You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@flink.apache.org by ch...@apache.org on 2018/01/17 13:44:54 UTC
flink git commit: [hotfix] [docs] Fix typos
Repository: flink
Updated Branches:
refs/heads/release-1.4 c91544d14 -> 0deaee835
[hotfix] [docs] Fix typos
This closes #5289.
Project: http://git-wip-us.apache.org/repos/asf/flink/repo
Commit: http://git-wip-us.apache.org/repos/asf/flink/commit/0deaee83
Tree: http://git-wip-us.apache.org/repos/asf/flink/tree/0deaee83
Diff: http://git-wip-us.apache.org/repos/asf/flink/diff/0deaee83
Branch: refs/heads/release-1.4
Commit: 0deaee835cc97bc09d1c3b78e2444b2da996be57
Parents: c91544d
Author: Greg Hogan <co...@greghogan.com>
Authored: Fri Jan 12 09:29:28 2018 -0500
Committer: zentol <ch...@apache.org>
Committed: Wed Jan 17 14:44:49 2018 +0100
----------------------------------------------------------------------
docs/dev/api_concepts.md | 2 +-
docs/dev/batch/hadoop_compatibility.md | 2 +-
docs/dev/batch/index.md | 22 ++++++++++----------
docs/dev/batch/iterations.md | 4 ++--
docs/dev/batch/python.md | 4 ++--
docs/dev/connectors/cassandra.md | 2 +-
docs/dev/connectors/kafka.md | 2 +-
docs/dev/connectors/kinesis.md | 2 +-
docs/dev/connectors/rabbitmq.md | 2 +-
docs/dev/datastream_api.md | 2 +-
docs/dev/java8.md | 2 +-
docs/dev/libs/cep.md | 8 +++----
docs/dev/libs/gelly/graph_generators.md | 6 +++---
docs/dev/libs/ml/cross_validation.md | 2 +-
docs/dev/libs/storm_compatibility.md | 4 ++--
docs/dev/linking_with_flink.md | 2 +-
docs/dev/migration.md | 2 +-
docs/dev/packaging.md | 2 +-
docs/dev/scala_api_extensions.md | 2 +-
docs/dev/stream/operators/asyncio.md | 10 ++++-----
docs/dev/stream/operators/index.md | 4 ++--
docs/dev/stream/operators/windows.md | 2 +-
docs/dev/stream/state/checkpointing.md | 2 +-
docs/dev/stream/state/index.md | 4 ++--
docs/dev/stream/testing.md | 4 ++--
docs/dev/table/common.md | 4 ++--
docs/dev/table/sourceSinks.md | 4 ++--
docs/dev/table/sql.md | 2 +-
docs/dev/table/udfs.md | 2 +-
docs/dev/types_serialization.md | 2 +-
docs/internals/ide_setup.md | 2 +-
docs/internals/job_scheduling.md | 2 +-
docs/monitoring/checkpoint_monitoring.md | 4 ++--
docs/ops/config.md | 2 +-
docs/ops/deployment/mesos.md | 2 +-
docs/ops/filesystems.md | 6 +++---
docs/ops/jobmanager_high_availability.md | 2 +-
docs/ops/security-ssl.md | 2 +-
docs/ops/state/large_state_tuning.md | 2 +-
docs/ops/upgrading.md | 2 +-
docs/start/flink_on_windows.md | 2 +-
.../flink/api/java/operators/UdfOperator.java | 2 +-
...ctionExecutionWithBroadcastVariableTest.java | 2 +-
.../flink/graph/gsa/GSAConfiguration.java | 6 +++---
.../pregel/VertexCentricConfiguration.java | 2 +-
.../spargel/ScatterGatherConfiguration.java | 4 ++--
.../flink/optimizer/UnionReplacementTest.java | 4 ++--
.../BroadcastVariableMaterialization.java | 2 +-
.../runtime/state/OperatorStateHandle.java | 2 +-
.../org/apache/flink/api/scala/DataSet.scala | 2 +-
.../streaming/api/datastream/DataStream.java | 2 +-
51 files changed, 85 insertions(+), 85 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/api_concepts.md
----------------------------------------------------------------------
diff --git a/docs/dev/api_concepts.md b/docs/dev/api_concepts.md
index cb43a42..c675225 100644
--- a/docs/dev/api_concepts.md
+++ b/docs/dev/api_concepts.md
@@ -460,7 +460,7 @@ The following example shows a key selector function that simply returns the fiel
// some ordinary POJO
public class WC {public String word; public int count;}
DataStream<WC> words = // [...]
-KeyedStream<WC> kyed = words
+KeyedStream<WC> keyed = words
.keyBy(new KeySelector<WC, String>() {
public String getKey(WC wc) { return wc.word; }
});
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/batch/hadoop_compatibility.md
----------------------------------------------------------------------
diff --git a/docs/dev/batch/hadoop_compatibility.md b/docs/dev/batch/hadoop_compatibility.md
index bbeea09..9f1478a2 100644
--- a/docs/dev/batch/hadoop_compatibility.md
+++ b/docs/dev/batch/hadoop_compatibility.md
@@ -42,7 +42,7 @@ This document shows how to use existing Hadoop MapReduce code with Flink. Please
### Project Configuration
-Support for Haddop input/output formats is part of the `flink-java` and
+Support for Hadoop input/output formats is part of the `flink-java` and
`flink-scala` Maven modules that are always required when writing Flink jobs.
The code is located in `org.apache.flink.api.java.hadoop` and
`org.apache.flink.api.scala.hadoop` in an additional sub-package for the
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/batch/index.md
----------------------------------------------------------------------
diff --git a/docs/dev/batch/index.md b/docs/dev/batch/index.md
index cb3b42c..f0fab8b 100644
--- a/docs/dev/batch/index.md
+++ b/docs/dev/batch/index.md
@@ -293,7 +293,7 @@ result = input1.join(input2)
pick the best strategy according to those estimates.
{% highlight java %}
// This executes a join by broadcasting the first data set
-// using a hash table for the broadcasted data
+// using a hash table for the broadcast data
result = input1.join(input2, JoinHint.BROADCAST_HASH_FIRST)
.where(0).equalTo(1);
{% endhighlight %}
@@ -613,7 +613,7 @@ val result = input1.join(input2).where(0).equalTo(1)
pick the best strategy according to those estimates.
{% highlight scala %}
// This executes a join by broadcasting the first data set
-// using a hash table for the broadcasted data
+// using a hash table for the broadcast data
val result = input1.join(input2, JoinHint.BROADCAST_HASH_FIRST)
.where(0).equalTo(1)
{% endhighlight %}
@@ -658,7 +658,7 @@ val data1: DataSet[Int] = // [...]
val data2: DataSet[String] = // [...]
val result: DataSet[(Int, String)] = data1.cross(data2)
{% endhighlight %}
- <p>Note: Cross is potentially a <b>very</b> compute-intensive operation which can challenge even large compute clusters! It is adviced to hint the system with the DataSet sizes by using <i>crossWithTiny()</i> and <i>crossWithHuge()</i>.</p>
+ <p>Note: Cross is potentially a <b>very</b> compute-intensive operation which can challenge even large compute clusters! It is advised to hint the system with the DataSet sizes by using <i>crossWithTiny()</i> and <i>crossWithHuge()</i>.</p>
</td>
</tr>
<tr>
@@ -994,7 +994,7 @@ Collection-based:
- `fromParallelCollection(SplittableIterator)` - Creates a data set from an iterator, in
parallel. The class specifies the data type of the elements returned by the iterator.
-- `generateSequence(from, to)` - Generates the squence of numbers in the given interval, in
+- `generateSequence(from, to)` - Generates the sequence of numbers in the given interval, in
parallel.
Generic:
@@ -1146,7 +1146,7 @@ using an
Flink comes with a variety of built-in output formats that are encapsulated behind operations on the
DataSet:
-- `writeAsText()` / `TextOuputFormat` - Writes elements line-wise as Strings. The Strings are
+- `writeAsText()` / `TextOutputFormat` - Writes elements line-wise as Strings. The Strings are
obtained by calling the *toString()* method of each element.
- `writeAsFormattedText()` / `TextOutputFormat` - Write elements line-wise as Strings. The Strings
are obtained by calling a user-defined *format()* method for each element.
@@ -1972,7 +1972,7 @@ Collection.
