Snowplow Scala Stream Collector is not giving 200 Ok response after the configuration file is run.
Its giving error object not found.
# 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
# http://www.apache.org/licenses/LICENSE-2.0.
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the Apache License Version 2.0 is distributed on an "AS
# IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
# 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 = "0.0.0.0"
port = 80
# Configure the P3P policy header.
p3p {
policyRef = "/w3c/p3p.xml"
CP = "NOI DSP COR NID PSA OUR IND COM NAV STA"
}
# 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, *.acme.com will match http://acme.com and http://sub.acme.com
enabled = ${?COLLECTOR_CROSS_DOMAIN_ENABLED}
domains = [ "*" ]
domains = [ ${?COLLECTOR_CROSS_DOMAIN_DOMAIN} ]
# Whether to only grant access to HTTPS or both HTTPS and HTTP sources
secure = true
secure = ${?COLLECTOR_CROSS_DOMAIN_SECURE}
}
# The collector returns a cookie to clients for user identification
# with the following domain and expiration.
#cookie {
enabled = true
#enabled = ${?COLLECTOR_COOKIE_ENABLED}
expiration ="365 days"
#expiration = ${?COLLECTOR_COOKIE_EXPIRATION}
# Network cookie name
name = _1234_
#name = ${?COLLECTOR_COOKIE_NAME}
# 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 = "{{cookieDomain}}"
}
# 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, where the names of the cookies must
# match entirely and the value could be a regular expression.
#doNotTrackCookie {
# enabled = false
#enabled = ${?COLLECTOR_DO_NOT_TRACK_COOKIE_ENABLED}
#name = {{doNotTrackCookieName}}
#name = ${?COLLECTOR_DO_NOT_TRACK_COOKIE_NAME}
#value = {{doNotTrackCookieValue}}
#value = ${?COLLECTOR_DO_NOT_TRACK_COOKIE_VALUE}
#}
# 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
enabled = ${?COLLECTOR_COOKIE_BOUNCE_ENABLED}
# 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"
fallbackNetworkUserId = ${?COLLECTOR_COOKIE_BOUNCE_FALLBACK_NETWORK_USER_ID}
# Optionally, specify the name of the header containing the originating protocol for use in the
# bounce redirect location. Use this if behind a load balancer that performs SSL termination.
# The value of this header must be http or https. Example, if behind an AWS Classic ELB.
forwardedProtocolHeader = "X-Forwarded-Proto"
}
# When enabled, the redirect url passed via the `u` query parameter is scanned for a placeholder
# token. All instances of that token are replaced withe the network ID. If the placeholder isn't
# specified, the default value is `${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
#enabled = ${?COLLECTOR_ROOT_RESPONSE_ENABLED}
#statusCode = 302
#statusCode = ${?COLLECTOR_ROOT_RESPONSE_STATUS_CODE}
# Optional, defaults to empty map
# headers = {
# Location = "https://127.0.0.1/",
# Location = ${?COLLECTOR_ROOT_RESPONSE_HEADERS_LOCATION},
#X-Custom = "something"
#}
# Optional, defaults to empty string
#body = "302, redirecting"
# body = ${?COLLECTOR_ROOT_RESPONSE_BODY}
#}
# Configuration related to CORS preflight requests
#cors {
# The Access-Control-Max-Age response header indicates how long the results of a preflight
# request can be cached. -1 seconds disables the cache. Chromium max is 10m, Firefox is 24h.
#accessControlMaxAge = 5 seconds
#accessControlMaxAge = ${?COLLECTOR_CORS_ACCESS_CONTROL_MAX_AGE}
#}
streams {
# Events which have successfully been collected will be stored in the good stream/topic
good = snowplow-raw
# Events that are too big (w.r.t Kinesis 1MB limit) will be stored in the bad stream/topic
bad =snowplow-enriched-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 = "kinesis"
# Region where the streams are located
region = us-east-1
## Optional endpoint url configuration to override aws kinesis endpoints,
## this can be used to specify local endpoints when using localstack
# customEndpoint = {{kinesisEndpoint}}
# customEndpoint = ${?COLLECTOR_STREAMS_SINK_CUSTOM_ENDPOINT}
# 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 http://docs.aws.amazon.com/AWSJavaSDK/latest/javadoc/com/amazonaws/auth/DefaultAWSCredentialsProviderChain.html)
# 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 = "XXXXXXXXXXX"
secretKey = "XXXXX"
}
# Minimum and maximum backoff periods, in milliseconds
backoffPolicy {
minBackoff = 0
maxBackoff = 0
}
# Or Google Pubsub
#googleProjectId = ID
## Minimum, maximum and total backoff periods, in milliseconds
## and multiplier between two backoff
#backoffPolicy {
# minBackoff = {{minBackoffMillis}}
# maxBackoff = {{maxBackoffMillis}}
# totalBackoff = {{totalBackoffMillis}} # must be >= 10000
# multiplier = {{backoffMultiplier}}
#}
# Or Kafka
#brokers = "{{kafkaBrokers}}"
## Number of retries to perform before giving up on sending a record
#retries = 0
# The kafka producer has a variety of possible configuration options defined at
# https://kafka.apache.org/documentation/#producerconfigs
# Some values are set to other values from this config by default:
# "bootstrap.servers" -> brokers
# retries -> retries
# "buffer.memory" -> buffer.byteLimit
# "linger.ms" -> buffer.timeLimit
#producerConf {
# acks = all
# "key.serializer" = "org.apache.kafka.common.serialization.StringSerializer"
# "value.serializer" = "org.apache.kafka.common.serialization.StringSerializer"
#}
# Or NSQ
## Host name for nsqd
#host = "{{nsqHost}}"
## TCP port for nsqd, 4150 by default
#port = {{nsqdPort}}
}
# 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 = 4500000
recordLimit = 500 # Not supported by Kafka; will be ignored
timeLimit = 5000
}
}
}
# Akka has a variety of possible configuration options defined at
# http://doc.akka.io/docs/akka/current/scala/general/configuration.html
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://doc.akka.io/docs/akka-http/current/scala/http/configuration.html
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
}
}
}