You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@flink.apache.org by mb...@apache.org on 2015/05/29 15:46:09 UTC
[5/6] flink git commit: [docs] Removed unnecessary Serializable from
ExecutionEnvironment JavaDocs
[docs] Removed unnecessary Serializable from ExecutionEnvironment JavaDocs
Also did for StreamExecutionEnvironment
Project: http://git-wip-us.apache.org/repos/asf/flink/repo
Commit: http://git-wip-us.apache.org/repos/asf/flink/commit/2315c7c5
Tree: http://git-wip-us.apache.org/repos/asf/flink/tree/2315c7c5
Diff: http://git-wip-us.apache.org/repos/asf/flink/diff/2315c7c5
Branch: refs/heads/master
Commit: 2315c7c5935a703eee10eb9eabb75aa8490d1457
Parents: 120bd0f
Author: mbalassi <mb...@apache.org>
Authored: Sun May 24 17:51:21 2015 +0200
Committer: mbalassi <mb...@apache.org>
Committed: Fri May 29 15:08:32 2015 +0200
----------------------------------------------------------------------
.../flink/api/java/ExecutionEnvironment.java | 30 +--------
.../environment/StreamExecutionEnvironment.java | 64 ++++++--------------
2 files changed, 21 insertions(+), 73 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/flink/blob/2315c7c5/flink-java/src/main/java/org/apache/flink/api/java/ExecutionEnvironment.java
----------------------------------------------------------------------
diff --git a/flink-java/src/main/java/org/apache/flink/api/java/ExecutionEnvironment.java b/flink-java/src/main/java/org/apache/flink/api/java/ExecutionEnvironment.java
index 9c76409..3a5b04f 100644
--- a/flink-java/src/main/java/org/apache/flink/api/java/ExecutionEnvironment.java
+++ b/flink-java/src/main/java/org/apache/flink/api/java/ExecutionEnvironment.java
@@ -19,7 +19,6 @@
package org.apache.flink.api.java;
import java.io.IOException;
-import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Calendar;
@@ -600,9 +599,7 @@ public abstract class ExecutionEnvironment {
/**
* Creates a DataSet from the given non-empty collection. The type of the data set is that
- * of the elements in the collection. The elements need to be serializable (as defined by
- * {@link java.io.Serializable}), because the framework may move the elements into the cluster
- * if needed.
+ * of the elements in the collection.
* <p>
* The framework will try and determine the exact type from the collection elements.
* In case of generic elements, it may be necessary to manually supply the type information
@@ -632,13 +629,8 @@ public abstract class ExecutionEnvironment {
}
/**
- * Creates a DataSet from the given non-empty collection. The type of the data set is that
- * of the elements in the collection. The elements need to be serializable (as defined by
- * {@link java.io.Serializable}), because the framework may move the elements into the cluster
- * if needed.
- * <p>
- * Note that this operation will result in a non-parallel data source, i.e. a data source with
- * a parallelism of one.
+ * Creates a DataSet from the given non-empty collection. Note that this operation will result
+ * in a non-parallel data source, i.e. a data source with a parallelism of one.
* <p>
* The returned DataSet is typed to the given TypeInformation.
*
@@ -663,9 +655,6 @@ public abstract class ExecutionEnvironment {
* explicitly in the form of the type class (this is due to the fact that the Java compiler
* erases the generic type information).
* <p>
- * The iterator must be serializable (as defined in {@link java.io.Serializable}), because the
- * framework may move it to a remote environment, if needed.
- * <p>
* Note that this operation will result in a non-parallel data source, i.e. a data source with
* a parallelism of one.
*
@@ -686,9 +675,6 @@ public abstract class ExecutionEnvironment {
* is generic. In that case, the type class (as given in {@link #fromCollection(Iterator, Class)}
* does not supply all type information.
* <p>
- * The iterator must be serializable (as defined in {@link java.io.Serializable}), because the
- * framework may move it to a remote environment, if needed.
- * <p>
* Note that this operation will result in a non-parallel data source, i.e. a data source with
* a parallelism of one.
