├── .gitignore ├── conf ├── spark │ └── spark-env.sh ├── hive │ ├── hive-env.sh │ └── hive-site.xml ├── httpfs │ └── httpfs-site.xml ├── hadoop │ ├── hdfs-site.xml │ ├── mapred-site.xml │ ├── yarn-site.xml │ └── core-site.xml ├── tez │ └── tez-site.xml ├── kafka │ └── server.properties └── hue │ └── hue-overrides.ini ├── run-bdp.sh ├── scripts ├── wait_to_die.sh ├── hive_start.sh ├── start_kafka.sh ├── mysql_init.sh ├── hadoop_init.sh └── entrypoint.sh ├── README.md └── Dockerfile /.gitignore: -------------------------------------------------------------------------------- 1 | *.gz 2 | *.tgz 3 | 4 | .idea/ 5 | *jar 6 | packages/ 7 | -------------------------------------------------------------------------------- /conf/spark/spark-env.sh: -------------------------------------------------------------------------------- 1 | export PYSPARK_PYTHON=/usr/bin/python3 2 | -------------------------------------------------------------------------------- /run-bdp.sh: -------------------------------------------------------------------------------- 1 | docker run -it -p 8088:8088 -p 8888:8888 -h bigdata bdp bash 2 | -------------------------------------------------------------------------------- /scripts/wait_to_die.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | while true; do 3 | sleep 100000 4 | done 5 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # BigDataComponents-master 2 | 3 | 最近准备入手大数据开发了，不知道从何入手，网上找了很多关于大数据的学习路线，基本都大同小异来来回回就那些东西，万事开头难啊，在此笔者总结了大数据最基本的学习技术栈。 4 | 5 | 6 | www.liyuze.work 7 | 8 | -------------------------------------------------------------------------------- /scripts/hive_start.sh: -------------------------------------------------------------------------------- 1 | #/usr/bin/env bash 2 | 3 | schematool -initSchema -dbType mysql 4 | nohup hive --service metastore > /dev/null 2>&1 & 5 | nohup hive --service hiveserver2 > /dev/null 2>&1 & -------------------------------------------------------------------------------- /scripts/start_kafka.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # zookeeper 4 | /usr/local/zookeeper/bin/zkServer.sh start 5 | 6 | # kafka 7 | nohup kafka-server-start.sh /etc/kafka/server.properties > /usr/local/kafka/log/kafka.log 2>&1 & -------------------------------------------------------------------------------- /conf/hive/hive-env.sh: -------------------------------------------------------------------------------- 1 | export HADOOP_HOME=/usr/local/hadoop 2 | export HIVE_CONF_DIR=/etc/hive 3 | export TEZ_HOME=/usr/local/tez 4 | export TEZ_CONF_DIR=/etc/tez 5 | export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:${TEZ_CONF_DIR}:${TEZ_HOME}/*:${TEZ_HOME}/lib/* -------------------------------------------------------------------------------- /scripts/mysql_init.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # create hive user and hive_metastore database 4 | mysql -uroot -proot -e "create user 'hive'@'localhost' identified by 'hive'; 5 | create database hive_metastore; 6 | grant all on hive_metastore.* to 'hive'@'localhost'; 7 | flush privileges;" 8 | -------------------------------------------------------------------------------- /conf/httpfs/httpfs-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | httpfs.proxyuser.hue.hosts 4 | * 5 | 6 | 7 | httpfs.proxyuser.hue.groups 8 | * 9 | 10 | -------------------------------------------------------------------------------- /scripts/hadoop_init.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # 初始化 4 | hadoop namenode -format && start-all.sh 5 | 6 | # 创建 hive 目录 7 | hadoop fs -mkdir -p /user/hive/warehouse /user/hive/tmp /user/hive/log /user/tez /user/root 8 | hadoop fs -chown root /user/root 9 | hadoop fs -chmod 777 /user/hive/warehouse /user/hive/tmp /user/hive/log 10 | hadoop fs -put /usr/local/tez/share/tez.tar.gz /user/tez/ 11 | -------------------------------------------------------------------------------- /conf/hadoop/hdfs-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | dfs.replication 4 | 1 5 | 6 | 7 | 8 | dfs.name.dir 9 | /usr/local/hadoop/data/namenode 10 | 11 | 12 | 13 | dfs.data.dir 14 | /usr/local/hadoop/data/datanode 15 | 16 | 17 | dfs.webhdfs.enable 18 | true 19 | 20 | 21 | -------------------------------------------------------------------------------- /conf/tez/tez-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | tez.lib.uris 5 | hdfs://bigdata:8020/user/tez/tez.tar.gz 6 | 7 | 8 | 9 | tez.use.cluster.hadoop-libs 10 | true 11 | 12 | 13 | 14 | tez.runtime.compress 15 | true 16 | 17 | 18 | 19 | tez.runtime.compress.codec 20 | org.apache.hadoop.io.compress.SnappyCodec 21 | 22 | 23 | -------------------------------------------------------------------------------- /conf/hadoop/mapred-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | mapreduce.framework.name 4 | yarn 5 | 6 | 7 | yarn.app.mapreduce.am.env 8 | HADOOP_MAPRED_HOME=/usr/local/hadoop 9 | 10 | 11 | mapreduce.map.env 12 | HADOOP_MAPRED_HOME=/usr/local/hadoop 13 | 14 | 15 | mapreduce.reduce.env 16 | HADOOP_MAPRED_HOME=/usr/local/hadoop 17 | 18 | 19 | -------------------------------------------------------------------------------- /conf/hadoop/yarn-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | yarn.nodemanager.aux-services 4 | mapreduce_shuffle 5 | 6 | 7 | yarn.resourcemanager.hostname 8 | bigdata 9 | 10 | 11 | 12 | yarn.nodemanager.vmem-check-enabled 13 | false 14 | 15 | 16 | yarn.nodemanager.pmem-check-enabled 17 | false 18 | 19 | 20 | -------------------------------------------------------------------------------- /scripts/entrypoint.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # ssh 4 | service ssh start 5 | 6 | # mysql 7 | chown -R mysql:mysql /var/lib/mysql 8 | service mysql start 9 | /run/mysql_init.sh 10 | 11 | # zookeeper 12 | /usr/local/zookeeper/bin/zkServer.sh start 13 | 14 | # kafka 15 | nohup kafka-server-start.sh /etc/kafka/server.properties > /usr/local/kafka/log/kafka.log 2>&1 & 16 | 17 | # hadoop 18 | su hadoop -c "bash /run/hadoop_init.sh" 19 | 20 | # hive 21 | su hadoop -c "bash /run/hive_start.sh" 22 | 23 | 24 | # hue 25 | /usr/share/hue/build/env/bin/hue syncdb --noinput 26 | /usr/share/hue/build/env/bin/hue migrate 27 | nohup /usr/share/hue/build/env/bin/supervisor > /dev/null 2>&1 & 28 | 29 | 30 | # temporary 31 | #while true; do sleep 1000; done 32 | -------------------------------------------------------------------------------- /conf/hadoop/core-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | fs.defaultFS 4 | hdfs://bigdata:8020/ 5 | NameNode URI 6 | 7 | 8 | 9 | hadoop.proxyuser.hive.hosts 10 | * 11 | 12 | 13 | hadoop.proxyuser.hive.groups 14 | * 15 | 16 | 17 | hadoop.proxyuser.hue.hosts 18 | * 19 | 20 | 21 | hadoop.proxyuser.hue.groups 22 | * 23 | 24 | 25 | httpfs.proxyuser.hue.hosts 26 | * 27 | 28 | 29 | httpfs.proxyuser.hue.groups 30 | * 31 | 32 | 33 | hadoop.proxyuser.root.hosts 34 | * 35 | 36 | 37 | hadoop.proxyuser.root.groups 38 | * 39 | 40 | 41 | -------------------------------------------------------------------------------- /conf/hive/hive-site.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | javax.jdo.option.ConnectionURL 5 | jdbc:mysql://localhost:3306/hive_metastore?createDatabaseIfNotExist=true&useSSL=false 6 | the URL of the MySQL database 7 | 8 | 9 | 10 | javax.jdo.option.ConnectionDriverName 11 | com.mysql.jdbc.Driver 12 | Driver class name for a JDBC metastore 13 | 14 | 15 | 16 | javax.jdo.option.ConnectionUserName 17 | hive 18 | 19 | 20 | 21 | javax.jdo.option.ConnectionPassword 22 | hive 23 | 24 | 25 | 26 | hive.metastore.warehouse.dir 27 | /user/hive/warehouse 28 | 29 | 30 | 31 | hive.exec.scratchdir 32 | /user/hive/tmp 33 | 34 | 35 | 36 | hive.querylog.location 37 | /user/hive/log 38 | 39 | 40 | 41 | hive.server2.enable.doAs 42 | false 43 | 44 | 45 | 46 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM gethue/hue 2 | 3 | RUN sed -i 's/security.ubuntu.com/mirrors.ustc.edu.cn/g' /etc/apt/sources.list 4 | RUN sed -i 's/archive.ubuntu.com/mirrors.ustc.edu.cn/g' /etc/apt/sources.list 5 | 6 | # set mysql password without prompt 7 | RUN apt-get update && apt-get install -y debconf-utils apt-utils && \ 8 | echo mysql-server-5.7 mysql-server/root_password password root | debconf-set-selections && \ 9 | echo mysql-server-5.7 mysql-server/root_password_again password root | debconf-set-selections && \ 10 | apt-get install -y mysql-server-5.7 -o pkg::Options::="--force-confdef" -o pkg::Options::="--force-confold" --fix-missing 11 | 12 | ENV DEBIAN_FRONTEND=noninteractive 13 | RUN apt-get install -y --no-install-recommends build-essential gcc openjdk-8-jdk net-tools vim wget telnet iputils-ping \ 14 | openssh-server openssh-client python python-dev python-pip libmysql-java tzdata && \ 15 | rm -rf /var/lib/apt/lists/* 16 | ENV JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64 17 | RUN echo "Asia/Shanghai" > /etc/timezone && \ 18 | rm -f /etc/localtime && \ 19 | dpkg-reconfigure -f noninteractive tzdata 20 | 21 | 22 | # add all packages 23 | ADD packages/*gz /usr/local/ 24 | 25 | # zookeeper 26 | RUN mv /usr/local/apache-zookeeper-3.5.6-bin /usr/local/zookeeper 27 | RUN mkdir /var/lib/zookeeper 28 | RUN sed "s#/tmp/zookeeper#/var/lib/zookeeper#" /usr/local/zookeeper/conf/zoo_sample.cfg > /usr/local/zookeeper/conf/zoo.cfg 29 | 30 | 31 | # hadoop 32 | RUN mv /usr/local/hadoop-3.1.3 /usr/local/hadoop 33 | RUN ln -s /usr/local/hadoop/etc/hadoop /etc/hadoop 34 | RUN mkdir -p /usr/local/hadoop/data/{namenode,datanode} /etc/hadoop-httpfs/conf/ 35 | 36 | RUN echo "\nStrictHostKeyChecking no\nUserKnownHostsFile" >> /etc/ssh/ssh_config && \ 37 | addgroup hadoop && \ 38 | adduser --ingroup hadoop --quiet --disabled-password hadoop && \ 39 | echo "hadoop ALL=(ALL) NOPASSWD:ALL" >> /etc/sudoers && \ 40 | su hadoop -c "ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa && cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys && chmod 0600 ~/.ssh/authorized_keys" && \ 41 | echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> /etc/hadoop/hadoop-env.sh && \ 42 | echo "bigdata" > /etc/hadoop/workers && \ 43 | chown -R hadoop:hadoop /usr/local/hadoop 44 | 45 | 46 | ENV HADOOP_HOME=/usr/local/hadoop 47 | ENV HADOOP_CONF_DIR=/etc/hadoop 48 | ENV HADOOP_MAPRED_HOME=${HADOOP_HOME} 49 | ENV HADOOP_COMMON_HOME=${HADOOP_HOME} 50 | ENV HADOOP_HDFS_HOME=${HADOOP_HOME} 51 | ENV YARN_HOME=${HADOOP_HOME} 52 | ENV HADOOP_COMMON_LIB_NATIVE_DIR=${HADOOP_HOME}/lib/native 53 | ENV HADOOP_OPTS="-Djava.library.path=${HADOOP_HOME}/lib" 54 | #ENV PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH 55 | ADD conf/hadoop /etc/hadoop 56 | ADD conf/httpfs/httpfs-site.xml /etc/hadoop-httpfs/conf/ 57 | 58 | # Spark 59 | RUN mv /usr/local/spark-2.4.4-bin-hadoop2.7 /usr/local/spark && \ 60 | ln -s /usr/local/spark/conf /etc/spark 61 | ADD conf/spark /etc/spark 62 | RUN cp /usr/local/spark/conf/log4j.properties.template /usr/local/spark/conf/log4j.properties 63 | 64 | # Kafka 65 | RUN mv /usr/local/kafka_2.12-2.3.1 /usr/local/kafka && \ 66 | ln -s /usr/local/kafka/config /etc/kafka 67 | ADD conf/kafka/server.properties /etc/kafka 68 | RUN mkdir /usr/local/kafka/data /usr/local/kafka/log 69 | 70 | # Tez 71 | RUN mv /usr/local/apache-tez-0.9.2-bin /usr/local/tez && \ 72 | ln -s /usr/local/tez/conf /etc/tez 73 | ENV TEZ_HOME=/usr/local/tez 74 | 75 | # Hive 76 | RUN mv /usr/local/apache-hive-3.1.2-bin /usr/local/hive && \ 77 | ln -s /usr/local/hive/conf /etc/hive 78 | ADD conf/hive /etc/hive 79 | RUN ln -s /usr/share/java/mysql-connector-java.jar /usr/local/hive/lib/mysql-connector-java.jar 80 | RUN rm /usr/local/hive/lib/guava-19.0.jar 81 | RUN cp /usr/local/hadoop/share/hadoop/hdfs/lib/guava-27.0-jre.jar /usr/local/hive/lib 82 | ENV HIVE_HOME=/usr/local/hive 83 | ENV HIVE_CONF_DIR=/etc/hive 84 | 85 | # Hue 86 | ADD conf/hue /usr/share/hue/desktop/conf 87 | 88 | # MySQL 89 | RUN chown -R mysql:mysql /var/lib/mysql 90 | 91 | # Flink 92 | RUN mv /usr/local/flink-1.9.1 /usr/local/flink 93 | ADD packages/flink-hadoop-uber.jar /usr/local/flink/lib/ 94 | 95 | # PATH 96 | ENV PATH=/usr/local/flink/bin:/usr/local/spark/bin:/usr/local/hive/bin:/usr/local/kafka/bin:/usr/local/hadoop/bin/:/usr/local/hadoop/sbin:$PATH 97 | RUN echo "PATH=/usr/local/flink/bin:/usr/local/spark/bin:/usr/local/hive/bin:/usr/local/kafka/bin:/usr/local/hadoop/bin/:/usr/local/hadoop/sbin:$PATH" >> /etc/environment 98 | 99 | # involved scripts 100 | ADD scripts/* /run/ 101 | 102 | WORKDIR / 103 | 104 | CMD ["bash", "-c", "/run/entrypoint.sh && /run/wait_to_die.sh"] 105 | -------------------------------------------------------------------------------- /conf/kafka/server.properties: -------------------------------------------------------------------------------- 1 | # Licensed to the Apache Software Foundation (ASF) under one or more 2 | # contributor license agreements. See the NOTICE file distributed with 3 | # this work for additional information regarding copyright ownership. 