<div class="codetabs" markdown="1">
<div data-lang="java" markdown="1">
{% highlight java %}
-// 1. The DataSet to be broadcasted
+// 1. The DataSet to be broadcast
DataSet<Integer> toBroadcast = env.fromElements(1, 2, 3);
DataSet<String> data = env.fromElements("a", "b");
@@ -1980,7 +1980,7 @@ DataSet<String> data = env.fromElements("a", "b");
data.map(new RichMapFunction<String, String>() {
@Override
public void open(Configuration parameters) throws Exception {
- // 3. Access the broadcasted DataSet as a Collection
+ // 3. Access the broadcast DataSet as a Collection
Collection<Integer> broadcastSet = getRuntimeContext().getBroadcastVariable("broadcastSetName");
}
@@ -1993,13 +1993,13 @@ data.map(new RichMapFunction<String, String>() {
{% endhighlight %}
Make sure that the names (`broadcastSetName` in the previous example) match when registering and
-accessing broadcasted data sets. For a complete example program, have a look at
+accessing broadcast data sets. For a complete example program, have a look at
{% gh_link /flink-examples/flink-examples-batch/src/main/java/org/apache/flink/examples/java/clustering/KMeans.java "K-Means Algorithm" %}.
</div>
<div data-lang="scala" markdown="1">
{% highlight scala %}
-// 1. The DataSet to be broadcasted
+// 1. The DataSet to be broadcast
val toBroadcast = env.fromElements(1, 2, 3)
val data = env.fromElements("a", "b")
@@ -2008,7 +2008,7 @@ data.map(new RichMapFunction[String, String]() {
var broadcastSet: Traversable[String] = null
override def open(config: Configuration): Unit = {
- // 3. Access the broadcasted DataSet as a Collection
+ // 3. Access the broadcast DataSet as a Collection
broadcastSet = getRuntimeContext().getBroadcastVariable[String]("broadcastSetName").asScala
}
@@ -2019,7 +2019,7 @@ data.map(new RichMapFunction[String, String]() {
{% endhighlight %}
Make sure that the names (`broadcastSetName` in the previous example) match when registering and
-accessing broadcasted data sets. For a complete example program, have a look at
+accessing broadcast data sets. For a complete example program, have a look at
{% gh_link /flink-examples/flink-examples-batch/src/main/scala/org/apache/flink/examples/scala/clustering/KMeans.scala "KMeans Algorithm" %}.
</div>
</div>
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/batch/iterations.md
----------------------------------------------------------------------
diff --git a/docs/dev/batch/iterations.md b/docs/dev/batch/iterations.md
index 67f2615..f5b65ac 100644
--- a/docs/dev/batch/iterations.md
+++ b/docs/dev/batch/iterations.md
@@ -119,13 +119,13 @@ setFinalState(state);
### Example: Incrementing Numbers
-In the following example, we **iteratively incremenet a set numbers**:
+In the following example, we **iteratively increment a set numbers**:
<p class="text-center">
<img alt="Iterate Operator Example" width="60%" src="{{site.baseurl}}/fig/iterations_iterate_operator_example.png" />
</p>
- 1. **Iteration Input**: The inital input is read from a data source and consists of five single-field records (integers `1` to `5`).
+ 1. **Iteration Input**: The initial input is read from a data source and consists of five single-field records (integers `1` to `5`).
2. **Step function**: The step function is a single `map` operator, which increments the integer field from `i` to `i+1`. It will be applied to every record of the input.
3. **Next Partial Solution**: The output of the step function will be the output of the map operator, i.e. records with incremented integers.
4. **Iteration Result**: After ten iterations, the initial numbers will have been incremented ten times, resulting in integers `11` to `15`.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/batch/python.md
----------------------------------------------------------------------
diff --git a/docs/dev/batch/python.md b/docs/dev/batch/python.md
index 0383f54..2211102 100644
--- a/docs/dev/batch/python.md
+++ b/docs/dev/batch/python.md
@@ -560,7 +560,7 @@ class MapperBcv(MapFunction):
factor = self.context.get_broadcast_variable("bcv")[0][0]
return value * factor
-# 1. The DataSet to be broadcasted
+# 1. The DataSet to be broadcast
toBroadcast = env.from_elements(1, 2, 3)
data = env.from_elements("a", "b")
@@ -569,7 +569,7 @@ data.map(MapperBcv()).with_broadcast_set("bcv", toBroadcast)
{% endhighlight %}
Make sure that the names (`bcv` in the previous example) match when registering and
-accessing broadcasted data sets.
+accessing broadcast data sets.
**Note**: As the content of broadcast variables is kept in-memory on each node, it should not become
too large. For simpler things like scalar values you can simply parameterize the rich function.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/connectors/cassandra.md
----------------------------------------------------------------------
diff --git a/docs/dev/connectors/cassandra.md b/docs/dev/connectors/cassandra.md
index 64d81b5..6e1470a 100644
--- a/docs/dev/connectors/cassandra.md
+++ b/docs/dev/connectors/cassandra.md
@@ -30,7 +30,7 @@ under the License.
This connector provides sinks that writes data into a [Apache Cassandra](https://cassandra.apache.org/) database.
<!--
- TODO: Perhaps worth mentioning current DataStax Java Driver version to match Cassandra versoin on user side.
+ TODO: Perhaps worth mentioning current DataStax Java Driver version to match Cassandra version on user side.
-->
To use this connector, add the following dependency to your project:
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/connectors/kafka.md
----------------------------------------------------------------------
diff --git a/docs/dev/connectors/kafka.md b/docs/dev/connectors/kafka.md
index e2df5fd..8e38146 100644
--- a/docs/dev/connectors/kafka.md
+++ b/docs/dev/connectors/kafka.md
@@ -633,7 +633,7 @@ the consumers until `transaction1` is committed or aborted. This has two implica
* First of all, during normal working of Flink applications, user can expect a delay in visibility
of the records produced into Kafka topics, equal to average time between completed checkpoints.
- * Secondly in case of Flink application failure, topics into which this application was writting,
+ * Secondly in case of Flink application failure, topics into which this application was writing,
will be blocked for the readers until the application restarts or the configured transaction
timeout time will pass. This remark only applies for the cases when there are multiple
agents/applications writing to the same Kafka topic.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/connectors/kinesis.md
----------------------------------------------------------------------
diff --git a/docs/dev/connectors/kinesis.md b/docs/dev/connectors/kinesis.md
index ff22ee0..9bcd70a 100644
--- a/docs/dev/connectors/kinesis.md
+++ b/docs/dev/connectors/kinesis.md
@@ -331,7 +331,7 @@ Otherwise, the returned stream name is used.
### Threading Model
-Since Flink 1.4.0, `FlinkKinesisProducer` switches its default underlying KPL from a one-thread-per-request mode to a thread-pool mode. KPL in thread-pool mode uses a queue and thread pool to execute requests to Kinesis. This limits the number of threads that KPL's native process may create, and therefore greatly lowers CPU utilizations and improves efficiency. **Thus, We highly recommend Flink users use thread-pool model.** The default thread pool size is `10`. Users can set the pool size in `java.util.Properties` instance with key `ThreadPoolSize`, as shown in the above example.
+Since Flink 1.4.0, `FlinkKinesisProducer` switches its default underlying KPL from a one-thread-per-request mode to a thread-pool mode. KPL in thread-pool mode uses a queue and thread pool to execute requests to Kinesis. This limits the number of threads that KPL's native process may create, and therefore greatly lowers CPU utilization and improves efficiency. **Thus, We highly recommend Flink users use thread-pool model.** The default thread pool size is `10`. Users can set the pool size in `java.util.Properties` instance with key `ThreadPoolSize`, as shown in the above example.
Users can still switch back to one-thread-per-request mode by setting a key-value pair of `ThreadingModel` and `PER_REQUEST` in `java.util.Properties`, as shown in the code commented out in above example.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/connectors/rabbitmq.md
----------------------------------------------------------------------
diff --git a/docs/dev/connectors/rabbitmq.md b/docs/dev/connectors/rabbitmq.md
index c3ad4b7..2a698c1 100644
--- a/docs/dev/connectors/rabbitmq.md
+++ b/docs/dev/connectors/rabbitmq.md
@@ -66,7 +66,7 @@ RabbitMQ source, the following is required -
- *Use correlation ids*: Correlation ids are a RabbitMQ application feature.
You have to set it in the message properties when injecting messages into RabbitMQ.
