diff --git a/docs/docs/cdc-ingestion/kafka-cdc.mdx b/docs/docs/cdc-ingestion/kafka-cdc.mdx index ba59d36d8206..c13411510202 100644 --- a/docs/docs/cdc-ingestion/kafka-cdc.mdx +++ b/docs/docs/cdc-ingestion/kafka-cdc.mdx @@ -233,7 +233,7 @@ To use this feature through `flink run`, run the following shell command. This action will build a single combined sink for all tables. For each Kafka topic's table to be synchronized, if the corresponding Paimon table does not exist, this action will automatically create the table, and its schema will be derived from all specified Kafka topic's tables. If the Paimon table already exists and its schema is different from that parsed -from Kafka record, this action will try to preform schema evolution. +from Kafka record, this action will try to perform schema evolution. Example diff --git a/docs/docs/cdc-ingestion/pulsar-cdc.md b/docs/docs/cdc-ingestion/pulsar-cdc.md index 048be02d3aaf..9e26f74f6bf4 100644 --- a/docs/docs/cdc-ingestion/pulsar-cdc.md +++ b/docs/docs/cdc-ingestion/pulsar-cdc.md @@ -228,7 +228,7 @@ Only tables with primary keys will be synchronized. This action will build a single combined sink for all tables. For each Pulsar topic's table to be synchronized, if the corresponding Paimon table does not exist, this action will automatically create the table, and its schema will be derived from all specified Pulsar topic's tables. If the Paimon table already exists and its schema is different from that parsed -from Pulsar record, this action will try to preform schema evolution. +from Pulsar record, this action will try to perform schema evolution. Example @@ -312,7 +312,7 @@ There are some useful options to build Flink Pulsar Source, but they are not pro pulsar.startCursor.fromMessageId EARLIEST - Sting + String Using a unique identifier of a single message to seek the start position. The common format is a triple '<long>ledgerId,<long>entryId,<int>partitionIndex'. Specially, you can set it to EARLIEST (-1, -1, -1) or LATEST (Long.MAX_VALUE, Long.MAX_VALUE, -1). diff --git a/docs/docs/iceberg/rest-catalog.mdx b/docs/docs/iceberg/rest-catalog.mdx index 547d97926347..457b138385e6 100644 --- a/docs/docs/iceberg/rest-catalog.mdx +++ b/docs/docs/iceberg/rest-catalog.mdx @@ -110,7 +110,7 @@ the query results: */ ``` -**Schema compatabilty and Partition evolution:** +**Schema compatibility and Partition evolution:** There is a fundamental difference between Paimon and Iceberg regarding the starting fieldId. Paimon uses fieldId 0, while Iceberg uses fieldId 1. If we create an Iceberg table using a Paimon schema directly, it will shift all fieldIds by +1, causing field disorder. However, it is possible to update the schema after table creation and start the schema from fieldId 0. diff --git a/docs/docs/primary-key-table/pk-clustering-override.md b/docs/docs/primary-key-table/pk-clustering-override.md index e638778a3e42..da46ed79a752 100644 --- a/docs/docs/primary-key-table/pk-clustering-override.md +++ b/docs/docs/primary-key-table/pk-clustering-override.md @@ -97,4 +97,4 @@ values, so queries like `WHERE id = 12345` remain efficient. - Merge engine: `partial-update` or `aggregation`. - Changelog producer: `lookup` or `full-compaction`. -- Configue: `sequence.fields` or `record-level.expire-time`. +- Configure: `sequence.fields` or `record-level.expire-time`. diff --git a/docs/generated/core_configuration.html b/docs/generated/core_configuration.html index 1a66fb0ab0b8..5e3404b9b6bb 100644 --- a/docs/generated/core_configuration.html +++ b/docs/generated/core_configuration.html @@ -1107,7 +1107,7 @@
partition.legacy-name
true Boolean - The legacy partition name is using `toString` fpr all types. If false, using cast to string for all types. + The legacy partition name is using `toString` for all types. If false, using cast to string for all types.
