This is an automated email from the ASF dual-hosted git repository.
yhu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/beam.git
The following commit(s) were added to refs/heads/master by this push:
new 783584d0773 Fix typo tranform; workaround non-ascii char (#25428)
783584d0773 is described below
commit 783584d0773d3a5ba532aca1dbc6f87ff4945786
Author: Yi Hu <[email protected]>
AuthorDate: Fri Feb 10 19:06:49 2023 -0500
Fix typo tranform; workaround non-ascii char (#25428)
---
.../apache/beam/runners/dataflow/BatchStatefulParDoOverrides.java | 2 +-
.../runners/dataflow/options/DataflowPipelineDebugOptions.java | 4 ++--
.../org/apache/beam/runners/samza/SamzaExecutionEnvironment.java | 2 +-
sdks/go/examples/pingpong/pingpong.go | 2 +-
.../main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryIO.java | 2 +-
.../java/org/apache/beam/sdk/io/gcp/datastore/DatastoreV1.java | 8 ++++----
.../kafka/src/main/java/org/apache/beam/sdk/io/kafka/KafkaIO.java | 2 +-
.../src/main/java/org/apache/beam/sdk/io/kinesis/KinesisIO.java | 2 +-
.../main/java/org/apache/beam/sdk/tpcds/SqlTransformRunner.java | 2 +-
sdks/python/apache_beam/io/gcp/bigquery_file_loads.py | 2 +-
sdks/python/apache_beam/ml/gcp/recommendations_ai.py | 2 +-
sdks/python/apache_beam/runners/interactive/cache_manager.py | 2 +-
.../python/apache_beam/runners/interactive/pipeline_instrument.py | 2 +-
.../apache_beam/testing/benchmarks/chicago_taxi/trainer/model.py | 2 +-
.../apache_beam/testing/benchmarks/cloudml/criteo_tft/criteo.py | 2 +-
15 files changed, 19 insertions(+), 19 deletions(-)
diff --git
a/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/BatchStatefulParDoOverrides.java
b/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/BatchStatefulParDoOverrides.java
index 229fdf65b68..1b0008a6963 100644
---
a/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/BatchStatefulParDoOverrides.java
+++
b/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/BatchStatefulParDoOverrides.java
@@ -58,7 +58,7 @@ import org.joda.time.Instant;
* grouping and expansion.
*
* <p>This implementation relies on implementation details of the Dataflow
runner, specifically
- * standard fusion behavior of {@link ParDo} tranforms following a {@link
GroupByKey}.
+ * standard fusion behavior of {@link ParDo} transforms following a {@link
GroupByKey}.
*/
public class BatchStatefulParDoOverrides {
diff --git
a/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/options/DataflowPipelineDebugOptions.java
b/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/options/DataflowPipelineDebugOptions.java
index 208de034a50..fb373d9aaf4 100644
---
a/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/options/DataflowPipelineDebugOptions.java
+++
b/runners/google-cloud-dataflow-java/src/main/java/org/apache/beam/runners/dataflow/options/DataflowPipelineDebugOptions.java
@@ -136,12 +136,12 @@ public interface DataflowPipelineDebugOptions extends
ExperimentalOptions, Pipel
}
/**
- * Mapping of old PTranform names to new ones, specified as JSON
<code>{"oldName":"newName",...}
+ * Mapping of old PTransform names to new ones, specified as JSON
<code>{"oldName":"newName",...}
* </code>. To mark a transform as deleted, make newName the empty string.
*/
@JsonIgnore
@Description(
- "Mapping of old PTranform names to new ones, specified as JSON "
+ "Mapping of old PTransform names to new ones, specified as JSON "
+ "{\"oldName\":\"newName\",...}. To mark a transform as deleted,
make newName the empty "
+ "string.")
Map<String, String> getTransformNameMapping();
diff --git
a/runners/samza/src/main/java/org/apache/beam/runners/samza/SamzaExecutionEnvironment.java
b/runners/samza/src/main/java/org/apache/beam/runners/samza/SamzaExecutionEnvironment.java
index 47d78e3d162..02c31edfd1d 100644
---
a/runners/samza/src/main/java/org/apache/beam/runners/samza/SamzaExecutionEnvironment.java
+++
b/runners/samza/src/main/java/org/apache/beam/runners/samza/SamzaExecutionEnvironment.java
@@ -35,7 +35,7 @@ public enum SamzaExecutionEnvironment {
/**
* Runs Samza job as a stand alone embedded library mode which can be
imported into your Java
- * application. You can increase your application’s capacity by spinning up
multiple instances.
+ * application. You can increase your application's capacity by spinning up
multiple instances.
