| <!DOCTYPE HTML> |
| <html lang="en"> |
| <head> |
| <!-- Generated by javadoc (17) --> |
| <title>Source code</title> |
| <meta name="viewport" content="width=device-width, initial-scale=1"> |
| <meta name="description" content="source: package: org.apache.hadoop.hbase.mapred, class: GroupingTableMap"> |
| <meta name="generator" content="javadoc/SourceToHTMLConverter"> |
| <link rel="stylesheet" type="text/css" href="../../../../../../stylesheet.css" title="Style"> |
| </head> |
| <body class="source-page"> |
| <main role="main"> |
| <div class="source-container"> |
| <pre><span class="source-line-no">001</span><span id="line-1">/*</span> |
| <span class="source-line-no">002</span><span id="line-2"> * Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="source-line-no">003</span><span id="line-3"> * or more contributor license agreements. See the NOTICE file</span> |
| <span class="source-line-no">004</span><span id="line-4"> * distributed with this work for additional information</span> |
| <span class="source-line-no">005</span><span id="line-5"> * regarding copyright ownership. The ASF licenses this file</span> |
| <span class="source-line-no">006</span><span id="line-6"> * to you under the Apache License, Version 2.0 (the</span> |
| <span class="source-line-no">007</span><span id="line-7"> * "License"); you may not use this file except in compliance</span> |
| <span class="source-line-no">008</span><span id="line-8"> * with the License. You may obtain a copy of the License at</span> |
| <span class="source-line-no">009</span><span id="line-9"> *</span> |
| <span class="source-line-no">010</span><span id="line-10"> * http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="source-line-no">011</span><span id="line-11"> *</span> |
| <span class="source-line-no">012</span><span id="line-12"> * Unless required by applicable law or agreed to in writing, software</span> |
| <span class="source-line-no">013</span><span id="line-13"> * distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="source-line-no">014</span><span id="line-14"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="source-line-no">015</span><span id="line-15"> * See the License for the specific language governing permissions and</span> |
| <span class="source-line-no">016</span><span id="line-16"> * limitations under the License.</span> |
| <span class="source-line-no">017</span><span id="line-17"> */</span> |
| <span class="source-line-no">018</span><span id="line-18">package org.apache.hadoop.hbase.mapred;</span> |
| <span class="source-line-no">019</span><span id="line-19"></span> |
| <span class="source-line-no">020</span><span id="line-20">import java.io.IOException;</span> |
| <span class="source-line-no">021</span><span id="line-21">import java.util.ArrayList;</span> |
| <span class="source-line-no">022</span><span id="line-22">import org.apache.hadoop.hbase.Cell;</span> |
| <span class="source-line-no">023</span><span id="line-23">import org.apache.hadoop.hbase.CellUtil;</span> |
| <span class="source-line-no">024</span><span id="line-24">import org.apache.hadoop.hbase.client.Result;</span> |
| <span class="source-line-no">025</span><span id="line-25">import org.apache.hadoop.hbase.io.ImmutableBytesWritable;</span> |
| <span class="source-line-no">026</span><span id="line-26">import org.apache.hadoop.hbase.util.Bytes;</span> |
| <span class="source-line-no">027</span><span id="line-27">import org.apache.hadoop.mapred.JobConf;</span> |
| <span class="source-line-no">028</span><span id="line-28">import org.apache.hadoop.mapred.MapReduceBase;</span> |
| <span class="source-line-no">029</span><span id="line-29">import org.apache.hadoop.mapred.OutputCollector;</span> |
| <span class="source-line-no">030</span><span id="line-30">import org.apache.hadoop.mapred.Reporter;</span> |
| <span class="source-line-no">031</span><span id="line-31">import org.apache.yetus.audience.InterfaceAudience;</span> |
| <span class="source-line-no">032</span><span id="line-32"></span> |
| <span class="source-line-no">033</span><span id="line-33">/**</span> |
| <span class="source-line-no">034</span><span id="line-34"> * Extract grouping columns from input record</span> |
| <span class="source-line-no">035</span><span id="line-35"> */</span> |
| <span class="source-line-no">036</span><span id="line-36">@InterfaceAudience.Public</span> |
| <span class="source-line-no">037</span><span id="line-37">public class GroupingTableMap extends MapReduceBase</span> |
| <span class="source-line-no">038</span><span id="line-38"> implements TableMap<ImmutableBytesWritable, Result> {</span> |
| <span class="source-line-no">039</span><span id="line-39"></span> |
| <span class="source-line-no">040</span><span id="line-40"> /**</span> |
| <span class="source-line-no">041</span><span id="line-41"> * JobConf parameter to specify the columns used to produce the key passed to collect from the map</span> |
| <span class="source-line-no">042</span><span id="line-42"> * phase</span> |
| <span class="source-line-no">043</span><span id="line-43"> */</span> |
| <span class="source-line-no">044</span><span id="line-44"> public static final String GROUP_COLUMNS = "hbase.mapred.groupingtablemap.columns";</span> |
| <span class="source-line-no">045</span><span id="line-45"></span> |
| <span class="source-line-no">046</span><span id="line-46"> protected byte[][] columns;</span> |
| <span class="source-line-no">047</span><span id="line-47"></span> |
| <span class="source-line-no">048</span><span id="line-48"> /**</span> |
| <span class="source-line-no">049</span><span id="line-49"> * Use this before submitting a TableMap job. It will appropriately set up the JobConf.</span> |
| <span class="source-line-no">050</span><span id="line-50"> * @param table table to be processed</span> |