partition.mark-done-action
diff --git a/paimon-api/src/main/java/org/apache/paimon/CoreOptions.java b/paimon-api/src/main/java/org/apache/paimon/CoreOptions.java index da734fa9386f..0195fbdd4436 100644 --- a/paimon-api/src/main/java/org/apache/paimon/CoreOptions.java +++ b/paimon-api/src/main/java/org/apache/paimon/CoreOptions.java @@ -544,7 +544,7 @@ public InlineElement getDescription() { .booleanType() .defaultValue(true) .withDescription( - "The legacy partition name is using `toString` fpr all types. If false, using " + "The legacy partition name is using `toString` for all types. If false, using " + "cast to string for all types."); public static final ConfigOption SNAPSHOT_NUM_RETAINED_MIN = diff --git a/paimon-api/src/main/java/org/apache/paimon/types/DataTypeCasts.java b/paimon-api/src/main/java/org/apache/paimon/types/DataTypeCasts.java index 454c1c65d744..a49e7e4ff6f6 100644 --- a/paimon-api/src/main/java/org/apache/paimon/types/DataTypeCasts.java +++ b/paimon-api/src/main/java/org/apache/paimon/types/DataTypeCasts.java @@ -179,9 +179,9 @@ public final class DataTypeCasts { /** * allowExplicit false : Returns whether the source type can be safely cast to the target type - * without loosing information. Implicit casts are used for type widening and type - * generalization (finding a common supertype for a set of types). Implicit casts are similar to - * the Java semantics (e.g. this is not possible: {@code int x = (String) z}). + * without losing information. Implicit casts are used for type widening and type generalization + * (finding a common supertype for a set of types). Implicit casts are similar to the Java + * semantics (e.g. this is not possible: {@code int x = (String) z}). * *

allowExplicit true : Returns whether the source type can be cast to the target type. * Explicit casts correspond to the SQL cast specification and represent the logic behind a diff --git a/paimon-core/src/main/java/org/apache/paimon/operation/ChangelogDeletion.java b/paimon-core/src/main/java/org/apache/paimon/operation/ChangelogDeletion.java index 450f7fcb690f..5a5f04fedc5d 100644 --- a/paimon-core/src/main/java/org/apache/paimon/operation/ChangelogDeletion.java +++ b/paimon-core/src/main/java/org/apache/paimon/operation/ChangelogDeletion.java @@ -85,7 +85,7 @@ public void cleanUnusedManifests(Changelog changelog, Set skippingSet) { } } - // the index and statics manifest list should handle by snapshot deletion. + // the index and statistics manifest list should handle by snapshot deletion. } @Override diff --git a/paimon-core/src/main/java/org/apache/paimon/schema/SchemaManager.java b/paimon-core/src/main/java/org/apache/paimon/schema/SchemaManager.java index 95c6f04514db..905f30704864 100644 --- a/paimon-core/src/main/java/org/apache/paimon/schema/SchemaManager.java +++ b/paimon-core/src/main/java/org/apache/paimon/schema/SchemaManager.java @@ -510,7 +510,7 @@ protected void updateLastColumn( && CastExecutors.resolve(sourceRootType, targetRootType) != null, String.format( - "Column type %s[%s] cannot be converted to %s without loosing information.", + "Column type %s[%s] cannot be converted to %s without losing information.", field.name(), sourceRootType, targetRootType)); return new DataField( field.id(), diff --git a/paimon-core/src/main/java/org/apache/paimon/utils/SnapshotManager.java b/paimon-core/src/main/java/org/apache/paimon/utils/SnapshotManager.java index b6a818604ee5..fcc936460ddd 