4 | # The ASF licenses this file to You under the Apache License, Version 2.0 5 | # (the "License"); you may not use this file except in compliance with 6 | # the License. You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | # see kafka.server.KafkaConfig for additional details and defaults 17 | 18 | ############################# Server Basics ############################# 19 | 20 | # The id of the broker. This must be set to a unique integer for each broker. 21 | broker.id=1000 22 | 23 | ############################# Socket Server Settings ############################# 24 | 25 | # The address the socket server listens on. It will get the value returned from 26 | # java.net.InetAddress.getCanonicalHostName() if not configured. 27 | # FORMAT: 28 | # listeners = listener_name://host_name:port 29 | # EXAMPLE: 30 | # listeners = PLAINTEXT://your.host.name:9092 31 | #listeners=PLAINTEXT://:9092 32 | 33 | # Hostname and port the broker will advertise to producers and consumers. If not set, 34 | # it uses the value for "listeners" if configured. Otherwise, it will use the value 35 | # returned from java.net.InetAddress.getCanonicalHostName(). 36 | #advertised.listeners=PLAINTEXT://your.host.name:9092 37 | 38 | # Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details 39 | #listener.security.protocol.map=PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL 40 | 41 | # The number of threads that the server uses for receiving requests from the network and sending responses to the network 42 | num.network.threads=3 43 | 44 | # The number of threads that the server uses for processing requests, which may include disk I/O 45 | num.io.threads=8 46 | 47 | # The send buffer (SO_SNDBUF) used by the socket server 48 | socket.send.buffer.bytes=102400 49 | 50 | # The receive buffer (SO_RCVBUF) used by the socket server 51 | socket.receive.buffer.bytes=102400 52 | 53 | # The maximum size of a request that the socket server will accept (protection against OOM) 54 | socket.request.max.bytes=104857600 55 | 56 | 57 | ############################# Log Basics ############################# 58 | 59 | # A comma separated list of directories under which to store log files 60 | log.dirs=/usr/local/kafka/data 61 | 62 | # The default number of log partitions per topic. More partitions allow greater 63 | # parallelism for consumption, but this will also result in more files across 64 | # the brokers. 65 | num.partitions=3 66 | 67 | # The number of threads per data directory to be used for log recovery at startup and flushing at shutdown. 68 | # This value is recommended to be increased for installations with data dirs located in RAID array. 69 | num.recovery.threads.per.data.dir=1 70 | 71 | ############################# Internal Topic Settings ############################# 72 | # The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state" 73 | # For anything other than development testing, a value greater than 1 is recommended for to ensure availability such as 3. 74 | offsets.topic.replication.factor=1 75 | transaction.state.log.replication.factor=1 76 | transaction.state.log.min.isr=1 77 | 78 | ############################# Log Flush Policy ############################# 79 | 80 | # Messages are immediately written to the filesystem but by default we only fsync() to sync 81 | # the OS cache lazily. The following configurations control the flush of data to disk. 82 | # There are a few important trade-offs here: 83 | # 1. Durability: Unflushed data may be lost if you are not using replication. 84 | # 2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush. 85 | # 3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to excessive seeks. 86 | # The settings below allow one to configure the flush policy to flush data after a period of time or 87 | # every N messages (or both). This can be done globally and overridden on a per-topic basis. 88 | 89 | # The number of messages to accept before forcing a flush of data to disk 90 | #log.flush.interval.messages=10000 91 | 92 | # The maximum amount of time a message can sit in a log before we force a flush 93 | #log.flush.interval.ms=1000 94 | 95 | ############################# Log Retention Policy ############################# 96 | 97 | # The following configurations control the disposal of log segments. The policy can 98 | # be set to delete segments after a period of time, or after a given size has accumulated. 99 | # A segment will be deleted whenever *either* of these criteria are met. Deletion always happens 100 | # from the end of the log. 101 | 102 | # The minimum age of a log file to be eligible for deletion due to age 103 | log.retention.hours=168 104 | 105 | # A size-based retention policy for logs. Segments are pruned from the log unless the remaining 106 | # segments drop below log.retention.bytes. Functions independently of log.retention.hours. 107 | #log.retention.bytes=1073741824 108 | 109 | # The maximum size of a log segment file. When this size is reached a new log segment will be created. 110 | log.segment.bytes=1073741824 111 | 112 | # The interval at which log segments are checked to see if they can be deleted according 113 | # to the retention policies 114 | log.retention.check.interval.ms=300000 115 | 116 | ############################# Zookeeper ############################# 117 | 118 | # Zookeeper connection string (see zookeeper docs for details). 119 | # This is a comma separated host:port pairs, each corresponding to a zk 120 | # server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002". 121 | # You can also append an optional chroot string to the urls to specify the 122 | # root directory for all kafka znodes. 123 | zookeeper.connect=localhost:2181 124 | 125 | # Timeout in ms for connecting to zookeeper 126 | zookeeper.connection.timeout.ms=6000 127 | 128 | 129 | ############################# Group Coordinator Settings ############################# 130 | 131 | # The following configuration specifies the time, in milliseconds, that the GroupCoordinator will delay the initial consumer rebalance. 132 | # The rebalance will be further delayed by the value of group.initial.rebalance.delay.ms as new members join the group, up to a maximum of max.poll.interval.ms. 133 | # The default value for this is 3 seconds. 134 | # We override this to 0 here as it makes for a better out-of-the-box experience for development and testing. 135 | # However, in production environments the default value of 3 seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application startup. 136 | group.initial.rebalance.delay.ms=0 137 | 138 | 139 | # extra config 140 | -------------------------------------------------------------------------------- /conf/hue/hue-overrides.ini: -------------------------------------------------------------------------------- 1 | # Hue configuration file 2 | # =================================== 3 | # 4 | # For complete documentation about the contents of this file, run 5 | # $ /build/env/bin/hue config_help 6 | # 7 | # All .ini files under the current directory are treated equally. Their 8 | # contents are merged to form the Hue configuration, which can 9 | # can be viewed on the Hue at 10 | # http://:/dump_config 11 | 12 | 13 | ########################################################################### 14 | # General configuration for core Desktop features (authentication, etc) 15 | ########################################################################### 16 | 17 | [desktop] 18 | 19 | # Set this to a random string, the longer the better. 20 | # This is used for secure hashing in the session store. 21 | # secret_key= 22 | 23 | # Execute this script to produce the Django secret key. This will be used when 24 | # 'secret_key' is not set. 25 | ## secret_key_script= 26 | 27 | # Webserver listens on this address and port 28 | http_host=0.0.0.0 29 | http_port=8888 30 | 31 | # A comma-separated list of available Hue load balancers 32 | ## hue_load_balancer= 33 | 34 | # Time zone name 35 | time_zone=Asia/Shanghai 36 | 37 | # Enable or disable debug mode. 38 | django_debug_mode=false 39 | 40 | # Enable development mode, where notably static files are not cached. 41 | ## dev=false 42 | 43 | # Enable or disable database debug mode. 44 | ## database_logging=false 45 | 46 | # Whether to send debug messages from JavaScript to the server logs. 47 | ## send_dbug_messages=false 48 | 49 | # Enable or disable backtrace for server error 50 | http_500_debug_mode=false 51 | 52 | # Enable or disable instrumentation. If django_debug_mode is True, this is automatically enabled 53 | ## instrumentation=false 54 | 55 | # Server email for internal error messages 56 | ## django_server_email='hue@localhost.localdomain' 57 | 58 | # Email backend 59 | ## django_email_backend=django.core.mail.backends.smtp.EmailBackend 60 | 61 | # Set to true to use CherryPy as the webserver, set to false 62 | # to use Gunicorn as the webserver. Defaults to CherryPy if 63 | # key is not specified. 64 | ## use_cherrypy_server=true 65 | 66 | # Gunicorn work class: gevent or evenlet, gthread or sync. 67 | ## gunicorn_work_class=eventlet 68 | 69 | # The number of Gunicorn worker processes. If not specified, it uses: (number of CPU * 2) + 1. 70 | ## gunicorn_number_of_workers=None 71 | 72 | # Webserver runs as this user 73 | ## server_user=hue 74 | ## server_group=hue 75 | 76 | # This should be the Hue admin and proxy user 77 | ## default_user=hue 78 | 79 | # This should be the hadoop cluster admin 80 | ## default_hdfs_superuser=hdfs 81 | 82 | # If set to false, runcpserver will not actually start the web server. 83 | # Used if Apache is being used as a WSGI container. 84 | ## enable_server=yes 85 | 86 | # Number of threads used by the CherryPy web server 87 | ## cherrypy_server_threads=50 88 | 89 | # This property specifies the maximum size of the receive buffer in bytes in thrift sasl communication, 90 | # default value is 2097152 (2 MB), which equals to (2 * 1024 * 1024) 91 | ## sasl_max_buffer=2097152 92 | 93 | # Hue will try to get the actual host of the Service, even if it resides behind a load balancer. 94 | # This will enable an automatic configuration of the service without requiring custom configuration of the service load balancer. 95 | # This is available for the Impala service only currently. It is highly recommended to only point to a series of coordinator-only nodes only. 96 | # enable_smart_thrift_pool=false 97 | 98 | # Filename of SSL Certificate 99 | ## ssl_certificate= 100 | 101 | # Filename of SSL RSA Private Key 102 | ## ssl_private_key= 103 | 104 | # Filename of SSL Certificate Chain 105 | ## ssl_certificate_chain= 106 | 107 | # SSL certificate password 108 | ## ssl_password= 109 | 110 | # Execute this script to produce the SSL password. This will be used when 'ssl_password' is not set. 111 | ## ssl_password_script= 112 | 113 | # X-Content-Type-Options: nosniff This is a HTTP response header feature that helps prevent attacks based on MIME-type confusion. 114 | ## secure_content_type_nosniff=true 115 | 116 | # X-Xss-Protection: \"1; mode=block\" This is a HTTP response header feature to force XSS protection. 117 | ## secure_browser_xss_filter=true 118 | 119 | # X-Content-Type-Options: nosniff This is a HTTP response header feature that helps prevent attacks based on MIME-type confusion. 120 | ## secure_content_security_policy="script-src 'self' 'unsafe-inline' 'unsafe-eval' *.google-analytics.com *.doubleclick.net data:;img-src 'self' *.google-analytics.com *.doubleclick.net http://*.tile.osm.org *.tile.osm.org *.gstatic.com data:;style-src 'self' 'unsafe-inline' fonts.googleapis.com;connect-src 'self';frame-src *;child-src 'self' data: *.vimeo.com;object-src 'none'" 121 | 122 | # Strict-Transport-Security HTTP Strict Transport Security(HSTS) is a policy which is communicated by the server to the user agent via HTTP response header field name "Strict-Transport-Security". HSTS policy specifies a period of time during which the user agent(browser) should only access the server in a secure fashion(https). 123 | ## secure_ssl_redirect=False 124 | ## secure_redirect_host=0.0.0.0 125 | ## secure_redirect_exempt=[] 126 | ## secure_hsts_seconds=31536000 127 | ## secure_hsts_include_subdomains=true 128 | 129 | # List of allowed and disallowed ciphers in cipher list format. 130 | # See http://www.openssl.org/docs/apps/ciphers.html for more information on 131 | # cipher list format. This list is from 132 | # https://wiki.mozilla.org/Security/Server_Side_TLS v3.7 intermediate 133 | # recommendation, which should be compatible with Firefox 1, Chrome 1, IE 7, 134 | # Opera 5 and Safari 1. 135 | ## ssl_cipher_list=ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:DHE-DSS-AES128-GCM-SHA256:kEDH+AESGCM:ECDHE-RSA-AES128-SHA256:ECDHE-ECDSA-AES128-SHA256:ECDHE-RSA-AES128-SHA:ECDHE-ECDSA-AES128-SHA:ECDHE-RSA-AES256-SHA384:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA:ECDHE-ECDSA-AES256-SHA:DHE-RSA-AES128-SHA256:DHE-RSA-AES128-SHA:DHE-DSS-AES128-SHA256:DHE-RSA-AES256-SHA256:DHE-DSS-AES256-SHA:DHE-RSA-AES256-SHA:AES128-GCM-SHA256:AES256-GCM-SHA384:AES128-SHA256:AES256-SHA256:AES128-SHA:AES256-SHA:AES:CAMELLIA:DES-CBC3-SHA:!aNULL:!eNULL:!EXPORT:!DES:!RC4:!MD5:!PSK:!aECDH:!EDH-DSS-DES-CBC3-SHA:!EDH-RSA-DES-CBC3-SHA:!KRB5-DES-CBC3-SHA 136 | 137 | # Path to default Certificate Authority certificates. 