Github user jackylk commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161675876 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala --- @@ -0,0 +1,151 @@ +/* + * 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" "spark-master" + */ + + def main(args: Array[String]) { + val rootPath = new File(this.getClass.getResource("/").getPath + + "../../../..").getCanonicalPath + val path = s"$rootPath/examples/spark2/src/main/resources/data1.csv" + val logger: Logger = LoggerFactory.getLogger(this.getClass) + CarbonProperties.getInstance() + .addProperty(CarbonCommonConstants.CARBON_TIMESTAMP_FORMAT, "yyyy/MM/dd HH:mm:ss") + .addProperty(CarbonCommonConstants.CARBON_DATE_FORMAT, "yyyy/MM/dd") + .addProperty(CarbonCommonConstants.ENABLE_UNSAFE_COLUMN_PAGE_LOADING, "true") + .addProperty(CarbonCommonConstants.DEFAULT_CARBON_MAJOR_COMPACTION_SIZE, "0.02") + + import org.apache.spark.sql.CarbonSession._ + if (args.length != 4) { + logger.error("Usage: java CarbonS3Example <access-key> <secret-key>" + + "<table-path> <spark-master>") + System.exit(0) + } + + val (accessKey, secretKey) = getKeyOnPrefix(args(2)) + val spark = SparkSession + .builder() + .master(args(3)) + .appName("S3Example") + .config("spark.driver.host", "localhost") + .config(accessKey, args(0)) + .config(secretKey, args(1)) + .getOrCreateCarbonSession() + + spark.sparkContext.setLogLevel("INFO") + + spark.sql( + s""" + | CREATE TABLE if not exists carbon_table( + | shortField SHORT, + | intField INT, + | bigintField LONG, + | doubleField DOUBLE, + | stringField STRING, + | timestampField TIMESTAMP, + | decimalField DECIMAL(18,2), + | dateField DATE, + | charField CHAR(5), + | floatField FLOAT + | ) + | STORED BY 'carbondata' + | LOCATION '${ 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 '$path' + | INTO TABLE carbon_table + | OPTIONS('HEADER'='true') + """.stripMargin) + + spark.sql( + s""" + | LOAD DATA LOCAL INPATH '$path' + | INTO TABLE carbon_table + | OPTIONS('HEADER'='true') + """.stripMargin) + + spark.sql("ALTER table carbon_table compact 'MINOR'") + spark.sql("show segments for table carbon_table").show() + + spark.sql( --- End diff -- remove this to make it simpler --- |
In reply to this post by qiuchenjian-2
Github user jackylk commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161676080 --- Diff: core/src/main/java/org/apache/carbondata/core/constants/CarbonCommonConstants.java --- @@ -168,6 +168,14 @@ public static final String S3A_PREFIX = "s3a://"; + public static final String S3N_ACCESS_KEY = "fs.s3n.awsAccessKeyId"; --- End diff -- Add comment for these 4 properties --- |
In reply to this post by qiuchenjian-2
Github user jackylk commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161676126 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3CsvExample.scala --- @@ -0,0 +1,111 @@ +/* + * 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 S3CsvExample { + + /** + * This example demonstrate to create local store and load data from CSV files on S3 + * + * @param args require three parameters "Access-key" "Secret-key" + * "s3 path to csv" "spark-master" + */ + --- End diff -- remove empty line --- |
In reply to this post by qiuchenjian-2
Github user ravipesala commented on the issue:
https://github.com/apache/carbondata/pull/1805 SDV Build Success , Please check CI http://144.76.159.231:8080/job/ApacheSDVTests/2906/ --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Success with Spark 2.2.1, Please check CI http://88.99.58.216:8080/job/ApacheCarbonPRBuilder/1585/ --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Failed with Spark 2.1.0, Please check CI http://136.243.101.176:8080/job/ApacheCarbonPRBuilder1/2820/ --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161697634 --- Diff: core/src/main/java/org/apache/carbondata/core/constants/CarbonCommonConstants.java --- @@ -168,6 +168,14 @@ public static final String S3A_PREFIX = "s3a://"; + public static final String S3N_ACCESS_KEY = "fs.s3n.awsAccessKeyId"; --- End diff -- Added comment. --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161697822 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3CsvExample.scala --- @@ -0,0 +1,111 @@ +/* + * 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 S3CsvExample { + + /** + * This example demonstrate to create local store and load data from CSV files on S3 + * + * @param args require three parameters "Access-key" "Secret-key" + * "s3 path to csv" "spark-master" + */ + + def main(args: Array[String]) { + val rootPath = new File(this.getClass.getResource("/").getPath + + "../../../..").getCanonicalPath + 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") --- End diff -- Removed all properties. --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161697900 