100644 --- a/paimon-core/src/main/java/org/apache/paimon/utils/SnapshotManager.java +++ b/paimon-core/src/main/java/org/apache/paimon/utils/SnapshotManager.java @@ -319,7 +319,7 @@ public boolean earliestFileNotExists() { } /** - * Returns a {@link Snapshot} whoes commit time is later than or equal to given timestamp mills. + * Returns a {@link Snapshot} whose commit time is later than or equal to given timestamp mills. * If there is no such a snapshot, returns null. */ public @Nullable Snapshot laterOrEqualTimeMills(long timestampMills) { diff --git a/paimon-core/src/test/java/org/apache/paimon/catalog/CatalogTestBase.java b/paimon-core/src/test/java/org/apache/paimon/catalog/CatalogTestBase.java index 07539d914f4b..9087eee6c7fd 100644 --- a/paimon-core/src/test/java/org/apache/paimon/catalog/CatalogTestBase.java +++ b/paimon-core/src/test/java/org/apache/paimon/catalog/CatalogTestBase.java @@ -2136,7 +2136,7 @@ private void baseAlterTable(Map initOptions) throws Exception { .satisfies( anyCauseMatches( IllegalStateException.class, - "Column type col1[DOUBLE] cannot be converted to DATE without loosing information.")); + "Column type col1[DOUBLE] cannot be converted to DATE without losing information.")); // Alter table update a column type throws ColumnNotExistException when column does not // exist diff --git a/paimon-core/src/test/java/org/apache/paimon/table/SchemaEvolutionTest.java b/paimon-core/src/test/java/org/apache/paimon/table/SchemaEvolutionTest.java index 01570b422ff0..9cfab9aa825b 100644 --- a/paimon-core/src/test/java/org/apache/paimon/table/SchemaEvolutionTest.java +++ b/paimon-core/src/test/java/org/apache/paimon/table/SchemaEvolutionTest.java @@ -563,7 +563,7 @@ public void testUpdateFieldType() throws Exception { "f0", DataTypes.STRING())))) .isInstanceOf(IllegalStateException.class) .hasMessage( - "Column type f0[BIGINT] cannot be converted to STRING without loosing information."); + "Column type f0[BIGINT] cannot be converted to STRING without losing information."); schemaManager.commitChanges( Collections.singletonList( SchemaChange.setOption("disable-explicit-type-casting", "false"))); diff --git a/paimon-flink/paimon-flink-cdc/src/test/java/org/apache/paimon/flink/action/cdc/kafka/KafkaSyncTableActionITCase.java b/paimon-flink/paimon-flink-cdc/src/test/java/org/apache/paimon/flink/action/cdc/kafka/KafkaSyncTableActionITCase.java index 596c6d2cc61d..9ea19fb5c356 100644 --- a/paimon-flink/paimon-flink-cdc/src/test/java/org/apache/paimon/flink/action/cdc/kafka/KafkaSyncTableActionITCase.java +++ b/paimon-flink/paimon-flink-cdc/src/test/java/org/apache/paimon/flink/action/cdc/kafka/KafkaSyncTableActionITCase.java @@ -234,7 +234,7 @@ protected void runSingleTableSchemaEvolutionWithSchemaIncludeRecord( "+I[105, hammer, 14oz carpenter's hammer, 0.875, 24]"); waitForResult(expected, table, rowType, primaryKeys); - // column type covert exception (int64 -> string) + // column type convert exception (int64 -> string) writeRecordsToKafka( topic, "kafka/%s/table/schema/%s/%s-data-5.txt", format, sourceDir, format); diff --git a/paimon-flink/paimon-flink-common/src/test/java/org/apache/paimon/flink/SchemaChangeITCase.java b/paimon-flink/paimon-flink-common/src/test/java/org/apache/paimon/flink/SchemaChangeITCase.java index 8e6ae0b123ea..43d817477f63 100644 --- a/paimon-flink/paimon-flink-common/src/test/java/org/apache/paimon/flink/SchemaChangeITCase.java +++ b/paimon-flink/paimon-flink-common/src/test/java/org/apache/paimon/flink/SchemaChangeITCase.java @@ -273,7 +273,7 @@ public void testModifyColumnTypeBooleanAndNumeric() { assertThatThrownBy(() -> sql("ALTER TABLE T MODIFY (f BOOLEAN)")) .hasRootCauseInstanceOf(IllegalStateException.class) .hasRootCauseMessage( - "Column type f[DOUBLE] cannot be converted to BOOLEAN without loosing information."); + "Column type f[DOUBLE] cannot be converted to BOOLEAN without losing information."); } @Test @@ -1605,13 +1605,13 @@ public void testDisableExplicitTypeCasting(String formatType) { assertThat(sql("SELECT * FROM T")).containsExactlyInAnyOrder(Row.of(1, 10), Row.of(2, 20)); assertThatCode(() -> sql("ALTER TABLE T MODIFY v SMALLINT")) .hasStackTraceContaining( - "Column type v[INT] cannot be converted to SMALLINT without loosing information"); + "Column type v[INT] cannot be converted to SMALLINT without losing information"); sql("ALTER TABLE T MODIFY v BIGINT"); assertThat(sql("SELECT * FROM T")) .containsExactlyInAnyOrder(Row.of(1, 10L), Row.of(2, 20L)); assertThatCode(() -> sql("ALTER TABLE T MODIFY v INT")) .hasStackTraceContaining( - "Column type v[BIGINT] cannot be converted to INT without loosing information"); + "Column type v[BIGINT] cannot be converted to INT without losing information"); // disable explicit type casting sql("ALTER TABLE T SET ('disable-explicit-type-casting' = 'false')"); sql("ALTER TABLE T MODIFY v INT"); diff --git a/paimon-hive/paimon-hive-connector-common/src/test/java/org/apache/paimon/iceberg/IcebergHiveMetadataCommitterITCaseBase.java b/paimon-hive/paimon-hive-connector-common/src/test/java/org/apache/paimon/iceberg/IcebergHiveMetadataCommitterITCaseBase.java index 765018109b2e..44d8c3a9a6b1 100644 --- a/paimon-hive/paimon-hive-connector-common/src/test/java/org/apache/paimon/iceberg/IcebergHiveMetadataCommitterITCaseBase.java +++ b/paimon-hive/paimon-hive-connector-common/src/test/java/org/apache/paimon/iceberg/IcebergHiveMetadataCommitterITCaseBase.java @@ -123,7 +123,7 @@ public void testPrimaryKeyTable() throws Exception { .toString() .contains("iceberg/test_db")); - // specify a dedicated hive database and table for paimon iceberg commiter + // specify a dedicated hive database and table for paimon iceberg committer tEnv.executeSql( "CREATE TABLE my_paimon.test_db.t1 ( pt INT, id INT, data STRING, PRIMARY KEY (pt, id) NOT ENFORCED ) " + "PARTITIONED BY (pt) WITH " @@ -216,7 +216,7 @@ public void testAppendOnlyTable() throws Exception { tEnv.executeSql( "SELECT data, id, pt FROM my_iceberg.test_db.t WHERE id > 1 ORDER BY pt, id"))); - // specify a dedicated hive database and table for paimon iceberg commiter + // specify a dedicated hive database and table for paimon iceberg committer tEnv.executeSql( "CREATE TABLE my_paimon.test_db.t1 ( pt INT, id INT, data STRING ) PARTITIONED BY (pt) WITH " + "( 'metadata.iceberg.storage' = 'hive-catalog', 'metadata.iceberg.uri' = '', 'file.format' = 'avro', " diff --git a/paimon-spark/paimon-spark-common/src/main/scala/org/apache/paimon/spark/commands/PaimonSparkWriter.scala b/paimon-spark/paimon-spark-common/src/main/scala/org/apache/paimon/spark/commands/PaimonSparkWriter.scala index b63de8511722..8e310dc9e092 100644 --- a/paimon-spark/paimon-spark-common/src/main/scala/org/apache/paimon/spark/commands/PaimonSparkWriter.scala +++ b/paimon-spark/paimon-spark-common/src/main/scala/org/apache/paimon/spark/commands/PaimonSparkWriter.scala @@ -434,7 +434,7 @@ case class PaimonSparkWriter( postCommit(commitMessages) } - /** Boostrap and repartition for cross partition mode. */ + /** Bootstrap and repartition for cross partition mode. */ private def bootstrapAndRepartitionByKeyHash( data: DataFrame, parallelism: Int, diff --git a/paimon-spark/paimon-spark-common/src/main/scala/org/apache/spark/sql/catalyst/parser/extensions/RewritePaimonFunctionCommands.scala b/paimon-spark/paimon-spark-common/src/main/scala/org/apache/spark/sql/catalyst/parser/extensions/RewritePaimonFunctionCommands.scala index 4fac049a5a51..0f9722a63311 100644 --- a/paimon-spark/paimon-spark-common/src/main/scala/org/apache/spark/sql/catalyst/parser/extensions/RewritePaimonFunctionCommands.scala +++ b/paimon-spark/paimon-spark-common/src/main/scala/org/apache/spark/sql/catalyst/parser/extensions/RewritePaimonFunctionCommands.scala @@ -68,7 +68,7 @@ case class RewritePaimonFunctionCommands(spark: SparkSession) ifExists, replace) => if (isPaimonBuildInFunction(funcIdent)) { - throw new UnsupportedOperationException(s"Can't create build-in function: $funcIdent") + throw new UnsupportedOperationException(s"Can't create built-in function: $funcIdent") } val v1Function = CatalogFunction(funcIdent, className, resources) CreatePaimonV1FunctionCommand(v1FunctionCatalog, v1Function, ifExists, replace) @@ -77,7 +77,7 @@ case class RewritePaimonFunctionCommands(spark: SparkSession) CatalogAndFunctionIdentifier(v1FunctionCatalog: SupportV1Function, funcIdent, false), ifExists) => if (isPaimonBuildInFunction(funcIdent)) { - throw new UnsupportedOperationException(s"Can't drop build-in function: $funcIdent") + throw new UnsupportedOperationException(s"Can't drop built-in function: $funcIdent") } // The function may be v1 function or not, anyway it can be safely deleted here. DropPaimonV1FunctionCommand(v1FunctionCatalog, funcIdent, ifExists) diff --git a/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/PaimonV1FunctionTestBase.scala b/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/PaimonV1FunctionTestBase.scala index 09aa98d93afa..88449fad5e19 100644 --- a/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/PaimonV1FunctionTestBase.scala +++ b/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/PaimonV1FunctionTestBase.scala @@ -95,7 +95,7 @@ abstract class PaimonV1FunctionTestBase extends PaimonSparkTestWithRestCatalogBa } } - test("Paimon V1 Function: select with build-in function") { + test("Paimon V1 Function: select with built-in function") { withUserDefinedFunction("udf_add2" -> false) { sql(s""" |CREATE FUNCTION udf_add2 AS '$UDFExampleAdd2Class' @@ -144,18 +144,18 @@ abstract class PaimonV1FunctionTestBase extends PaimonSparkTestWithRestCatalogBa } test("Paimon V1 Function: unsupported operation") { - // create a build-in function + // create a built-in function assert(intercept[Exception] { sql(s""" |CREATE FUNCTION sys.max_pt AS '$UDFExampleAdd2Class' |USING JAR '$testUDFJarPath' |""".stripMargin) - }.getMessage.contains("Can't create build-in function")) + }.getMessage.contains("Can't create built-in function")) - // drop a build-in function + // drop a built-in function assert(intercept[Exception] { sql("DROP FUNCTION sys.max_pt") - }.getMessage.contains("Can't drop build-in function")) + }.getMessage.contains("Can't drop built-in function")) } test("Paimon V1 Function: user defined aggregate function") {