viirya commented on code in PR #43283:
URL: https://github.com/apache/spark/pull/43283#discussion_r1350544362


##########
core/src/test/scala/org/apache/spark/util/HadoopFSUtilsSuite.scala:
##########
@@ -30,4 +30,36 @@ class HadoopFSUtilsSuite extends SparkFunSuite {
     assert(HadoopFSUtils.shouldFilterOutPathName("_cd_common_metadata"))
     assert(HadoopFSUtils.shouldFilterOutPathName("a._COPYING_"))
   }
+
+  test("SPARK-45452: HadoopFSUtils - path filtering") {
+    // Case 1: Regular and metadata paths
+    assert(!HadoopFSUtils.shouldFilterOutPath("/abcd"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/abcd/efg"))
+    
assert(!HadoopFSUtils.shouldFilterOutPath("/year=2023/month=10/day=8/hour=13"))
+    
assert(!HadoopFSUtils.shouldFilterOutPath("/part=__HIVE_DEFAULT_PARTITION__"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/_cd=123"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/_cd=123/1"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/_metadata"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/_metadata/1"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/_common_metadata"))
+    assert(!HadoopFSUtils.shouldFilterOutPath("/_common_metadata/1"))
+    // Case 2: Hidden paths and the paths ending `._COPYING_`
+    assert(HadoopFSUtils.shouldFilterOutPath("/.ab"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/.ab/cde"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/.ab/_metadata/1"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/ab/.cde"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/ab/.cde/fg"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/ab/.cde/_metadata"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/ab/.cde/_common_metadata"))
+    
assert(HadoopFSUtils.shouldFilterOutPath("/ab/.cde/year=2023/month=10/day=8/hour=13"))
+    
assert(HadoopFSUtils.shouldFilterOutPath("/x/.hidden/part=__HIVE_DEFAULT_PARTITION__"))
+    assert(HadoopFSUtils.shouldFilterOutPath("/a._COPYING_"))
+    // Case 3: Understored paths (except metadata paths of Case 1)

Review Comment:
   Understored? Underscored?



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to