Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/20316#discussion_r162842712 --- Diff: sql/core/src/main/java/org/apache/spark/sql/vectorized/ColumnarBatch.java --- @@ -96,16 +90,6 @@ public void setNumRows(int numRows) { */ public int numRows() { return numRows; } - /** - * Returns the schema that makes up this batch. - */ - public StructType schema() { return schema; } - - /** - * Returns the max capacity (in number of rows) for this batch. - */ - public int capacity() { return capacity; } --- End diff -- For `ColumnarBatch` consumers, they don't care about `capacity`, but only `numRows`, `capacity` is only needed by column vector builders. Also they don't care about schema/field names, but only the data type of each column.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org