Skip to content

[SPARK-21374][CORE] Fix reading globbed paths from S3 into DF with disabled FS cache #18623

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
andrey-tpt wants to merge 1 commit into from
Closed

[SPARK-21374][CORE] Fix reading globbed paths from S3 into DF with disabled FS cache #18623

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions core/src/main/scala/org/apache/spark/deploy/SparkHadoopUtil.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,14 +226,22 @@ class SparkHadoopUtil extends Logging {
}

def globPath(pattern: Path): Seq[Path] = {
val fs = pattern.getFileSystem(conf)
globPath(pattern, conf)
}

def globPath(pattern: Path, hadoopConf: Configuration): Seq[Path] = {
val fs = pattern.getFileSystem(hadoopConf)
Option(fs.globStatus(pattern)).map { statuses =>
statuses.map(_.getPath.makeQualified(fs.getUri, fs.getWorkingDirectory)).toSeq
}.getOrElse(Seq.empty[Path])
}

def globPathIfNecessary(pattern: Path): Seq[Path] = {
if (isGlobPath(pattern)) globPath(pattern) else Seq(pattern)
globPathIfNecessary(pattern, conf)
}

def globPathIfNecessary(pattern: Path, hadoopConf: Configuration): Seq[Path] = {
if (isGlobPath(pattern)) globPath(pattern, hadoopConf) else Seq(pattern)
}

/**
Expand Down
4 changes: 2 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,7 +132,7 @@ case class DataSource(
val hdfsPath = new Path(path)
val fs = hdfsPath.getFileSystem(hadoopConf)
val qualified = hdfsPath.makeQualified(fs.getUri, fs.getWorkingDirectory)
SparkHadoopUtil.get.globPathIfNecessary(qualified)
SparkHadoopUtil.get.globPathIfNecessary(qualified, hadoopConf)
Copy link
Member

@zsxwing zsxwing Aug 3, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you pass FileSystem into globPathIfNecessary?

}.toArray
new InMemoryFileIndex(sparkSession, globbedPaths, options, None, fileStatusCache)
}
Expand Down Expand Up @@ -364,7 +364,7 @@ case class DataSource(
val hdfsPath = new Path(path)
val fs = hdfsPath.getFileSystem(hadoopConf)
val qualified = hdfsPath.makeQualified(fs.getUri, fs.getWorkingDirectory)
val globPath = SparkHadoopUtil.get.globPathIfNecessary(qualified)
val globPath = SparkHadoopUtil.get.globPathIfNecessary(qualified, hadoopConf)

if (globPath.isEmpty) {
throw new AnalysisException(s"Path does not exist: $qualified")
Expand Down