The correlation id is used by the source to deduplicate any messages that
- have been reproccessed when restoring from a checkpoint.
+ have been reprocessed when restoring from a checkpoint.
- *Non-parallel source*: The source must be non-parallel (parallelism set
to 1) in order to achieve exactly-once. This limitation is mainly due to
RabbitMQ's approach to dispatching messages from a single queue to multiple
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/datastream_api.md
----------------------------------------------------------------------
diff --git a/docs/dev/datastream_api.md b/docs/dev/datastream_api.md
index d7ab2e7..32cb519 100644
--- a/docs/dev/datastream_api.md
+++ b/docs/dev/datastream_api.md
@@ -490,7 +490,7 @@ env.generateSequence(1,10).map(new MyMapper()).setBufferTimeout(timeoutMillis);
LocalStreamEnvironment env = StreamExecutionEnvironment.createLocalEnvironment
env.setBufferTimeout(timeoutMillis)
-env.genereateSequence(1,10).map(myMap).setBufferTimeout(timeoutMillis)
+env.generateSequence(1,10).map(myMap).setBufferTimeout(timeoutMillis)
{% endhighlight %}
</div>
</div>
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/java8.md
----------------------------------------------------------------------
diff --git a/docs/dev/java8.md b/docs/dev/java8.md
index eb9a290..4949833 100644
--- a/docs/dev/java8.md
+++ b/docs/dev/java8.md
@@ -169,7 +169,7 @@ Create/Import your Eclipse project.
If you are using Maven, you also need to change the Java version in your `pom.xml` for the `maven-compiler-plugin`. Otherwise right click the `JRE System Library` section of your project and open the `Properties` window in order to switch to a Java 8 JRE (or above) that supports Lambda Expressions.
-The Eclipse JDT compiler needs a special compiler flag in order to store type information in `.class` files. Open the JDT configuration file at `{project directoy}/.settings/org.eclipse.jdt.core.prefs` with your favorite text editor and add the following line:
+The Eclipse JDT compiler needs a special compiler flag in order to store type information in `.class` files. Open the JDT configuration file at `{project directory}/.settings/org.eclipse.jdt.core.prefs` with your favorite text editor and add the following line:
~~~
org.eclipse.jdt.core.compiler.codegen.lambda.genericSignature=generate
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/libs/cep.md
----------------------------------------------------------------------
diff --git a/docs/dev/libs/cep.md b/docs/dev/libs/cep.md
index d814a38..16f29ea 100644
--- a/docs/dev/libs/cep.md
+++ b/docs/dev/libs/cep.md
@@ -150,7 +150,7 @@ it to a looping one by using [Quantifiers](#quantifiers). Each pattern can have
#### Quantifiers
-In FlinkCEP, you can specifiy looping patterns using these methods: `pattern.oneOrMore()`, for patterns that expect one or more occurrences of a given event (e.g. the `b+` mentioned before); and `pattern.times(#ofTimes)`, for patterns that
+In FlinkCEP, you can specify looping patterns using these methods: `pattern.oneOrMore()`, for patterns that expect one or more occurrences of a given event (e.g. the `b+` mentioned before); and `pattern.times(#ofTimes)`, for patterns that
expect a specific number of occurrences of a given type of event, e.g. 4 `a`'s; and `pattern.times(#fromTimes, #toTimes)`, for patterns that expect a specific minimum number of occurrences and a maximum number of occurrences of a given type of event, e.g. 2-4 `a`s.
You can make looping patterns greedy using the `pattern.greedy()` method, but you cannot yet make group patterns greedy. You can make all patterns, looping or not, optional using the `pattern.optional()` method.
@@ -1089,7 +1089,7 @@ Pattern<Event, ?> notNext = start.notNext("not");
if other events occur between the matching (negative) event and the previous matching event
(relaxed contiguity):</p>
{% highlight java %}
-Pattern<Event, ?> notFollowedBy = start.notFllowedBy("not");
+Pattern<Event, ?> notFollowedBy = start.notFollowedBy("not");
{% endhighlight %}
</td>
</tr>
@@ -1211,7 +1211,7 @@ val notNext = start.notNext("not")
if other events occur between the matching (negative) event and the previous matching event
(relaxed contiguity):</p>
{% highlight scala %}
-val notFollowedBy = start.notFllowedBy("not")
+val notFollowedBy = start.notFollowedBy("not")
{% endhighlight %}
</td>
</tr>
@@ -1448,7 +1448,7 @@ To treat partial patterns, the `select` and `flatSelect` API calls offer an over
parameters
* `PatternTimeoutFunction`/`PatternFlatTimeoutFunction`
- * [OutputTag]({{ site.baseurl }}/dev/stream/side_output.html) for the side output in which the timeouted matches will be returned
+ * [OutputTag]({{ site.baseurl }}/dev/stream/side_output.html) for the side output in which the timed out matches will be returned
* and the known `PatternSelectFunction`/`PatternFlatSelectFunction`.
<div class="codetabs" markdown="1">
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/libs/gelly/graph_generators.md
----------------------------------------------------------------------
diff --git a/docs/dev/libs/gelly/graph_generators.md b/docs/dev/libs/gelly/graph_generators.md
index d4ad229..cbd65da 100644
--- a/docs/dev/libs/gelly/graph_generators.md
+++ b/docs/dev/libs/gelly/graph_generators.md
@@ -555,10 +555,10 @@ val graph = new RMatGraph(env.getJavaEnv, rnd, vertexCount, edgeCount).generate(
</div>
</div>
-The default RMat contants can be overridden as shown in the following example.
-The contants define the interdependence of bits from each generated edge's source
+The default RMat constants can be overridden as shown in the following example.
+The constants define the interdependence of bits from each generated edge's source
and target labels. The RMat noise can be enabled and progressively perturbs the
-contants while generating each edge.
+constants while generating each edge.
The RMat generator can be configured to produce a simple graph by removing self-loops
and duplicate edges. Symmetrization is performed either by a "clip-and-flip" throwing away
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/libs/ml/cross_validation.md
----------------------------------------------------------------------
diff --git a/docs/dev/libs/ml/cross_validation.md b/docs/dev/libs/ml/cross_validation.md
index ef3d2ff..e264282 100644
--- a/docs/dev/libs/ml/cross_validation.md
+++ b/docs/dev/libs/ml/cross_validation.md
@@ -54,7 +54,7 @@ Traditionally, training and testing would be done to train an algorithms as norm
In a train-test-holdout strategy we sacrifice the sample size of the initial fitting algorithm for increased confidence that our model is not over-fit.
-When using `trainTestHoldout` splitter, the *fraction* `Double` is replaced by a *fraction* array of length three. The first element coresponds to the portion to be used for training, second for testing, and third for holdout. The weights of this array are *relative*, e.g. an array `Array(3.0, 2.0, 1.0)` would results in approximately 50% of the observations being in the training set, 33% of the observations in the testing set, and 17% of the observations in holdout set.
+When using `trainTestHoldout` splitter, the *fraction* `Double` is replaced by a *fraction* array of length three. The first element corresponds to the portion to be used for training, second for testing, and third for holdout. The weights of this array are *relative*, e.g. an array `Array(3.0, 2.0, 1.0)` would results in approximately 50% of the observations being in the training set, 33% of the observations in the testing set, and 17% of the observations in holdout set.
### K-Fold Splits
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/libs/storm_compatibility.md
----------------------------------------------------------------------
diff --git a/docs/dev/libs/storm_compatibility.md b/docs/dev/libs/storm_compatibility.md
index 4f499f1..853b8e1 100644
--- a/docs/dev/libs/storm_compatibility.md
+++ b/docs/dev/libs/storm_compatibility.md
@@ -54,10 +54,10 @@ Add the following dependency to your `pom.xml` if you want to execute Storm code
**Please note**: Do not add `storm-core` as a dependency. It is already included via `flink-storm`.
**Please note**: `flink-storm` is not part of the provided binary Flink distribution.
-Thus, you need to include `flink-storm` classes (and their dependencies) in your program jar (also called ueber-jar or fat-jar) that is submitted to Flink's JobManager.
+Thus, you need to include `flink-storm` classes (and their dependencies) in your program jar (also called uber-jar or fat-jar) that is submitted to Flink's JobManager.
See *WordCount Storm* within `flink-storm-examples/pom.xml` for an example how to package a jar correctly.