* These instances will then dynamically coordinate with each other and
distribute work among
* themselves. If an instance fails, the tasks running on it will be
re-assigned to the remaining
* ones. By default, Samza uses Zookeeper for coordination across individual
instances.
diff --git a/sdks/go/examples/pingpong/pingpong.go
b/sdks/go/examples/pingpong/pingpong.go
index 99286495c3f..6ea649272d2 100644
--- a/sdks/go/examples/pingpong/pingpong.go
+++ b/sdks/go/examples/pingpong/pingpong.go
@@ -44,7 +44,7 @@ func init() {
register.Iter1[string]()
}
-// stitch constructs two composite PTranformations that provide input to each
other. It
+// stitch constructs two composite PTransforms that provide input to each
other. It
// is a (deliberately) complex DAG to show what kind of structures are
possible.
func stitch(s beam.Scope, words beam.PCollection) (beam.PCollection,
beam.PCollection) {
ping := s.Scope("ping")
diff --git
a/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryIO.java
b/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryIO.java
index e871d156b09..478404de759 100644
---
a/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryIO.java
+++
b/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryIO.java
@@ -990,7 +990,7 @@ public class BigQueryIO {
* Specifies that a query should be run with a BATCH priority.
*
* <p>Batch mode queries are queued by BigQuery. These are started as
soon as idle resources
- * are available, usually within a few minutes. Batch queries don’t
count towards your
+ * are available, usually within a few minutes. Batch queries don't
count towards your
* concurrent rate limit.
*/
BATCH
diff --git
a/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/datastore/DatastoreV1.java
b/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/datastore/DatastoreV1.java
index a8870e4d612..d876d00a500 100644
---
a/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/datastore/DatastoreV1.java
+++
b/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/datastore/DatastoreV1.java
@@ -1304,10 +1304,10 @@ public class DatastoreV1 {
/**
* A {@link PTransform} that writes mutations to Cloud Datastore.
*
- * <p>It requires a {@link DoFn} that tranforms an object of type {@code T}
to a {@link Mutation}.
- * {@code T} is usually either an {@link Entity} or a {@link Key}
<b>Note:</b> Only idempotent
- * Cloud Datastore mutation operations (upsert and delete) should be used by
the {@code DoFn}
- * provided, as the commits are retried when failures occur.
+ * <p>It requires a {@link DoFn} that transforms an object of type {@code T}
to a {@link
+ * Mutation}. {@code T} is usually either an {@link Entity} or a {@link Key}
<b>Note:</b> Only
+ * idempotent Cloud Datastore mutation operations (upsert and delete) should
be used by the {@code
+ * DoFn} provided, as the commits are retried when failures occur.
*/
private abstract static class Mutate<T> extends PTransform<PCollection<T>,
PDone> {
diff --git
a/sdks/java/io/kafka/src/main/java/org/apache/beam/sdk/io/kafka/KafkaIO.java
b/sdks/java/io/kafka/src/main/java/org/apache/beam/sdk/io/kafka/KafkaIO.java
index e5c40ddf4d1..26c895ddc89 100644
--- a/sdks/java/io/kafka/src/main/java/org/apache/beam/sdk/io/kafka/KafkaIO.java
+++ b/sdks/java/io/kafka/src/main/java/org/apache/beam/sdk/io/kafka/KafkaIO.java
@@ -229,7 +229,7 @@ import org.slf4j.LoggerFactory;
* TopicPartition} has been stopped/removed, so it stops reading from it
and returns {@code
* ProcessContinuation.stop()}.
* <li>At 10:45 the pipeline author wants to read from TopicPartition A
again.
- * <li>At 11:00AM when {@link WatchForKafkaTopicPartitions} is invoked by
firing timer, it doesn’t
+ * <li>At 11:00AM when {@link WatchForKafkaTopicPartitions} is invoked by
firing timer, it doesn't
* know that TopicPartition A has been stopped/removed. All it knows is
that TopicPartition A
* is still an active TopicPartition and it will not emit TopicPartition
A again.
* </ul>
diff --git
a/sdks/java/io/kinesis/src/main/java/org/apache/beam/sdk/io/kinesis/KinesisIO.java
b/sdks/java/io/kinesis/src/main/java/org/apache/beam/sdk/io/kinesis/KinesisIO.java
index 637bd84b7a6..4cf8f9f4e31 100644
---
a/sdks/java/io/kinesis/src/main/java/org/apache/beam/sdk/io/kinesis/KinesisIO.java
+++
b/sdks/java/io/kinesis/src/main/java/org/apache/beam/sdk/io/kinesis/KinesisIO.java
@@ -134,7 +134,7 @@ import org.slf4j.LoggerFactory;
* .apply( ... ) // other transformations
* }</pre>
*
- * <p>There’s also possibility to start reading using arbitrary point in time
- in this case you
+ * <p>There's also possibility to start reading using arbitrary point in time
- in this case you
* need to provide {@link Instant} object:
*
* <pre>{@code
diff --git
a/sdks/java/testing/tpcds/src/main/java/org/apache/beam/sdk/tpcds/SqlTransformRunner.java
b/sdks/java/testing/tpcds/src/main/java/org/apache/beam/sdk/tpcds/SqlTransformRunner.java
index cd337e87d87..f8287fc3c99 100644
---
a/sdks/java/testing/tpcds/src/main/java/org/apache/beam/sdk/tpcds/SqlTransformRunner.java
+++
b/sdks/java/testing/tpcds/src/main/java/org/apache/beam/sdk/tpcds/SqlTransformRunner.java
@@ -262,7 +262,7 @@ public class SqlTransformRunner {
}
/**
- * This is the default method in BeamTpcds.main method. Run job using
SqlTranform.query() method.
