[SPARK-28912][STREAMING] Fixed MatchError in getCheckpointFiles()

### What changes were proposed in this pull request?

This change fixes issue SPARK-28912.

### Why are the changes needed?

If checkpoint directory is set to name which matches regex pattern used for checkpoint files then logs are flooded with MatchError exceptions and old checkpoint files are not removed.

### Does this PR introduce any user-facing change?

No.

### How was this patch tested?

Manually.

1. Start Hadoop in a pseudo-distributed mode.

2. In another terminal run command  nc -lk 9999

3. In the Spark shell execute the following statements:

    ```scala
    val ssc = new StreamingContext(sc, Seconds(30))
    ssc.checkpoint("hdfs://localhost:9000/checkpoint-01")
    val lines = ssc.socketTextStream("localhost", 9999)
    val words = lines.flatMap(_.split(" "))
    val pairs = words.map(word => (word, 1))
    val wordCounts = pairs.reduceByKey(_ + _)
    wordCounts.print()
    ssc.start()
    ssc.awaitTermination()
    ```

Closes #25654 from avkgh/SPARK-28912.

Authored-by: avk <nullp7r@gmail.com>
Signed-off-by: Dongjoon Hyun <dhyun@apple.com>

Author: avkgh

streaming/src/main/scala/org/apache/spark/streaming/Checkpoint.scala

@@ -131,8 +131,8 @@ object Checkpoint extends Logging {
     try {
       val statuses = fs.listStatus(path)
       if (statuses != null) {
-        val paths = statuses.map(_.getPath)
-        val filtered = paths.filter(p => REGEX.findFirstIn(p.toString).nonEmpty)
+        val paths = statuses.filterNot(_.isDirectory).map(_.getPath)
+        val filtered = paths.filter(p => REGEX.findFirstIn(p.getName).nonEmpty)
         filtered.sortWith(sortFunc)
       } else {
         logWarning(s"Listing $path returned null")

streaming/src/test/scala/org/apache/spark/streaming/CheckpointSuite.scala

@@ -847,6 +847,23 @@ class CheckpointSuite extends TestSuiteBase with DStreamCheckpointTester
     checkpointWriter.stop()
   }
 
+  test("SPARK-28912: Fix MatchError in getCheckpointFiles") {
+    withTempDir { tempDir =>
+      val fs = FileSystem.get(tempDir.toURI, new Configuration)
+      val checkpointDir = tempDir.getAbsolutePath + "/checkpoint-01"
+
+      assert(Checkpoint.getCheckpointFiles(checkpointDir, Some(fs)).length === 0)
+
+      // Ignore files whose parent path match.
+      fs.create(new Path(checkpointDir, "this-is-matched-before-due-to-parent-path")).close()
+      assert(Checkpoint.getCheckpointFiles(checkpointDir, Some(fs)).length === 0)
+
+      // Ignore directories whose names match.
+      fs.mkdirs(new Path(checkpointDir, "checkpoint-1000000000"))
+      assert(Checkpoint.getCheckpointFiles(checkpointDir, Some(fs)).length === 0)
+    }
+  }
+
   test("SPARK-6847: stack overflow when updateStateByKey is followed by a checkpointed dstream") {
     // In this test, there are two updateStateByKey operators. The RDD DAG is as follows:
     //