-If you want to avoid large ueber-jars, you can manually copy `storm-core-0.9.4.jar`, `json-simple-1.1.jar` and `flink-storm-{{site.version}}.jar` into Flink's `lib/` folder of each cluster node (*before* the cluster is started).
+If you want to avoid large uber-jars, you can manually copy `storm-core-0.9.4.jar`, `json-simple-1.1.jar` and `flink-storm-{{site.version}}.jar` into Flink's `lib/` folder of each cluster node (*before* the cluster is started).
For this case, it is sufficient to include only your own Spout and Bolt classes (and their internal dependencies) into the program jar.
# Execute Storm Topologies
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/linking_with_flink.md
----------------------------------------------------------------------
diff --git a/docs/dev/linking_with_flink.md b/docs/dev/linking_with_flink.md
index 3f55b9e..f2380b2 100644
--- a/docs/dev/linking_with_flink.md
+++ b/docs/dev/linking_with_flink.md
@@ -109,7 +109,7 @@ import org.apache.flink.api.scala.createTypeInformation
{% endhighlight %}
The reason is that Flink analyzes the types that are used in a program and generates serializers
-and comparaters for them. By having either of those imports you enable an implicit conversion
+and comparators for them. By having either of those imports you enable an implicit conversion
that creates the type information for Flink operations.
If you would rather use SBT, see [here]({{ site.baseurl }}/quickstart/scala_api_quickstart.html#sbt).
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/migration.md
----------------------------------------------------------------------
diff --git a/docs/dev/migration.md b/docs/dev/migration.md
index 5ac6961..dea8b7a 100644
--- a/docs/dev/migration.md
+++ b/docs/dev/migration.md
@@ -165,7 +165,7 @@ public class BufferingSink implements SinkFunction<Tuple2<String, Integer>>,
{% endhighlight %}
-The `CountMapper` is a `RichFlatMapFuction` which assumes a grouped-by-key input stream of the form
+The `CountMapper` is a `RichFlatMapFunction` which assumes a grouped-by-key input stream of the form
`(word, 1)`. The function keeps a counter for each incoming key (`ValueState<Integer> counter`) and if
the number of occurrences of a certain word surpasses the user-provided threshold, a tuple is emitted
containing the word itself and the number of occurrences.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/packaging.md
----------------------------------------------------------------------
diff --git a/docs/dev/packaging.md b/docs/dev/packaging.md
index 769a675..f43ff87 100644
--- a/docs/dev/packaging.md
+++ b/docs/dev/packaging.md
@@ -48,7 +48,7 @@ automatically when exporting JAR files.
### Packaging Programs through Plans
-Additionally, we support packaging programs as *Plans*. Instead of defining a progam in the main
+Additionally, we support packaging programs as *Plans*. Instead of defining a program in the main
method and calling
`execute()` on the environment, plan packaging returns the *Program Plan*, which is a description of
the program's data flow. To do that, the program must implement the
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/scala_api_extensions.md
----------------------------------------------------------------------
diff --git a/docs/dev/scala_api_extensions.md b/docs/dev/scala_api_extensions.md
index 41836f9..7c1ae67 100644
--- a/docs/dev/scala_api_extensions.md
+++ b/docs/dev/scala_api_extensions.md
@@ -61,7 +61,7 @@ data.map {
{% endhighlight %}
This extension introduces new methods in both the DataSet and DataStream Scala API
-that have a one-to-one correspondance in the extended API. These delegating methods
+that have a one-to-one correspondence in the extended API. These delegating methods
do support anonymous pattern matching functions.
#### DataSet API
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/stream/operators/asyncio.md
----------------------------------------------------------------------
diff --git a/docs/dev/stream/operators/asyncio.md b/docs/dev/stream/operators/asyncio.md
index c473638..702d2ae 100644
--- a/docs/dev/stream/operators/asyncio.md
+++ b/docs/dev/stream/operators/asyncio.md
@@ -142,7 +142,7 @@ class AsyncDatabaseRequest extends AsyncFunction[String, (String, String)] {
implicit lazy val executor: ExecutionContext = ExecutionContext.fromExecutor(Executors.directExecutor())
- override def asyncInvoke(str: String, resultFutre: ResultFuture[(String, String)]): Unit = {
+ override def asyncInvoke(str: String, resultFuture: ResultFuture[(String, String)]): Unit = {
// issue the asynchronous request, receive a future for the result
val resultFuture: Future[String] = client.query(str)
@@ -193,7 +193,7 @@ To control in which order the resulting records are emitted, Flink offers two mo
- **Ordered**: In that case, the stream order is preserved. Result records are emitted in the same order as the asynchronous
requests are triggered (the order of the operators input records). To achieve that, the operator buffers a result record
- until all its preceeding records are emitted (or timed out).
+ until all its preceding records are emitted (or timed out).
This usually introduces some amount of extra latency and some overhead in checkpointing, because records or results are maintained
in the checkpointed state for a longer time, compared to the unordered mode.
Use `AsyncDataStream.orderedWait(...)` for this mode.
@@ -227,10 +227,10 @@ asynchronous requests in checkpoints and restores/re-triggers the requests when
### Implementation Tips
-For implementations with *Futures* that have an *Executor* (or *ExecutionContext* in Scala) for callbacks, we suggets to use a `DirectExecutor`, because the
+For implementations with *Futures* that have an *Executor* (or *ExecutionContext* in Scala) for callbacks, we suggests to use a `DirectExecutor`, because the
callback typically does minimal work, and a `DirectExecutor` avoids an additional thread-to-thread handover overhead. The callback typically only hands
the result to the `ResultFuture`, which adds it to the output buffer. From there, the heavy logic that includes record emission and interaction
-with the checkpoint bookkeepting happens in a dedicated thread-pool anyways.
+with the checkpoint bookkeeping happens in a dedicated thread-pool anyways.
A `DirectExecutor` can be obtained via `org.apache.flink.runtime.concurrent.Executors.directExecutor()` or
`com.google.common.util.concurrent.MoreExecutors.directExecutor()`.
@@ -249,6 +249,6 @@ For example, the following patterns result in a blocking `asyncInvoke(...)` func
- Using a database client whose lookup/query method call blocks until the result has been received back
- - Blocking/waiting on the future-type objects returned by an aynchronous client inside the `asyncInvoke(...)` method
+ - Blocking/waiting on the future-type objects returned by an asynchronous client inside the `asyncInvoke(...)` method
{% top %}
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/stream/operators/index.md
----------------------------------------------------------------------
diff --git a/docs/dev/stream/operators/index.md b/docs/dev/stream/operators/index.md
index 0ed0b2a..b0325ca 100644
--- a/docs/dev/stream/operators/index.md
+++ b/docs/dev/stream/operators/index.md
@@ -271,7 +271,7 @@ windowedStream.fold("start", new FoldFunction<Integer, String>() {
<td><strong>Aggregations on windows</strong><br>WindowedStream → DataStream</td>
<td>
<p>Aggregates the contents of a window. The difference between min
- and minBy is that min returns the minimun value, whereas minBy returns
+ and minBy is that min returns the minimum value, whereas minBy returns
the element that has the minimum value in this field (same for max and maxBy).</p>
{% highlight java %}
windowedStream.sum(0);
@@ -540,7 +540,7 @@ val result: DataStream[String] =
<td><strong>Aggregations</strong><br>KeyedStream → DataStream</td>
<td>
<p>Rolling aggregations on a keyed data stream. The difference between min
- and minBy is that min returns the minimun value, whereas minBy returns
+ and minBy is that min returns the minimum value, whereas minBy returns
the element that has the minimum value in this field (same for max and maxBy).</p>
{% highlight scala %}
keyedStream.sum(0)
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/stream/operators/windows.md
----------------------------------------------------------------------
diff --git a/docs/dev/stream/operators/windows.md b/docs/dev/stream/operators/windows.md
index e161854..0327d06 100644
--- a/docs/dev/stream/operators/windows.md
+++ b/docs/dev/stream/operators/windows.md
@@ -811,7 +811,7 @@ input
#### Incremental Window Aggregation with AggregateFunction
The following example shows how an incremental `AggregateFunction` can be combined with
-a `ProcesWindowFunction` to compute the average and also emit the key and window along with
+a `ProcessWindowFunction` to compute the average and also emit the key and window along with
the average.
