You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@zeppelin.apache.org by mo...@apache.org on 2017/01/08 11:02:00 UTC
zeppelin git commit: [ZEPPELIN-1874] fix: sparkR doens't render
output properly
Repository: zeppelin
Updated Branches:
refs/heads/master 169727571 -> ae12ba31a
[ZEPPELIN-1874] fix: sparkR doens't render output properly
### What is this PR for?
Zeppelin sparkr only shows first element of all outputs due to invalid implementation
```scala
// https://github.com/apache/zeppelin/blob/master/spark/src/main/scala/org/apache/zeppelin/spark/ZeppelinRDisplay.scala#L71
private def textDisplay(body: Element): RDisplay = {
// we are extracting only the first element. it shouldn't
RDisplay(body.getElementsByTag("p").first().html(), TEXT, SUCCESS)
}
```
#### FYI
SparkR interpreter sends message which containing multiple whitespaces, newlines. But zeppelin frontend breaks the space characters. This should be handled by other issue ([ZEPPELIN-1914](https://issues.apache.org/jira/browse/ZEPPELIN-1914)). As you can see the screenshot below, the paragraph result sent from websocket keeps consequent whitespaces and newlines until rendering.
<img width="716" alt="screen shot 2017-01-06 at 4 50 06 pm" src="https://cloud.githubusercontent.com/assets/4968473/21711367/f11d7c72-d431-11e6-8b6b-e4b7cc603afb.png">
### What type of PR is it?
[Bug Fix]
### Todos
N/A
### What is the Jira issue?
[ZEPPELIN-1874](https://issues.apache.org/jira/browse/ZEPPELIN-1874)
### How should this be tested?
1. Build Zeppelin with Spark 2.0+, R, sparkR
2. Execute this paragraph
```
%spark.r
mtcarsDF <- createDataFrame(mtcars)
model <- glm(vs ~ mpg + disp + hp + wt , data = mtcarsDF, family = "binomial")
summary(model)
```
3. Check you can get all result.
```
Deviance Residuals:
(Note: These are approximate quantiles with relative error <= 0.01)
Min 1Q Median 3Q Max
-2.11025 -0.08567 -0.00069 0.13214 1.10483
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -23.623 23.144 -1.0207 0.30739
mpg 0.78475 0.65026 1.2068 0.2275
disp -0.031549 0.027342 -1.1539 0.24854
hp -0.072188 0.045509 -1.5862 0.11269
wt 7.335 5.2336 1.4015 0.16105
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 43.860 on 31 degrees of freedom
Residual deviance: 12.873 on 27 degrees of freedom
AIC: 22.87
Number of Fisher Scoring iterations: 9
```
### Screenshots (if appropriate)
Buggy (doesn't show full result)
<img width="714" alt="buggy" src="https://cloud.githubusercontent.com/assets/4968473/21711437/723f00be-d432-11e6-9701-1bcd81f86fb7.png">
### Questions:
* Does the licenses files need update? - NO
* Is there breaking changes for older versions? - NO
* Does this needs documentation? - NO
Author: 1ambda <1a...@gmail.com>
Closes #1857 from 1ambda/ZEPPELIN-1874/sparkr-doesnot-render-all-output and squashes the following commits:
ba3a457 [1ambda] fix: sparkRTest
3f97404 [1ambda] fix: sparkR doens't render output properly
Project: http://git-wip-us.apache.org/repos/asf/zeppelin/repo
Commit: http://git-wip-us.apache.org/repos/asf/zeppelin/commit/ae12ba31
Tree: http://git-wip-us.apache.org/repos/asf/zeppelin/tree/ae12ba31
Diff: http://git-wip-us.apache.org/repos/asf/zeppelin/diff/ae12ba31
Branch: refs/heads/master