*
@@ -699,10 +685,6 @@ public abstract class ExecutionEnvironment {
* @see #fromCollection(Iterator, Class)
*/
public <X> DataSource<X> fromCollection(Iterator<X> data, TypeInformation<X> type) {
- if (!(data instanceof Serializable)) {
- throw new IllegalArgumentException("The iterator must be serializable.");
- }
-
return new DataSource<X>(this, new IteratorInputFormat<X>(data), type, Utils.getCallLocationName());
}
@@ -710,8 +692,6 @@ public abstract class ExecutionEnvironment {
/**
* Creates a new data set that contains the given elements. The elements must all be of the same type,
* for example, all of the {@link String} or {@link Integer}. The sequence of elements must not be empty.
- * Furthermore, the elements must be serializable (as defined in {@link java.io.Serializable}, because the
- * execution environment may ship the elements into the cluster.
* <p>
* The framework will try and determine the exact type from the collection elements.
* In case of generic elements, it may be necessary to manually supply the type information
@@ -738,8 +718,6 @@ public abstract class ExecutionEnvironment {
/**
* Creates a new data set that contains elements in the iterator. The iterator is splittable, allowing the
* framework to create a parallel data source that returns the elements in the iterator.
- * The iterator must be serializable (as defined in {@link java.io.Serializable}, because the
- * execution environment may ship the elements into the cluster.
* <p>
* Because the iterator will remain unmodified until the actual execution happens, the type of data
* returned by the iterator must be given explicitly in the form of the type class (this is due to the
@@ -758,8 +736,6 @@ public abstract class ExecutionEnvironment {
/**
* Creates a new data set that contains elements in the iterator. The iterator is splittable, allowing the
* framework to create a parallel data source that returns the elements in the iterator.
- * The iterator must be serializable (as defined in {@link java.io.Serializable}, because the
- * execution environment may ship the elements into the cluster.
* <p>
* Because the iterator will remain unmodified until the actual execution happens, the type of data
* returned by the iterator must be given explicitly in the form of the type information.
http://git-wip-us.apache.org/repos/asf/flink/blob/2315c7c5/flink-staging/flink-streaming/flink-streaming-core/src/main/java/org/apache/flink/streaming/api/environment/StreamExecutionEnvironment.java
----------------------------------------------------------------------
diff --git a/flink-staging/flink-streaming/flink-streaming-core/src/main/java/org/apache/flink/streaming/api/environment/StreamExecutionEnvironment.java b/flink-staging/flink-streaming/flink-streaming-core/src/main/java/org/apache/flink/streaming/api/environment/StreamExecutionEnvironment.java
index 09a8788..8dd15bb 100644
--- a/flink-staging/flink-streaming/flink-streaming-core/src/main/java/org/apache/flink/streaming/api/environment/StreamExecutionEnvironment.java
+++ b/flink-staging/flink-streaming/flink-streaming-core/src/main/java/org/apache/flink/streaming/api/environment/StreamExecutionEnvironment.java
@@ -70,7 +70,6 @@ import org.apache.hadoop.mapreduce.Job;
import java.io.File;
import java.io.IOException;
-import java.io.Serializable;
import java.util.Collection;
import java.util.Iterator;
import java.util.List;
@@ -438,15 +437,12 @@ public abstract class StreamExecutionEnvironment {
/**
* Creates a new data stream that contains the given elements. The elements must all be of the same type, for
- * example, all of the {@link String} or {@link Integer}. The sequence of elements must not be empty. Furthermore,
- * the elements must be serializable (as defined in {@link java.io.Serializable}), because the execution
- * environment
- * may ship the elements into the cluster.
- * <p/>
+ * example, all of the {@link String} or {@link Integer}.
+ * <p>
* The framework will try and determine the exact type from the elements. In case of generic elements, it may be
* necessary to manually supply the type information via {@link #fromCollection(java.util.Collection,
* org.apache.flink.api.common.typeinfo.TypeInformation)}.
- * <p/>
+ * <p>
* Note that this operation will result in a non-parallel data stream source, i.e. a data stream source with a
* degree of parallelism one.
*
@@ -471,15 +467,14 @@ public abstract class StreamExecutionEnvironment {
/**
* Creates a data stream from the given non-empty collection. The type of the data stream is that of the
- * elements in
- * the collection. The elements need to be serializable (as defined by {@link java.io.Serializable}), because the
- * framework may move the elements into the cluster if needed.
- * <p/>
+ * elements in the collection.
+ *
+ * <p>
* The framework will try and determine the exact type from the collection elements. In case of generic
- * elements, it
- * may be necessary to manually supply the type information via {@link #fromCollection(java.util.Collection,
- * org.apache.flink.api.common.typeinfo.TypeInformation)}.
