This is an automated email from the ASF dual-hosted git repository. voonhous pushed a commit to branch release-1.2.1 in repository https://gitbox.apache.org/repos/asf/hudi.git
commit 9023d94478d5c68cf8269e08fc07bc3f9a22b425 Author: Xinli Shang <[email protected]> AuthorDate: Sun May 17 20:15:40 2026 -0700 [MINOR] Fix typos in comments and assertion messages (#18763) Corrects a handful of long-standing typos in code comments and test assertion messages across the codebase. No functional changes. - atleast -> at least (8 occurrences) - commited -> committed (1 occurrence in comment) - existance -> existence (1 occurrence in exception message) - transfering -> transferring (2 occurrences) - succesfully -> successfully (1 occurrence in comment) Co-authored-by: Xinli Shang <[email protected]> (cherry picked from commit cd2c8b831c8b7c8f46b1f175bdb323329f60c8ab) --- .../main/java/org/apache/hudi/client/utils/LazyIterableIterator.java | 2 +- .../org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java | 2 +- .../test/java/org/apache/hudi/client/TestCoalescingPartitioner.java | 2 +- .../src/test/java/org/apache/hudi/table/TestHoodieSparkTable.java | 2 +- .../java/org/apache/hudi/table/action/compact/CompactionTestBase.java | 4 ++-- .../testsuite/generator/GenericRecordPartialPayloadGenerator.java | 2 +- .../org/apache/hudi/integ/testsuite/TestFileDeltaInputWriter.java | 2 +- .../datasources/parquet/Spark41LegacyHoodieParquetFileFormat.scala | 2 +- .../sql/execution/datasources/parquet/Spark41ParquetReader.scala | 2 +- .../deltastreamer/TestHoodieDeltaStreamerWithMultiWriter.java | 2 +- scripts/pr_compliance.py | 2 +- 11 files changed, 12 insertions(+), 12 deletions(-) diff --git a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/client/utils/LazyIterableIterator.java b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/client/utils/LazyIterableIterator.java index b921c6ddfc81..64a92ee1ae8c 100644 --- a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/client/utils/LazyIterableIterator.java +++ b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/client/utils/LazyIterableIterator.java @@ -28,7 +28,7 @@ import java.util.Iterator; * Provide a way to obtain a inputItr of type O (output), out of an inputItr of type I (input) * <p> * Things to remember: - Assumes Spark calls hasNext() to check for elements, before calling next() to obtain them - - * Assumes hasNext() gets called atleast once. - Concrete Implementation is responsible for calling inputIterator.next() + * Assumes hasNext() gets called at least once. - Concrete Implementation is responsible for calling inputIterator.next() * and doing the processing in computeNext() */ public abstract class LazyIterableIterator<I, O> implements Iterable<O>, Iterator<O> { diff --git a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java index db30f301d97a..5d09762909be 100644 --- a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java +++ b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java @@ -2026,7 +2026,7 @@ public abstract class HoodieBackedTableMetadataWriter<I, O> implements HoodieTab // scheduling of INDEX only initializes the file group and not add commit // so if there are no committed file slices, look for inflight slices if (isNonGlobalRLI) { - // For isNonGlobalRLI, new partitions added to the data table will cause new filegroups that are not yet commited + // For isNonGlobalRLI, new partitions added to the data table will cause new filegroups that are not yet committed // therefore, we always need to look for inflight filegroups fileSlices = getPartitionLatestFileSlicesIncludingInflight(metadataMetaClient, Option.ofNullable(fsView), partitionPath); } else if (fileSlices.isEmpty()) { diff --git a/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/client/TestCoalescingPartitioner.java b/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/client/TestCoalescingPartitioner.java index 0f3b972574ce..9f99742e0c0e 100644 --- a/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/client/TestCoalescingPartitioner.java +++ b/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/client/TestCoalescingPartitioner.java @@ -123,7 +123,7 @@ public class TestCoalescingPartitioner extends HoodieClientTestBase { }, true).collect(); assertEquals(targetPartitions, countsPerPartition.size()); - // lets validate that atleast we have 50% of data in each spark partition compared to ideal scenario (we can't assume hash of strings will evenly distribute). + // lets validate that at least we have 50% of data in each spark partition compared to ideal scenario (we can't assume hash of strings will evenly distribute). countsPerPartition.forEach(pair -> { int numElements = pair.getValue(); int idealExpectedCount = inputNumPartitions / targetPartitions; diff --git a/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/TestHoodieSparkTable.java b/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/TestHoodieSparkTable.java index e50bb9e5ecb7..9808de708374 100644 --- a/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/TestHoodieSparkTable.java +++ b/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/TestHoodieSparkTable.java @@ -107,7 +107,7 @@ public class TestHoodieSparkTable extends HoodieCommonTestHarness { // lets create the data file. so that we can validate later. localStorage.create(storagePath); } catch (IOException e) { - throw new HoodieException("Failed to check data file existance " + fileName); + throw new HoodieException("Failed to check data file existence " + fileName); } }); HoodieTable hoodieTable = HoodieSparkTable.create(writeConfig, getEngineContext(), metaClient); diff --git a/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/action/compact/CompactionTestBase.java b/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/action/compact/CompactionTestBase.java index ae6b60ccf679..677ece46d801 100644 --- a/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/action/compact/CompactionTestBase.java +++ b/hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/action/compact/CompactionTestBase.java @@ -104,7 +104,7 @@ public class CompactionTestBase extends HoodieClientTestBase { if (opPair != null) { assertEquals(fileSlice.getBaseInstantTime(), opPair.getKey(), "Expect baseInstant to match compaction Instant"); assertTrue(fileSlice.getLogFiles().count() > 0, - "Expect atleast one log file to be present where the latest delta commit was written"); + "Expect at least one log file to be present where the latest delta commit was written"); assertFalse(fileSlice.getBaseFile().isPresent(), "Expect no data-file to be present"); } else { assertTrue(fileSlice.getBaseInstantTime().compareTo(latestDeltaCommit) <= 0, @@ -210,7 +210,7 @@ public class CompactionTestBase extends HoodieClientTestBase { if (hasDeltaCommitAfterPendingCompaction) { assertFalse(fileSliceList.stream().anyMatch(fs -> fs.getLogFiles().count() == 0), - "Verify all file-slices have atleast one log-file"); + "Verify all file-slices have at least one log-file"); } else { assertFalse(fileSliceList.stream().anyMatch(fs -> fs.getLogFiles().count() > 0), "Verify all file-slices have no log-files"); diff --git a/hudi-integ-test/src/main/java/org/apache/hudi/integ/testsuite/generator/GenericRecordPartialPayloadGenerator.java b/hudi-integ-test/src/main/java/org/apache/hudi/integ/testsuite/generator/GenericRecordPartialPayloadGenerator.java index 999f83de66c0..b42ad4396c1b 100644 --- a/hudi-integ-test/src/main/java/org/apache/hudi/integ/testsuite/generator/GenericRecordPartialPayloadGenerator.java +++ b/hudi-integ-test/src/main/java/org/apache/hudi/integ/testsuite/generator/GenericRecordPartialPayloadGenerator.java @@ -63,7 +63,7 @@ public class GenericRecordPartialPayloadGenerator extends GenericRecordFullPaylo return validate((Object) record); } - // Atleast 1 entry should be null + // At least 1 entry should be null private boolean validate(Object object) { if (object == null) { return true; diff --git a/hudi-integ-test/src/test/java/org/apache/hudi/integ/testsuite/TestFileDeltaInputWriter.java b/hudi-integ-test/src/test/java/org/apache/hudi/integ/testsuite/TestFileDeltaInputWriter.java index a33ee7c5fb4f..ad6ae1767383 100644 --- a/hudi-integ-test/src/test/java/org/apache/hudi/integ/testsuite/TestFileDeltaInputWriter.java +++ b/hudi-integ-test/src/test/java/org/apache/hudi/integ/testsuite/TestFileDeltaInputWriter.java @@ -98,7 +98,7 @@ public class TestFileDeltaInputWriter extends UtilitiesTestBase { DeltaWriteStats deltaWriteStats = fileSinkWriter.getDeltaWriteStats(); FileSystem fs = HadoopFSUtils.getFs(basePath, jsc.hadoopConfiguration()); FileStatus[] fileStatuses = fs.listStatus(new Path(deltaWriteStats.getFilePath())); - // Atleast 1 file was written + // At least 1 file was written assertEquals(1, fileStatuses.length); // File length should be greater than 0 assertTrue(fileStatuses[0].getLen() > 0); diff --git a/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41LegacyHoodieParquetFileFormat.scala b/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41LegacyHoodieParquetFileFormat.scala index 8dff79c1e07b..91b085b693aa 100644 --- a/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41LegacyHoodieParquetFileFormat.scala +++ b/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41LegacyHoodieParquetFileFormat.scala @@ -187,7 +187,7 @@ class Spark41LegacyHoodieParquetFileFormat(private val shouldAppendPartitionValu } // When there are vectorized reads, we can avoid - // 1. opening the file twice by transfering the SeekableInputStream + // 1. opening the file twice by transferring the SeekableInputStream // 2. reading the footer twice by reading all row groups in advance and filter row groups // according to filters that require push down val openedFooter = ParquetFooterReader.openFileAndReadFooter(sharedConf, file, enableVectorizedReader) diff --git a/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41ParquetReader.scala b/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41ParquetReader.scala index f5ccd7b54176..d15520106e23 100644 --- a/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41ParquetReader.scala +++ b/hudi-spark-datasource/hudi-spark4.1.x/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/Spark41ParquetReader.scala @@ -108,7 +108,7 @@ class Spark41ParquetReader(enableVectorizedReader: Boolean, partitionSchema, internalSchemaOpt) // When there are vectorized reads, we can avoid - // 1. opening the file twice by transfering the SeekableInputStream + // 1. opening the file twice by transferring the SeekableInputStream // 2. reading the footer twice by reading all row groups in advance and filter row groups // according to filters that require push down val originalFooter = diff --git a/hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestHoodieDeltaStreamerWithMultiWriter.java b/hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestHoodieDeltaStreamerWithMultiWriter.java index fbd8726242a6..5e09ac923794 100644 --- a/hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestHoodieDeltaStreamerWithMultiWriter.java +++ b/hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestHoodieDeltaStreamerWithMultiWriter.java @@ -419,7 +419,7 @@ public class TestHoodieDeltaStreamerWithMultiWriter extends HoodieDeltaStreamerT }); Future backfillJobFuture = service.submit(() -> { try { - // trigger backfill atleast after 1 requested entry is added to timeline from continuous job. If not, there is a chance that backfill will complete even before + // trigger backfill at least after 1 requested entry is added to timeline from continuous job. If not, there is a chance that backfill will complete even before // continuous job starts. awaitCondition(new GetCommitsAfterInstant(tableBasePath, lastSuccessfulCommit)); backfillJob.sync(); diff --git a/scripts/pr_compliance.py b/scripts/pr_compliance.py index aafeb9c2a0d0..5bf1a23b69e1 100644 --- a/scripts/pr_compliance.py +++ b/scripts/pr_compliance.py @@ -46,7 +46,7 @@ class Outcomes: #parsing the next section NEXTSECTION = 2 - #parsing has concluded succesfully, exit with no error + #parsing has concluded successfully, exit with no error SUCCESS = 3
