zeppelin-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From k..@apache.org
Subject zeppelin git commit: [ZEPPELIN-2865] upgrade Beam interpreter to latest version
Date Sun, 20 Aug 2017 11:16:36 GMT
Repository: zeppelin
Updated Branches:
  refs/heads/master 7b5db0492 -> b87bcf5a9


[ZEPPELIN-2865] upgrade Beam interpreter to latest version

### What is this PR for?
upgrade Beam interpreter to use the latest version of Apache Beam.

### What type of PR is it?
[Improvement]

### Todos
*

### What is the Jira issue?
* https://issues.apache.org/jira/browse/ZEPPELIN-2865

### How should this be tested?
* Start the Zeppelin server
* The prefix of interpreter is %beam and then write your code with required imports and the
runner

Refer to `docs/interpreter/beam.md` for an example;

### Screenshots (if appropriate)

### Questions:
* Does the licenses files need update?  no
* Is there breaking changes for older versions? no
* Does this needs documentation? yes, updated `docs/interpreter/beam.md` and `README.md`

Author: mingmxu <mingmxu@ebay.com>

Closes #2541 from XuMingmin/ZEPPELIN-2865 and squashes the following commits:

520f0fd7 [mingmxu] restore the notice message of scala-2.10
93b3e24d [mingmxu] upgrade to Apache Beam 2.0.0


Project: http://git-wip-us.apache.org/repos/asf/zeppelin/repo
Commit: http://git-wip-us.apache.org/repos/asf/zeppelin/commit/b87bcf5a
Tree: http://git-wip-us.apache.org/repos/asf/zeppelin/tree/b87bcf5a
Diff: http://git-wip-us.apache.org/repos/asf/zeppelin/diff/b87bcf5a

Branch: refs/heads/master
Commit: b87bcf5a996dbf40b2d4d9d2804e422235e47d6a
Parents: 7b5db04
Author: mingmxu <mingmxu@ebay.com>
Authored: Wed Aug 16 09:47:25 2017 -0700
Committer: 1ambda <1amb4a@gmail.com>
Committed: Sun Aug 20 20:16:32 2017 +0900

----------------------------------------------------------------------
 beam/README.md           |  2 +-
 beam/pom.xml             | 10 +++++++++-
 docs/interpreter/beam.md | 14 +++-----------
 3 files changed, 13 insertions(+), 13 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/zeppelin/blob/b87bcf5a/beam/README.md
----------------------------------------------------------------------
diff --git a/beam/README.md b/beam/README.md
index 57150a0..948c95c 100644
--- a/beam/README.md
+++ b/beam/README.md
@@ -8,7 +8,7 @@ Current interpreter implementation supports the static repl. It compiles the
cod
 You have to first build the Beam interpreter by enable the **beam** profile as follows:
 
 ```
-mvn clean package -Pbeam -DskipTests
+mvn clean package -Pbeam -DskipTests -Pscala-2.10
 ```
 
 ### Notice

http://git-wip-us.apache.org/repos/asf/zeppelin/blob/b87bcf5a/beam/pom.xml
----------------------------------------------------------------------
diff --git a/beam/pom.xml b/beam/pom.xml
index c02695c..1666527 100644
--- a/beam/pom.xml
+++ b/beam/pom.xml
@@ -35,7 +35,7 @@
   <properties>
     <beam.hadoop.version>2.3.0</beam.hadoop.version>
     <beam.spark.version>1.6.2</beam.spark.version>
-    <beam.beam.version>0.2.0-incubating</beam.beam.version>
+    <beam.beam.version>2.0.0</beam.beam.version>
 
     <!-- library versions -->
     <netty.version>4.1.1.Final</netty.version>
@@ -211,6 +211,14 @@
       <version>${beam.beam.version}</version>
       <type>jar</type>
     </dependency>
+
+    <dependency>
+      <groupId>org.apache.beam</groupId>
+      <artifactId>beam-runners-flink_${scala.binary.version}</artifactId>
+      <version>${beam.beam.version}</version>
+      <exclusions>
+      </exclusions>
+    </dependency>
   
     <dependency>
       <groupId>${project.groupId}</groupId>

http://git-wip-us.apache.org/repos/asf/zeppelin/blob/b87bcf5a/docs/interpreter/beam.md
----------------------------------------------------------------------
diff --git a/docs/interpreter/beam.md b/docs/interpreter/beam.md
index cbcd5e3..d992b8e 100644
--- a/docs/interpreter/beam.md
+++ b/docs/interpreter/beam.md
@@ -44,18 +44,10 @@ import java.io.Serializable;
 import java.util.Arrays;
 import java.util.List;
 import java.util.ArrayList;
-import org.apache.spark.api.java.*;
-import org.apache.spark.api.java.function.Function;
-import org.apache.spark.SparkConf;
-import org.apache.spark.streaming.*;
-import org.apache.spark.SparkContext;
 import org.apache.beam.runners.direct.*;
 import org.apache.beam.sdk.runners.*;
 import org.apache.beam.sdk.options.*;
-import org.apache.beam.runners.spark.*;
-import org.apache.beam.runners.spark.io.ConsoleIO;
 import org.apache.beam.runners.flink.*;
-import org.apache.beam.runners.flink.examples.WordCount.Options;
 import org.apache.beam.sdk.Pipeline;
 import org.apache.beam.sdk.io.TextIO;
 import org.apache.beam.sdk.options.PipelineOptionsFactory;
@@ -89,12 +81,12 @@ public class MinimalWordCount {
 	};  
   static final List<String> SENTENCES = Arrays.asList(SENTENCES_ARRAY);
   public static void main(String[] args) {
-    Options options = PipelineOptionsFactory.create().as(Options.class);
+    PipelineOptions options = PipelineOptionsFactory.create().as(PipelineOptions.class);
     options.setRunner(FlinkRunner.class);
     Pipeline p = Pipeline.create(options);
     p.apply(Create.of(SENTENCES).withCoder(StringUtf8Coder.of()))
          .apply("ExtractWords", ParDo.of(new DoFn<String, String>() {
-           @Override
+           @ProcessElement
            public void processElement(ProcessContext c) {
              for (String word : c.element().split("[^a-zA-Z']+")) {
                if (!word.isEmpty()) {
@@ -105,7 +97,7 @@ public class MinimalWordCount {
          }))
         .apply(Count.<String> perElement())
         .apply("FormatResults", ParDo.of(new DoFn<KV<String, Long>, String>()
{
-          @Override
+          @ProcessElement
           public void processElement(DoFn<KV<String, Long>, String>.ProcessContext
arg0)
             throws Exception {
             s.add("\n" + arg0.element().getKey() + "\t" + arg0.element().getValue());


Mime
View raw message