address comments

cloud-fan · cloud-fan · commit 4bf69d860392 · 2018-01-02T14:00:20.000+08:00
diff --git a/sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedParquetRecordReader.java b/sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedParquetRecordReader.java
@@ -251,6 +251,7 @@ public boolean nextBatch() throws IOException {
     for (WritableColumnVector vector : columnVectors) {
       vector.reset();
     }
+    columnarBatch.setNumRows(0);
     if (rowsReturned >= totalRowCount) return false;
     checkEndOfRowGroup();
 
diff --git a/sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatch.java b/sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatch.java
@@ -23,9 +23,9 @@
 import org.apache.spark.sql.types.StructType;
 
 /**
- * This class is a wrapper of multiple ColumnVectors and represents a table. It provides a row-view
- * of this batch so that Spark can access the data row by row. Instance of it is meant to be reused
- * during the entire data loading process.
+ * This class is a wrapper of multiple ColumnVectors and represents a logical table-like data
+ * structure. It provides a row-view of this batch so that Spark can access the data row by row.
+ * Instance of it is meant to be reused during the entire data loading process.
  */
 public final class ColumnarBatch {
   public static final int DEFAULT_BATCH_SIZE = 4 * 1024;

Original file line number	Diff line number	Diff line change
`@@ -251,6 +251,7 @@ public boolean nextBatch() throws IOException {`
`251`	`251`	`for (WritableColumnVector vector : columnVectors) {`
`252`	`252`	`vector.reset();`
`253`	`253`	`}`
	`254`	`+ columnarBatch.setNumRows(0);`
`254`	`255`	`if (rowsReturned >= totalRowCount) return false;`
`255`	`256`	`checkEndOfRowGroup();`
`256`	`257`