138 | ## ssl_cacerts=/etc/hue/cacerts.pem 139 | 140 | # Choose whether Hue should validate certificates received from the server. 141 | ## ssl_validate=true 142 | 143 | # Default LDAP/PAM/.. username and password of the hue user used for authentications with other services. 144 | # Inactive if password is empty. 145 | # e.g. LDAP pass-through authentication for HiveServer2 or Impala. Apps can override them individually. 146 | ## auth_username=hue 147 | ## auth_password= 148 | 149 | # Default encoding for site data 150 | ## default_site_encoding=utf-8 151 | 152 | # Help improve Hue with anonymous usage analytics. 153 | # Use Google Analytics to see how many times an application or specific section of an application is used, nothing more. 154 | ## collect_usage=true 155 | 156 | # Tile layer server URL for the Leaflet map charts 157 | # Read more on http://leafletjs.com/reference.html#tilelayer 158 | # Make sure you add the tile domain to the img-src section of the 'secure_content_security_policy' configuration parameter as well. 159 | ## leaflet_tile_layer=http://{s}.tile.osm.org/{z}/{x}/{y}.png 160 | 161 | # The copyright message for the specified Leaflet maps Tile Layer 162 | ## leaflet_tile_layer_attribution='© OpenStreetMap contributors' 163 | 164 | # All the map options accordingly to http://leafletjs.com/reference-0.7.7.html#map-options 165 | # To change CRS, just use the name, ie. "EPSG4326" 166 | ## leaflet_map_options='{}' 167 | 168 | # All the tile layer options, accordingly to http://leafletjs.com/reference-0.7.7.html#tilelayer 169 | ## leaflet_tile_layer_options='{}' 170 | 171 | # X-Frame-Options HTTP header value. Use 'DENY' to deny framing completely 172 | ## http_x_frame_options=SAMEORIGIN 173 | 174 | # Enable X-Forwarded-Host header if the load balancer requires it. 175 | ## use_x_forwarded_host=true 176 | 177 | # Support for HTTPS termination at the load-balancer level with SECURE_PROXY_SSL_HEADER. 178 | ## secure_proxy_ssl_header=false 179 | 180 | # Comma-separated list of Django middleware classes to use. 181 | # See https://docs.djangoproject.com/en/1.4/ref/middleware/ for more details on middlewares in Django. 182 | ## middleware=desktop.auth.backend.LdapSynchronizationBackend 183 | 184 | # Comma-separated list of regular expressions, which match the redirect URL. 185 | # For example, to restrict to your local domain and FQDN, the following value can be used: 186 | # ^\/.*$,^http:\/\/www.mydomain.com\/.*$ 187 | ## redirect_whitelist=^(\/[a-zA-Z0-9]+.*|\/)$ 188 | 189 | # Comma separated list of apps to not load at server startup. 190 | # e.g.: pig,zookeeper 191 | ## app_blacklist= 192 | 193 | # Id of the cluster where Hue is located. 194 | ## cluster_id='default' 195 | 196 | # Choose whether to show the new SQL editor. 197 | ## use_new_editor=true 198 | 199 | # Global setting to allow or disable end user downloads in all Hue. 200 | # e.g. Query result in Editors and Dashboards, file in File Browser... 201 | ## enable_download=true 202 | 203 | # Choose whether to enable SQL syntax check or not 204 | ## enable_sql_syntax_check=true 205 | 206 | # Choose whether to show the improved assist panel and the right context panel 207 | ## use_new_side_panels=false 208 | 209 | # Choose whether to use new charting library across the whole Hue. 210 | ## use_new_charts=false 211 | 212 | # Choose whether to allow multi tenancy or not. 213 | ## enable_organizations=false 214 | 215 | # Editor autocomplete timeout (ms) when fetching columns, fields, tables etc. 216 | # To disable this type of autocompletion set the value to 0. 217 | ## editor_autocomplete_timeout=30000 218 | 219 | # Enable saved default configurations for Hive, Impala, Spark, and Oozie. 220 | ## use_default_configuration=false 221 | 222 | # The directory where to store the auditing logs. Auditing is disable if the value is empty. 223 | # e.g. /var/log/hue/audit.log 224 | ## audit_event_log_dir= 225 | 226 | # Size in KB/MB/GB for audit log to rollover. 227 | ## audit_log_max_file_size=100MB 228 | 229 | # Timeout in seconds for REST calls. 230 | ## rest_conn_timeout=120 231 | 232 | # A json file containing a list of log redaction rules for cleaning sensitive data 233 | # from log files. It is defined as: 234 | # 235 | # { 236 | # "version": 1, 237 | # "rules": [ 238 | # { 239 | # "description": "This is the first rule", 240 | # "trigger": "triggerstring 1", 241 | # "search": "regex 1", 242 | # "replace": "replace 1" 243 | # }, 244 | # { 245 | # "description": "This is the second rule", 246 | # "trigger": "triggerstring 2", 247 | # "search": "regex 2", 248 | # "replace": "replace 2" 249 | # } 250 | # ] 251 | # } 252 | # 253 | # Redaction works by searching a string for the [TRIGGER] string. If found, 254 | # the [REGEX] is used to replace sensitive information with the 255 | # [REDACTION_MASK]. If specified with 'log_redaction_string', the 256 | # 'log_redaction_string' rules will be executed after the 257 | # 'log_redaction_file' rules. 258 | # 259 | # For example, here is a file that would redact passwords and social security numbers: 260 | 261 | # { 262 | # "version": 1, 263 | # "rules": [ 264 | # { 265 | # "description": "Redact passwords", 266 | # "trigger": "password", 267 | # "search": "password=\".*\"", 268 | # "replace": "password=\"???\"" 269 | # }, 270 | # { 271 | # "description": "Redact social security numbers", 272 | # "trigger": "", 273 | # "search": "\d{3}-\d{2}-\d{4}", 274 | # "replace": "XXX-XX-XXXX" 275 | # } 276 | # ] 277 | # } 278 | ## log_redaction_file= 279 | 280 | # Comma separated list of strings representing the host/domain names that the Hue server can serve. 281 | # e.g.: localhost,domain1,* 282 | ## allowed_hosts="*" 283 | 284 | # Allow use django debug tool with Chrome browser for debugging issue, django_debug_mode must be true also 285 | ## enable_django_debug_tool=false 286 | 287 | # Comma separated list of users' username that allow to use django debug tool. If it is empty, all users are allowed. 288 | ## django_debug_tool_users= 289 | 290 | # Number of characters in rest api reponse calls to dump to the logs when debug is enabled. Set to -1 for entire response. 291 | ## rest_response_size=2000 292 | 293 | # Turn on Prometheus metrics end point /metrics. 294 | ## enable_prometheus=false 295 | 296 | # Administrators 297 | # ---------------- 298 | [[django_admins]] 299 | ## [[[admin1]]] 300 | ## name=john 301 | ## email=john@doe.com 302 | 303 | # UI customizations 304 | # ------------------- 305 | [[custom]] 306 | 307 | # Top banner HTML code 308 | # e.g.

Test Lab A2 Hue Services

309 | ## banner_top_html='
This is Hue 4 Beta! - Please feel free to email any feedback / questions to team@gethue.com or @gethue.
' 310 | 311 | # Login splash HTML code 312 | # e.g. WARNING: You are required to have authorization before you proceed 313 | ## login_splash_html=

GetHue.com



WARNING: You have accessed a computer managed by GetHue. You are required to have authorization from GetHue before you proceed. 314 | 315 | # Cache timeout in milliseconds for the assist, autocomplete, etc. 316 | # defaults to 10 days, set to 0 to disable caching 317 | ## cacheable_ttl=864000000 318 | 319 | # SVG code to replace the default Hue logo in the top bar and sign in screen 320 | # e.g. 321 | ## logo_svg= 322 | 323 | # Configuration options for user authentication into the web application 324 | # ------------------------------------------------------------------------ 325 | [[auth]] 326 | 327 | # Authentication backend. Common settings are: 328 | # - django.contrib.auth.backends.ModelBackend (entirely Django backend) 329 | # - desktop.auth.backend.AllowAllBackend (allows everyone) 330 | # - desktop.auth.backend.AllowFirstUserDjangoBackend 331 | # (Default. Relies on Django and user manager, after the first login) 332 | # - desktop.auth.backend.LdapBackend 333 | # - desktop.auth.backend.PamBackend 334 | # - desktop.auth.backend.SpnegoDjangoBackend 335 | # - desktop.auth.backend.KnoxSpnegoDjangoBackend 336 | # - desktop.auth.backend.RemoteUserDjangoBackend 337 | # - libsaml.backend.SAML2Backend 338 | # - liboauth.backend.OAuthBackend 339 | # - desktop.auth.backend.OIDCBackend 340 | # (New oauth, support Twitter, Facebook, Google+ and Linkedin 341 | # Multiple Authentication backends are supported by specifying a comma-separated list in order of priority. 342 | # However, in order to enable OAuthBackend, it must be the ONLY backend configured. 343 | ## backend=desktop.auth.backend.AllowFirstUserDjangoBackend 344 | 345 | # Class which defines extra accessor methods for User objects. 346 | ## user_aug=desktop.auth.backend.DefaultUserAugmentor 347 | 348 | # The service to use when querying PAM. 349 | ## pam_service=login 350 | 351 | # When using the desktop.auth.backend.RemoteUserDjangoBackend, this sets 352 | # the normalized name of the header that contains the remote user. 353 | # The HTTP header in the request is converted to a key by converting 354 | # all characters to uppercase, replacing any hyphens with underscores 355 | # and adding an HTTP_ prefix to the name. So, for example, if the header 356 | # is called Remote-User that would be configured as HTTP_REMOTE_USER 357 | # 358 | # Defaults to HTTP_REMOTE_USER 359 | ## remote_user_header=HTTP_REMOTE_USER 360 | 361 | # Ignore the case of usernames when searching for existing users. 362 | # Supported in remoteUserDjangoBackend and SpnegoDjangoBackend 363 | ## ignore_username_case=true 364 | 365 | # Forcibly cast usernames to lowercase, takes precedence over force_username_uppercase 366 | # Supported in remoteUserDjangoBackend and SpnegoDjangoBackend 367 | ## force_username_lowercase=true 368 | 369 | # Forcibly cast usernames to uppercase, cannot be combined with force_username_lowercase 370 | ## force_username_uppercase=false 371 | 372 | # Users will expire after they have not logged in for 'n' amount of seconds. 373 | # A negative number means that users will never expire. 374 | ## expires_after=-1 375 | 376 | # Apply 'expires_after' to superusers. 377 | ## expire_superusers=true 378 | 379 | # Users will automatically be logged out after 'n' seconds of inactivity. 380 | # A negative number means that idle sessions will not be timed out. 381 | idle_session_timeout=-1 382 | 383 | # Force users to change password on first login with desktop.auth.backend.AllowFirstUserDjangoBackend 384 | ## change_default_password=false 385 | 386 | # Number of login attempts allowed before a record is created for failed logins 387 | ## login_failure_limit=3 388 | 389 | # After number of allowed login attempts are exceeded, do we lock out this IP and optionally user agent? 390 | ## login_lock_out_at_failure=false 391 | 392 | # If set, defines period of inactivity in hours after which failed logins will be forgotten. 393 | # A value of 0 or None will disable this check. Default: None 394 | ## login_cooloff_time=None 395 | 396 | # If True, lock out based on an IP address AND a user agent. 397 | # This means requests from different user agents but from the same IP are treated differently. 398 | ## login_lock_out_use_user_agent=false 399 | 400 | # If True, lock out based on IP and user 401 | ## login_lock_out_by_combination_user_and_ip=false 402 | 403 | # If True, it will look for the IP address from the header defined at reverse_proxy_header. 404 | ## behind_reverse_proxy=false 405 | 406 | # If behind_reverse_proxy is True, it will look for the IP address from this header. Default: HTTP_X_FORWARDED_FOR 407 | ## reverse_proxy_header=HTTP_X_FORWARDED_FOR 408 | 409 | # Configuration options for connecting to LDAP and Active Directory 410 | # ------------------------------------------------------------------- 411 | [[ldap]] 412 | 413 | # The search base for finding users and groups 414 | ## base_dn="DC=mycompany,DC=com" 415 | 416 | # URL of the LDAP server 417 | ## ldap_url=ldap://auth.mycompany.com 418 | 419 | # The NT domain used for LDAP authentication 420 | ## nt_domain=mycompany.com 421 | 422 | # A PEM-format file containing certificates for the CA's that 423 | # Hue will trust for authentication over TLS. 424 | # The certificate for the CA that signed the 425 | # LDAP server certificate must be included among these certificates. 