lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

1. Small file size handling for inserts into log files. In summary, the total size of the log file is compared with the parquet max file size and if there is scope to add inserts the add it.

Browse Source
This commit is contained in:
Nishith Agarwal
2018-06-11 20:27:56 -07:00
committed by vinoth chandar
parent 324de298bc
commit 459e523d9e
21 changed files with 824 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
hoodie-spark/src/main/scala/com/uber/hoodie/IncrementalRelation.scala
View File

@@ -73,7 +73,7 @@ class IncrementalRelation(val sqlContext: SQLContext,
// use schema from a file produced in the latest instant
val latestSchema = {
val latestMeta = HoodieCommitMetadata
.fromBytes(commitTimeline.getInstantDetails(commitsToReturn.last).get)
.fromBytes(commitTimeline.getInstantDetails(commitsToReturn.last).get, classOf[HoodieCommitMetadata])
val metaFilePath = latestMeta.getFileIdAndFullPaths(basePath).values().iterator().next()
AvroConversionUtils.convertAvroSchemaToStructType(ParquetUtils.readAvroSchema(
sqlContext.sparkContext.hadoopConfiguration, new Path(metaFilePath)))
@@ -84,7 +84,8 @@ class IncrementalRelation(val sqlContext: SQLContext,
override def buildScan(): RDD[Row] = {
val fileIdToFullPath = mutable.HashMap[String, String]()
for (commit <- commitsToReturn) {
val metadata: HoodieCommitMetadata = HoodieCommitMetadata.fromBytes(commitTimeline.getInstantDetails(commit).get)
val metadata: HoodieCommitMetadata = HoodieCommitMetadata.fromBytes(commitTimeline.getInstantDetails(commit)
.get, classOf[HoodieCommitMetadata])
fileIdToFullPath ++= metadata.getFileIdAndFullPaths(basePath).toMap
}
val sOpts = optParams.filter(p => !p._1.equalsIgnoreCase("path"))