[SPARK-24773] Avro: support logical timestamp type with different precisions #21935
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -36,11 +36,12 @@ import org.apache.spark.sql._ | |
| import org.apache.spark.sql.execution.datasources.DataSource | ||
| import org.apache.spark.sql.internal.SQLConf | ||
| import org.apache.spark.sql.test.{SharedSQLContext, SQLTestUtils} | ||
| import org.apache.spark.sql.types.{StructType, _} | ||
|
|
||
|
|
||
| class AvroSuite extends QueryTest with SharedSQLContext with SQLTestUtils { | ||
| val episodesAvro = testFile("episodes.avro") | ||
| val testAvro = testFile("test.avro") | ||
| val timestampAvro = testFile("timestamp.avro") | ||
|
Contributor
There was a problem hiding this comment. at least we should provide how the binary file is generated, or just do roundtrip test: Spark write avro files and then read it.
Member
Author
There was a problem hiding this comment. The schema and data is stated in https://github.com/apache/spark/pull/21935/files#diff-9364b0610f92b3cc35a4bc43a80751bfR397 |
||
|
|
||
| override protected def beforeAll(): Unit = { | ||
| super.beforeAll() | ||
|
|
@@ -331,6 +332,82 @@ class AvroSuite extends QueryTest with SharedSQLContext with SQLTestUtils { | |
| } | ||
| } | ||
|
|
||
| test("Logical type: timestamp_millis") { | ||
| val sparkSession = spark | ||
| import sparkSession.implicits._ | ||
|
|
||
| val expected = | ||
| Seq(1L, 666L).toDF("timestamp_millis").select('timestamp_millis.cast(TimestampType)).collect() | ||
| val df = spark.read.format("avro").load(timestampAvro).select('timestamp_millis) | ||
|
|
||
| checkAnswer(df, expected) | ||
|
|
||
| withTempPath { dir => | ||
| df.write.format("avro").save(dir.toString) | ||
| checkAnswer(spark.read.format("avro").load(dir.toString), expected) | ||
| } | ||
| } | ||
|
|
||
| test("Logical type: timestamp_micros") { | ||
| val sparkSession = spark | ||
| import sparkSession.implicits._ | ||
|
|
||
| val expected = | ||
| Seq(2L, 999L).toDF("timestamp_micros").select('timestamp_micros.cast(TimestampType)).collect() | ||
| val df = spark.read.format("avro").load(timestampAvro).select('timestamp_micros) | ||
|
|
||
| checkAnswer(df, expected) | ||
|
|
||
| withTempPath { dir => | ||
| df.write.format("avro").save(dir.toString) | ||
| checkAnswer(spark.read.format("avro").load(dir.toString), expected) | ||
| } | ||
| } | ||
|
|
||
| test("Logical type: specify different output timestamp types") { | ||
| val sparkSession = spark | ||
| import sparkSession.implicits._ | ||
|
|
||
| val df = spark.read.format("avro").load(timestampAvro) | ||
|
|
||
| val expected = Seq((1L, 2L), (666L, 999L)) | ||
| .toDF("timestamp_millis", "timestamp_micros") | ||
| .select('timestamp_millis.cast(TimestampType), 'timestamp_micros.cast(TimestampType)) | ||
| .collect() | ||
|
|
||
| Seq("TIMESTAMP_MILLIS", "TIMESTAMP_MICROS").foreach { timestampType => | ||
| withTempPath { dir => | ||
| df.write.format("avro").option("outputTimestampType", timestampType).save(dir.toString) | ||
| checkAnswer(spark.read.format("avro").load(dir.toString), expected) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| test("Logical type: user specified schema") { | ||
| val sparkSession = spark | ||
| import sparkSession.implicits._ | ||
|
|
||
| val expected = Seq((1L, 2L), (666L, 999L)) | ||
| .toDF("timestamp_millis", "timestamp_micros") | ||
| .select('timestamp_millis.cast(TimestampType), 'timestamp_micros.cast(TimestampType)) | ||
| .collect() | ||
|
|
||
| val avroSchema = s""" | ||
| { | ||
| "namespace": "logical", | ||
| "type": "record", | ||
| "name": "test", | ||
| "fields": [ | ||
| {"name": "timestamp_millis", "type": {"type": "long","logicalType": "timestamp-millis"}}, | ||
| {"name": "timestamp_micros", "type": {"type": "long","logicalType": "timestamp-micros"}} | ||
| ] | ||
| } | ||
| """ | ||
| val df = spark.read.format("avro").option("avroSchema", avroSchema).load(timestampAvro) | ||
|
|
||
| checkAnswer(df, expected) | ||
| } | ||
|
|
||
| test("Array data types") { | ||
| withTempPath { dir => | ||
| val testSchema = StructType(Seq( | ||
|
|
@@ -511,7 +588,8 @@ class AvroSuite extends QueryTest with SharedSQLContext with SQLTestUtils { | |
|
|
||
| // TimesStamps are converted to longs | ||
| val times = spark.read.format("avro").load(avroDir).select("Time").collect() | ||
| assert(times.map(_(0)).toSet == | ||
| Set(new Timestamp(666), new Timestamp(777), new Timestamp(42))) | ||
|
|
||
| // DecimalType should be converted to string | ||
| val decimals = spark.read.format("avro").load(avroDir).select("Decimal").collect() | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's add a comment to say it's for backward compatibility reasons. Also we should only do it when logical type is null. For other logical types, we should fail here.