Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/19769#discussion_r155703855
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala
---
@@ -363,9 +370,25 @@ class ParquetFileFormat
fileSplit.getLocations,
null)
+ val sharedConf = broadcastedHadoopConf.value.value
+ // PARQUET_INT96_TIMESTAMP_CONVERSION says to apply timezone
conversions to int96 timestamps'
+ // *only* if the file was created by something other than
"parquet-mr", so check the actual
+ // writer here for this file. We have to do this per-file, as each
file in the table may
+ // have different writers.
+ def isCreatedByParquetMr(): Boolean = {
+ val footer = ParquetFileReader.readFooter(sharedConf,
fileSplit.getPath, SKIP_ROW_GROUPS)
+ footer.getFileMetaData().getCreatedBy().startsWith("parquet-mr")
+ }
+ val convertTz =
+ if (timestampConversion && !isCreatedByParquetMr()) {
+
Some(DateTimeUtils.getTimeZone(sharedConf.get(SQLConf.SESSION_LOCAL_TIMEZONE.key)))
+ } else {
+ None
+ }
+
val attemptId = new TaskAttemptID(new TaskID(new JobID(),
TaskType.MAP, 0), 0)
val hadoopAttemptContext =
- new TaskAttemptContextImpl(broadcastedHadoopConf.value.value,
attemptId)
+ new TaskAttemptContextImpl(broadcastedHadoopConf.value.value,
attemptId);
--- End diff --
nit: we don't need `;` at the end of this line.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
