carbondata-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jackylk <...@git.apache.org>
Subject [GitHub] carbondata pull request #1805: [CARBONDATA-1827] S3 Carbon Implementation
Date Wed, 17 Jan 2018 15:46:28 GMT
Github user jackylk commented on a diff in the pull request:

    https://github.com/apache/carbondata/pull/1805#discussion_r162090105
  
    --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala
---
    @@ -0,0 +1,157 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *    http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +package org.apache.carbondata.examples
    +
    +import java.io.File
    +
    +import org.apache.hadoop.fs.s3a.Constants.{ACCESS_KEY, ENDPOINT, SECRET_KEY}
    +import org.apache.spark.sql.SparkSession
    +import org.slf4j.{Logger, LoggerFactory}
    +
    +import org.apache.carbondata.core.constants.CarbonCommonConstants
    +
    +object S3Example {
    +
    +  /**
    +   * This example demonstrate usage of
    +   * 1. create carbon table with storage location on object based storage
    +   *    like AWS S3, Huawei OBS, etc
    +   * 2. load data into carbon table, the generated file will be stored on object based
storage
    +   *    query the table.
    +   * 3. With the indexing feature of carbondata, the data read from object based storage
is minimum,
    +   *    thus providing both high performance analytic and low cost storage
    +   *
    +   * @param args require three parameters "Access-key" "Secret-key"
    +   *             "s3 bucket path" "spark-master" "s3-endpoint"
    +   */
    +  def main(args: Array[String]) {
    +    val rootPath = new File(this.getClass.getResource("/").getPath
    +                            + "../../../..").getCanonicalPath
    +    val path = s"$rootPath/examples/spark2/src/main/resources/data1.csv"
    +    val logger: Logger = LoggerFactory.getLogger(this.getClass)
    +
    +    import org.apache.spark.sql.CarbonSession._
    +    if (args.length < 4 || args.length > 5) {
    +      logger.error("Usage: java CarbonS3Example <access-key> <secret-key>"
+
    +                   "<table-path> <spark-master> <s3-endpoint>")
    +      System.exit(0)
    +    }
    +
    +    val (accessKey, secretKey, endpoint) = getKeyOnPrefix(args(2))
    +    val spark = SparkSession
    +      .builder()
    +      .master(args(3))
    +      .appName("S3Example")
    +      .config("spark.driver.host", "localhost")
    +      .config(accessKey, args(0))
    +      .config(secretKey, args(1))
    +      .config(endpoint, getS3EndPoint(args))
    +      .getOrCreateCarbonSession()
    +
    +    spark.sparkContext.setLogLevel("INFO")
    +
    +    spark.sql(
    +      s"""
    +         | CREATE TABLE if not exists carbon_table(
    +         | shortField SHORT,
    +         | intField INT,
    +         | bigintField LONG,
    +         | doubleField DOUBLE,
    +         | stringField STRING,
    +         | timestampField TIMESTAMP,
    +         | decimalField DECIMAL(18,2),
    +         | dateField DATE,
    +         | charField CHAR(5),
    +         | floatField FLOAT
    +         | )
    +         | STORED BY 'carbondata'
    +         | LOCATION '${ args(2) }'
    +         | TBLPROPERTIES('SORT_COLUMNS'='', 'DICTIONARY_INCLUDE'='dateField, charField')
    +       """.stripMargin)
    +
    +    spark.sql(
    +      s"""
    +         | LOAD DATA LOCAL INPATH '$path'
    +         | INTO TABLE carbon_table
    +         | OPTIONS('HEADER'='true')
    +       """.stripMargin)
    +
    +    spark.sql(
    +      s"""
    +         | LOAD DATA LOCAL INPATH '$path'
    +         | INTO TABLE carbon_table
    +         | OPTIONS('HEADER'='true')
    +       """.stripMargin)
    +
    +    spark.sql(
    +      s"""
    +         | LOAD DATA LOCAL INPATH '$path'
    +         | INTO TABLE carbon_table
    +         | OPTIONS('HEADER'='true')
    +       """.stripMargin)
    +
    +    spark.sql(
    --- End diff --
    
    remove one load to make it simpler


---

Mime
View raw message