npawar commented on a change in pull request #6847:
URL: https://github.com/apache/incubator-pinot/pull/6847#discussion_r621670967
##########
File path:
pinot-core/src/main/java/org/apache/pinot/core/segment/processing/collector/GenericRowSorter.java
##########
@@ -81,6 +81,10 @@ public GenericRowSorter(List<String> sortOrder, Schema
schema) {
};
}
+ public Comparator<GenericRow> getGenericRowComparator() {
Review comment:
Yes can do. Will do it when I make similar changes on RollupCollector,
which will let me stop using the sort method entirely.
##########
File path:
pinot-core/src/main/java/org/apache/pinot/core/util/GenericRowSerDeUtils.java
##########
@@ -0,0 +1,326 @@
+/**
+ * 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.pinot.core.util;
+
+import java.nio.ByteBuffer;
+import java.nio.charset.StandardCharsets;
+import java.util.List;
+import org.apache.pinot.segment.local.segment.memory.PinotDataBuffer;
+import org.apache.pinot.spi.data.FieldSpec;
+import org.apache.pinot.spi.data.readers.GenericRow;
+
+
+/**
+ * Utility methods for serde of {@link GenericRow}
+ * Deserialization assumes it is deserializing from a {@link PinotDataBuffer}
+ */
+public final class GenericRowSerDeUtils {
+
+ private GenericRowSerDeUtils() {
+
+ }
+
+ /**
+ * Serialize the given GenericRow
+ * @param genericRow GenericRow to serialize
+ * @param fieldSpecs the fields to serialize
+ * @return serialized bytes
+ */
+ public static byte[] serializeGenericRow(GenericRow genericRow,
List<FieldSpec> fieldSpecs) {
+ int numBytes = 0;
+
+ for (FieldSpec fieldSpec : fieldSpecs) {
+ Object value = genericRow.getValue(fieldSpec.getName());
+
+ if (fieldSpec.isSingleValueField()) {
+ switch (fieldSpec.getDataType().getStoredType()) {
+
+ case INT:
+ numBytes += Integer.BYTES;
+ break;
+ case LONG:
+ numBytes += Long.BYTES;
+ break;
+ case FLOAT:
+ numBytes += Float.BYTES;
+ break;
+ case DOUBLE:
+ numBytes += Double.BYTES;
+ break;
+ case STRING:
+ byte[] stringBytes = ((String)
value).getBytes(StandardCharsets.UTF_8);
+ numBytes += Integer.BYTES; // string length
+ numBytes += stringBytes.length;
+ break;
+ case BYTES:
+ numBytes += Integer.BYTES; // byte array length
+ numBytes += ((byte[]) value).length;
+ break;
+ default:
+ throw new UnsupportedOperationException(
+ String.format("DataType '%s' not supported",
fieldSpec.getDataType()));
+ }
+ } else {
+ Object[] multiValue = (Object[]) value;
+ numBytes += Integer.BYTES; // array length
+
+ switch (fieldSpec.getDataType().getStoredType()) {
+ case INT:
+ numBytes += Integer.BYTES * multiValue.length;
+ break;
+ case LONG:
+ numBytes += Long.BYTES * multiValue.length;
+ break;
+ case FLOAT:
+ numBytes += Float.BYTES * multiValue.length;
+ break;
+ case DOUBLE:
+ numBytes += Double.BYTES * multiValue.length;
+ break;
+ case STRING:
+ for (Object element : multiValue) {
+ byte[] stringBytes = ((String)
element).getBytes(StandardCharsets.UTF_8);
+ numBytes += Integer.BYTES; // string length
+ numBytes += stringBytes.length;
+ }
+ break;
+ case BYTES:
+ for (Object element : multiValue) {
+ numBytes += Integer.BYTES; // byte array length
+ numBytes += ((byte[]) element).length;
+ }
+ break;
+ default:
+ throw new UnsupportedOperationException(
+ String.format("DataType '%s' not supported",
fieldSpec.getDataType()));
+ }
+ }
+ }
+
+ byte[] genericRowBytes = new byte[numBytes];
+ ByteBuffer byteBuffer =
ByteBuffer.wrap(genericRowBytes).order(PinotDataBuffer.NATIVE_ORDER);
+
+ for (FieldSpec fieldSpec : fieldSpecs) {
+ Object value = genericRow.getValue(fieldSpec.getName());
+
+ if (fieldSpec.isSingleValueField()) {
+ switch (fieldSpec.getDataType()) {
Review comment:
oops, I thought I changed them all but seems I missed these
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org
For additional commands, e-mail: commits-h...@pinot.apache.org
