[GitHub] [spark] MaxGekk commented on a change in pull request #27953: [SPARK-31183][SQL] Rebase date/timestamp from/to Julian calendar in Avro

[GitBox <gi...@apache.org>]

MaxGekk commented on a change in pull request #27953: [SPARK-31183][SQL] Rebase date/timestamp from/to Julian calendar in Avro
URL: https://github.com/apache/spark/pull/27953#discussion_r395225334
 
 

 ##########
 File path: external/avro/src/test/scala/org/apache/spark/sql/avro/AvroLogicalTypeSuite.scala
 ##########
 @@ -348,6 +348,90 @@ abstract class AvroLogicalTypeSuite extends QueryTest with SharedSparkSession {
       assert(msg.contains("Unscaled value too large for precision"))
     }
   }
+
+  private def readResourceAvroFile(name: String): DataFrame = {
+    val url = Thread.currentThread().getContextClassLoader.getResource(name)
+    spark.read.format("avro").load(url.toString)
+  }
+
+  test("SPARK-31183: compatibility with Spark 2.4 in reading dates/timestamps") {
+    withSQLConf(SQLConf.LEGACY_AVRO_REBASE_DATETIME.key -> "true") {
+      checkAnswer(
+        readResourceAvroFile("before_1582_date_v2_4.avro"),
+        Row(java.sql.Date.valueOf("1001-01-01")))
+      checkAnswer(readResourceAvroFile(
+        "before_1582_ts_micros_v2_4.avro"),
+        Row(java.sql.Timestamp.valueOf("1001-01-01 01:02:03.123456")))
+    }
+  }
+
+  test("SPARK-31183: rebasing microseconds timestamps in write") {
+    val tsStr = "1001-01-01 01:02:03.123456"
+    val nonRebased = "1001-01-07 01:09:05.123456"
+    withTempPath { dir =>
+      val path = dir.getAbsolutePath
+      withSQLConf(SQLConf.LEGACY_AVRO_REBASE_DATETIME.key -> "true") {
+        Seq(tsStr).toDF("tsS")
+          .select($"tsS".cast("timestamp").as("ts"))
+          .write.format("avro")
+          .save(path)
+
+        checkAnswer(spark.read.format("avro").load(path), Row(Timestamp.valueOf(tsStr)))
+      }
+      withSQLConf(SQLConf.LEGACY_AVRO_REBASE_DATETIME.key -> "false") {
+        checkAnswer(spark.read.format("avro").load(path), Row(Timestamp.valueOf(nonRebased)))
+      }
+    }
+  }
+
+  test("SPARK-31183: rebasing milliseconds timestamps in write") {
+    val tsStr = "1001-01-01 01:02:03.123456"
+    val rebased = "1001-01-01 01:02:03.123"
+    val nonRebased = "1001-01-07 01:09:05.123"
+    val timestampSchema = """
 
 Review comment:
   done

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org