[beam] branch release-2.19.0 updated: [BEAM-9123] HadoopResourceId returns wrong directoryName bugfix

[bo...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

boyuanz pushed a commit to branch release-2.19.0
in repository https://gitbox.apache.org/repos/asf/beam.git


The following commit(s) were added to refs/heads/release-2.19.0 by this push:
     new 5ab8ead  [BEAM-9123] HadoopResourceId returns wrong directoryName bugfix
     new 526158c  Merge pull request #10626 from dmvk/BEAM-9123-backport-2.19
5ab8ead is described below

commit 5ab8ead726dea577205056cc03a417c3753a65f2
Author: marek.simunek <ma...@firma.seznam.cz>
AuthorDate: Wed Jan 15 16:42:18 2020 +0100

    [BEAM-9123] HadoopResourceId returns wrong directoryName bugfix
---
 .../org/apache/beam/sdk/io/hdfs/HadoopResourceId.java     |  4 ++++
 .../org/apache/beam/sdk/io/hdfs/HadoopResourceIdTest.java | 15 +++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/sdks/java/io/hadoop-file-system/src/main/java/org/apache/beam/sdk/io/hdfs/HadoopResourceId.java b/sdks/java/io/hadoop-file-system/src/main/java/org/apache/beam/sdk/io/hdfs/HadoopResourceId.java
index 4e5f6e2..b68839b 100644
--- a/sdks/java/io/hadoop-file-system/src/main/java/org/apache/beam/sdk/io/hdfs/HadoopResourceId.java
+++ b/sdks/java/io/hadoop-file-system/src/main/java/org/apache/beam/sdk/io/hdfs/HadoopResourceId.java
@@ -65,6 +65,10 @@ class HadoopResourceId implements ResourceId {
 
   @Override
   public String getFilename() {
+    if (isDirectory()) {
+      Path parentPath = new Path(uri).getParent();
+      return parentPath == null ? null : parentPath.getName();
+    }
     return new Path(uri).getName();
   }
 
diff --git a/sdks/java/io/hadoop-file-system/src/test/java/org/apache/beam/sdk/io/hdfs/HadoopResourceIdTest.java b/sdks/java/io/hadoop-file-system/src/test/java/org/apache/beam/sdk/io/hdfs/HadoopResourceIdTest.java
index 4d7fb8d..1726a3e 100644
--- a/sdks/java/io/hadoop-file-system/src/test/java/org/apache/beam/sdk/io/hdfs/HadoopResourceIdTest.java
+++ b/sdks/java/io/hadoop-file-system/src/test/java/org/apache/beam/sdk/io/hdfs/HadoopResourceIdTest.java
@@ -17,6 +17,9 @@
  */
 package org.apache.beam.sdk.io.hdfs;
 
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertNull;
+
 import java.net.URI;
 import java.util.Collections;
 import org.apache.beam.sdk.io.FileSystems;
@@ -65,4 +68,16 @@ public class HadoopResourceIdTest {
             "hdfs://" + hdfsClusterBaseUri.getPath(), true /* isDirectory */);
     ResourceIdTester.runResourceIdBattery(baseDirectory);
   }
+
+  @Test
+  public void testGetFilename() {
+    assertNull(toResourceIdentifier("").getFilename());
+    assertEquals("abc", toResourceIdentifier("/dirA/abc").getFilename());
+    assertEquals("abc", toResourceIdentifier("/dirA/abc/").getFilename());
+    assertEquals("xyz.txt", toResourceIdentifier("/dirA/abc/xyz.txt").getFilename());
+  }
+
+  private ResourceId toResourceIdentifier(String path) {
+    return new HadoopResourceId(hdfsClusterBaseUri.resolve(path));
+  }
 }