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 #1584: [CARBONDATA-1827] Added S3 Implementation
Date Sat, 13 Jan 2018 03:19:46 GMT
Github user jackylk commented on a diff in the pull request:

    https://github.com/apache/carbondata/pull/1584#discussion_r161362197
  
    --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala
---
    @@ -0,0 +1,152 @@
    +/*
    + * 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, SECRET_KEY}
    +import org.apache.spark.sql.SparkSession
    +import org.slf4j.{Logger, LoggerFactory}
    +
    +import org.apache.carbondata.core.constants.CarbonCommonConstants
    +import org.apache.carbondata.core.util.CarbonProperties
    +
    +object S3Example {
    +
    +  /**
    +   * This example demonstrate usage of s3 as a store.
    +   *
    +   * @param args require three parameters "Access-key" "Secret-key"
    +   *             "s3 bucket path"
    +   */
    +
    +  def main(args: Array[String]) {
    +    val rootPath = new File(this.getClass.getResource("/").getPath
    +                            + "../../../..").getCanonicalPath
    +    val warehouse = s"$rootPath/examples/spark2/target/warehouse"
    +    val path = s"$rootPath/examples/spark2/src/main/resources/data1.csv"
    +    val logger: Logger = LoggerFactory.getLogger(this.getClass)
    +    CarbonProperties.getInstance()
    +      .addProperty(CarbonCommonConstants.CARBON_TIMESTAMP_FORMAT, "yyyy/MM/dd HH:mm:ss")
    +      .addProperty(CarbonCommonConstants.CARBON_DATE_FORMAT, "yyyy/MM/dd")
    +      .addProperty(CarbonCommonConstants.ENABLE_UNSAFE_COLUMN_PAGE_LOADING, "true")
    +      .addProperty(CarbonCommonConstants.DEFAULT_CARBON_MAJOR_COMPACTION_SIZE, "0.02")
    +
    +    import org.apache.spark.sql.CarbonSession._
    +    if (args.length != 3) {
    +      logger.error("Usage: java CarbonS3Example <access-key> <secret-key>"
+
    +                   "<carbon store location>")
    +      System.exit(0)
    +    }
    +
    +    val (accessKey, secretKey) = getKeyOnPrefix(args(2))
    +    val spark = SparkSession
    +      .builder()
    +      .master("local")
    +      .appName("CarbonSessionExample")
    +      .config("spark.sql.warehouse.dir", warehouse)
    +      .config("spark.driver.host", "localhost")
    +      .config(accessKey, args(0))
    +      .config(secretKey, args(1))
    +      .getOrCreateCarbonSession(args(2), warehouse)
    --- End diff --
    
    Do not use store path, now carbon supports specifying location when creating table. This
is the standard way to create table. So user can create one session and decide the table storage
location in CREATE TABLE DDL, it can be HDFS, S3, or others.


---

Mime
View raw message