426 | # See more here http://www.openldap.org/doc/admin24/tls.html. 427 | ## ldap_cert= 428 | ## use_start_tls=true 429 | 430 | # Distinguished name of the user to bind as -- not necessary if the LDAP server 431 | # supports anonymous searches 432 | ## bind_dn="CN=ServiceAccount,DC=mycompany,DC=com" 433 | 434 | # Password of the bind user -- not necessary if the LDAP server supports 435 | # anonymous searches 436 | ## bind_password= 437 | 438 | # Execute this script to produce the bind user password. This will be used 439 | # when 'bind_password' is not set. 440 | ## bind_password_script= 441 | 442 | # Pattern for searching for usernames -- Use for the parameter 443 | # For use when using LdapBackend for Hue authentication 444 | ## ldap_username_pattern="uid=,ou=People,dc=mycompany,dc=com" 445 | 446 | # Create users in Hue when they try to login with their LDAP credentials 447 | # For use when using LdapBackend for Hue authentication 448 | ## create_users_on_login = true 449 | 450 | # Synchronize a users groups when they login 451 | ## sync_groups_on_login=true 452 | 453 | # A comma-separated list of Ldap groups with users that can login 454 | ## login_groups= 455 | 456 | # Ignore the case of usernames when searching for existing users in Hue. 457 | ## ignore_username_case=true 458 | 459 | # Force usernames to lowercase when creating new users from LDAP. 460 | # Takes precedence over force_username_uppercase 461 | ## force_username_lowercase=true 462 | 463 | # Force usernames to uppercase, cannot be combined with force_username_lowercase 464 | ## force_username_uppercase=false 465 | 466 | # Use search bind authentication. 467 | ## search_bind_authentication=true 468 | 469 | # Choose which kind of subgrouping to use: nested or suboordinate (deprecated). 470 | ## subgroups=suboordinate 471 | 472 | # Define the number of levels to search for nested members. 473 | ## nested_members_search_depth=10 474 | 475 | # Whether or not to follow referrals 476 | ## follow_referrals=false 477 | 478 | # Enable python-ldap debugging. 479 | ## debug=false 480 | 481 | # Sets the debug level within the underlying LDAP C lib. 482 | ## debug_level=255 483 | 484 | # Possible values for trace_level are 0 for no logging, 1 for only logging the method calls with arguments, 485 | # 2 for logging the method calls with arguments and the complete results and 9 for also logging the traceback of method calls. 486 | ## trace_level=0 487 | 488 | [[[users]]] 489 | 490 | # Base filter for searching for users 491 | ## user_filter="objectclass=*" 492 | 493 | # The username attribute in the LDAP schema 494 | ## user_name_attr=sAMAccountName 495 | 496 | [[[groups]]] 497 | 498 | # Base filter for searching for groups 499 | ## group_filter="objectclass=*" 500 | 501 | # The group name attribute in the LDAP schema 502 | ## group_name_attr=cn 503 | 504 | # The attribute of the group object which identifies the members of the group 505 | ## group_member_attr=members 506 | 507 | [[[ldap_servers]]] 508 | 509 | ## [[[[mycompany]]]] 510 | 511 | # The search base for finding users and groups 512 | ## base_dn="DC=mycompany,DC=com" 513 | 514 | # URL of the LDAP server 515 | ## ldap_url=ldap://auth.mycompany.com 516 | 517 | # The NT domain used for LDAP authentication 518 | ## nt_domain=mycompany.com 519 | 520 | # A PEM-format file containing certificates for the CA's that 521 | # Hue will trust for authentication over TLS. 522 | # The certificate for the CA that signed the 523 | # LDAP server certificate must be included among these certificates. 524 | # See more here http://www.openldap.org/doc/admin24/tls.html. 525 | ## ldap_cert= 526 | ## use_start_tls=true 527 | 528 | # Distinguished name of the user to bind as -- not necessary if the LDAP server 529 | # supports anonymous searches 530 | ## bind_dn="CN=ServiceAccount,DC=mycompany,DC=com" 531 | 532 | # Password of the bind user -- not necessary if the LDAP server supports 533 | # anonymous searches 534 | ## bind_password= 535 | 536 | # Execute this script to produce the bind user password. This will be used 537 | # when 'bind_password' is not set. 538 | ## bind_password_script= 539 | 540 | # Pattern for searching for usernames -- Use for the parameter 541 | # For use when using LdapBackend for Hue authentication 542 | ## ldap_username_pattern="uid=,ou=People,dc=mycompany,dc=com" 543 | 544 | ## Use search bind authentication. 545 | ## search_bind_authentication=true 546 | 547 | # Whether or not to follow referrals 548 | ## follow_referrals=false 549 | 550 | # Enable python-ldap debugging. 551 | ## debug=false 552 | 553 | # Sets the debug level within the underlying LDAP C lib. 554 | ## debug_level=255 555 | 556 | # Possible values for trace_level are 0 for no logging, 1 for only logging the method calls with arguments, 557 | # 2 for logging the method calls with arguments and the complete results and 9 for also logging the traceback of method calls. 558 | ## trace_level=0 559 | 560 | ## [[[[[users]]]]] 561 | 562 | # Base filter for searching for users 563 | ## user_filter="objectclass=Person" 564 | 565 | # The username attribute in the LDAP schema 566 | ## user_name_attr=sAMAccountName 567 | 568 | ## [[[[[groups]]]]] 569 | 570 | # Base filter for searching for groups 571 | ## group_filter="objectclass=groupOfNames" 572 | 573 | # The username attribute in the LDAP schema 574 | ## group_name_attr=cn 575 | 576 | # Configuration options for specifying the Source Version Control. 577 | # ---------------------------------------------------------------- 578 | [[vcs]] 579 | 580 | ## [[[git-read-only]]] 581 | ## Base URL to Remote Server 582 | # remote_url=https://github.com/cloudera/hue/tree/master 583 | 584 | ## Base URL to Version Control API 585 | # api_url=https://api.github.com 586 | ## [[[github]]] 587 | 588 | ## Base URL to Remote Server 589 | # remote_url=https://github.com/cloudera/hue/tree/master 590 | 591 | ## Base URL to Version Control API 592 | # api_url=https://api.github.com 593 | 594 | # These will be necessary when you want to write back to the repository. 595 | ## Client ID for Authorized Application 596 | # client_id= 597 | 598 | ## Client Secret for Authorized Application 599 | # client_secret= 600 | ## [[[svn]] 601 | ## Base URL to Remote Server 602 | # remote_url=https://github.com/cloudera/hue/tree/master 603 | 604 | ## Base URL to Version Control API 605 | # api_url=https://api.github.com 606 | 607 | # These will be necessary when you want to write back to the repository. 608 | ## Client ID for Authorized Application 609 | # client_id= 610 | 611 | ## Client Secret for Authorized Application 612 | # client_secret= 613 | 614 | # Configuration options for specifying the Desktop Database. For more info, 615 | # see http://docs.djangoproject.com/en/1.11/ref/settings/#database-engine 616 | # ------------------------------------------------------------------------ 617 | [[database]] 618 | # Database engine is typically one of: 619 | # postgresql_psycopg2, mysql, sqlite3 or oracle. 620 | # 621 | # Note that for sqlite3, 'name', below is a path to the filename. For other backends, it is the database name 622 | # Note for Oracle, options={"threaded":true} must be set in order to avoid crashes. 623 | # Note for Oracle, you can use the Oracle Service Name by setting "host=" and "port=" and then "name=:/". 624 | # Note for MariaDB use the 'mysql' engine. 625 | #engine=mysql 626 | #host=localhost 627 | #port=3306 628 | #user=hue 629 | #password=hue 630 | #name=hue 631 | # conn_max_age option to make database connection persistent value in seconds 632 | # https://docs.djangoproject.com/en/1.11/ref/databases/#persistent-connections 633 | ## conn_max_age=0 634 | # Execute this script to produce the database password. This will be used when 'password' is not set. 635 | ## password_script=/path/script 636 | ## name=desktop/desktop.db 637 | ## options={} 638 | # Database schema, to be used only when public schema is revoked in postgres 639 | ## schema=public 640 | 641 | # Configuration options for specifying the Desktop session. 642 | # For more info, see https://docs.djangoproject.com/en/1.4/topics/http/sessions/ 643 | # ------------------------------------------------------------------------ 644 | [[session]] 645 | # The name of the cookie to use for sessions. 646 | # This can have any value that is not used by the other cookie names in your application. 647 | ## cookie_name=sessionid 648 | 649 | # The cookie containing the users' session ID will expire after this amount of time in seconds. 650 | # Default is 2 weeks. 651 | ## ttl=1209600 652 | 653 | # The cookie containing the users' session ID and csrf cookie will be secure. 654 | # Should only be enabled with HTTPS. 655 | ## secure=false 656 | 657 | # The cookie containing the users' session ID and csrf cookie will use the HTTP only flag. 658 | ## http_only=true 659 | 660 | # Use session-length cookies. Logs out the user when she closes the browser window. 661 | ## expire_at_browser_close=false 662 | 663 | # If set, limits the number of concurrent user sessions. 1 represents 1 browser session per user. Default: 0 (unlimited sessions per user) 664 | ## concurrent_user_session_limit=0 665 | 666 | # A list of hosts which are trusted origins for unsafe requests. See django's CSRF_TRUSTED_ORIGINS for more information 667 | ## trusted_origins=.cloudera.com 668 | 669 | # Configuration options for connecting to an external SMTP server 670 | # ------------------------------------------------------------------------ 671 | [[smtp]] 672 | 673 | # The SMTP server information for email notification delivery 674 | host=localhost 675 | port=25 676 | user= 677 | password= 678 | 679 | # Whether to use a TLS (secure) connection when talking to the SMTP server 680 | tls=no 681 | 682 | # Default email address to use for various automated notification from Hue 683 | ## default_from_email=hue@localhost 684 | 685 | 686 | # Configuration options for KNOX integration for secured CDPD cluster 687 | # ------------------------------------------------------------------------ 688 | [[knox]] 689 | 690 | # This is a list of hosts that knox proxy requests can come from 691 | ## knox_proxyhosts=server1.domain.com,server2.domain.com 692 | # List of Kerberos principal name which is allowed to impersonate others 693 | ## knox_principal=knox1,knox2 694 | # Comma separated list of strings representing the ports that the Hue server can trust as knox port. 695 | ## knox_ports=80,8443 696 | 697 | # Configuration options for Kerberos integration for secured Hadoop clusters 698 | # ------------------------------------------------------------------------ 699 | [[kerberos]] 700 | 701 | # Path to Hue's Kerberos keytab file 702 | ## hue_keytab= 703 | # Kerberos principal name for Hue 704 | ## hue_principal=hue/hostname.foo.com 705 | # Frequency in seconds with which Hue will renew its keytab 706 | ## keytab_reinit_frequency=3600 707 | # Path to keep Kerberos credentials cached 708 | ## ccache_path=/var/run/hue/hue_krb5_ccache 709 | # Path to kinit 710 | ## kinit_path=/path/to/kinit 711 | 712 | # Mutual authentication from the server, attaches HTTP GSSAPI/Kerberos Authentication to the given Request object 713 | ## mutual_authentication="OPTIONAL" or "REQUIRED" or "DISABLED" 714 | 715 | # Configuration options for using OAuthBackend (Core) login 716 | # ------------------------------------------------------------------------ 717 | [[oauth]] 718 | # The Consumer key of the application 719 | ## consumer_key=XXXXXXXXXXXXXXXXXXXXX 720 | 721 | # The Consumer secret of the application 722 | ## consumer_secret=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX 723 | 724 | # The Request token URL 725 | ## request_token_url=https://api.twitter.com/oauth/request_token 726 | 727 | # The Access token URL 728 | ## access_token_url=https://api.twitter.com/oauth/access_token 729 | 730 | # The Authorize URL 731 | ## authenticate_url=https://api.twitter.com/oauth/authorize 732 | 733 | # Configuration options for using OIDCBackend (Core) login for SSO 734 | # ------------------------------------------------------------------------ 735 | [[oidc]] 736 | # The client ID as relay party set in OpenID provider 737 | ## oidc_rp_client_id=XXXXXXXXXXXXXXXXXXXXX 738 | 739 | # The client secret as relay party set in OpenID provider 740 | ## oidc_rp_client_secret=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX 741 | 742 | # The OpenID provider authoriation endpoint 743 | ## oidc_op_authorization_endpoint=https://keycloak.example.com/auth/realms/Cloudera/protocol/openid-connect/auth 744 | 745 | # The OpenID provider token endpoint 746 | ## oidc_op_token_endpoint=https://keycloak.example.com/auth/realms/cloudera/protocol/openid-connect/token 747 | 748 | # The OpenID provider user info endpoint 749 | ## oidc_op_user_endpoint=https://keycloak.example.com/auth/realms/cloudera/protocol/openid-connect/userinfo 750 | 751 | # The OpenID provider signing key in PEM or DER format 752 | ## oidc_rp_idp_sign_key=/path/to/key_file 753 | 754 | # The OpenID provider authoriation endpoint 755 | ## oidc_op_jwks_endpoint=https://keycloak.example.com/auth/realms/Cloudera/protocol/openid-connect/certs 756 | 757 | # Whether Hue as OpenID Connect client verify SSL cert 758 | ## oidc_verify_ssl=true 759 | 760 | # As relay party Hue URL path to redirect to after login 761 | ## login_redirect_url=https://localhost:8888/oidc/callback/ 762 | 763 | # The OpenID provider URL path to redirect to after logout 764 | ## logout_redirect_url=https://keycloak.example.com/auth/realms/cloudera/protocol/openid-connect/logout 765 | 766 | # As relay party Hue URL path to redirect to after login 767 | ## login_redirect_url_failure=https://localhost:8888/hue/oidc_failed/ 768 | 769 | # Create a new user from OpenID Connect on login if it doesn't exist 770 | ## create_users_on_login=true 771 | 772 | # When creating a new user, which 'claims' attribute from the OIDC provider to be used for creating the username. 