Skip to content

Instantly share code, notes, and snippets.

What would you like to do?
# Copyright (c) 2013-2018 Snowplow Analytics Ltd. All rights reserved.
# This program is licensed to you under the Apache License Version 2.0, and
# you may not use this file except in compliance with the Apache License
# Version 2.0. You may obtain a copy of the Apache License Version 2.0 at
# Unless required by applicable law or agreed to in writing, software
# distributed under the Apache License Version 2.0 is distributed on an "AS
# implied. See the Apache License Version 2.0 for the specific language
# governing permissions and limitations there under.
# This file (application.conf.example) contains a template with
# configuration options for the Scala Stream Collector.
# To use, copy this to 'application.conf' and modify the configuration options.
# 'collector' contains configuration options for the main Scala collector.
collector {
# The collector runs as a web service specified on the following interface and port.
interface = ""
port = 8080
# Configure the P3P policy header.
p3p {
policyRef = "/w3c/p3p.xml"
# Cross domain policy configuration.
# If "enabled" is set to "false", the collector will respond with a 404 to the /crossdomain.xml
# route.
crossDomain {
enabled = false
# Domains that are granted access, * will match and
domains = [ "*" ]
# Whether to only grant access to HTTPS or both HTTPS and HTTP sources
secure = true
# The collector returns a cookie to clients for user identification
# with the following domain and expiration.
cookie {
enabled = true
expiration = "365 days" # e.g. "365 days"
# Network cookie name
name = "_sp_cookie"
# The domain is optional and will make the cookie accessible to other
# applications on the domain. Comment out this line to tie cookies to
# the collector's full domain
# domain = ""
# If you have a do not track cookie in place, the Scala Stream Collector can respect it by
# completely bypassing the processing of an incoming request carrying this cookie, the collector
# will simply reply by a 200 saying "do not track".
# The cookie name and value must match the configuration below.
doNotTrackCookie {
enabled = false
name = "dnt_cookie"
value = "true"
# When enabled and the cookie specified above is missing, performs a redirect to itself to check
# if third-party cookies are blocked using the specified name. If they are indeed blocked,
# fallbackNetworkId is used instead of generating a new random one.
cookieBounce {
enabled = false
# The name of the request parameter which will be used on redirects checking that third-party
# cookies work.
name = "n3pc"
# Network user id to fallback to when third-party cookies are blocked.
fallbackNetworkUserId = "00000000-0000-4000-A000-000000000000"
# Optionally, specify the name of the header containing the originating protocol for use in the
# bounce redirect location. Use this if behind a load balancer that performs SSL termination.
# The value of this header must be http or https. Example, if behind an AWS Classic ELB.
forwardedProtocolHeader = "X-Forwarded-Proto"
# When enabled, the redirect url passed via the `u` query parameter is scanned for a placeholder
# token. All instances of that token are replaced withe the network ID. If the placeholder isn't
# specified, the default value is `${SP_NUID}`.
redirectMacro {
enabled = false
# Optional custom placeholder token (defaults to the literal `${SP_NUID}`)
placeholder = "[TOKEN]"
# Customize response handling for requests for the root path ("/").
# Useful if you need to redirect to web content or privacy policies regarding the use of this collector.
rootResponse {
enabled = false
statusCode = 302
# Optional, defaults to empty map
headers = {
Location = "",
X-Custom = "something"
# Optional, defaults to empty string
body = "302, redirecting"
streams {
# Events which have successfully been collected will be stored in the good stream/topic
good = good
# Events that are too big (w.r.t Kinesis 1MB limit) will be stored in the bad stream/topic
bad = bad
# Whether to use the incoming event's ip as the partition key for the good stream/topic
# Note: Nsq does not make use of partition key.
useIpAddressAsPartitionKey = false
# Enable the chosen sink by uncommenting the appropriate configuration
sink {
# Choose between kinesis, googlepubsub, kafka, nsq, or stdout.
# To use stdout, comment or remove everything in the "collector.streams.sink" section except
# "enabled" which should be set to "stdout".
enabled = googlepubsub
# Region where the streams are located
# region = "none"
## Optional endpoint url configuration to override aws kinesis endpoints,
## this can be used to specify local endpoints when using localstack
# customEndpoint = "none"
# Thread pool size for Kinesis API requests
# threadPoolSize = 10
# The following are used to authenticate for the Amazon Kinesis sink.
# If both are set to 'default', the default provider chain is used
# (see
# If both are set to 'iam', use AWS IAM Roles to provision credentials.
# If both are set to 'env', use environment variables AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY
# aws {
# accessKey = iam
# secretKey = iam
# }
# Minimum and maximum backoff periods, in milliseconds
# backoffPolicy {
# minBackoff = 1
# maxBackoff = 2
# }
# Or Google Pubsub
googleProjectId = your-google-project-id
## Minimum, maximum and total backoff periods, in milliseconds
## and multiplier between two backoff
backoffPolicy {
minBackoff = 1000
maxBackoff = 5000
totalBackoff = 10000 # must be >= 10000
multiplier = 2
# Or Kafka
#brokers = "none"
## Number of retries to perform before giving up on sending a record
#retries = 0
# Or NSQ
## Host name for nsqd
#host = "none"
## TCP port for nsqd, 4150 by default
#port = 0
# Incoming events are stored in a buffer before being sent to Kinesis/Kafka.
# Note: Buffering is not supported by NSQ.
# The buffer is emptied whenever:
# - the number of stored records reaches record-limit or
# - the combined size of the stored records reaches byte-limit or
# - the time in milliseconds since the buffer was last emptied reaches time-limit
buffer {
byteLimit = 1
recordLimit = 1 # Not supported by Kafka; will be ignored
timeLimit = 1
# Akka has a variety of possible configuration options defined at
akka {
loglevel = DEBUG # 'OFF' for no logging, 'DEBUG' for all logging.
loggers = ["akka.event.slf4j.Slf4jLogger"]
# akka-http is the server the Stream collector uses and has configurable options defined at
http.server {
# To obtain the hostname in the collector, the 'remote-address' header
# should be set. By default, this is disabled, and enabling it
# adds the 'Remote-Address' header to every request automatically.
remote-address-header = on
raw-request-uri-header = on
# Define the maximum request length (the default is 2048)
parsing {
max-uri-length = 32768
uri-parsing-mode = relaxed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.