Skip to content

[SPARK-46530][PYTHON][SQL][FOLLOW-UP] Uses path separator instead of file separator to correctly check PySpark library existence #44590

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
HyukjinKwon wants to merge 1 commit into from
Closed

[SPARK-46530][PYTHON][SQL][FOLLOW-UP] Uses path separator instead of file separator to correctly check PySpark library existence #44590

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
6 changes: 4 additions & 2 deletions core/src/main/scala/org/apache/spark/api/python/PythonUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,17 +36,19 @@ private[spark] object PythonUtils extends Logging {
val PY4J_ZIP_NAME = "py4j-0.10.9.7-src.zip"

/** Get the PYTHONPATH for PySpark, either from SPARK_HOME, if it is set, or from our JAR */
def sparkPythonPath: String = {
def sparkPythonPaths: Seq[String] = {
val pythonPath = new ArrayBuffer[String]
for (sparkHome <- sys.env.get("SPARK_HOME")) {
pythonPath += Seq(sparkHome, "python", "lib", "pyspark.zip").mkString(File.separator)
pythonPath +=
Seq(sparkHome, "python", "lib", PY4J_ZIP_NAME).mkString(File.separator)
}
pythonPath ++= SparkContext.jarOfObject(this)
pythonPath.mkString(File.pathSeparator)
pythonPath.toSeq
}

def sparkPythonPath: String = sparkPythonPaths.mkString(File.pathSeparator)

/** Merge PYTHONPATHS with the appropriate separator. Ignores blank strings. */
def mergePythonPaths(paths: String*): String = {
paths.filter(_ != "").mkString(File.pathSeparator)
Expand Down
4 changes: 1 addition & 3 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceManager.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,6 @@ package org.apache.spark.sql.execution.datasources
import java.io.File
import java.util.Locale
import java.util.concurrent.ConcurrentHashMap
import java.util.regex.Pattern

import scala.jdk.CollectionConverters._

Expand Down Expand Up @@ -91,8 +90,7 @@ object DataSourceManager extends Logging {
private lazy val shouldLoadPythonDataSources: Boolean = {
Utils.checkCommandAvailable(PythonUtils.defaultPythonExec) &&
// Make sure PySpark zipped files also exist.
PythonUtils.sparkPythonPath
.split(Pattern.quote(File.separator)).forall(new File(_).exists())
PythonUtils.sparkPythonPaths.forall(new File(_).exists())
}

private def initialDataSourceBuilders: Map[String, UserDefinedPythonDataSource] = {
Expand Down