Lucene faceting may use too much memory, if so
# set this parameter to "low". ("none" disables all aggregations, "full" uses Lucene facets where possible)
api.aggregation.accuracy=full

#-------------------------------------------------------------------------------
# 2.7] Amazon AWS Settings
#-------------------------------------------------------------------------------
# Used for s3cmd, see their web page for details: 
s3.gpg.passphrase=

#-------------------------------------------------------------------------------
# 2.8] MongoDB Properties
#-------------------------------------------------------------------------------
# (server/port should normally point to localhost:27017), where API nodes have a mongos
db.server=localhost
db.port= 27017
# db.sharded - 0 = false and 1 = true
db.sharded=1
# The max number of documents to store (eg 10M). Docs will be dropped in order of age.
# (Not currently supported):
db.capacity=10000000
# MongoDB config server or servers (must be 1 or 3 comma separated IPs), non-EC2/AWS installations only
db.config.servers=
db.replica.sets=
#----------------------------------------------
# db.cluster.subnet - used for non-EC2/AWS only installations to help mongodb configurations
# identify proper host ip addresses, e.g. 127.0.0.
db.cluster.subnet=
#----------------------------------------------
# The location from which to fetch the geo.bson dump used for feature.geo
# can start s3://, http:// or https://, else is assumed to be a file, eg
#db.geo_archive=s3://config.saas.infinite.ikanow.com/geo.bson.tar.gz
# Can always be retrieved here
db.geo_archive=http://yum.ikanow.com/infinit.e-preinstall/artifacts/geo.bson.tar.gz

#-------------------------------------------------------------------------------
# 2.9] UI inactivity timeout (in seconds)
#-------------------------------------------------------------------------------
# After this many seconds of inactivity, users are logged out from their Infinit.e session
access.timeout=1800
# This is a regex that, if specified, will allow only access to REST commands matching
# the pattern - only applied to remote clients. Connections from localhost always have access 
# to everything
# Eg the commented out example will allow only login/keepalive and querying.
#remote.access.allow=^/api/(knowledge/document/query|auth/login|auth/keepalive)
remote.access.allow=
# This parameter does the opposite, allows everything except specified commands
remote.access.deny=
# Uncomment ui.logging, set to true: in order to log any success:false or HTTP errors from the API, except:
# If you specify the ui.logging.api.regex, it should start with either '*' or '!' and then the regex:
# if it starts with '*' then it will log any api call with a substring matching the regex (in addition to all errors)
# if is starts with '!' (or nothing at all) then it will show errors only, and filter them according to the regex
#ui.logging=true
#ui.logging.api.regex=

#-------------------------------------------------------------------------------
# 2.10] Elasticsearch Properties
#----------------------------------------------
# Discovery mode = ec2 (if running on AWS) or zen (specify a list of IPs below):
elastic.node.discovery=ec2
#----------------------------------------------
# ES nodes, e.g.: elastic.search.nodes='NODE1:9300','NODE2:9300','NODE3:9300':
# Needed if discovery.mode=zen (not EC2/AWS), a set of IPs to try (>= 1 must be running elasticsearch)
elastic.search.nodes=
#-------------------------------------------------------------------------------
# mlockall = should equal true except if running on a machine with < 4GB of RAM
bootstrap.mlockall=true
# (Should normally be localhost:9300, unless an API node is running with no index node) 
elastic.url=localhost:9300
# If you know your logstash and elasticsearch versions are matched up, you can improve the output performance by setting this to "binary"
elastic.logstash=http