<div class="codetabs" markdown="1">
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/stream/state/checkpointing.md
----------------------------------------------------------------------
diff --git a/docs/dev/stream/state/checkpointing.md b/docs/dev/stream/state/checkpointing.md
index 67d95d5..cd9816d 100644
--- a/docs/dev/stream/state/checkpointing.md
+++ b/docs/dev/stream/state/checkpointing.md
@@ -50,7 +50,7 @@ By default, checkpointing is disabled. To enable checkpointing, call `enableChec
Other parameters for checkpointing include:
- *exactly-once vs. at-least-once*: You can optionally pass a mode to the `enableCheckpointing(n)` method to choose between the two guarantee levels.
- Exactly-once is preferrable for most applications. At-least-once may be relevant for certain super-low-latency (consistently few milliseconds) applications.
+ Exactly-once is preferable for most applications. At-least-once may be relevant for certain super-low-latency (consistently few milliseconds) applications.
- *checkpoint timeout*: The time after which a checkpoint-in-progress is aborted, if it did not complete by then.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/stream/state/index.md
----------------------------------------------------------------------
diff --git a/docs/dev/stream/state/index.md b/docs/dev/stream/state/index.md
index 1cfadca..fe725af 100644
--- a/docs/dev/stream/state/index.md
+++ b/docs/dev/stream/state/index.md
@@ -33,7 +33,7 @@ For example:
- When an application searches for certain event patterns, the state will store the sequence of events encountered so far.
- When aggregating events per minute/hour/day, the state holds the pending aggregates.
- When training a machine learning model over a stream of data points, the state holds the current version of the model parameters.
- - When historic data needs to be managed, the state allows efficient access to events occured in the past.
+ - When historic data needs to be managed, the state allows efficient access to events that occurred in the past.
Flink needs to be aware of the state in order to make state fault tolerant using [checkpoints](checkpointing.html) and to allow [savepoints]({{ site.baseurl }}/ops/state/savepoints.html) of streaming applications.
@@ -53,4 +53,4 @@ Where to go next?
* [Queryable State](queryable_state.html): Explains how to access state from outside of Flink during runtime.
* [Custom Serialization for Managed State](custom_serialization.html): Discusses custom serialization logic for state and its upgrades.
-{% top %}
\ No newline at end of file
+{% top %}
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/stream/testing.md
----------------------------------------------------------------------
diff --git a/docs/dev/stream/testing.md b/docs/dev/stream/testing.md
index ce31629..0a43d31 100644
--- a/docs/dev/stream/testing.md
+++ b/docs/dev/stream/testing.md
@@ -68,7 +68,7 @@ public class SumReduceTest {
@Test
public void testSum() throws Exception {
- // intiantiate your function
+ // instantiate your function
SumReduce sumReduce = new SumReduce();
// call the methods that you have implemented
@@ -83,7 +83,7 @@ public class SumReduceTest {
class SumReduceTest extends FlatSpec with Matchers {
"SumReduce" should "add values" in {
- // intiantiate your function
+ // instantiate your function
val sumReduce: SumReduce = new SumReduce()
// call the methods that you have implemented
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/table/common.md
----------------------------------------------------------------------
diff --git a/docs/dev/table/common.md b/docs/dev/table/common.md
index a63c4dc..f562f6a 100644
--- a/docs/dev/table/common.md
+++ b/docs/dev/table/common.md
@@ -160,7 +160,7 @@ An input table can be registered from various sources:
* a `TableSource`, which accesses external data, such as a file, database, or messaging system.
* a `DataStream` or `DataSet` from a DataStream or DataSet program. Registering a `DataStream` or `DataSet` is discussed in the [Integration with DataStream and DataSet API](#integration-with-datastream-and-dataset-api) section.
-An output table can be registerd using a `TableSink`.
+An output table can be registered using a `TableSink`.
### Register a Table
@@ -271,7 +271,7 @@ val tableEnv = TableEnvironment.getTableEnvironment(env)
val csvSink: TableSink = new CsvTableSink("/path/to/file", ...)
// define the field names and types
-val fieldNames: Arary[String] = Array("a", "b", "c")
+val fieldNames: Array[String] = Array("a", "b", "c")
val fieldTypes: Array[TypeInformation[_]] = Array(Types.INT, Types.STRING, Types.LONG)
// register the TableSink as table "CsvSinkTable"
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/table/sourceSinks.md
----------------------------------------------------------------------
diff --git a/docs/dev/table/sourceSinks.md b/docs/dev/table/sourceSinks.md
index 2b10278..413d7a9 100644
--- a/docs/dev/table/sourceSinks.md
+++ b/docs/dev/table/sourceSinks.md
@@ -463,7 +463,7 @@ The following `TimestampExtractor` implementations are currently available:
* `ExistingField(fieldName)`: Extracts the value of a rowtime attribute from an existing `LONG` or `SQL_TIMESTAMP` field.
* `StreamRecordTimestamp()`: Extracts the value of a rowtime attribute from the timestamp of the `DataStream` `StreamRecord`. Note, this `TimestampExtractor` is not available for batch table sources.
-A custom `TimestampExtrator` can be defined by implementing the corresponding interface.
+A custom `TimestampExtractor` can be defined by implementing the corresponding interface.
#### Provided WatermarkStrategies
@@ -479,7 +479,7 @@ A custom `WatermarkStrategy` can be defined by implementing the corresponding in
### CsvTableSource
-The `CsvTableSource` is already included in `flink-table` without additional dependecies.
+The `CsvTableSource` is already included in `flink-table` without additional dependencies.
The easiest way to create a `CsvTableSource` is by using the enclosed builder `CsvTableSource.builder()`, the builder has the following methods to configure properties:
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/table/sql.md
----------------------------------------------------------------------
diff --git a/docs/dev/table/sql.md b/docs/dev/table/sql.md
index 3097d9e..dd6adc1 100644
--- a/docs/dev/table/sql.md
+++ b/docs/dev/table/sql.md
@@ -94,7 +94,7 @@ val result2 = tableEnv.sqlQuery(
// SQL update with a registered table
// create and register a TableSink
TableSink csvSink = new CsvTableSink("/path/to/file", ...)
-val fieldNames: Arary[String] = Array("product", "amount")
+val fieldNames: Array[String] = Array("product", "amount")
val fieldTypes: Array[TypeInformation[_]] = Array(Types.STRING, Types.INT)
tableEnv.registerTableSink("RubberOrders", fieldNames, fieldTypes, csvSink)
// run a SQL update query on the Table and emit the result to the TableSink
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/table/udfs.md
----------------------------------------------------------------------
diff --git a/docs/dev/table/udfs.md b/docs/dev/table/udfs.md
index 0e09302..02c047e 100644
--- a/docs/dev/table/udfs.md
+++ b/docs/dev/table/udfs.md
@@ -665,7 +665,7 @@ We recommended that user-defined functions should be written by Java instead of
Integrating UDFs with the Runtime
---------------------------------
-Sometimes it might be necessary for a user-defined function to get global runtime information or do some setup/clean-up work before the actual work. User-defined functions provide `open()` and `close()` methods that can be overriden and provide similar functionality as the methods in `RichFunction` of DataSet or DataStream API.
+Sometimes it might be necessary for a user-defined function to get global runtime information or do some setup/clean-up work before the actual work. User-defined functions provide `open()` and `close()` methods that can be overridden and provide similar functionality as the methods in `RichFunction` of DataSet or DataStream API.
The `open()` method is called once before the evaluation method. The `close()` method after the last call to the evaluation method.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/dev/types_serialization.md
----------------------------------------------------------------------
diff --git a/docs/dev/types_serialization.md b/docs/dev/types_serialization.md
index 1f0c466..b0a4b28 100644
--- a/docs/dev/types_serialization.md
+++ b/docs/dev/types_serialization.md
@@ -64,7 +64,7 @@ The most frequent issues where users need to interact with Flink's data type han
Call `.getConfig().addDefaultKryoSerializer(clazz, serializer)` on the `StreamExecutionEnvironment` or `ExecutionEnvironment`.
Additional Kryo serializers are available in many libraries. See [Custom Serializers]({{ site.baseurl }}/dev/custom_serializers.html) for more details on working with custom serializers.
-* **Adding Type Hints:** Sometimes, when Flink cannot infer the generic types despits all tricks, a user must pass a *type hint*. That is generally
+* **Adding Type Hints:** Sometimes, when Flink cannot infer the generic types despite all tricks, a user must pass a *type hint*. That is generally
only necessary in the Java API. The [Type Hints Section](#type-hints-in-the-java-api) describes that in more detail.