773 | # Default to 'preferred_username'. Possible values include: 'email' 774 | ## oidc_username_attribute=preferred_username 775 | 776 | # The group of users will be created and updated as superuser. To use this feature, setup in Keycloak: 777 | # 1. add the name of the group here 778 | # 2. in Keycloak, go to your_realm --> your_clients --> Mappers, add a mapper 779 | # Mapper Type: Group Membership (this is predefined mapper type) 780 | # Token Claim Name: group_membership (required exact string) 781 | ## superuser_group=hue_superusers 782 | 783 | # Configuration options for Metrics 784 | # ------------------------------------------------------------------------ 785 | [[metrics]] 786 | 787 | # Enable the metrics URL "/desktop/metrics" 788 | ## enable_web_metrics=True 789 | 790 | # If specified, Hue will write metrics to this file. 791 | ## location=/var/log/hue/metrics.json 792 | 793 | # Time in milliseconds on how frequently to collect metrics 794 | ## collection_interval=30000 795 | 796 | 797 | # Configuration options for the request Tracing 798 | # ------------------------------------------------------------------------ 799 | [[tracing]] 800 | ## If tracing is enabled. 801 | # enabled=false 802 | 803 | ## Trace all the requests instead of a few specific ones like the SQL Editor. Much noisiers. 804 | # trace_all=false 805 | 806 | 807 | # Configuration options for the Task Server 808 | # ------------------------------------------------------------------------ 809 | [[task_server]] 810 | 811 | # If resource intensive or blocking can be delegated to an already running task server. 812 | ## enabled=False 813 | 814 | # Switch on the integration with the Task Scheduler. 815 | ## beat_enabled=False 816 | 817 | # Number of query results rows to fetch into the result storage. 818 | ## fetch_result_limit=2000 819 | 820 | # Django file storage class to use to temporarily store query results 821 | ## result_storage='{"backend": "django.core.files.storage.FileSystemStorage", "properties": {"location": "./logs"}}' 822 | 823 | # How the task server and tasks communicate. 824 | ## broker_url=amqp://guest:guest@localhost// 825 | 826 | # Where to store task results. Defaults to local file system path. Celery comes with a several other backends. 827 | ## celery_result_backend=file:///$HUE_ROOT/logs 828 | 829 | # Default options provided to the task server at startup. 830 | ## celeryd_opts='--time-limit=300' 831 | 832 | # Django cache to use to store temporarily used data during query execution. This is in addition to result_file_storage and result_backend. 833 | ## execution_storage='{"BACKEND": "django.core.cache.backends.locmem.LocMemCache", "LOCATION": "celery-hue"}' 834 | 835 | # Path to a file containing a list of beat schedules. 836 | # beat_schedules_file=/etc/hue/conf/schedules.py 837 | # e.g. 838 | # periodic_tasks = [{ 839 | # 'add-every-monday-morning': { 840 | # 'task': 'desktop.celery.debug_task', 841 | # 'schedule': crontab(minute='*'), 842 | # }, 843 | # }, 844 | # { 845 | # 'customer_count_query': { 846 | # 'task': 'notebook.tasks.run_sync_query', 847 | # 'schedule': crontab(minute='*'), 848 | # 'args': (None, None), 849 | # }, 850 | # } 851 | # ] 852 | 853 | # Settings for the Google Cloud lib 854 | # ------------------------------------------------------------------------ 855 | [[gc_accounts]] 856 | [[[default]]] 857 | # The JSON credentials to authenticate to Google Cloud e.g. '{ "type": "service_account", "project_id": .... }' 858 | # json_credentials=None 859 | 860 | ########################################################################### 861 | # Settings to configure the snippets available in the Notebook 862 | ########################################################################### 863 | 864 | [notebook] 865 | 866 | ## Show the notebook menu or not 867 | # show_notebooks=true 868 | 869 | ## Flag to enable the selection of queries from files, saved queries into the editor or as snippet. 870 | # enable_external_statements=false 871 | 872 | ## Flag to enable the bulk submission of queries as a background task through Oozie. 873 | # enable_batch_execute=true 874 | 875 | ## Flag to turn on the SQL indexer. 876 | # enable_sql_indexer=false 877 | 878 | ## Flag to turn on the Presentation mode of the editor. 879 | # enable_presentation=true 880 | 881 | ## Flag to enable the SQL query builder of the table assist. 882 | # enable_query_builder=true 883 | 884 | ## Flag to enable the creation of a coordinator for the current SQL query. 885 | # enable_query_scheduling=false 886 | 887 | ## Main flag to override the automatic starting of the DBProxy server. 888 | # enable_dbproxy_server=true 889 | 890 | ## Classpath to be appended to the default DBProxy server classpath. 891 | # dbproxy_extra_classpath= 892 | 893 | ## Comma separated list of interpreters that should be shown on the wheel. This list takes precedence over the 894 | ## order in which the interpreter entries appear. Only the first 5 interpreters will appear on the wheel. 895 | # interpreters_shown_on_wheel= 896 | 897 | # One entry for each type of snippet. 898 | [[interpreters]] 899 | # Define the name and how to connect and execute the language. 900 | # https://docs.gethue.com/administrator/configuration/editor/ 901 | 902 | # [[[mysql]]] 903 | # name = MySQL 904 | # interface=sqlalchemy 905 | # ## https://docs.sqlalchemy.org/en/latest/dialects/mysql.html 906 | # options='{"url": "mysql://root:secret@database:3306/hue"}' 907 | # ## options='{"url": "mysql://${USER}:${PASSWORD}@localhost:3306/hue"}' 908 | 909 | # [[[hive]]] 910 | # name=Hive 911 | # interface=hiveserver2 912 | 913 | # [[[llap]]] 914 | # name=LLAP 915 | # interface=hiveserver2 916 | 917 | # [[[impala]]] 918 | # name=Impala 919 | # interface=hiveserver2 920 | 921 | # [[[postgresql]]] 922 | # name = postgresql 923 | # interface=sqlalchemy 924 | # options='{"url": "postgresql://hue:hue@host:5432/hue"}' 925 | 926 | # [[[druid]]] 927 | # name = Druid 928 | # interface=sqlalchemy 929 | # options='{"url": "druid://host:8082/druid/v2/sql/"}' 930 | 931 | # [[[sql]]] 932 | # name=SparkSql 933 | # interface=livy 934 | 935 | # [[[spark]]] 936 | # name=Scala 937 | # interface=livy 938 | 939 | # [[[pyspark]]] 940 | # name=PySpark 941 | # interface=livy 942 | 943 | # [[[r]]] 944 | # name=R 945 | # interface=livy 946 | 947 | # [[jar]]] 948 | # name=Spark Submit Jar 949 | # interface=livy-batch 950 | 951 | # [[[py]]] 952 | # name=Spark Submit Python 953 | # interface=livy-batch 954 | 955 | # [[[text]]] 956 | # name=Text 957 | # interface=text 958 | 959 | # [[[markdown]]] 960 | # name=Markdown 961 | # interface=text 962 | 963 | # [[[sqlite]]] 964 | # name = SQLite 965 | # interface=rdbms 966 | 967 | # [[[oracle]]] 968 | # name = Oracle 969 | # interface=rdbms 970 | 971 | # [[[solr]]] 972 | # name = Solr SQL 973 | # interface=solr 974 | # ## Name of the collection handler 975 | # options='{"collection": "default"}' 976 | 977 | # [[[pig]]] 978 | # name=Pig 979 | # interface=oozie 980 | 981 | # [[[java]]] 982 | # name=Java 983 | # interface=oozie 984 | 985 | # [[[spark2]]] 986 | # name=Spark 987 | # interface=oozie 988 | 989 | # [[[mapreduce]]] 990 | # name=MapReduce 991 | # interface=oozie 992 | 993 | # [[[sqoop1]]] 994 | # name=Sqoop1 995 | # interface=oozie 996 | 997 | # [[[distcp]]] 998 | # name=Distcp 999 | # interface=oozie 1000 | 1001 | # [[[shell]]] 1002 | # name=Shell 1003 | # interface=oozie 1004 | 1005 | # [[[presto]]] 1006 | # name=Presto SQL 1007 | # interface=presto 1008 | # ## Specific options for connecting to the Presto server. 1009 | # ## The JDBC driver presto-jdbc.jar need to be in the CLASSPATH environment variable. 1010 | # ## If 'user' and 'password' are omitted, they will be prompted in the UI. 1011 | # options='{"url": "jdbc:presto://localhost:8080/catalog/schema", "driver": "io.prestosql.jdbc.PrestoDriver", "user": "root", "password": "root"}' 1012 | 1013 | # [[[clickhouse]]] 1014 | # name=ClickHouse 1015 | # interface=jdbc 1016 | # ## Specific options for connecting to the ClickHouse server. 1017 | # ## The JDBC driver clickhouse-jdbc.jar and its related jars need to be in the CLASSPATH environment variable. 1018 | # options='{"url": "jdbc:clickhouse://localhost:8123", "driver": "ru.yandex.clickhouse.ClickHouseDriver", "user": "readonly", "password": ""}' 1019 | 1020 | # [[[vertica]]] 1021 | # name=Vertica 1022 | # interface=jdbc 1023 | # ## Specific options for connecting to a Vertica server. 1024 | # ## The JDBC driver vertica-jdbc-*.jar and its related jars need to be in the CLASSPATH environment variable. 1025 | # ## If 'user' and 'password' are omitted, they will be prompted in the UI. 1026 | # options='{"url": "jdbc:vertica://localhost:5434", "driver": "com.vertica.jdbc.Driver"}' 1027 | 1028 | 1029 | ########################################################################### 1030 | # Settings to configure your Analytics Dashboards 1031 | ########################################################################### 1032 | 1033 | [dashboard] 1034 | 1035 | # Activate the Dashboard link in the menu. 1036 | ## is_enabled=true 1037 | 1038 | # Activate the SQL Dashboard (beta). 1039 | ## has_sql_enabled=false 1040 | 1041 | # Activate the Query Builder (beta). 1042 | ## has_query_builder_enabled=false 1043 | 1044 | # Activate the static report layout (beta). 1045 | ## has_report_enabled=false 1046 | 1047 | # Activate the new grid layout system. 1048 | ## use_gridster=true 1049 | 1050 | # Activate the widget filter and comparison (beta). 1051 | ## has_widget_filter=false 1052 | 1053 | # Activate the tree widget (to drill down fields as dimensions, alpha). 1054 | ## has_tree_widget=false 1055 | 1056 | [[engines]] 1057 | 1058 | # [[[solr]]] 1059 | # Requires Solr 6+ 1060 | ## analytics=true 1061 | ## nesting=false 1062 | 1063 | # [[[sql]]] 1064 | ## analytics=true 1065 | ## nesting=false 1066 | 1067 | 1068 | ########################################################################### 1069 | # Settings to configure your Hadoop cluster. 1070 | ########################################################################### 1071 | 1072 | [hadoop] 1073 | 1074 | # Configuration for HDFS NameNode 1075 | # ------------------------------------------------------------------------ 1076 | [[hdfs_clusters]] 1077 | # HA support by using HttpFs 1078 | 1079 | [[[default]]] 1080 | # Enter the filesystem uri 1081 | fs_defaultfs=hdfs://localhost:8020 1082 | 1083 | # NameNode logical name. 1084 | ## logical_name= 1085 | 1086 | # Use WebHdfs/HttpFs as the communication mechanism. 1087 | # Domain should be the NameNode or HttpFs host. 1088 | # Default port is 14000 for HttpFs. 1089 | webhdfs_url=http://localhost:9870/webhdfs/v1 1090 | 1091 | # Change this if your HDFS cluster is Kerberos-secured 1092 | ## security_enabled=false 1093 | 1094 | # In secure mode (HTTPS), if SSL certificates from YARN Rest APIs 1095 | # have to be verified against certificate authority 1096 | ## ssl_cert_ca_verify=True 1097 | 1098 | # Directory of the Hadoop configuration 1099 | ## hadoop_conf_dir=$HADOOP_CONF_DIR when set or '/etc/hadoop/conf' 1100 | 1101 | # Configuration for YARN (MR2) 1102 | # ------------------------------------------------------------------------ 1103 | [[yarn_clusters]] 1104 | 1105 | [[[default]]] 1106 | # Enter the host on which you are running the ResourceManager 1107 | resourcemanager_host=localhost 1108 | 1109 | # The port where the ResourceManager IPC listens on 1110 | resourcemanager_port=8032 1111 | 1112 | # Whether to submit jobs to this cluster 1113 | submit_to=True 1114 | 1115 | # Resource Manager logical name (required for HA) 1116 | ## logical_name= 1117 | 1118 | # Change this if your YARN cluster is Kerberos-secured 1119 | ## security_enabled=false 1120 | 1121 | # URL of the ResourceManager API 1122 | resourcemanager_api_url=http://localhost:8088 1123 | 1124 | # URL of the ProxyServer API 1125 | proxy_api_url=http://localhost:8088 1126 | 1127 | # URL of the HistoryServer API 1128 | history_server_api_url=http://localhost:19888 1129 | 1130 | # URL of the Spark History Server 1131 | spark_history_server_url=http://localhost:18088 1132 | 1133 | # Change this if your Spark History Server is Kerberos-secured 1134 | ## spark_history_server_security_enabled=false 1135 | 1136 | # In secure mode (HTTPS), if SSL certificates from YARN Rest APIs 1137 | # have to be verified against certificate authority 1138 | ## ssl_cert_ca_verify=True 1139 | 1140 | # HA support by specifying multiple clusters. 1141 | # Redefine different properties there. 