[GitHub] rdblue closed pull request #49: Fix type handling in Spark and Pig.

[GitBox <gi...@apache.org>]

rdblue closed pull request #49: Fix type handling in Spark and Pig.
URL: https://github.com/apache/incubator-iceberg/pull/49
 
 
   

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/pig/src/main/java/com/netflix/iceberg/pig/PigParquetReader.java b/pig/src/main/java/com/netflix/iceberg/pig/PigParquetReader.java
index 1de637f..dbd9282 100644
--- a/pig/src/main/java/com/netflix/iceberg/pig/PigParquetReader.java
+++ b/pig/src/main/java/com/netflix/iceberg/pig/PigParquetReader.java
@@ -38,6 +38,7 @@
 import com.netflix.iceberg.parquet.ParquetValueReaders.StructReader;
 import com.netflix.iceberg.parquet.ParquetValueReaders.UnboxedReader;
 import com.netflix.iceberg.parquet.TypeWithSchemaVisitor;
+import com.netflix.iceberg.types.Type.TypeID;
 import com.netflix.iceberg.types.Types;
 import org.apache.parquet.column.ColumnDescriptor;
 import org.apache.parquet.schema.DecimalMetadata;
@@ -208,8 +209,10 @@ public PigParquetReader(Schema readSchema, MessageType fileSchema, Map<Integer,
           case INT_8:
           case INT_16:
           case INT_32:
-            if(expected.typeId() == Types.LongType.get().typeId()) {
+            if (expected != null && expected.typeId() == Types.LongType.get().typeId()) {
               return new IntAsLongReader(desc);
+            } else {
+              return new UnboxedReader(desc);
             }
           case INT_64: return new UnboxedReader<>(desc);
           case TIMESTAMP_MILLIS: return new TimestampMillisReader(desc);
@@ -234,13 +237,20 @@ public PigParquetReader(Schema readSchema, MessageType fileSchema, Map<Integer,
         case FIXED_LEN_BYTE_ARRAY:
         case BINARY:
           return new BytesReader(desc);
-        case BOOLEAN:
         case INT32:
-        case INT64:
+          if (expected != null && expected.typeId() == TypeID.LONG) {
+            return new IntAsLongReader(desc);
+          } else {
+            return new UnboxedReader<>(desc);
+          }
         case FLOAT:
-          if(expected.typeId() == Types.DoubleType.get().typeId()) {
+          if (expected != null && expected.typeId() == TypeID.DOUBLE) {
             return new FloatAsDoubleReader(desc);
+          } else {
+            return new UnboxedReader<>(desc);
           }
+        case BOOLEAN:
+        case INT64:
         case DOUBLE:
           return new UnboxedReader<>(desc);
         default:
diff --git a/spark/src/main/java/com/netflix/iceberg/spark/data/SparkParquetReaders.java b/spark/src/main/java/com/netflix/iceberg/spark/data/SparkParquetReaders.java
index 1791014..336ffb1 100644
--- a/spark/src/main/java/com/netflix/iceberg/spark/data/SparkParquetReaders.java
+++ b/spark/src/main/java/com/netflix/iceberg/spark/data/SparkParquetReaders.java
@@ -204,10 +204,15 @@ private SparkParquetReaders() {
           case JSON:
           case UTF8:
             return new StringReader(desc);
-          case DATE:
           case INT_8:
           case INT_16:
           case INT_32:
+            if (expected != null && expected.typeId() == Types.LongType.get().typeId()) {
+              return new IntAsLongReader(desc);
+            } else {
+              return new UnboxedReader(desc);
+            }
+          case DATE:
           case INT_64:
           case TIMESTAMP_MICROS:
             return new UnboxedReader<>(desc);


 

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services