diff --git a/docs/configurations.md b/docs/configurations.md index cf5c2d7b8..7042d8237 100644 --- a/docs/configurations.md +++ b/docs/configurations.md @@ -76,4 +76,7 @@ summary: "Here we list all possible configurations and what they mean" - [usePrefix](#usePrefix) ()
Standard prefix for all metrics + - [S3Configs](s3_hoodie.html) (Hoodie S3 Configs)
+ Configurations required for S3 and Hoodie co-operability. + {% include callout.html content="Hoodie is a young project. A lot of pluggable interfaces and configurations to support diverse workloads need to be created. Get involved [here](https://github.com/uber/hoodie)" type="info" %} diff --git a/docs/s3_filesystem.md b/docs/s3_filesystem.md index c1bdd2fb1..faa424033 100644 --- a/docs/s3_filesystem.md +++ b/docs/s3_filesystem.md @@ -10,6 +10,10 @@ Hoodie works with HDFS by default. There is an experimental work going on Hoodie ## S3 configs +There are two configurations required for Hoodie-S3 compatibility: +- Adding AWS Credentials for Hoodie +- Adding required Jars to classpath + Add the required configs in your core-site.xml from where Hoodie can fetch them. Replace the `fs.defaultFS` with your S3 bucket name and Hoodie should be able to read/write from the bucket. ``` @@ -44,4 +48,8 @@ Add the required configs in your core-site.xml from where Hoodie can fetch them. ``` +AWS hadoop libraries to add to your classpath - + - com.amazonaws:aws-java-sdk:1.10.34 + - org.apache.hadoop:hadoop-aws:2.7.3 + diff --git a/hoodie-client/pom.xml b/hoodie-client/pom.xml index 617dc9c4b..11e6b85a3 100644 --- a/hoodie-client/pom.xml +++ b/hoodie-client/pom.xml @@ -118,6 +118,11 @@ io.dropwizard.metrics metrics-core + + com.beust + jcommander + 1.48 + diff --git a/hoodie-client/src/test/java/HoodieClientExample.java b/hoodie-client/src/test/java/HoodieClientExample.java index 711b4bb04..39724f67e 100644 --- a/hoodie-client/src/test/java/HoodieClientExample.java +++ b/hoodie-client/src/test/java/HoodieClientExample.java @@ -14,6 +14,9 @@ * limitations under the License. */ + +import com.beust.jcommander.JCommander; +import com.beust.jcommander.Parameter; import com.uber.hoodie.HoodieWriteClient; import com.uber.hoodie.common.HoodieTestDataGenerator; import com.uber.hoodie.common.model.HoodieRecord; @@ -22,13 +25,6 @@ import com.uber.hoodie.common.util.FSUtils; import com.uber.hoodie.config.HoodieIndexConfig; import com.uber.hoodie.config.HoodieWriteConfig; import com.uber.hoodie.index.HoodieIndex; -import org.apache.commons.cli.CommandLine; -import org.apache.commons.cli.CommandLineParser; -import org.apache.commons.cli.BasicParser; -import org.apache.commons.cli.HelpFormatter; -import org.apache.commons.cli.Option; -import org.apache.commons.cli.Options; -import org.apache.commons.cli.ParseException; import org.apache.log4j.LogManager; import org.apache.log4j.Logger; import org.apache.spark.SparkConf; @@ -44,38 +40,23 @@ import java.util.Properties; */ public class HoodieClientExample { + @Parameter(names={"--table-path", "-p"}, description = "path for Hoodie sample table") + private String inputTablePath = "file:///tmp/hoodie/sample-table"; + + @Parameter(names={"--table-name", "-n"}, description = "table name for Hoodie sample table") + private String inputTableName = "sample-table"; private static Logger logger = LogManager.getLogger(HoodieClientExample.class); - private static final String DEFAULT_TABLE_PATH = "file:///tmp/hoodie/sample-table"; - private static final String DEFAULT_TABLE_NAME = "sample-table"; public static void main(String[] args) throws Exception { - Options options = new Options(); - Option path = new Option("p", "table-path", true, "input table path"); - path.setRequired(false); - options.addOption(path); + HoodieClientExample cli = new HoodieClientExample(); + new JCommander(cli, args); + cli.run(); + } - Option name = new Option("n", "table-name", true, "input table name"); - name.setRequired(false); - options.addOption(name); - - CommandLineParser parser = new BasicParser(); - HelpFormatter formatter = new HelpFormatter(); - CommandLine cmd; - - try { - cmd = parser.parse(options, args); - } catch (ParseException e) { - System.out.println(e.getMessage()); - formatter.printHelp("HoodieClientExample", options); - System.exit(1); - return; - } - - String inputTablePath = cmd.getOptionValue("table-path", DEFAULT_TABLE_PATH); - String inputTableName = cmd.getOptionValue("table-name", DEFAULT_TABLE_NAME); + public void run() throws Exception { HoodieTestDataGenerator dataGen = new HoodieTestDataGenerator(); SparkConf sparkConf = new SparkConf().setAppName("hoodie-client-example"); diff --git a/hoodie-common/src/main/java/com/uber/hoodie/common/util/FSUtils.java b/hoodie-common/src/main/java/com/uber/hoodie/common/util/FSUtils.java index 77448d058..2f554aecb 100644 --- a/hoodie-common/src/main/java/com/uber/hoodie/common/util/FSUtils.java +++ b/hoodie-common/src/main/java/com/uber/hoodie/common/util/FSUtils.java @@ -18,7 +18,6 @@ package com.uber.hoodie.common.util; import com.google.common.annotations.VisibleForTesting; import com.google.common.base.Preconditions; -import com.uber.hoodie.common.table.HoodieTimeline; import com.uber.hoodie.common.table.log.HoodieLogFile; import com.uber.hoodie.common.table.timeline.HoodieInstant; import com.uber.hoodie.exception.HoodieIOException;