1142 | # e.g. 1143 | 1144 | # [[[ha]]] 1145 | # Resource Manager logical name (required for HA) 1146 | ## logical_name=my-rm-name 1147 | 1148 | # Un-comment to enable 1149 | ## submit_to=True 1150 | 1151 | # URL of the ResourceManager API 1152 | ## resourcemanager_api_url=http://localhost:8088 1153 | 1154 | # ... 1155 | 1156 | 1157 | ########################################################################### 1158 | # Settings to configure Beeswax with Hive 1159 | ########################################################################### 1160 | 1161 | [beeswax] 1162 | 1163 | # Host where HiveServer2 is running. 1164 | # If Kerberos security is enabled, use fully-qualified domain name (FQDN). 1165 | hive_server_host=localhost 1166 | 1167 | # Binary thrift port for HiveServer2. 1168 | hive_server_port=10000 1169 | 1170 | # Http thrift port for HiveServer2. 1171 | ## hive_server_http_port=10001 1172 | 1173 | # Host where LLAP is running 1174 | ## llap_server_host = localhost 1175 | 1176 | # LLAP binary thrift port 1177 | ## llap_server_port = 10500 1178 | 1179 | # LLAP HTTP Thrift port 1180 | ## llap_server_thrift_port = 10501 1181 | 1182 | # Alternatively, use Service Discovery for LLAP (Hive Server Interactive) and/or Hiveserver2, this will override server and thrift port 1183 | 1184 | # Whether to use Service Discovery for LLAP 1185 | ## hive_discovery_llap = true 1186 | 1187 | # is llap (hive server interactive) running in an HA configuration (more than 1) 1188 | # important as the zookeeper structure is different 1189 | ## hive_discovery_llap_ha = false 1190 | 1191 | # Shortcuts to finding LLAP znode Key 1192 | # Non-HA - hiveserver-interactive-site - hive.server2.zookeeper.namespace ex hive2 = /hive2 1193 | # HA-NonKerberized - _llap ex app name llap0 = /llap0_llap 1194 | # HA-Kerberized - _llap-sasl ex app name llap0 = /llap0_llap-sasl 1195 | ## hive_discovery_llap_znode = /hiveserver2-hive2 1196 | 1197 | # Whether to use Service Discovery for HiveServer2 1198 | ## hive_discovery_hs2 = true 1199 | 1200 | # Hiveserver2 is hive-site hive.server2.zookeeper.namespace ex hiveserver2 = /hiverserver2 1201 | ## hive_discovery_hiveserver2_znode = /hiveserver2 1202 | 1203 | # Applicable only for LLAP HA 1204 | # To keep the load on zookeeper to a minimum 1205 | # ---- we cache the LLAP activeEndpoint for the cache_timeout period 1206 | # ---- we cache the hiveserver2 endpoint for the length of session 1207 | # configurations to set the time between zookeeper checks 1208 | ## cache_timeout = 60 1209 | 1210 | # Host where Hive Metastore Server (HMS) is running. 1211 | # If Kerberos security is enabled, the fully-qualified domain name (FQDN) is required. 1212 | ## hive_metastore_host=localhost 1213 | 1214 | # Configure the port the Hive Metastore Server runs on. 1215 | ## hive_metastore_port=9083 1216 | 1217 | # Hive configuration directory, where hive-site.xml is located 1218 | ## hive_conf_dir=/etc/hive/conf 1219 | 1220 | # Timeout in seconds for thrift calls to Hive service 1221 | ## server_conn_timeout=120 1222 | 1223 | # Choose whether to use the old GetLog() thrift call from before Hive 0.14 to retrieve the logs. 1224 | # If false, use the FetchResults() thrift call from Hive 1.0 or more instead. 1225 | ## use_get_log_api=false 1226 | 1227 | # Limit the number of partitions that can be listed. 1228 | ## list_partitions_limit=10000 1229 | 1230 | # The maximum number of partitions that will be included in the SELECT * LIMIT sample query for partitioned tables. 1231 | ## query_partitions_limit=10 1232 | 1233 | # A limit to the number of rows that can be downloaded from a query before it is truncated. 1234 | # A value of -1 means there will be no limit. 1235 | ## download_row_limit=100000 1236 | 1237 | # A limit to the number of bytes that can be downloaded from a query before it is truncated. 1238 | # A value of -1 means there will be no limit. 1239 | ## download_bytes_limit=-1 1240 | 1241 | # Hue will try to close the Hive query when the user leaves the editor page. 1242 | # This will free all the query resources in HiveServer2, but also make its results inaccessible. 1243 | ## close_queries=false 1244 | 1245 | # Hue will use at most this many HiveServer2 sessions per user at a time. 1246 | # For Tez, increase the number to more if you need more than one query at the time, e.g. 2 or 3 (Tez has a maximum of 1 query by session). 1247 | ## max_number_of_sessions=1 1248 | 1249 | # Thrift version to use when communicating with HiveServer2. 1250 | # Version 11 comes with Hive 3.0. If issues, try 7. 1251 | ## thrift_version=11 1252 | 1253 | # A comma-separated list of white-listed Hive configuration properties that users are authorized to set. 1254 | ## config_whitelist=hive.map.aggr,hive.exec.compress.output,hive.exec.parallel,hive.execution.engine,mapreduce.job.queuename 1255 | 1256 | # Override the default desktop username and password of the hue user used for authentications with other services. 1257 | # e.g. Used for LDAP/PAM pass-through authentication. 1258 | ## auth_username=hue 1259 | ## auth_password= 1260 | 1261 | # Use SASL framework to establish connection to host. 1262 | ## use_sasl=false 1263 | 1264 | [[ssl]] 1265 | # Path to Certificate Authority certificates. 1266 | ## cacerts=/etc/hue/cacerts.pem 1267 | 1268 | # Choose whether Hue should validate certificates received from the server. 1269 | ## validate=true 1270 | 1271 | ########################################################################### 1272 | # Settings to configure Metastore 1273 | ########################################################################### 1274 | 1275 | [metastore] 1276 | # Flag to turn on the new version of the create table wizard. 1277 | ## enable_new_create_table=true 1278 | 1279 | # Flag to force all metadata calls (e.g. list tables, table or column details...) to happen via HiveServer2 if available instead of Impala. 1280 | ## force_hs2_metadata=false 1281 | 1282 | 1283 | ########################################################################### 1284 | # Settings to configure Impala 1285 | ########################################################################### 1286 | 1287 | [impala] 1288 | # Host of the Impala Server (one of the Impalad) 1289 | ## server_host=localhost 1290 | 1291 | # Port of the Impala Server 1292 | ## server_port=21050 1293 | 1294 | # Kerberos principal 1295 | ## impala_principal=impala/hostname.foo.com 1296 | 1297 | # Turn on/off impersonation mechanism when talking to Impala 1298 | ## impersonation_enabled=False 1299 | 1300 | # Number of initial rows of a result set to ask Impala to cache in order 1301 | # to support re-fetching them for downloading them. 1302 | # Set to 0 for disabling the option and backward compatibility. 1303 | ## querycache_rows=50000 1304 | 1305 | # Timeout in seconds for thrift calls 1306 | ## server_conn_timeout=120 1307 | 1308 | # Hue will try to close the Impala query when the user leaves the editor page. 1309 | # This will free all the query resources in Impala, but also make its results inaccessible. 1310 | ## close_queries=true 1311 | 1312 | # If > 0, the query will be timed out (i.e. cancelled) if Impala does not do any work 1313 | # (compute or send back results) for that query within QUERY_TIMEOUT_S seconds. 1314 | ## query_timeout_s=300 1315 | 1316 | # If > 0, the session will be timed out (i.e. cancelled) if Impala does not do any work 1317 | # (compute or send back results) for that session within SESSION_TIMEOUT_S seconds (default 15 min). 1318 | ## session_timeout_s=900 1319 | 1320 | # Override the desktop default username and password of the hue user used for authentications with other services. 1321 | # e.g. Used for LDAP/PAM pass-through authentication. 1322 | ## auth_username=hue 1323 | ## auth_password= 1324 | 1325 | # Username and password for Impala Daemon Web interface for getting Impala queries in JobBrowser 1326 | # Set when webserver_htpassword_user and webserver_htpassword_password are set for Impala 1327 | ## daemon_api_username= 1328 | ## daemon_api_password= 1329 | # Execute this script to produce the password to avoid entering in clear text 1330 | ## daemon_api_password_script= 1331 | 1332 | # A comma-separated list of white-listed Impala configuration properties that users are authorized to set. 1333 | # config_whitelist=debug_action,explain_level,mem_limit,optimize_partition_key_scans,query_timeout_s,request_pool 1334 | 1335 | # Path to the impala configuration dir which has impalad_flags file 1336 | ## impala_conf_dir=${HUE_CONF_DIR}/impala-conf 1337 | 1338 | # Use SASL framework to establish connection to host. 1339 | ## use_sasl=true 1340 | 1341 | [[ssl]] 1342 | # SSL communication enabled for this server. 1343 | ## enabled=false 1344 | 1345 | # Path to Certificate Authority certificates. 1346 | ## cacerts=/etc/hue/cacerts.pem 1347 | 1348 | # Choose whether Hue should validate certificates received from the server. 1349 | ## validate=true 1350 | 1351 | 1352 | ########################################################################### 1353 | # Settings to configure the Spark application. 1354 | ########################################################################### 1355 | 1356 | [spark] 1357 | # The Livy Server URL. 1358 | ## livy_server_url=http://localhost:8998 1359 | 1360 | # Configure Livy to start in local 'process' mode, or 'yarn' workers. 1361 | ## livy_server_session_kind=yarn 1362 | 1363 | # Whether Livy requires client to perform Kerberos authentication. 1364 | ## security_enabled=false 1365 | 1366 | # Whether Livy requires client to use csrf protection. 1367 | ## csrf_enabled=false 1368 | 1369 | # Host of the Sql Server 1370 | ## sql_server_host=localhost 1371 | 1372 | # Port of the Sql Server 1373 | ## sql_server_port=10000 1374 | 1375 | # Choose whether Hue should validate certificates received from the server. 1376 | ## ssl_cert_ca_verify=true 1377 | 1378 | # Use SASL framework to establish connection to host. 1379 | ## use_sasl=false 1380 | 1381 | ########################################################################### 1382 | # Settings to configure the Oozie app 1383 | ########################################################################### 1384 | 1385 | [oozie] 1386 | # Location on local FS where the examples are stored. 1387 | ## local_data_dir=..../examples 1388 | 1389 | # Location on local FS where the data for the examples is stored. 1390 | ## sample_data_dir=...thirdparty/sample_data 1391 | 1392 | # Location on HDFS where the oozie examples and workflows are stored. 1393 | # Parameters are $TIME and $USER, e.g. /user/$USER/hue/workspaces/workflow-$TIME 1394 | ## remote_data_dir=/user/hue/oozie/workspaces 1395 | 1396 | # Maximum of Oozie workflows or coodinators to retrieve in one API call. 1397 | ## oozie_jobs_count=100 1398 | 1399 | # Use Cron format for defining the frequency of a Coordinator instead of the old frequency number/unit. 1400 | ## enable_cron_scheduling=true 1401 | 1402 | # Flag to enable the saved Editor queries to be dragged and dropped into a workflow. 1403 | ## enable_document_action=true 1404 | 1405 | # Flag to enable Oozie backend filtering instead of doing it at the page level in Javascript. Requires Oozie 4.3+. 1406 | ## enable_oozie_backend_filtering=true 1407 | 1408 | # Flag to enable the Impala action. 1409 | ## enable_impala_action=false 1410 | 1411 | # Flag to enable the Altus action. 1412 | ## enable_altus_action=false 1413 | 1414 | 1415 | ########################################################################### 1416 | # Settings to configure the Filebrowser app 1417 | ########################################################################### 1418 | 1419 | [filebrowser] 1420 | # Location on local filesystem where the uploaded archives are temporary stored. 1421 | ## archive_upload_tempdir=/tmp 1422 | 1423 | # Show Download Button for HDFS file browser. 1424 | ## show_download_button=true 1425 | 1426 | # Show Upload Button for HDFS file browser. 1427 | ## show_upload_button=true 1428 | 1429 | # Flag to enable the extraction of a uploaded archive in HDFS. 1430 | ## enable_extract_uploaded_archive=true 1431 | 1432 | # Redirect client to WebHdfs or S3 for file download. Note: Turning this on will override notebook/redirect_whitelist for user selected file downloads on WebHdfs & S3. 1433 | ## redirect_download=false 1434 | 1435 | ########################################################################### 1436 | # Settings to configure Pig 1437 | ########################################################################### 1438 | 1439 | [pig] 1440 | # Path to directory with piggybank.jar on local filesystem. 1441 | ## local_sample_dir=/usr/share/hue/apps/pig/examples 1442 | 1443 | # Location piggybank.jar will be copied to in HDFS. 1444 | ## remote_data_dir=/user/hue/pig/examples 1445 | 1446 | 1447 | ########################################################################### 1448 | # Settings to configure Sqoop2 1449 | ########################################################################### 1450 | 1451 | [sqoop] 1452 | # If the Sqoop2 app is enabled. Sqoop2 project is deprecated. Sqoop1 is recommended. 