From 819788f865160ab6445b8ad8c707631a82577c13 Mon Sep 17 00:00:00 2001 From: studystill <137779852+studystill@users.noreply.github.com> Date: Mon, 11 Mar 2024 08:34:32 +0800 Subject: [PATCH] [MINOR] Remove repetitive words in docs (#10844) Signed-off-by: studystill --- .../scala/org/apache/spark/sql/HoodieCatalystPlansUtils.scala | 2 +- .../java/org/apache/hudi/common/bloom/InternalBloomFilter.java | 2 +- .../main/java/org/apache/hudi/sink/bulk/sort/SortOperator.java | 2 +- .../src/main/scala/org/apache/hudi/HoodieFileIndex.scala | 2 +- rfc/rfc-76/rfc-76.md | 2 +- scripts/pr_compliance.py | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystPlansUtils.scala b/hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystPlansUtils.scala index b9110f1ed93b..40e62ddd0efc 100644 --- a/hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystPlansUtils.scala +++ b/hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/HoodieCatalystPlansUtils.scala @@ -144,7 +144,7 @@ trait HoodieCatalystPlansUtils { def createMITJoin(left: LogicalPlan, right: LogicalPlan, joinType: JoinType, condition: Option[Expression], hint: String): LogicalPlan /** - * true if both plans produce the same attributes in the the same order + * true if both plans produce the same attributes in the same order */ def produceSameOutput(a: LogicalPlan, b: LogicalPlan): Boolean } diff --git a/hudi-common/src/main/java/org/apache/hudi/common/bloom/InternalBloomFilter.java b/hudi-common/src/main/java/org/apache/hudi/common/bloom/InternalBloomFilter.java index ac93de2d58fb..7ef766a2a3c5 100644 --- a/hudi-common/src/main/java/org/apache/hudi/common/bloom/InternalBloomFilter.java +++ b/hudi-common/src/main/java/org/apache/hudi/common/bloom/InternalBloomFilter.java @@ -199,7 +199,7 @@ public String toString() { } /** - * @return size of the the bloomfilter + * @return size of the bloomfilter */ public int getVectorSize() { return this.vectorSize; diff --git a/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/bulk/sort/SortOperator.java b/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/bulk/sort/SortOperator.java index e91535a24736..357bc07160d3 100644 --- a/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/bulk/sort/SortOperator.java +++ b/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/bulk/sort/SortOperator.java @@ -100,7 +100,7 @@ public void open() throws Exception { collector = new StreamRecordCollector<>(output); - // register the the metrics. + // register the metrics. getMetricGroup().gauge("memoryUsedSizeInBytes", (Gauge) sorter::getUsedMemoryInBytes); getMetricGroup().gauge("numSpillFiles", (Gauge) sorter::getNumSpillFiles); getMetricGroup().gauge("spillInBytes", (Gauge) sorter::getSpillInBytes); diff --git a/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala b/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala index 3444feaecff6..affed871cad9 100644 --- a/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala +++ b/hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala @@ -63,7 +63,7 @@ import scala.util.{Failure, Success, Try} * who's directory level is 3).We can still read it as a partitioned table. We will mapping the * partition path (e.g. 2021/03/10) to the only partition column (e.g. "dt"). * - * 3、Else the the partition columns size is not equal to the partition directory level and the + * 3、Else the partition columns size is not equal to the partition directory level and the * size is great than "1" (e.g. partition column is "dt,hh", the partition path is "2021/03/10/12") * , we read it as a Non-Partitioned table because we cannot know how to mapping the partition * path with the partition columns in this case. diff --git a/rfc/rfc-76/rfc-76.md b/rfc/rfc-76/rfc-76.md index 1ddc107b5ce7..e9f176f1d5f7 100644 --- a/rfc/rfc-76/rfc-76.md +++ b/rfc/rfc-76/rfc-76.md @@ -61,7 +61,7 @@ Let's consider following scenario: while persisting the dataset, writing one of To provide for aforementioned requirement of the records obtaining globally unique synthetic keys either of the 2 following properties have to hold true: Key generation has to be deterministic and reproducible (so that upon Spark retries we could be certain same records will be obtaining the identity value they did during previous pass) Records have to be getting globally unique identity value every time (such that key collisions are simply impossible) -Note that, deterministic and reproducible identity value association is is only feasible for the incoming datasets represented as "determinate" RDDs. However, It's worth pointing out that other RDD classes (such as "unordered", "indeterminate") are very rare occurrences involving some inherent non-determinism (varying content, order, etc), and pose challenges in terms of their respective handling by Hudi even w/o auto-generation (for ex, for such RDDs Hudi can't provide for uniqueness guarantee even for "insert" operation in the presence of failures). +Note that, deterministic and reproducible identity value association is only feasible for the incoming datasets represented as "determinate" RDDs. However, It's worth pointing out that other RDD classes (such as "unordered", "indeterminate") are very rare occurrences involving some inherent non-determinism (varying content, order, etc), and pose challenges in terms of their respective handling by Hudi even w/o auto-generation (for ex, for such RDDs Hudi can't provide for uniqueness guarantee even for "insert" operation in the presence of failures). For achieving our goal of providing globally unique keys we're planning on relying on the following synthetic key format comprised of 2 components (Reserved) Commit timestamp: Use reserved commit timestamp as prefix (to provide for global uniqueness of rows) Row id: unique identifier of the row (record) w/in the provided batch diff --git a/scripts/pr_compliance.py b/scripts/pr_compliance.py index b9a7aaffe574..dcd3c4c0caf4 100644 --- a/scripts/pr_compliance.py +++ b/scripts/pr_compliance.py @@ -108,7 +108,7 @@ def test_title(): # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # -#Enums for the the outcome of parsing a single line +#Enums for the outcome of parsing a single line class Outcomes: #error was found so we should stop parsing and exit with error ERROR = 0