* **Manually creating a `TypeInformation`:** This may be necessary for some API calls where it is not possible for Flink to infer
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/internals/ide_setup.md
----------------------------------------------------------------------
diff --git a/docs/internals/ide_setup.md b/docs/internals/ide_setup.md
index ea80f56..340544d 100644
--- a/docs/internals/ide_setup.md
+++ b/docs/internals/ide_setup.md
@@ -47,7 +47,7 @@ git clone https://github.com/apache/flink.git
## IntelliJ IDEA
A brief guide on how to set up IntelliJ IDEA IDE for development of the Flink core.
-As Eclipse is known to have issues with mixed Scala and Java projects, more and more contributers are migrating to IntelliJ IDEA.
+As Eclipse is known to have issues with mixed Scala and Java projects, more and more contributors are migrating to IntelliJ IDEA.
The following documentation describes the steps to setup IntelliJ IDEA 2016.2.5
([https://www.jetbrains.com/idea/download/](https://www.jetbrains.com/idea/download/))
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/internals/job_scheduling.md
----------------------------------------------------------------------
diff --git a/docs/internals/job_scheduling.md b/docs/internals/job_scheduling.md
index 668dfa3..1d44e86 100644
--- a/docs/internals/job_scheduling.md
+++ b/docs/internals/job_scheduling.md
@@ -39,7 +39,7 @@ but also for batch programs, it happens frequently.
The figure below illustrates that. Consider a program with a data source, a *MapFunction*, and a *ReduceFunction*.
The source and MapFunction are executed with a parallelism of 4, while the ReduceFunction is executed with a
-parallism of 3. A pipeline consists of the sequence Source - Map - Reduce. On a cluster with 2 TaskManagers with
+parallelism of 3. A pipeline consists of the sequence Source - Map - Reduce. On a cluster with 2 TaskManagers with
3 slots each, the program will be executed as described below.
<div style="text-align: center;">
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/monitoring/checkpoint_monitoring.md
----------------------------------------------------------------------
diff --git a/docs/monitoring/checkpoint_monitoring.md b/docs/monitoring/checkpoint_monitoring.md
index 6c2c289..25ed3dd 100644
--- a/docs/monitoring/checkpoint_monitoring.md
+++ b/docs/monitoring/checkpoint_monitoring.md
@@ -75,7 +75,7 @@ jobmanager.web.checkpoints.history: 15
### Summary Tab
-The summary computes a simple min/average/maximum statitics over all completed checkpoints for the End to End Duration, State Size, and Bytes Buffered During Alignment (see [History](#history) for details about what these mean).
+The summary computes a simple min/average/maximum statistics over all completed checkpoints for the End to End Duration, State Size, and Bytes Buffered During Alignment (see [History](#history) for details about what these mean).
<center>
<img src="{{ site.baseurl }}/fig/checkpoint_monitoring-summary.png" width="700px" alt="Checkpoint Monitoring: Summary">
@@ -96,7 +96,7 @@ The configuration list your streaming configuration:
### Checkpoint Details
-When you click on a *More details* link for a checkpoint, you get a Minumum/Average/Maximum summary over all its operators and also the detailed numbers per single subtask.
+When you click on a *More details* link for a checkpoint, you get a Minimum/Average/Maximum summary over all its operators and also the detailed numbers per single subtask.
<center>
<img src="{{ site.baseurl }}/fig/checkpoint_monitoring-details.png" width="700px" alt="Checkpoint Monitoring: Details">
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/config.md
----------------------------------------------------------------------
diff --git a/docs/ops/config.md b/docs/ops/config.md
index bcf7671..375e6bd 100644
--- a/docs/ops/config.md
+++ b/docs/ops/config.md
@@ -62,7 +62,7 @@ for JobManager or TaskManager-specific options, respectively.
- `taskmanager.numberOfTaskSlots`: The number of parallel operator or user function instances that a single TaskManager can run (DEFAULT: 1). If this value is larger than 1, a single TaskManager takes multiple instances of a function or operator. That way, the TaskManager can utilize multiple CPU cores, but at the same time, the available memory is divided between the different operator or function instances. This value is typically proportional to the number of physical CPU cores that the TaskManager's machine has (e.g., equal to the number of cores, or half the number of cores). [More about task slots](config.html#configuring-taskmanager-processing-slots).
-- `parallelism.default`: The default parallelism to use for programs that have no parallelism specified. (DEFAULT: 1). For setups that have no concurrent jobs running, setting this value to NumTaskManagers * NumSlotsPerTaskManager will cause the system to use all available execution resources for the program's execution. **Note**: The default parallelism can be overwriten for an entire job by calling `setParallelism(int parallelism)` on the `ExecutionEnvironment` or by passing `-p <parallelism>` to the Flink Command-line frontend. It can be overwritten for single transformations by calling `setParallelism(int
+- `parallelism.default`: The default parallelism to use for programs that have no parallelism specified. (DEFAULT: 1). For setups that have no concurrent jobs running, setting this value to NumTaskManagers * NumSlotsPerTaskManager will cause the system to use all available execution resources for the program's execution. **Note**: The default parallelism can be overwritten for an entire job by calling `setParallelism(int parallelism)` on the `ExecutionEnvironment` or by passing `-p <parallelism>` to the Flink Command-line frontend. It can be overwritten for single transformations by calling `setParallelism(int
parallelism)` on an operator. See [Parallel Execution]({{site.baseurl}}/dev/parallel.html) for more information about parallelism.
- `fs.default-scheme`: The default filesystem scheme to be used, with the necessary authority to contact, e.g. the host:port of the NameNode in the case of HDFS (if needed).
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/deployment/mesos.md
----------------------------------------------------------------------
diff --git a/docs/ops/deployment/mesos.md b/docs/ops/deployment/mesos.md
index 56d0cde..5bbdc7d 100644
--- a/docs/ops/deployment/mesos.md
+++ b/docs/ops/deployment/mesos.md
@@ -55,7 +55,7 @@ the state before the failure.
The artifact server is responsible for providing resources to the worker
nodes. The resources can be anything from the Flink binaries to shared secrets
-or configuration files. For instance, in non-containered environments, the
+or configuration files. For instance, in non-containerized environments, the
artifact server will provide the Flink binaries. What files will be served
depends on the configuration overlay used.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/filesystems.md
----------------------------------------------------------------------
diff --git a/docs/ops/filesystems.md b/docs/ops/filesystems.md
index 5b2a1e7..ea0caa9 100644
--- a/docs/ops/filesystems.md
+++ b/docs/ops/filesystems.md
@@ -46,7 +46,7 @@ including any NFS or SAN that is mounted into that local file system.
- **S3**: Flink directly provides file systems to talk to Amazon S3, registered under the scheme *"s3://"*.
There are two alternative implementations, `flink-s3-fs-presto` and `flink-s3-fs-hadoop`, based on code from the [Presto project](https://prestodb.io/)
and the [Hadoop Project](https://hadoop.apache.org/). Both implementations are self-contained with no dependency footprint.
-To use those when using Flink as a library, add the resective maven dependency (`org.apache.flink:flink-s3-fs-presto:{{ site.version }}` or `org.apache.flink:flink-s3-fs-hadoop:{{ site.version }}`).
+To use those when using Flink as a library, add the respective maven dependency (`org.apache.flink:flink-s3-fs-presto:{{ site.version }}` or `org.apache.flink:flink-s3-fs-hadoop:{{ site.version }}`).
When starting a Flink application from the Flink binaries, copy or move the respective jar file from the `opt` folder to the `lib` folder.
See [AWS setup](deployment/aws.html) for details.
@@ -57,7 +57,7 @@ See [AWS setup](deployment/aws.html) for details.
For a scheme where Flink does not implemented a file system itself, Flink will try to use Hadoop to instantiate a file system for the respective scheme.
All Hadoop file systems are automatically available once `flink-runtime` and the relevant Hadoop libraries are in classpath.
-That way, Flink seamslessly supports all of Hadoop file systems, and all Hadoop-compatible file systems (HCFS), for example:
+That way, Flink seamlessly supports all of Hadoop file systems, and all Hadoop-compatible file systems (HCFS), for example:
- **hdfs**
- **ftp**
@@ -104,7 +104,7 @@ the total number of concurrent streams (`fs.<scheme>.limit.total`). If the file
If the opening of the stream takes longer than `fs.<scheme>.limit.timeout`, the stream opening will fail.
