Skip to content

[SPARK-52339][SQL][3.5] Fix comparison of InMemoryFileIndex instances #51256

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
bersprockets wants to merge 1 commit into from
+25 −1
Closed

[SPARK-52339][SQL][3.5] Fix comparison of InMemoryFileIndex instances #51256

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
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/InMemoryFileIndex.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,7 @@ class InMemoryFileIndex(
}

override def equals(other: Any): Boolean = other match {
case hdfs: InMemoryFileIndex => rootPaths.toSet == hdfs.rootPaths.toSet
case hdfs: InMemoryFileIndex => rootPaths.sorted == hdfs.rootPaths.sorted
case _ => false
}

Expand Down
24 changes: 24 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileIndexSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -554,6 +554,30 @@ class FileIndexSuite extends SharedSparkSession {
assert(FileIndexOptions.isValidOption("modifiedafter"))
assert(FileIndexOptions.isValidOption("pathglobfilter"))
}

test("SPARK-52339: Correctly compare root paths") {
withTempDir { dir =>
val file1 = new File(dir, "text1.txt")
stringToFile(file1, "text1")
val file2 = new File(dir, "text2.txt")
stringToFile(file2, "text2")
val path1 = new Path(file1.getCanonicalPath)
val path2 = new Path(file2.getCanonicalPath)

val schema = StructType(Seq(StructField("a", StringType, false)))

// Verify that the order of paths doesn't matter
val fileIndex1a = new InMemoryFileIndex(spark, Seq(path1, path2), Map.empty, Some(schema))
val fileIndex1b = new InMemoryFileIndex(spark, Seq(path2, path1), Map.empty, Some(schema))
assert(fileIndex1a == fileIndex1b)

// Verify that a different number of paths does matter
val fileIndex2a = new InMemoryFileIndex(spark, Seq(path1, path1), Map.empty, Some(schema))
val fileIndex2b = new InMemoryFileIndex(spark, Seq(path1, path1, path1),
Map.empty, Some(schema))
assert(fileIndex2a != fileIndex2b)
}
}
}

object DeletionRaceFileSystem {
Expand Down