Github user jiadexin commented on a diff in the pull request: https://github.com/apache/incubator-hawq/pull/972#discussion_r85678597 --- Diff: pxf/pxf-jdbc/src/main/java/org/apache/hawq/pxf/plugins/jdbc/JdbcPartitionFragmenter.java --- @@ -0,0 +1,284 @@ +package org.apache.hawq.pxf.plugins.jdbc; + +/* + * 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. + */ + +import org.apache.hawq.pxf.api.Fragmenter; +import org.apache.hawq.pxf.api.FragmentsStats; +import org.apache.hawq.pxf.plugins.jdbc.utils.DbProduct; +import org.apache.hawq.pxf.plugins.jdbc.utils.ByteUtil; +import org.apache.hawq.pxf.api.Fragment; +import org.apache.hawq.pxf.api.utilities.InputData; + +import java.net.InetAddress; +import java.text.SimpleDateFormat; +import java.util.*; + + +/** + * Fragmenter class for JDBC data resources. + * + * Extends the {@link Fragmenter} abstract class, with the purpose of transforming + * an input data path (an JDBC Database table name and user request parameters) into a list of regions + * that belong to this table. + * <p> + * <h4>The parameter Patterns </h4> + * There are three parameters, the format is as follows:<p> + * <pre> + * <code>PARTITION_BY=column_name:column_type&RANGE=start_value[:end_value]&INTERVAL=interval_num[:interval_unit]</code> + * </pre> + * The <code>PARTITION_BY</code> parameter can be split by colon(':'),the <code>column_type</code> current supported : <code>date,int,enum</code> . + * The Date format is 'yyyy-MM-dd'. <p> + * The <code>RANGE</code> parameter can be split by colon(':') ,used to identify the starting range of each fragment. + * The range is left-closed, ie:<code> '>= start_value AND < end_value' </code>.If the <code>column_type</code> is <code>int</code>, + * the <code>end_value</code> can be empty. If the <code>column_type</code>is <code>enum</code>,the parameter <code>RANGE</code> can be empty. <p> + * The <code>INTERVAL</code> parameter can be split by colon(':'), indicate the interval value of one fragment. + * When <code>column_type</code> is <code>date</code>,this parameter must be split by colon, and <code>interval_unit</code> can be <code>year,month,day</code>. + * When <code>column_type</code> is <code>int</code>, the <code>interval_unit</code> can be empty. + * When <code>column_type</code> is <code>enum</code>,the <code>INTERVAL</code> parameter can be empty. + * </p> + * <p> + * The syntax examples is :<p> + * <code>PARTITION_BY=createdate:date&RANGE=2008-01-01:2010-01-01&INTERVAL=1:month'</code> <p> + * <code>PARTITION_BY=year:int&RANGE=2008:2010&INTERVAL=1</code> <p> + * <code>PARTITION_BY=grade:enum&RANGE=excellent:good:general:bad</code> + * </p> + * + */ +public class JdbcPartitionFragmenter extends Fragmenter { + String[] partition_by = null; + String[] range = null; + String[] interval = null; + PartitionType partitionType = null; + String partitionColumn = null; + IntervalType intervalType = null; + int intervalNum = 1; + + enum PartitionType { + DATE, + INT, + ENUM; + + public static PartitionType getType(String str) { + return valueOf(str.toUpperCase()); + } + } + + enum IntervalType { + DAY, + MONTH, + YEAR; + + public static IntervalType type(String str) { + return valueOf(str.toUpperCase()); + } + } + + //The unit interval, in milliseconds, that is used to estimate the number of slices for the date partition type + static Map<IntervalType, Long> intervals = new HashMap<IntervalType, Long>(); + + static { + intervals.put(IntervalType.DAY, (long) 24 * 60 * 60 * 1000); + intervals.put(IntervalType.MONTH, (long) 30 * 24 * 60 * 60 * 1000);//30 day + intervals.put(IntervalType.YEAR, (long) 365 * 30 * 24 * 60 * 60 * 1000);//365 day + } + + /** + * Constructor for JdbcPartitionFragmenter. + * + * @param inConf input data such as which Jdbc table to scan + * @throws JdbcFragmentException + */ + public JdbcPartitionFragmenter(InputData inConf) throws JdbcFragmentException { + super(inConf); + if(inConf.getUserProperty("PARTITION_BY") == null ) --- End diff -- The PARTITION_BY parameter is not must required. Has been revised to: return a single fragment
--- 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. ---