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala --- @@ -0,0 +1,151 @@ +/* + * 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" "spark-master" + */ + + def main(args: Array[String]) { + val rootPath = new File(this.getClass.getResource("/").getPath + + "../../../..").getCanonicalPath + val path = s"$rootPath/examples/spark2/src/main/resources/data1.csv" + val logger: Logger = LoggerFactory.getLogger(this.getClass) + CarbonProperties.getInstance() + .addProperty(CarbonCommonConstants.CARBON_TIMESTAMP_FORMAT, "yyyy/MM/dd HH:mm:ss") + .addProperty(CarbonCommonConstants.CARBON_DATE_FORMAT, "yyyy/MM/dd") + .addProperty(CarbonCommonConstants.ENABLE_UNSAFE_COLUMN_PAGE_LOADING, "true") + .addProperty(CarbonCommonConstants.DEFAULT_CARBON_MAJOR_COMPACTION_SIZE, "0.02") + + import org.apache.spark.sql.CarbonSession._ + if (args.length != 4) { + logger.error("Usage: java CarbonS3Example <access-key> <secret-key>" + + "<table-path> <spark-master>") + System.exit(0) + } + + val (accessKey, secretKey) = getKeyOnPrefix(args(2)) + val spark = SparkSession + .builder() + .master(args(3)) + .appName("S3Example") + .config("spark.driver.host", "localhost") + .config(accessKey, args(0)) + .config(secretKey, args(1)) + .getOrCreateCarbonSession() + + spark.sparkContext.setLogLevel("INFO") + + spark.sql( + s""" + | CREATE TABLE if not exists carbon_table( + | shortField SHORT, + | intField INT, + | bigintField LONG, + | doubleField DOUBLE, + | stringField STRING, + | timestampField TIMESTAMP, + | decimalField DECIMAL(18,2), + | dateField DATE, + | charField CHAR(5), + | floatField FLOAT + | ) + | STORED BY 'carbondata' + | LOCATION '${ 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 '$path' + | INTO TABLE carbon_table + | OPTIONS('HEADER'='true') + """.stripMargin) + + spark.sql( + s""" + | LOAD DATA LOCAL INPATH '$path' + | INTO TABLE carbon_table + | OPTIONS('HEADER'='true') + """.stripMargin) + + spark.sql("ALTER table carbon_table compact 'MINOR'") --- End diff -- Added --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161697998 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala --- @@ -0,0 +1,151 @@ +/* + * 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" "spark-master" + */ + + 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) + 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") --- End diff -- done --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161698051 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala --- @@ -0,0 +1,151 @@ +/* + * 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. --- End diff -- done --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161698128 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3Example.scala --- @@ -0,0 +1,151 @@ +/* + * 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" "spark-master" + */ + --- End diff -- removed. --- |
In reply to this post by qiuchenjian-2
Github user jatin9896 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1805#discussion_r161698430 --- Diff: examples/spark2/src/main/scala/org/apache/carbondata/examples/S3CsvExample.scala --- @@ -0,0 +1,111 @@ +/* + * 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 S3CsvExample { + + /** + * This example demonstrate to create local store and load data from CSV files on S3 + * + * @param args require three parameters "Access-key" "Secret-key" + * "s3 path to csv" "spark-master" + */ + --- End diff -- done --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Success with Spark 2.2.1, Please check CI http://88.99.58.216:8080/job/ApacheCarbonPRBuilder/1598/ --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Failed with Spark 2.1.0, Please check CI http://136.243.101.176:8080/job/ApacheCarbonPRBuilder1/2833/ --- |
In reply to this post by qiuchenjian-2
Github user ravipesala commented on the issue:
https://github.com/apache/carbondata/pull/1805 SDV Build Success , Please check CI http://144.76.159.231:8080/job/ApacheSDVTests/2916/ --- |
In reply to this post by qiuchenjian-2
Github user jackylk commented on the issue:
https://github.com/apache/carbondata/pull/1805 retest this please --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Success with Spark 2.2.1, Please check CI http://88.99.58.216:8080/job/ApacheCarbonPRBuilder/1615/ --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Failed with Spark 2.1.0, Please check CI http://136.243.101.176:8080/job/ApacheCarbonPRBuilder1/2851/ --- |
In reply to this post by qiuchenjian-2
Github user CarbonDataQA commented on the issue:
https://github.com/apache/carbondata/pull/1805 Build Success with Spark 2.2.1, Please check CI http://88.99.58.216:8080/job/ApacheCarbonPRBuilder/1621/ --- |
Free forum by Nabble | Edit this page |