Github user davies commented on a diff in the pull request: https://github.com/apache/spark/pull/12017#discussion_r57681187 --- Diff: sql/core/src/main/java/org/apache/spark/sql/execution/datasources/parquet/VectorizedColumnReader.java --- @@ -246,11 +215,48 @@ private void decodeDictionaryIds(int rowId, int num, ColumnVector column, ColumnVector dictionaryIds) { switch (descriptor.getType()) { case INT32: + if (column.dataType() == DataTypes.IntegerType) { + for (int i = rowId; i < rowId + num; ++i) { + column.putInt(i, dictionary.decodeToInt(dictionaryIds.getInt(i))); + } + } else if (column.dataType() == DataTypes.ByteType) { + for (int i = rowId; i < rowId + num; ++i) { + column.putByte(i, (byte) dictionary.decodeToInt(dictionaryIds.getInt(i))); + } + } else if (column.dataType() == DataTypes.ShortType) { + for (int i = rowId; i < rowId + num; ++i) { + column.putShort(i, (short) dictionary.decodeToInt(dictionaryIds.getInt(i))); + } + } else if (DecimalType.is64BitDecimalType(column.dataType())) { + for (int i = rowId; i < rowId + num; ++i) { + column.putLong(i, dictionary.decodeToInt(dictionaryIds.getInt(i))); --- End diff -- we use int for small decimal
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org