#-------------------------------------------------------------------------------
# 2.11] Harvester Properties
#-------------------------------------------------------------------------------
# Comma-separated-list from File,Database,Feed (note Database and Feed need jars not bundled with the RPM)
harvester.types=File,Database,Feed
# Web crawling etiquette: the time to way between consecutive accesses to the same time (10s is standard)
harvest.feed.wait=10000
# The minimum time between consecutive harvests (avoids thrashing FS/DB/RSS when there's nothing to get)
harvest.mintime.ms=300000
# The minimum time between consecutive source harvests (set if needs to be longer than harvest.mintime.ms,
# eg if you want to pick up a source quickly the first time but then not update so frequently)
harvest.source.mintime.ms=
# Restricts the number of docs that can be harvested per cycle for memory reasons:
harvest.maxdocs_persource=5000
# Threading configuration type:num_threads (type from above):
# (eg for RSS heavy increase the "feed", for DB heavy increase the "file" etc. Beyond 20 there is limited benefit). 
harvest.threads=file:5,database:5,feed:20
# This controls the batch size of sources picked up by a thread, this does not normally need to be changed (its default is shown)
# (It can be reduced in cases where a small number of very long-running sources need to be harvested).
#harvest.distribution.batch.harvest=20
# This disables entity and association aggregation. For almost all applications you will not want to set this.
#harvest.disable_aggregation=false
# This controls what % of 1 CPU is used to update entity and association counts and synchronization, shouldn't need to change it
# (Reducing it will speed up raw harvest speeds, Increasing it will keep entity etc freqs more up-to-date)
#harvest.aggregation.duty_cycle=0.5
# This parameter uses the Java Security Manager to prevent scripts accessing local network services (at the expense of some performance)
# It can be turned off for uses of the platform where sources must be approved before being added (etc)
harvest.security=false
# This is a comma-separated list of hosts in the following format "http://<HOST>[:<PORT>]" or "socks://<HOST>:<PORT>"
# When specified, all requests for external content from the harvester are proxied (round-robin) through the specified hosts
harvest.proxy=
# Content controls:
#This is the maximum size of content (before gzip) that will be stored (truncated above this)
#store.maxcontent=16000000
#If true (default false), stores the raw content of a document (as well as the post-processed text)
#store.rawcontent=false
#If true (default false), then the doc_content.gzip_content also contains the JSON metadata, stored as a string 
#store.metadata_as_content=false

#-------------------------------------------------------------------------------
# 2.12] Hadoop Properties
#-------------------------------------------------------------------------------
hadoop.configpath=/mnt/opt/hadoop-infinite/mapreduce/

 #-------------------------------------------------------------------------------
# 2.13] Entity Extractor Properties
#-------------------------------------------------------------------------------
# Alchemy extraction level
# 1==people postproc, 2==geo postproc, 3==both
# (This uses some hard-coded heuristics to work around known AlchemyAPI errors)
app.alchemy.postproc=3
#This should list any custom extractor class names
#extractor.entity.custom=

#-------------------------------------------------------------------------------
# 2.14] Interface Related Properties for the AppConstants.js file found in:
#       /mnt/opt/infinite-tomcat/interface-engine/webapps/ROOT/
#-------------------------------------------------------------------------------
# For SaaS applications, the URL of the web page (eg containing CMS links for forgot password/logout etc):
# (Can be left blank otherwise)
ui.domain.url=
# Forgot password URL: (SaaS only, ie integrated with a CMS)
# (relative to ui.domain.url):
ui.forgot.password=forgot-password/
# Logout URL: (SaaS only, ie integrated with a CMS)
# (relative to ui.domain.url):
ui.logout=?action=logout
# If using a different search engine than google (eg something internal), set this
#ui.externalsearch.name=Google
#This URL has the search terms appended at the end (URL encoded)
#ui.externalsearch.url=https://www.google.com/search?hl=en&q=

#-------------------------------------------------------------------------------
# 2.15] Maps API key:
#-------------------------------------------------------------------------------
# Can be any non-zero string for MapQuest open API
google.maps.api.key=NULL_KEY

#-------------------------------------------------------------------------------
# 2.16] Enterprise variables - ignore for non-enterprise installs
#-------------------------------------------------------------------------------
 
#####
# Proxy settings for port 8090
# The location of the case manager GUI - Reverse Proxies requests to <domain>:8090/casemanager
# If the case manager server is located on a different domain name, change casemanager.master to be the domain name of that server.
casemanager.master=localhost.localdomain
# The location of the splunk monitor server - Reverse Proxies requests to <domain>:8090/splunk
# If the splunk server is located on a different domain, change monitor.master to be the domain name of that server.
monitor.master=localhost.localdomain
 
####
# Enterprise settings need by the GUI
# The location of the case manager app server - set to "local" to point to <domain>/caseserver
# NOTE THAT THE DOMAIN MUST MATCH THE URL OF THE MAIN GUI OR AUTHENTICATION WON'T WORK
#app.case.api.url=local
# The location of the case manager GUI - set to "local" to point to <domain>:8090/casemanager
# (redirects to 8090/casemanage)
# NOTE THAT THE DOMAIN MUST MATCH THE URL OF THE MAIN GUI OR AUTHENTICATION WON'T WORK
#app.case.url=local

#-------------------------------------------------------------------------------