Commit: ae12ba31afc610c3927338d7380eec2d3e37aba6
Parents: 1697275
Author: 1ambda <1a...@gmail.com>
Authored: Sat Jan 7 05:35:40 2017 +0900
Committer: Lee moon soo <mo...@apache.org>
Committed: Sun Jan 8 03:01:54 2017 -0800
----------------------------------------------------------------------
.../org/apache/zeppelin/spark/ZeppelinRDisplay.scala | 12 +++++++-----
.../apache/zeppelin/rest/ZeppelinSparkClusterTest.java | 2 +-
2 files changed, 8 insertions(+), 6 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/zeppelin/blob/ae12ba31/spark/src/main/scala/org/apache/zeppelin/spark/ZeppelinRDisplay.scala
----------------------------------------------------------------------
diff --git a/spark/src/main/scala/org/apache/zeppelin/spark/ZeppelinRDisplay.scala b/spark/src/main/scala/org/apache/zeppelin/spark/ZeppelinRDisplay.scala
index 8419a11..fe4072d 100644
--- a/spark/src/main/scala/org/apache/zeppelin/spark/ZeppelinRDisplay.scala
+++ b/spark/src/main/scala/org/apache/zeppelin/spark/ZeppelinRDisplay.scala
@@ -18,15 +18,15 @@
package org.apache.zeppelin.spark
import org.apache.zeppelin.interpreter.InterpreterResult.Code
-import org.apache.zeppelin.interpreter.InterpreterResult.Code.{SUCCESS, ERROR}
+import org.apache.zeppelin.interpreter.InterpreterResult.Code.{SUCCESS}
import org.apache.zeppelin.interpreter.InterpreterResult.Type
import org.apache.zeppelin.interpreter.InterpreterResult.Type.{TEXT, HTML, TABLE, IMG}
import org.jsoup.Jsoup
import org.jsoup.nodes.Element
-import org.jsoup.nodes.Document
+import org.jsoup.nodes.Document.OutputSettings
+import org.jsoup.safety.Whitelist
import scala.collection.JavaConversions._
-
import scala.util.matching.Regex
case class RDisplay(content: String, `type`: Type, code: Code)
@@ -64,11 +64,13 @@ object ZeppelinRDisplay {
}
return htmlDisplay(body, imageWidth)
-
}
private def textDisplay(body: Element): RDisplay = {
- RDisplay(body.getElementsByTag("p").first().html(), TEXT, SUCCESS)
+ // remove HTML tag while preserving whitespaces and newlines
+ val text = Jsoup.clean(body.html(), "",
+ Whitelist.none(), new OutputSettings().prettyPrint(false))
+ RDisplay(text, TEXT, SUCCESS)
}
private def tableDisplay(body: Element): RDisplay = {
http://git-wip-us.apache.org/repos/asf/zeppelin/blob/ae12ba31/zeppelin-server/src/test/java/org/apache/zeppelin/rest/ZeppelinSparkClusterTest.java
----------------------------------------------------------------------
diff --git a/zeppelin-server/src/test/java/org/apache/zeppelin/rest/ZeppelinSparkClusterTest.java b/zeppelin-server/src/test/java/org/apache/zeppelin/rest/ZeppelinSparkClusterTest.java
index 5e1e355..4816e4f 100644
--- a/zeppelin-server/src/test/java/org/apache/zeppelin/rest/ZeppelinSparkClusterTest.java
+++ b/zeppelin-server/src/test/java/org/apache/zeppelin/rest/ZeppelinSparkClusterTest.java
@@ -183,7 +183,7 @@ public class ZeppelinSparkClusterTest extends AbstractTestRestApi {
waitForFinish(p);
System.err.println("sparkRTest=" + p.getResult().message().get(0).getData());
assertEquals(Status.FINISHED, p.getStatus());
- assertEquals("[1] 3", p.getResult().message().get(0).getData());
+ assertEquals("[1] 3", p.getResult().message().get(0).getData().trim());
}
ZeppelinServer.notebook.removeNote(note.getId(), anonymous);
}