To prevent inactive streams from taking up the complete pool (preventing new connections to be opened), you can add an inactivity timeout for streams:
-`fs.<scheme>.limit.stream-timeout`. If a stream does not read/write any bytes for at least that amout of time, it is forcibly closed.
+`fs.<scheme>.limit.stream-timeout`. If a stream does not read/write any bytes for at least that amount of time, it is forcibly closed.
These limits are enforced per TaskManager, so each TaskManager in a Flink application or cluster will open up to that number of connections.
In addition, the The limit are also enforced only per FileSystem instance. Because File Systems are created per scheme and authority, different
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/jobmanager_high_availability.md
----------------------------------------------------------------------
diff --git a/docs/ops/jobmanager_high_availability.md b/docs/ops/jobmanager_high_availability.md
index 2b590cc..a994558 100644
--- a/docs/ops/jobmanager_high_availability.md
+++ b/docs/ops/jobmanager_high_availability.md
@@ -82,7 +82,7 @@ In order to start an HA-cluster add the following configuration keys to `conf/fl
<pre>high-availability.cluster-id: /default_ns # important: customize per cluster</pre>
- **Important**: You should not set this value manually when runnig a YARN
+ **Important**: You should not set this value manually when running a YARN
cluster, a per-job YARN session, or on another cluster manager. In those
cases a cluster-id is automatically being generated based on the application
id. Manually setting a cluster-id overrides this behaviour in YARN.
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/security-ssl.md
----------------------------------------------------------------------
diff --git a/docs/ops/security-ssl.md b/docs/ops/security-ssl.md
index 8c7bf2b..961af89 100644
--- a/docs/ops/security-ssl.md
+++ b/docs/ops/security-ssl.md
@@ -140,6 +140,6 @@ security.ssl.truststore-password: password
flink run -m yarn-cluster -yt deploy-keys/ TestJob.jar
~~~
-When deployed using YARN, flink's web dashboard is accessible through YARN proxy's Tracking URL. To ensure that the YARN proxy is able to access flink's https url you need to configure YARN proxy to accept flink's SSL certificates. Add the custom CA certificate into Java's default trustore on the YARN Proxy node.
+When deployed using YARN, flink's web dashboard is accessible through YARN proxy's Tracking URL. To ensure that the YARN proxy is able to access flink's https url you need to configure YARN proxy to accept flink's SSL certificates. Add the custom CA certificate into Java's default truststore on the YARN Proxy node.
{% top %}
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/state/large_state_tuning.md
----------------------------------------------------------------------
diff --git a/docs/ops/state/large_state_tuning.md b/docs/ops/state/large_state_tuning.md
index 85ffd99..28ef99b 100644
--- a/docs/ops/state/large_state_tuning.md
+++ b/docs/ops/state/large_state_tuning.md
@@ -58,7 +58,7 @@ The two numbers that are of particular interest when scaling up checkpoints are:
- The amount of data buffered during alignments. For exactly-once semantics, Flink *aligns* the streams at
operators that receive multiple input streams, buffering some data for that alignment.
- The buffered data volume is ideally low - higher amounts means that checkpoint barriers are reveived at
+ The buffered data volume is ideally low - higher amounts means that checkpoint barriers are received at
very different times from the different input streams.
Note that when the here indicated numbers can be occasionally high in the presence of transient backpressure, data skew,
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/ops/upgrading.md
----------------------------------------------------------------------
diff --git a/docs/ops/upgrading.md b/docs/ops/upgrading.md
index 2a34c17..f5c8ee0 100644
--- a/docs/ops/upgrading.md
+++ b/docs/ops/upgrading.md
@@ -107,7 +107,7 @@ When upgrading an application by changing its topology, a few things need to be
* **Adding a stateful operator:** The state of the operator will be initialized with the default state unless it takes over the state of another operator.
* **Removing a stateful operator:** The state of the removed operator is lost unless another operator takes it over. When starting the upgraded application, you have to explicitly agree to discard the state.
* **Changing of input and output types of operators:** When adding a new operator before or behind an operator with internal state, you have to ensure that the input or output type of the stateful operator is not modified to preserve the data type of the internal operator state (see above for details).
-* **Changing operator chaining:** Operators can be chained together for improved performance. When restoring from a savepoint taken since 1.3.x it is possible to modify chains while preversing state consistency. It is possible a break the chain such that a stateful operator is moved out of the chain. It is also possible to append or inject a new or existing stateful operator into a chain, or to modify the operator order within a chain. However, when upgrading a savepoint to 1.3.x it is paramount that the topology did not change in regards to chaining. All operators that are part of a chain should be assigned an ID as described in the [Matching Operator State](#Matching Operator State) section above.
+* **Changing operator chaining:** Operators can be chained together for improved performance. When restoring from a savepoint taken since 1.3.x it is possible to modify chains while preserving state consistency. It is possible a break the chain such that a stateful operator is moved out of the chain. It is also possible to append or inject a new or existing stateful operator into a chain, or to modify the operator order within a chain. However, when upgrading a savepoint to 1.3.x it is paramount that the topology did not change in regards to chaining. All operators that are part of a chain should be assigned an ID as described in the [Matching Operator State](#Matching Operator State) section above.
## Upgrading the Flink Framework Version
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/docs/start/flink_on_windows.md
----------------------------------------------------------------------
diff --git a/docs/start/flink_on_windows.md b/docs/start/flink_on_windows.md
index 2cbc163..1cc45c6 100644
--- a/docs/start/flink_on_windows.md
+++ b/docs/start/flink_on_windows.md
@@ -56,7 +56,7 @@ Starting jobmanager.
## Installing Flink from Git
-If you are installing Flink from the git repository and you are using the Windows git shell, Cygwin can produce a failure similiar to this one:
+If you are installing Flink from the git repository and you are using the Windows git shell, Cygwin can produce a failure similar to this one:
~~~bash
c:/flink/bin/start-local.sh: line 30: $'\r': command not found
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-java/src/main/java/org/apache/flink/api/java/operators/UdfOperator.java
----------------------------------------------------------------------
diff --git a/flink-java/src/main/java/org/apache/flink/api/java/operators/UdfOperator.java b/flink-java/src/main/java/org/apache/flink/api/java/operators/UdfOperator.java
index 249a5cb..c74385f 100644
--- a/flink-java/src/main/java/org/apache/flink/api/java/operators/UdfOperator.java
+++ b/flink-java/src/main/java/org/apache/flink/api/java/operators/UdfOperator.java
@@ -88,7 +88,7 @@ public interface UdfOperator<O extends UdfOperator<O>> {
* <p>The runtime context itself is available in all UDFs via
* {@link org.apache.flink.api.common.functions.AbstractRichFunction#getRuntimeContext()}.
*
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
* @param name The name under which the broadcast data set retrieved.
* @return The operator itself, to allow chaining function calls.
*/
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-java/src/test/java/org/apache/flink/api/common/operators/CollectionExecutionWithBroadcastVariableTest.java
----------------------------------------------------------------------
diff --git a/flink-java/src/test/java/org/apache/flink/api/common/operators/CollectionExecutionWithBroadcastVariableTest.java b/flink-java/src/test/java/org/apache/flink/api/common/operators/CollectionExecutionWithBroadcastVariableTest.java
index 096e309..3ca32fd 100644
--- a/flink-java/src/test/java/org/apache/flink/api/common/operators/CollectionExecutionWithBroadcastVariableTest.java
+++ b/flink-java/src/test/java/org/apache/flink/api/common/operators/CollectionExecutionWithBroadcastVariableTest.java
@@ -35,7 +35,7 @@ import static org.junit.Assert.assertTrue;
import static org.junit.Assert.fail;
/**
- * Tests for {@link CollectionExecutor} with broadcasted variables.
+ * Tests for {@link CollectionExecutor} with broadcast variables.
*/
@SuppressWarnings("serial")
public class CollectionExecutionWithBroadcastVariableTest {
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/gsa/GSAConfiguration.java
----------------------------------------------------------------------
diff --git a/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/gsa/GSAConfiguration.java b/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/gsa/GSAConfiguration.java
index f09a890..36734dd 100644
--- a/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/gsa/GSAConfiguration.java
+++ b/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/gsa/GSAConfiguration.java
@@ -55,7 +55,7 @@ public class GSAConfiguration extends IterationConfiguration {
* Adds a data set as a broadcast set to the gather function.