1453 | ## is_enabled=false 1454 | 1455 | # Sqoop server URL 1456 | ## server_url=http://localhost:12000/sqoop 1457 | 1458 | # Path to configuration directory 1459 | ## sqoop_conf_dir=/etc/sqoop2/conf 1460 | 1461 | # Choose whether Hue should validate certificates received from the server. 1462 | ## ssl_cert_ca_verify=true 1463 | 1464 | # For autocompletion, fill out the librdbms section. 1465 | 1466 | ########################################################################### 1467 | # Settings to configure Proxy 1468 | ########################################################################### 1469 | 1470 | [proxy] 1471 | # Comma-separated list of regular expressions, 1472 | # which match 'host:port' of requested proxy target. 1473 | ## whitelist=(localhost|127\.0\.0\.1):(50030|50070|50060|50075) 1474 | 1475 | # Comma-separated list of regular expressions, 1476 | # which match any prefix of 'host:port/path' of requested proxy target. 1477 | # This does not support matching GET parameters. 1478 | ## blacklist= 1479 | 1480 | 1481 | ########################################################################### 1482 | # Settings to configure HBase Browser 1483 | ########################################################################### 1484 | 1485 | [hbase] 1486 | # Comma-separated list of HBase Thrift servers for clusters in the format of '(name|host:port)'. 1487 | # Use full hostname. If hbase.thrift.ssl.enabled in hbase-site is set to true, https will be used otherwise it will use http 1488 | # If using Kerberos we assume GSSAPI SASL, not PLAIN. 1489 | ## hbase_clusters=(Cluster|localhost:9090) 1490 | 1491 | # HBase configuration directory, where hbase-site.xml is located. 1492 | ## hbase_conf_dir=/etc/hbase/conf 1493 | 1494 | # Hard limit of rows or columns per row fetched before truncating. 1495 | ## truncate_limit = 500 1496 | 1497 | # Should come from hbase-site.xml, do not set. 'framed' is used to chunk up responses, used with the nonblocking server in Thrift but is not supported in Hue. 1498 | # 'buffered' used to be the default of the HBase Thrift Server. Default is buffered when not set in hbase-site.xml. 1499 | ## thrift_transport=buffered 1500 | 1501 | # Choose whether Hue should validate certificates received from the server. 1502 | ## ssl_cert_ca_verify=true 1503 | 1504 | 1505 | ########################################################################### 1506 | # Settings to configure Solr Search 1507 | ########################################################################### 1508 | 1509 | [search] 1510 | 1511 | # URL of the Solr Server 1512 | ## solr_url=http://localhost:8983/solr/ 1513 | 1514 | # Requires FQDN in solr_url if enabled 1515 | ## security_enabled=false 1516 | 1517 | ## Query sent when no term is entered 1518 | ## empty_query=*:* 1519 | 1520 | 1521 | ########################################################################### 1522 | # Settings to configure Solr API lib 1523 | ########################################################################### 1524 | 1525 | [libsolr] 1526 | 1527 | # Choose whether Hue should validate certificates received from the server. 1528 | ## ssl_cert_ca_verify=true 1529 | 1530 | # Default path to Solr in ZooKeeper. 1531 | ## solr_zk_path=/solr 1532 | 1533 | 1534 | ########################################################################### 1535 | # Settings to configure the Data Import Wizard 1536 | ########################################################################### 1537 | 1538 | [indexer] 1539 | 1540 | # Filesystem directory containing Solr Morphline indexing libs. 1541 | ## config_indexer_libs_path=/tmp/smart_indexer_lib 1542 | 1543 | # Filesystem directory containing JDBC libs. 1544 | ## config_jdbc_libs_path=/user/oozie/libext/jdbc_drivers 1545 | 1546 | # Filesystem directory containing jar libs. 1547 | ## config_jars_libs_path=/user/oozie/libext/libs 1548 | 1549 | # Flag to turn on the Solr Morphline indexer. 1550 | ## enable_scalable_indexer=true 1551 | 1552 | # Flag to turn on Sqoop ingest. 1553 | ## enable_sqoop=true 1554 | 1555 | # Flag to turn on Kafka topic ingest. 1556 | ## enable_kafka=false 1557 | 1558 | 1559 | ########################################################################### 1560 | # Settings to configure Job Designer 1561 | ########################################################################### 1562 | 1563 | [jobsub] 1564 | 1565 | # Location on local FS where examples and template are stored. 1566 | ## local_data_dir=..../data 1567 | 1568 | # Location on local FS where sample data is stored 1569 | ## sample_data_dir=...thirdparty/sample_data 1570 | 1571 | 1572 | ########################################################################### 1573 | # Settings to configure Job Browser. 1574 | ########################################################################### 1575 | 1576 | [jobbrowser] 1577 | # Share submitted jobs information with all users. If set to false, 1578 | # submitted jobs are visible only to the owner and administrators. 1579 | ## share_jobs=true 1580 | 1581 | # Whether to disalbe the job kill button for all users in the jobbrowser 1582 | ## disable_killing_jobs=false 1583 | 1584 | # Offset in bytes where a negative offset will fetch the last N bytes for the given log file (default 1MB). 1585 | ## log_offset=-1000000 1586 | 1587 | # Maximum number of jobs to fetch and display when pagination is not supported for the type. 1588 | ## max_job_fetch=500 1589 | 1590 | # Show the version 2 of app which unifies all the past browsers into one. 1591 | ## enable_v2=true 1592 | 1593 | # Show the Impala query section for listing and showing more troubleshooting information. 1594 | ## enable_query_browser=true 1595 | 1596 | # Show the Hive query section for listing and showing more troubleshooting information. 1597 | ## enable_hive_query_browser=false 1598 | 1599 | 1600 | ########################################################################### 1601 | # Settings to configure Sentry / Security App. 1602 | ########################################################################### 1603 | 1604 | [security] 1605 | 1606 | # Use Sentry API V1 for Hive. 1607 | ## hive_v1=true 1608 | 1609 | # Use Sentry API V2 for Hive. 1610 | ## hive_v2=false 1611 | 1612 | # Use Sentry API V2 for Solr. 1613 | ## solr_v2=true 1614 | 1615 | 1616 | ########################################################################### 1617 | # Settings to configure the Zookeeper application. 1618 | ########################################################################### 1619 | 1620 | [zookeeper] 1621 | 1622 | [[clusters]] 1623 | 1624 | [[[default]]] 1625 | # Zookeeper ensemble. Comma separated list of Host/Port. 1626 | # e.g. localhost:2181,localhost:2182,localhost:2183 1627 | ## host_ports=localhost:2181 1628 | 1629 | # The URL of the REST contrib service (required for znode browsing). 1630 | ## rest_url=http://localhost:9998 1631 | 1632 | # Name of Kerberos principal when using security. 1633 | ## principal_name=zookeeper 1634 | 1635 | 1636 | ########################################################################### 1637 | # Settings for the User Admin application 1638 | ########################################################################### 1639 | 1640 | [useradmin] 1641 | # Default home directory permissions 1642 | ## home_dir_permissions=0755 1643 | 1644 | # The name of the default user group that users will be a member of 1645 | ## default_user_group=default 1646 | 1647 | [[password_policy]] 1648 | # Set password policy to all users. The default policy requires password to be at least 8 characters long, 1649 | # and contain both uppercase and lowercase letters, numbers, and special characters. 1650 | 1651 | ## is_enabled=false 1652 | ## pwd_regex="^(?=.*?[A-Z])(?=(.*[a-z]){1,})(?=(.*[\d]){1,})(?=(.*[\W_]){1,}).{8,}$" 1653 | ## pwd_hint="The password must be at least 8 characters long, and must contain both uppercase and lowercase letters, at least one number, and at least one special character." 1654 | ## pwd_error_message="The password must be at least 8 characters long, and must contain both uppercase and lowercase letters, at least one number, and at least one special character." 1655 | 1656 | 1657 | ########################################################################### 1658 | # Settings to configure liboozie 1659 | ########################################################################### 1660 | 1661 | [liboozie] 1662 | # The URL where the Oozie service runs on. This is required in order for 1663 | # users to submit jobs. Empty value disables the config check. 1664 | ## oozie_url=http://localhost:11000/oozie 1665 | 1666 | # Requires FQDN in oozie_url if enabled 1667 | ## security_enabled=false 1668 | 1669 | # Location on HDFS where the workflows/coordinator are deployed when submitted. 1670 | ## remote_deployement_dir=/user/hue/oozie/deployments 1671 | 1672 | 1673 | ########################################################################### 1674 | # Settings for the AWS lib 1675 | ########################################################################### 1676 | 1677 | [aws] 1678 | [[aws_accounts]] 1679 | # Default AWS account 1680 | ## [[[default]]] 1681 | # AWS credentials 1682 | ## access_key_id= 1683 | ## secret_access_key= 1684 | ## security_token= 1685 | 1686 | # Execute this script to produce the AWS access key ID. 1687 | ## access_key_id_script=/path/access_key_id.sh 1688 | 1689 | # Execute this script to produce the AWS secret access key. 1690 | ## secret_access_key_script=/path/secret_access_key.sh 1691 | 1692 | # Allow to use either environment variables or 1693 | # EC2 InstanceProfile to retrieve AWS credentials. 1694 | ## allow_environment_credentials=yes 1695 | 1696 | # AWS region to use, if no region is specified, will attempt to connect to standard s3.amazonaws.com endpoint 1697 | ## region=us-east-1 1698 | 1699 | # Endpoint overrides 1700 | ## host= 1701 | 1702 | # Proxy address and port 1703 | ## proxy_address= 1704 | ## proxy_port=8080 1705 | ## proxy_user= 1706 | ## proxy_pass= 1707 | 1708 | # Secure connections are the default, but this can be explicitly overridden: 1709 | ## is_secure=true 1710 | 1711 | # The default calling format uses https://.s3.amazonaws.com but 1712 | # this may not make sense if DNS is not configured in this way for custom endpoints. 1713 | # e.g. Use boto.s3.connection.OrdinaryCallingFormat for https://s3.amazonaws.com/ 1714 | ## calling_format=boto.s3.connection.OrdinaryCallingFormat 1715 | 1716 | # The time in seconds before a delegate key is expired. Used when filebrowser/redirect_download is used. Default to 4 Hours. 1717 | ## key_expiry=14400 1718 | 1719 | ########################################################################### 1720 | # Settings for the Azure lib 1721 | ########################################################################### 1722 | [azure] 1723 | [[azure_accounts]] 1724 | # Default Azure account 1725 | [[[default]]] 1726 | # Azure credentials 1727 | ## client_id= 1728 | # Execute this script to produce the ADLS client id. 1729 | ## client_id_script=/path/client_id.sh 1730 | ## client_secret= 1731 | # Execute this script to produce the ADLS client secret. 1732 | ## client_secret_script=/path/client_secret.sh 1733 | ## tenant_id= 1734 | # Execute this script to produce the ADLS tenant id. 1735 | ## tenant_id_script=/path/tenant_id.sh 1736 | 1737 | [[adls_clusters]] 1738 | # Default ADLS cluster 1739 | [[[default]]] 1740 | ## fs_defaultfs=adl://.azuredatalakestore.net 1741 | ## webhdfs_url=https://.azuredatalakestore.net/webhdfs/v1 1742 | 1743 | [[abfs_clusters]] 1744 | # Default ABFS cluster 1745 | [[[default]]] 1746 | ## fs_defaultfs=abfss://@.dfs.core.windows.net 1747 | ## webhdfs_url=https://@.dfs.core.windows.net 1748 | 1749 | ########################################################################### 1750 | # Settings for the Sentry lib 1751 | ########################################################################### 1752 | 1753 | [libsentry] 1754 | # Hostname or IP of server. 1755 | ## hostname=localhost 1756 | 1757 | # Port the sentry service is running on. 1758 | ## port=8038 1759 | 1760 | # Sentry configuration directory, where sentry-site.xml is located. 1761 | ## sentry_conf_dir=/etc/sentry/conf 1762 | 1763 | # Number of seconds when the privilege list of a user is cached. 1764 | ## privilege_checker_caching=300 1765 | 1766 | 1767 | ########################################################################### 1768 | # Settings to configure the ZooKeeper Lib 1769 | ########################################################################### 1770 | 1771 | [libzookeeper] 1772 | # ZooKeeper ensemble. Comma separated list of Host/Port. 1773 | # e.g. localhost:2181,localhost:2182,localhost:2183 1774 | ## ensemble=localhost:2181 1775 | 1776 | # Name of Kerberos principal when using security. 