Github user kumarvishal09 commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/2654#discussion_r214086463
--- Diff:
core/src/main/java/org/apache/carbondata/core/datastore/columnar/BlockIndexerStorageForNoDictionary.java
---
@@ -0,0 +1,157 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.carbondata.core.datastore.columnar;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+import org.apache.carbondata.core.constants.CarbonCommonConstants;
+import org.apache.carbondata.core.metadata.datatype.DataType;
+
+public class BlockIndexerStorageForNoDictionary {
+
+ private short[] rowIdPage;
+
+ private short[] rowIdRlePage;
+
+ private DataType dataType;
+
+ public BlockIndexerStorageForNoDictionary(Object[] dataPage, DataType
dataType,
+ boolean isNoDictionary, boolean isSortRequired) {
+ this.dataType = dataType;
+ ColumnWithRowIdForNoDictionary<Short>[] dataWithRowId =
+ createColumnWithRowId(dataPage, isNoDictionary);
+ if (isSortRequired) {
+ Arrays.sort(dataWithRowId);
+ }
+ short[] rowIds = extractDataAndReturnRowId(dataWithRowId, dataPage);
+ rleEncodeOnRowId(rowIds);
+ }
+
+ /**
+ * Create an object with each column array and respective rowId
+ *
+ * @return
+ */
+ private ColumnWithRowIdForNoDictionary<Short>[]
createColumnWithRowId(Object[] dataPage,
+ boolean isNoDictionary) {
+ ColumnWithRowIdForNoDictionary<Short>[] columnWithIndexs =
+ new ColumnWithRowIdForNoDictionary[dataPage.length];
+ if (isNoDictionary) {
+ for (short i = 0; i < columnWithIndexs.length; i++) {
+ columnWithIndexs[i] = new
ColumnWithRowIdForNoDictionary<>(dataPage[i], i, dataType);
+ }
+ }
+ return columnWithIndexs;
+ }
+
+ private short[]
extractDataAndReturnRowId(ColumnWithRowIdForNoDictionary<Short>[] dataWithRowId,
+ Object[] dataPage) {
+ short[] indexes = new short[dataWithRowId.length];
+ for (int i = 0; i < indexes.length; i++) {
+ indexes[i] = dataWithRowId[i].getIndex();
+ dataPage[i] = dataWithRowId[i].getColumn();
+ }
+ return indexes;
+ }
+
+ /**
+ * It compresses depends up on the sequence numbers.
+ * [1,2,3,4,6,8,10,11,12,13] is translated to [1,4,6,8,10,13] and [0,6].
In
+ * first array the start and end of sequential numbers and second array
+ * keeps the indexes of where sequential numbers starts. If there is no
+ * sequential numbers then the same array it returns with empty second
+ * array.
+ *
+ * @param rowIds
+ */
+ private void rleEncodeOnRowId(short[] rowIds) {
--- End diff --
This method is common for BlockIndexStorageForShot please move it to some
util class
---
