Github user windpiger commented on a diff in the pull request:
https://github.com/apache/spark/pull/17176#discussion_r104400143
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala ---
@@ -159,36 +159,37 @@ class HadoopTableReader(
def verifyPartitionPath(
partitionToDeserializer: Map[HivePartition, Class[_ <:
Deserializer]]):
Map[HivePartition, Class[_ <: Deserializer]] = {
- if (!sparkSession.sessionState.conf.verifyPartitionPath) {
- partitionToDeserializer
- } else {
- var existPathSet = collection.mutable.Set[String]()
- var pathPatternSet = collection.mutable.Set[String]()
- partitionToDeserializer.filter {
- case (partition, partDeserializer) =>
- def updateExistPathSetByPathPattern(pathPatternStr: String) {
- val pathPattern = new Path(pathPatternStr)
- val fs = pathPattern.getFileSystem(hadoopConf)
- val matches = fs.globStatus(pathPattern)
- matches.foreach(fileStatus => existPathSet +=
fileStatus.getPath.toString)
- }
- // convert /demo/data/year/month/day to /demo/data/*/*/*/
- def getPathPatternByPath(parNum: Int, tempPath: Path): String
= {
+ var existPathSet = collection.mutable.Set[String]()
+ var pathPatternSet = collection.mutable.Set[String]()
+ partitionToDeserializer.filter {
+ case (partition, partDeserializer) =>
+ def updateExistPathSetByPathPattern(pathPatternStr: String) {
+ val pathPattern = new Path(pathPatternStr)
+ val fs = pathPattern.getFileSystem(hadoopConf)
+ val matches = fs.globStatus(pathPattern)
+ matches.foreach(fileStatus => existPathSet +=
fileStatus.getPath.toString)
+ }
+ // convert /demo/data/year/month/day to /demo/data/*/*/*/
+ def getPathPatternByPath(parNum: Int, tempPath: Path,
partitionName: String): String = {
+ // if the partition path does not end with partition name, we
should not
--- End diff --
if the partition location has been altered to another location, we should
not do this pattern, or we will list pattern files which does not belong to the
partition
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
