You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by sr...@apache.org on 2016/11/18 21:45:29 UTC
spark git commit: [SPARK-18422][CORE] Fix wholeTextFiles test to pass
on Windows in JavaAPISuite
Repository: spark
Updated Branches:
refs/heads/master 795e9fc92 -> 40d59ff5e
[SPARK-18422][CORE] Fix wholeTextFiles test to pass on Windows in JavaAPISuite
## What changes were proposed in this pull request?
This PR fixes the test `wholeTextFiles` in `JavaAPISuite.java`. This is failed due to the different path format on Windows.
For example, the path in `container` was
```
C:\projects\spark\target\tmp\1478967560189-0/part-00000
```
whereas `new URI(res._1()).getPath()` was as below:
```
/C:/projects/spark/target/tmp/1478967560189-0/part-00000
```
## How was this patch tested?
Tests in `JavaAPISuite.java`.
Tested via AppVeyor.
**Before**
Build: https://ci.appveyor.com/project/spark-test/spark/build/63-JavaAPISuite-1
Diff: https://github.com/apache/spark/compare/master...spark-test:JavaAPISuite-1
```
[info] Test org.apache.spark.JavaAPISuite.wholeTextFiles started
[error] Test org.apache.spark.JavaAPISuite.wholeTextFiles failed: java.lang.AssertionError: expected:<spark is easy to use.
[error] > but was:<null>, took 0.578 sec
[error] at org.apache.spark.JavaAPISuite.wholeTextFiles(JavaAPISuite.java:1089)
...
```
**After**
Build started: [CORE] `org.apache.spark.JavaAPISuite` [![PR-15866](https://ci.appveyor.com/api/projects/status/github/spark-test/spark?branch=198DDA52-F201-4D2B-BE2F-244E0C1725B2&svg=true)](https://ci.appveyor.com/project/spark-test/spark/branch/198DDA52-F201-4D2B-BE2F-244E0C1725B2)
Diff: https://github.com/apache/spark/compare/master...spark-test:198DDA52-F201-4D2B-BE2F-244E0C1725B2
```
[info] Test org.apache.spark.JavaAPISuite.wholeTextFiles started
...
```
Author: hyukjinkwon <gu...@gmail.com>
Closes #15866 from HyukjinKwon/SPARK-18422.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/40d59ff5
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/40d59ff5
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/40d59ff5
Branch: refs/heads/master
Commit: 40d59ff5eaac6df237fe3d50186695c3806b268c
Parents: 795e9fc
Author: hyukjinkwon <gu...@gmail.com>
Authored: Fri Nov 18 21:45:18 2016 +0000
Committer: Sean Owen <so...@cloudera.com>
Committed: Fri Nov 18 21:45:18 2016 +0000
----------------------------------------------------------------------
.../test/java/org/apache/spark/JavaAPISuite.java | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/40d59ff5/core/src/test/java/org/apache/spark/JavaAPISuite.java
----------------------------------------------------------------------
diff --git a/core/src/test/java/org/apache/spark/JavaAPISuite.java b/core/src/test/java/org/apache/spark/JavaAPISuite.java
index 533025b..7bebe06 100644
--- a/core/src/test/java/org/apache/spark/JavaAPISuite.java
+++ b/core/src/test/java/org/apache/spark/JavaAPISuite.java
@@ -20,7 +20,6 @@ package org.apache.spark;
import java.io.*;
import java.nio.channels.FileChannel;
import java.nio.ByteBuffer;
-import java.net.URI;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.Arrays;
@@ -46,6 +45,7 @@ import com.google.common.collect.Iterators;
import com.google.common.collect.Lists;
import com.google.common.base.Throwables;
import com.google.common.io.Files;
+import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.DefaultCodec;
@@ -1075,18 +1075,23 @@ public class JavaAPISuite implements Serializable {
byte[] content2 = "spark is also easy to use.\n".getBytes(StandardCharsets.UTF_8);
String tempDirName = tempDir.getAbsolutePath();
- Files.write(content1, new File(tempDirName + "/part-00000"));
- Files.write(content2, new File(tempDirName + "/part-00001"));
+ String path1 = new Path(tempDirName, "part-00000").toUri().getPath();
+ String path2 = new Path(tempDirName, "part-00001").toUri().getPath();
+
+ Files.write(content1, new File(path1));
+ Files.write(content2, new File(path2));
Map<String, String> container = new HashMap<>();
- container.put(tempDirName+"/part-00000", new Text(content1).toString());
- container.put(tempDirName+"/part-00001", new Text(content2).toString());
+ container.put(path1, new Text(content1).toString());
+ container.put(path2, new Text(content2).toString());
JavaPairRDD<String, String> readRDD = sc.wholeTextFiles(tempDirName, 3);
List<Tuple2<String, String>> result = readRDD.collect();
for (Tuple2<String, String> res : result) {
- assertEquals(res._2(), container.get(new URI(res._1()).getPath()));
+ // Note that the paths from `wholeTextFiles` are in URI format on Windows,
+ // for example, file:/C:/a/b/c.
+ assertEquals(res._2(), container.get(new Path(res._1()).toUri().getPath()));
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org