- * <p/>
+ * elements, it may be necessary to manually supply the type information via
+ * {@link #fromCollection(java.util.Collection, org.apache.flink.api.common.typeinfo.TypeInformation)}.
+ * <p>
+ *
* Note that this operation will result in a non-parallel data stream source, i.e. a data stream source with a
* degree of parallelism one.
*
@@ -503,12 +498,8 @@ public abstract class StreamExecutionEnvironment {
}
/**
- * Creates a data stream from the given non-empty collection. The type of the data stream is the type given by
- * typeInfo. The elements need to be serializable (as defined by {@link java.io.Serializable}), because the
- * framework may move the elements into the cluster if needed.
- * <p/>
- * Note that this operation will result in a non-parallel data stream source, i.e. a data stream source with a
- * degree of parallelism one.
+ * Creates a data stream from the given non-empty collection.Note that this operation will result in
+ * a non-parallel data stream source, i.e. a data stream source with a degree of parallelism one.
*
* @param data
* The collection of elements to create the data stream from
@@ -535,11 +526,7 @@ public abstract class StreamExecutionEnvironment {
* Creates a data stream from the given iterator. Because the iterator will remain unmodified until the actual
* execution happens, the type of data returned by the iterator must be given explicitly in the form of the type
* class (this is due to the fact that the Java compiler erases the generic type information).
- * <p/>
- * The iterator must be serializable (as defined in {@link java.io.Serializable}), because the framework may
- * move it
- * to a remote environment, if needed.
- * <p/>
+ * <p>
* Note that this operation will result in a non-parallel data stream source, i.e. a data stream source with a
* degree of parallelism of one.
*
@@ -562,11 +549,7 @@ public abstract class StreamExecutionEnvironment {
* information. This method is useful for cases where the type is generic. In that case, the type class (as
* given in
* {@link #fromCollection(java.util.Iterator, Class)} does not supply all type information.
- * <p/>
- * The iterator must be serializable (as defined in {@link java.io.Serializable}), because the framework may
- * move it
- * to a remote environment, if needed.
- * <p/>
+ * <p>
* Note that this operation will result in a non-parallel data stream source, i.e. a data stream source with a
* degree of parallelism one.
*
@@ -581,9 +564,6 @@ public abstract class StreamExecutionEnvironment {
public <OUT> DataStreamSource<OUT> fromCollection(Iterator<OUT> data, TypeInformation<OUT>
typeInfo) {
Preconditions.checkNotNull(data, "The iterator must not be null");
- if (!(data instanceof Serializable)) {
- throw new IllegalArgumentException("The iterator must be serializable.");
- }
SourceFunction<OUT> function = new FromIteratorFunction<OUT>(data);
return addSource(function, "Collection Source").returns(typeInfo);
@@ -597,12 +577,8 @@ public abstract class StreamExecutionEnvironment {
/**
* Creates a new data stream that contains elements in the iterator. The iterator is splittable, allowing the
- * framework to create a parallel data stream source that returns the elements in the iterator. The iterator
- * must be
- * serializable (as defined in {@link java.io.Serializable}, because the execution environment may ship the
- * elements
- * into the cluster.
- * <p/>
+ * framework to create a parallel data stream source that returns the elements in the iterator.
+ * <p>
* Because the iterator will remain unmodified until the actual execution happens, the type of data returned by the
* iterator must be given explicitly in the form of the type class (this is due to the fact that the Java compiler
* erases the generic type information).
@@ -621,12 +597,8 @@ public abstract class StreamExecutionEnvironment {
/**
* Creates a new data stream that contains elements in the iterator. The iterator is splittable, allowing the
- * framework to create a parallel data stream source that returns the elements in the iterator. The iterator
- * must be
- * serializable (as defined in {@link java.io.Serializable}, because the execution environment may ship the
- * elements
- * into the cluster.
- * <p/>
+ * framework to create a parallel data stream source that returns the elements in the iterator.
+ * <p>
* Because the iterator will remain unmodified until the actual execution happens, the type of data returned by the
* iterator must be given explicitly in the form of the type information. This method is useful for cases where the
* type is generic. In that case, the type class (as given in {@link #fromParallelCollection(org.apache.flink.util.SplittableIterator,