1777 | ## principal_name=zookeeper 1778 | 1779 | 1780 | ########################################################################### 1781 | # Settings for the RDBMS application 1782 | ########################################################################### 1783 | 1784 | [librdbms] 1785 | # The RDBMS app can have any number of databases configured in the databases 1786 | # section. A database is known by its section name 1787 | # (IE sqlite, mysql, psql, and oracle in the list below). 1788 | 1789 | [[databases]] 1790 | # sqlite configuration. 1791 | ## [[[sqlite]]] 1792 | # Name to show in the UI. 1793 | ## nice_name=SQLite 1794 | 1795 | # For SQLite, name defines the path to the database. 1796 | ## name=/tmp/sqlite.db 1797 | 1798 | # Database backend to use. 1799 | ## engine=sqlite 1800 | 1801 | # Database options to send to the server when connecting. 1802 | # https://docs.djangoproject.com/en/1.4/ref/databases/ 1803 | ## options={} 1804 | 1805 | # mysql, oracle, or postgresql configuration. 1806 | ## [[[mysql]]] 1807 | # Name to show in the UI. 1808 | ## nice_name="My SQL DB" 1809 | 1810 | # For MySQL and PostgreSQL, name is the name of the database. 1811 | # For Oracle, Name is instance of the Oracle server. For express edition 1812 | # this is 'xe' by default. 1813 | ## name=mysqldb 1814 | 1815 | # Database backend to use. This can be: 1816 | # 1. mysql 1817 | # 2. postgresql 1818 | # 3. oracle 1819 | ## engine=mysql 1820 | 1821 | # IP or hostname of the database to connect to. 1822 | ## host=localhost 1823 | 1824 | # Port the database server is listening to. Defaults are: 1825 | # 1. MySQL: 3306 1826 | # 2. PostgreSQL: 5432 1827 | # 3. Oracle Express Edition: 1521 1828 | ## port=3306 1829 | 1830 | # Username to authenticate with when connecting to the database. 1831 | ## user=example 1832 | 1833 | # Password matching the username to authenticate with when 1834 | # connecting to the database. 1835 | ## password=example 1836 | 1837 | # Database options to send to the server when connecting. 1838 | # https://docs.djangoproject.com/en/1.4/ref/databases/ 1839 | ## options={} 1840 | 1841 | 1842 | ########################################################################### 1843 | # Settings to configure SAML 1844 | ########################################################################### 1845 | 1846 | [libsaml] 1847 | # Xmlsec1 binary path. This program should be executable by the user running Hue. 1848 | ## xmlsec_binary=/usr/local/bin/xmlsec1 1849 | 1850 | # Entity ID for Hue acting as service provider. 1851 | # Can also accept a pattern where '' will be replaced with server URL base. 1852 | ## entity_id="/saml2/metadata/" 1853 | 1854 | # Create users from SSO on login. 1855 | ## create_users_on_login=true 1856 | 1857 | # Required attributes to ask for from IdP. 1858 | # This requires a comma separated list. 1859 | ## required_attributes=uid 1860 | 1861 | # Optional attributes to ask for from IdP. 1862 | # This requires a comma separated list. 1863 | ## optional_attributes= 1864 | 1865 | # IdP metadata in the form of a file. This is generally an XML file containing metadata that the Identity Provider generates. 1866 | ## metadata_file= 1867 | 1868 | # Private key to encrypt metadata with. 1869 | ## key_file= 1870 | 1871 | # Signed certificate to send along with encrypted metadata. 1872 | ## cert_file= 1873 | 1874 | # Path to a file containing the password private key. 1875 | ## key_file_password=/path/key 1876 | 1877 | # Execute this script to produce the private key password. This will be used when 'key_file_password' is not set. 1878 | ## key_file_password_script=/path/pwd.sh 1879 | 1880 | # A mapping from attributes in the response from the IdP to django user attributes. 1881 | ## user_attribute_mapping={'uid': ('username', )} 1882 | 1883 | # Have Hue initiated authn requests be signed and provide a certificate. 1884 | ## authn_requests_signed=false 1885 | 1886 | # Have Hue initiated authn response be signed. 1887 | ## want_response_signed=false 1888 | 1889 | # Have Hue initiated authn assertions response be signed. 1890 | ## want_assertions_signed=false 1891 | 1892 | # Have Hue initiated logout requests be signed and provide a certificate. 1893 | ## logout_requests_signed=false 1894 | 1895 | # Username can be sourced from 'attributes' or 'nameid'. 1896 | ## username_source=attributes 1897 | 1898 | # Performs the logout or not. 1899 | ## logout_enabled=true 1900 | 1901 | 1902 | ########################################################################### 1903 | # Settings to configure OAuth 1904 | ########################################################################### 1905 | 1906 | [liboauth] 1907 | # NOTE: 1908 | # To work, each of the active (i.e. uncommented) service must have 1909 | # applications created on the social network. 1910 | # Then the "consumer key" and "consumer secret" must be provided here. 1911 | # 1912 | # The addresses where to do so are: 1913 | # Twitter: https://dev.twitter.com/apps 1914 | # Google+ : https://cloud.google.com/ 1915 | # Facebook: https://developers.facebook.com/apps 1916 | # Linkedin: https://www.linkedin.com/secure/developer 1917 | # 1918 | # Additionnaly, the following must be set in the application settings: 1919 | # Twitter: Callback URL (aka Redirect URL) must be set to http://YOUR_HUE_IP_OR_DOMAIN_NAME/oauth/social_login/oauth_authenticated 1920 | # Google+ : CONSENT SCREEN must have email address 1921 | # Facebook: Sandbox Mode must be DISABLED 1922 | # Linkedin: "In OAuth User Agreement", r_emailaddress is REQUIRED 1923 | 1924 | # The Consumer key of the application 1925 | ## consumer_key_twitter= 1926 | ## consumer_key_google= 1927 | ## consumer_key_facebook= 1928 | ## consumer_key_linkedin= 1929 | 1930 | # The Consumer secret of the application 1931 | ## consumer_secret_twitter= 1932 | ## consumer_secret_google= 1933 | ## consumer_secret_facebook= 1934 | ## consumer_secret_linkedin= 1935 | 1936 | # The Request token URL 1937 | ## request_token_url_twitter=https://api.twitter.com/oauth/request_token 1938 | ## request_token_url_google=https://accounts.google.com/o/oauth2/auth 1939 | ## request_token_url_linkedin=https://www.linkedin.com/uas/oauth2/authorization 1940 | ## request_token_url_facebook=https://graph.facebook.com/oauth/authorize 1941 | 1942 | # The Access token URL 1943 | ## access_token_url_twitter=https://api.twitter.com/oauth/access_token 1944 | ## access_token_url_google=https://accounts.google.com/o/oauth2/token 1945 | ## access_token_url_facebook=https://graph.facebook.com/oauth/access_token 1946 | ## access_token_url_linkedin=https://api.linkedin.com/uas/oauth2/accessToken 1947 | 1948 | # The Authenticate URL 1949 | ## authenticate_url_twitter=https://api.twitter.com/oauth/authorize 1950 | ## authenticate_url_google=https://www.googleapis.com/oauth2/v1/userinfo?access_token= 1951 | ## authenticate_url_facebook=https://graph.facebook.com/me?access_token= 1952 | ## authenticate_url_linkedin=https://api.linkedin.com/v1/people/~:(email-address)?format=json&oauth2_access_token= 1953 | 1954 | # Username Map. Json Hash format. 1955 | # Replaces username parts in order to simplify usernames obtained 1956 | # Example: {"@sub1.domain.com":"_S1", "@sub2.domain.com":"_S2"} 1957 | # converts 'email@sub1.domain.com' to 'email_S1' 1958 | ## username_map={} 1959 | 1960 | # Whitelisted domains (only applies to Google OAuth). CSV format. 1961 | ## whitelisted_domains_google= 1962 | 1963 | 1964 | ########################################################################### 1965 | # Settings to configure Kafka 1966 | ########################################################################### 1967 | 1968 | [kafka] 1969 | 1970 | [[kafka]] 1971 | # Enable the Kafka integration. 1972 | ## is_enabled=false 1973 | 1974 | # Base URL of Kafka Ksql API. 1975 | ## ksql_api_url=http://127.0.0.1:8088 1976 | 1977 | 1978 | ########################################################################### 1979 | # Settings to configure Metadata 1980 | ########################################################################### 1981 | 1982 | [metadata] 1983 | 1984 | [[manager]] 1985 | # Cloudera Manager API URL (without version suffix). 1986 | ## api_url=http://localhost:7180/api 1987 | 1988 | [[optimizer]] 1989 | # Type of Optimizer connector to query, e.g. optimizer, dummy 1990 | # interface=optimizer 1991 | 1992 | # Hostname to Optimizer API or compatible service. 1993 | ## hostname=navoptapi.us-west-1.optimizer.altus.cloudera.com 1994 | 1995 | # The name of the key of the service. 1996 | ## auth_key_id=e0819f3a-1e6f-4904-be69-5b704bacd1245 1997 | 1998 | # The private part of the key associated with the auth_key. 1999 | ## auth_key_secret='-----BEGIN PRIVATE KEY....' 2000 | 2001 | # Execute this script to produce the auth_key secret. This will be used when `auth_key_secret` is not set. 2002 | ## auth_key_secret_script=/path/to/script.sh 2003 | 2004 | # The name of the workload where queries are uploaded and optimizations are calculated from. Automatically guessed from auth_key and cluster_id if not specified. 2005 | ## tenant_id= 2006 | 2007 | # Perform Sentry privilege filtering. 2008 | # Default to true automatically if the cluster is secure. 2009 | ## apply_sentry_permissions=False 2010 | 2011 | # Cache timeout in milliseconds for the Optimizer metadata used in assist, autocomplete, etc. 2012 | # Defaults to 10 days, set to 0 to disable caching. 2013 | ## cacheable_ttl=864000000 2014 | 2015 | # Automatically upload queries after their execution in order to improve recommendations. 2016 | ## auto_upload_queries=true 2017 | 2018 | # Automatically upload queried tables DDL in order to improve recommendations. 2019 | ## auto_upload_ddl=true 2020 | 2021 | # Automatically upload queried tables and columns stats in order to improve recommendations. 2022 | ## auto_upload_stats=false 2023 | 2024 | # Allow admins to upload the last N executed queries in the quick start wizard. Use 0 to disable. 2025 | ## query_history_upload_limit=10000 2026 | 2027 | [[catalog]] 2028 | # The type of Catalog: Apache Atlas, Cloudera Navigator... 2029 | ## interface=atlas 2030 | # Catalog API URL (without version suffix). 2031 | ## api_url=http://localhost:21000/atlas/v2 2032 | 2033 | # Username of the CM user used for authentication. 2034 | ## server_user=hue 2035 | # Password of the user used for authentication. 2036 | ## server_password= 2037 | 2038 | # Limits found entities to a specific cluster. When empty the entities from all clusters will be included in the 2039 | # search results. 2040 | ## search_cluster= 2041 | 2042 | # Set to true when authenticating via kerberos instead of username/password 2043 | ## kerberos_enabled=core_site.is_kerberos_enabled() 2044 | 2045 | # Directory of the configurations. 2046 | ## conf_dir=HUE_CONF_DIR/hive-conf 2047 | 2048 | # Deprecated by [[catalog]] 2049 | [[navigator]] 2050 | # Navigator API URL (without version suffix). 2051 | ## api_url=http://localhost:7187/api 2052 | 2053 | # Which authentication to use: CM or external via LDAP or SAML. 2054 | ## navmetadataserver_auth_type=CMDB 2055 | 2056 | # Username of the CM user used for authentication. 2057 | ## navmetadataserver_cmdb_user=hue 2058 | # CM password of the user used for authentication. 2059 | ## navmetadataserver_cmdb_password= 2060 | # Execute this script to produce the CM password. This will be used when the plain password is not set. 2061 | # navmetadataserver_cmdb_password_script= 2062 | 2063 | # Username of the LDAP user used for authentication. 2064 | ## navmetadataserver_ldap_user=hue 2065 | # LDAP password of the user used for authentication. 2066 | ## navmetadataserver_ldap_ppassword= 2067 | # Execute this script to produce the LDAP password. This will be used when the plain password is not set. 2068 | ## navmetadataserver_ldap_password_script= 2069 | 2070 | # Username of the SAML user used for authentication. 2071 | ## navmetadataserver_saml_user=hue 2072 | ## SAML password of the user used for authentication. 2073 | # navmetadataserver_saml_password= 2074 | # Execute this script to produce the SAML password. This will be used when the plain password is not set. 2075 | ## navmetadataserver_saml_password_script= 2076 | 2077 | # Perform Sentry privilege filtering. 2078 | # Default to true automatically if the cluster is secure. 2079 | ## apply_sentry_permissions=False 2080 | 2081 | # Max number of items to fetch in one call in object search. 2082 | ## fetch_size_search=450 2083 | 2084 | # Max number of items to fetch in one call in object search autocomplete. 2085 | ## fetch_size_search_interactive=450 2086 | 2087 | # If metadata search is enabled, also show the search box in the left assist. 2088 | ## enable_file_search=false 2089 | 2090 | [[prometheus]] 2091 | # Configuration options for Prometheus API. 2092 | ## api_url=http://localhost:9090/api 2093 | --------------------------------------------------------------------------------