+ * This is the default method in BeamTpcds.main method. Run job using
SqlTransform.query() method.
*
* @param args Command line arguments
* @throws Exception
diff --git a/sdks/python/apache_beam/io/gcp/bigquery_file_loads.py
b/sdks/python/apache_beam/io/gcp/bigquery_file_loads.py
index 0e06dc94c9a..72421bd0e11 100644
--- a/sdks/python/apache_beam/io/gcp/bigquery_file_loads.py
+++ b/sdks/python/apache_beam/io/gcp/bigquery_file_loads.py
@@ -333,7 +333,7 @@ class UpdateDestinationSchema(beam.DoFn):
regardless of whether data is loaded directly to the destination table or
loaded into temporary tables before being copied into the destination.
- This tranform takes as input a (destination, job_reference) pair where the
+ This transform takes as input a (destination, job_reference) pair where the
job_reference refers to a completed load job into a temporary table.
This transform emits (destination, job_reference) pairs where the
diff --git a/sdks/python/apache_beam/ml/gcp/recommendations_ai.py
b/sdks/python/apache_beam/ml/gcp/recommendations_ai.py
index b6eb4cfb4bc..696ea5e322e 100644
--- a/sdks/python/apache_beam/ml/gcp/recommendations_ai.py
+++ b/sdks/python/apache_beam/ml/gcp/recommendations_ai.py
@@ -78,7 +78,7 @@ def get_recommendation_user_event_client():
class CreateCatalogItem(PTransform):
"""Creates catalogitem information.
- The ``PTranform`` returns a PCollectionTuple with a PCollections of
+ The ``PTransform`` returns a PCollectionTuple with a PCollections of
successfully and failed created CatalogItems.
Example usage::
diff --git a/sdks/python/apache_beam/runners/interactive/cache_manager.py
b/sdks/python/apache_beam/runners/interactive/cache_manager.py
index 1960733ba38..b04eb92132a 100644
--- a/sdks/python/apache_beam/runners/interactive/cache_manager.py
+++ b/sdks/python/apache_beam/runners/interactive/cache_manager.py
@@ -236,7 +236,7 @@ class FileBasedCacheManager(CacheManager):
return reader, version
def write(self, values, *labels):
- """Imitates how a WriteCache tranform works without running a pipeline.
+ """Imitates how a WriteCache transform works without running a pipeline.
For testing and cache manager development, not for production usage because
the write is not sharded and does not use Beam execution model.
diff --git a/sdks/python/apache_beam/runners/interactive/pipeline_instrument.py
b/sdks/python/apache_beam/runners/interactive/pipeline_instrument.py
index 540d54d1c39..8e5d50ed3f3 100644
--- a/sdks/python/apache_beam/runners/interactive/pipeline_instrument.py
+++ b/sdks/python/apache_beam/runners/interactive/pipeline_instrument.py
@@ -300,7 +300,7 @@ class PipelineInstrument(object):
v in transforms.items() if v.unique_name in required_transform_labels
]
- # The required transforms are the tranforms that we want to cut out of
+ # The required transforms are the transforms that we want to cut out of
# the pipeline_proto and insert into a new pipeline to return.
required_transform_ids = (
roots + caching_transform_ids + unbounded_source_ids)
diff --git
a/sdks/python/apache_beam/testing/benchmarks/chicago_taxi/trainer/model.py
b/sdks/python/apache_beam/testing/benchmarks/chicago_taxi/trainer/model.py
index 8297863d567..3d112bea0a8 100644
--- a/sdks/python/apache_beam/testing/benchmarks/chicago_taxi/trainer/model.py
+++ b/sdks/python/apache_beam/testing/benchmarks/chicago_taxi/trainer/model.py
@@ -99,7 +99,7 @@ def eval_input_receiver_fn(tf_transform_output, schema):
Returns:
EvalInputReceiver function, which contains:
- - Tensorflow graph which parses raw untranformed features, applies the
+ - Tensorflow graph which parses raw untransformed features, applies the
tf-transform preprocessing operators.
- Set of raw, untransformed features.
- Label against which predictions will be compared.
diff --git
a/sdks/python/apache_beam/testing/benchmarks/cloudml/criteo_tft/criteo.py
b/sdks/python/apache_beam/testing/benchmarks/cloudml/criteo_tft/criteo.py
index cd14bd9e659..d2a0b652ca6 100644
--- a/sdks/python/apache_beam/testing/benchmarks/cloudml/criteo_tft/criteo.py
+++ b/sdks/python/apache_beam/testing/benchmarks/cloudml/criteo_tft/criteo.py
@@ -15,7 +15,7 @@
# limitations under the License.
#
-"""Schema and tranform definition for the Criteo dataset."""
+"""Schema and transform definition for the Criteo dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