*
* @param name The name under which the broadcast data is available in the gather function.
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
*/
public void addBroadcastSetForGatherFunction(String name, DataSet<?> data) {
this.bcVarsGather.add(new Tuple2<>(name, data));
@@ -65,7 +65,7 @@ public class GSAConfiguration extends IterationConfiguration {
* Adds a data set as a broadcast set to the sum function.
*
* @param name The name under which the broadcast data is available in the sum function.
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
*/
public void addBroadcastSetForSumFunction(String name, DataSet<?> data) {
this.bcVarsSum.add(new Tuple2<>(name, data));
@@ -75,7 +75,7 @@ public class GSAConfiguration extends IterationConfiguration {
* Adds a data set as a broadcast set to the apply function.
*
* @param name The name under which the broadcast data is available in the apply function.
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
*/
public void addBroadcastSetForApplyFunction(String name, DataSet<?> data) {
this.bcVarsApply.add(new Tuple2<>(name, data));
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/pregel/VertexCentricConfiguration.java
----------------------------------------------------------------------
diff --git a/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/pregel/VertexCentricConfiguration.java b/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/pregel/VertexCentricConfiguration.java
index 39b9bcf..3a05c44 100644
--- a/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/pregel/VertexCentricConfiguration.java
+++ b/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/pregel/VertexCentricConfiguration.java
@@ -45,7 +45,7 @@ public class VertexCentricConfiguration extends IterationConfiguration {
* Adds a data set as a broadcast set to the compute function.
*
* @param name The name under which the broadcast data set is available in the compute function.
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
*/
public void addBroadcastSet(String name, DataSet<?> data) {
this.bcVars.add(new Tuple2<>(name, data));
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/spargel/ScatterGatherConfiguration.java
----------------------------------------------------------------------
diff --git a/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/spargel/ScatterGatherConfiguration.java b/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/spargel/ScatterGatherConfiguration.java
index 0422f13..d44ff7e 100644
--- a/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/spargel/ScatterGatherConfiguration.java
+++ b/flink-libraries/flink-gelly/src/main/java/org/apache/flink/graph/spargel/ScatterGatherConfiguration.java
@@ -56,7 +56,7 @@ public class ScatterGatherConfiguration extends IterationConfiguration {
* Adds a data set as a broadcast set to the scatter function.
*
* @param name The name under which the broadcast data is available in the scatter function.
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
*/
public void addBroadcastSetForScatterFunction(String name, DataSet<?> data) {
this.bcVarsScatter.add(new Tuple2<>(name, data));
@@ -66,7 +66,7 @@ public class ScatterGatherConfiguration extends IterationConfiguration {
* Adds a data set as a broadcast set to the gather function.
*
* @param name The name under which the broadcast data is available in the gather function.
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
*/
public void addBroadcastSetForGatherFunction(String name, DataSet<?> data) {
this.bcVarsGather.add(new Tuple2<>(name, data));
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-optimizer/src/test/java/org/apache/flink/optimizer/UnionReplacementTest.java
----------------------------------------------------------------------
diff --git a/flink-optimizer/src/test/java/org/apache/flink/optimizer/UnionReplacementTest.java b/flink-optimizer/src/test/java/org/apache/flink/optimizer/UnionReplacementTest.java
index be6804b..a7576dc 100644
--- a/flink-optimizer/src/test/java/org/apache/flink/optimizer/UnionReplacementTest.java
+++ b/flink-optimizer/src/test/java/org/apache/flink/optimizer/UnionReplacementTest.java
@@ -424,12 +424,12 @@ public class UnionReplacementTest extends CompilerTestBase {
DualInputPlanNode join = resolver.getNode("join");
- // check input of join is broadcasted
+ // check input of join is broadcast
assertEquals("First join input should be fully replicated.",
PartitioningProperty.FULL_REPLICATION, join.getInput1().getGlobalProperties().getPartitioning());
NAryUnionPlanNode union = (NAryUnionPlanNode)join.getInput1().getSource();
- // check that all union inputs are broadcasted
+ // check that all union inputs are broadcast
for (Channel c : union.getInputs()) {
assertEquals("Union input should be fully replicated",
PartitioningProperty.FULL_REPLICATION, c.getGlobalProperties().getPartitioning());
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-runtime/src/main/java/org/apache/flink/runtime/broadcast/BroadcastVariableMaterialization.java
----------------------------------------------------------------------
diff --git a/flink-runtime/src/main/java/org/apache/flink/runtime/broadcast/BroadcastVariableMaterialization.java b/flink-runtime/src/main/java/org/apache/flink/runtime/broadcast/BroadcastVariableMaterialization.java
index 9c2c109..4e90f8c 100644
--- a/flink-runtime/src/main/java/org/apache/flink/runtime/broadcast/BroadcastVariableMaterialization.java
+++ b/flink-runtime/src/main/java/org/apache/flink/runtime/broadcast/BroadcastVariableMaterialization.java
@@ -40,7 +40,7 @@ import java.util.Set;
* This class represents a single materialization of a broadcast variable and maintains a reference count for it. If the
* reference count reaches zero the variable is no longer accessible and will eventually be garbage-collected.
*
- * @param <T> The type of the elements in the broadcasted data set.
+ * @param <T> The type of the elements in the broadcast data set.
*/
public class BroadcastVariableMaterialization<T, C> {
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-runtime/src/main/java/org/apache/flink/runtime/state/OperatorStateHandle.java
----------------------------------------------------------------------
diff --git a/flink-runtime/src/main/java/org/apache/flink/runtime/state/OperatorStateHandle.java b/flink-runtime/src/main/java/org/apache/flink/runtime/state/OperatorStateHandle.java
index 7c49338..a357dc4 100644
--- a/flink-runtime/src/main/java/org/apache/flink/runtime/state/OperatorStateHandle.java
+++ b/flink-runtime/src/main/java/org/apache/flink/runtime/state/OperatorStateHandle.java
@@ -37,7 +37,7 @@ public class OperatorStateHandle implements StreamStateHandle {
*/
public enum Mode {
SPLIT_DISTRIBUTE, // The operator state partitions in the state handle are split and distributed to one task each.
- BROADCAST // The operator state partitions are broadcasted to all task.
+ BROADCAST // The operator state partitions are broadcast to all task.
}
private static final long serialVersionUID = 35876522969227335L;
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-scala/src/main/scala/org/apache/flink/api/scala/DataSet.scala
----------------------------------------------------------------------
diff --git a/flink-scala/src/main/scala/org/apache/flink/api/scala/DataSet.scala b/flink-scala/src/main/scala/org/apache/flink/api/scala/DataSet.scala
index bfe7567..78bed45 100644
--- a/flink-scala/src/main/scala/org/apache/flink/api/scala/DataSet.scala
+++ b/flink-scala/src/main/scala/org/apache/flink/api/scala/DataSet.scala
@@ -268,7 +268,7 @@ class DataSet[T: ClassTag](set: JavaDataSet[T]) {
* The runtime context itself is available in all UDFs via
* `org.apache.flink.api.common.functions.AbstractRichFunction#getRuntimeContext()`
*
- * @param data The data set to be broadcasted.
+ * @param data The data set to be broadcast.
* @param name The name under which the broadcast data set retrieved.
* @return The operator itself, to allow chaining function calls.
*/
http://git-wip-us.apache.org/repos/asf/flink/blob/0deaee83/flink-streaming-java/src/main/java/org/apache/flink/streaming/api/datastream/DataStream.java
----------------------------------------------------------------------
diff --git a/flink-streaming-java/src/main/java/org/apache/flink/streaming/api/datastream/DataStream.java b/flink-streaming-java/src/main/java/org/apache/flink/streaming/api/datastream/DataStream.java
index 2274968..83c1126 100644
--- a/flink-streaming-java/src/main/java/org/apache/flink/streaming/api/datastream/DataStream.java
+++ b/flink-streaming-java/src/main/java/org/apache/flink/streaming/api/datastream/DataStream.java
@@ -363,7 +363,7 @@ public class DataStream<T> {
/**
* Sets the partitioning of the {@link DataStream} so that the output elements
- * are broadcasted to every parallel instance of the next operation.
+ * are broadcast to every parallel instance of the next operation.
*
* @return The DataStream with broadcast partitioning set.
*/