Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/12616#discussion_r62738019
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala
---
@@ -97,21 +102,30 @@ class FileStreamSource(
assert(startId <= endId)
val files = metadataLog.get(Some(startId + 1),
Some(endId)).flatMap(_._2)
logInfo(s"Processing ${files.length} files from ${startId + 1}:$endId")
- logDebug(s"Streaming ${files.mkString(", ")}")
- dataFrameBuilder(files)
+ logTrace(s"Files are:\n\t" + files.mkString("\n\t"))
+ val newOptions = options.filterKeys(_ != "path")
+ val newDataSource =
+ DataSource(
+ sparkSession,
+ paths = files,
+ userSpecifiedSchema = Some(schema),
+ className = fileFormatClassName,
+ options = new CaseInsensitiveMap(newOptions))
+ Dataset.ofRows(sparkSession,
LogicalRelation(newDataSource.resolveRelation()))
}
private def fetchAllFiles(): Seq[String] = {
- val startTime = System.nanoTime()
- val files = fs.listStatus(new Path(path))
- .filterNot(_.getPath.getName.startsWith("_"))
- .map(_.getPath.toUri.toString)
- val endTime = System.nanoTime()
- logDebug(s"Listed ${files.size} in ${(endTime.toDouble - startTime) /
1000000}ms")
+ val startTime = System.nanoTime
+ val globbedPaths =
SparkHadoopUtil.get.globPathIfNecessary(qualifiedBasePath)
+ val catalog = new ListingFileCatalog(sparkSession, globbedPaths,
options, Some(new StructType))
+ val files = catalog.allFiles().map(_.getPath.toUri.toString)
+ val endTime = System.nanoTime
+ logInfo(s"Listed ${files.size} in ${(endTime.toDouble - startTime) /
1000000}ms")
--- End diff --
Nice!
---
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
