shaofengshi closed pull request #322: KYLIN-3644 Fix SparkFactDistinct step 
NumberFormatException
URL: https://github.com/apache/kylin/pull/322
 
 
   

This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:

As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):

diff --git 
a/core-cube/src/main/java/org/apache/kylin/cube/util/KeyValueBuilder.java 
b/core-cube/src/main/java/org/apache/kylin/cube/util/KeyValueBuilder.java
index 0ba4fd8ed1..0636a5c343 100644
--- a/core-cube/src/main/java/org/apache/kylin/cube/util/KeyValueBuilder.java
+++ b/core-cube/src/main/java/org/apache/kylin/cube/util/KeyValueBuilder.java
@@ -56,7 +56,7 @@ private void initNullStrings() {
         }
     }
 
-    protected boolean isNull(String v) {
+    public boolean isNull(String v) {
         return nullStrs.contains(v);
     }
 
diff --git 
a/engine-spark/src/main/java/org/apache/kylin/engine/spark/SparkFactDistinct.java
 
b/engine-spark/src/main/java/org/apache/kylin/engine/spark/SparkFactDistinct.java
index 5cfd2d7ccb..cdd0ac22d7 100644
--- 
a/engine-spark/src/main/java/org/apache/kylin/engine/spark/SparkFactDistinct.java
+++ 
b/engine-spark/src/main/java/org/apache/kylin/engine/spark/SparkFactDistinct.java
@@ -63,6 +63,7 @@
 import org.apache.kylin.cube.cuboid.CuboidUtil;
 import org.apache.kylin.cube.model.CubeDesc;
 import org.apache.kylin.cube.model.CubeJoinedFlatTableEnrich;
+import org.apache.kylin.cube.util.KeyValueBuilder;
 import org.apache.kylin.dict.DictionaryGenerator;
 import org.apache.kylin.dict.IDictionaryBuilder;
 import org.apache.kylin.engine.EngineFactory;
@@ -250,6 +251,7 @@ protected void execute(OptionsHelper optionsHelper) throws 
Exception {
         private Map<Integer, DimensionRangeInfo> dimensionRangeInfoMap;
         private transient ByteBuffer tmpbuf;
         private LongAccumulator bytesWritten;
+        private KeyValueBuilder keyValueBuilder;
 
         public FlatOutputFucntion(String cubeName, String segmentId, String 
metaurl, SerializableConfiguration conf,
                 int samplingPercent, LongAccumulator bytesWritten) {
@@ -272,6 +274,7 @@ private void init() {
                 CubeJoinedFlatTableEnrich intermediateTableDesc = new 
CubeJoinedFlatTableEnrich(
                         EngineFactory.getJoinedFlatTableDesc(cubeSegment), 
cubeDesc);
 
+                keyValueBuilder = new KeyValueBuilder(intermediateTableDesc);
                 reducerMapping = new 
FactDistinctColumnsReducerMapping(cubeInstance);
                 tmpbuf = ByteBuffer.allocate(4096);
 
@@ -317,7 +320,7 @@ private void init() {
 
                 for (int i = 0; i < allCols.size(); i++) {
                     String fieldValue = row[columnIndex[i]];
-                    if (fieldValue == null)
+                    if (fieldValue == null || 
keyValueBuilder.isNull(fieldValue))
                         continue;
 
                     final DataType type = allCols.get(i).getType();


 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to