yanghua commented on a change in pull request #2740:
URL: https://github.com/apache/hudi/pull/2740#discussion_r608299680
##########
File path: hudi-cli/src/main/scala/org/apache/hudi/cli/SparkHelpers.scala
##########
@@ -40,7 +40,7 @@ import scala.collection.mutable._
object SparkHelpers {
@throws[Exception]
def skipKeysAndWriteNewFile(instantTime: String, fs: FileSystem, sourceFile:
Path, destinationFile: Path, keysToSkip: Set[String]) {
- val sourceRecords = ParquetUtils.readAvroRecords(fs.getConf, sourceFile)
+ val sourceRecords = new ParquetUtils().readAvroRecords(fs.getConf,
sourceFile)
Review comment:
Can we use the universal method `DataFileUtils.getInstance` to get the
instance?
##########
File path: hudi-cli/src/main/scala/org/apache/hudi/cli/SparkHelpers.scala
##########
@@ -125,7 +125,7 @@ class SparkHelper(sqlContext: SQLContext, fs: FileSystem) {
* @return
*/
def fileKeysAgainstBF(conf: Configuration, sqlContext: SQLContext, file:
String): Boolean = {
- val bf = ParquetUtils.readBloomFilterFromParquetMetadata(conf, new
Path(file))
+ val bf = new ParquetUtils().readBloomFilterFromMetadata(conf, new
Path(file))
Review comment:
ditto
##########
File path: hudi-cli/src/main/scala/org/apache/hudi/cli/SparkHelpers.scala
##########
@@ -40,7 +40,7 @@ import scala.collection.mutable._
object SparkHelpers {
@throws[Exception]
def skipKeysAndWriteNewFile(instantTime: String, fs: FileSystem, sourceFile:
Path, destinationFile: Path, keysToSkip: Set[String]) {
- val sourceRecords = ParquetUtils.readAvroRecords(fs.getConf, sourceFile)
+ val sourceRecords = new ParquetUtils().readAvroRecords(fs.getConf,
sourceFile)
Review comment:
Can we use the universal method `DataFileUtils.getInstance` to get the
instance?
--
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:
[email protected]