| <span class="source-line-no">051</span><span id="line-51"> * @param columns space separated list of columns to fetch</span> |
| <span class="source-line-no">052</span><span id="line-52"> * @param groupColumns space separated list of columns used to form the key used in collect</span> |
| <span class="source-line-no">053</span><span id="line-53"> * @param mapper map class</span> |
| <span class="source-line-no">054</span><span id="line-54"> * @param job job configuration object</span> |
| <span class="source-line-no">055</span><span id="line-55"> */</span> |
| <span class="source-line-no">056</span><span id="line-56"> @SuppressWarnings("unchecked")</span> |
| <span class="source-line-no">057</span><span id="line-57"> public static void initJob(String table, String columns, String groupColumns,</span> |
| <span class="source-line-no">058</span><span id="line-58"> Class<? extends TableMap> mapper, JobConf job) {</span> |
| <span class="source-line-no">059</span><span id="line-59"></span> |
| <span class="source-line-no">060</span><span id="line-60"> TableMapReduceUtil.initTableMapJob(table, columns, mapper, ImmutableBytesWritable.class,</span> |
| <span class="source-line-no">061</span><span id="line-61"> Result.class, job);</span> |
| <span class="source-line-no">062</span><span id="line-62"> job.set(GROUP_COLUMNS, groupColumns);</span> |
| <span class="source-line-no">063</span><span id="line-63"> }</span> |
| <span class="source-line-no">064</span><span id="line-64"></span> |
| <span class="source-line-no">065</span><span id="line-65"> @Override</span> |
| <span class="source-line-no">066</span><span id="line-66"> public void configure(JobConf job) {</span> |
| <span class="source-line-no">067</span><span id="line-67"> super.configure(job);</span> |
| <span class="source-line-no">068</span><span id="line-68"> String[] cols = job.get(GROUP_COLUMNS, "").split(" ");</span> |
| <span class="source-line-no">069</span><span id="line-69"> columns = new byte[cols.length][];</span> |
| <span class="source-line-no">070</span><span id="line-70"> for (int i = 0; i < cols.length; i++) {</span> |
| <span class="source-line-no">071</span><span id="line-71"> columns[i] = Bytes.toBytes(cols[i]);</span> |
| <span class="source-line-no">072</span><span id="line-72"> }</span> |
| <span class="source-line-no">073</span><span id="line-73"> }</span> |
| <span class="source-line-no">074</span><span id="line-74"></span> |
| <span class="source-line-no">075</span><span id="line-75"> /**</span> |
| <span class="source-line-no">076</span><span id="line-76"> * Extract the grouping columns from value to construct a new key. Pass the new key and value to</span> |
| <span class="source-line-no">077</span><span id="line-77"> * reduce. If any of the grouping columns are not found in the value, the record is skipped.</span> |
| <span class="source-line-no">078</span><span id="line-78"> */</span> |
| <span class="source-line-no">079</span><span id="line-79"> public void map(ImmutableBytesWritable key, Result value,</span> |
| <span class="source-line-no">080</span><span id="line-80"> OutputCollector<ImmutableBytesWritable, Result> output, Reporter reporter) throws IOException {</span> |
| <span class="source-line-no">081</span><span id="line-81"></span> |
| <span class="source-line-no">082</span><span id="line-82"> byte[][] keyVals = extractKeyValues(value);</span> |
| <span class="source-line-no">083</span><span id="line-83"> if (keyVals != null) {</span> |
| <span class="source-line-no">084</span><span id="line-84"> ImmutableBytesWritable tKey = createGroupKey(keyVals);</span> |
| <span class="source-line-no">085</span><span id="line-85"> output.collect(tKey, value);</span> |
| <span class="source-line-no">086</span><span id="line-86"> }</span> |
| <span class="source-line-no">087</span><span id="line-87"> }</span> |
| <span class="source-line-no">088</span><span id="line-88"></span> |
| <span class="source-line-no">089</span><span id="line-89"> /**</span> |
| <span class="source-line-no">090</span><span id="line-90"> * Extract columns values from the current record. This method returns null if any of the columns</span> |
| <span class="source-line-no">091</span><span id="line-91"> * are not found. Override this method if you want to deal with nulls differently.</span> |
| <span class="source-line-no">092</span><span id="line-92"> * @return array of byte values</span> |
| <span class="source-line-no">093</span><span id="line-93"> */</span> |
| <span class="source-line-no">094</span><span id="line-94"> protected byte[][] extractKeyValues(Result r) {</span> |
| <span class="source-line-no">095</span><span id="line-95"> byte[][] keyVals = null;</span> |
| <span class="source-line-no">096</span><span id="line-96"> ArrayList<byte[]> foundList = new ArrayList<>();</span> |
| <span class="source-line-no">097</span><span id="line-97"> int numCols = columns.length;</span> |
| <span class="source-line-no">098</span><span id="line-98"> if (numCols > 0) {</span> |
| <span class="source-line-no">099</span><span id="line-99"> for (Cell value : r.listCells()) {</span> |
| <span class="source-line-no">100</span><span id="line-100"> byte[] column =</span> |
| <span class="source-line-no">101</span><span id="line-101"> CellUtil.makeColumn(CellUtil.cloneFamily(value), CellUtil.cloneQualifier(value));</span> |
| <span class="source-line-no">102</span><span id="line-102"> for (int i = 0; i < numCols; i++) {</span> |
| <span class="source-line-no">103</span><span id="line-103"> if (Bytes.equals(column, columns[i])) {</span> |
| <span class="source-line-no">104</span><span id="line-104"> foundList.add(CellUtil.cloneValue(value));</span> |
| <span class="source-line-no">105</span><span id="line-105"> break;</span> |
| <span class="source-line-no">106</span><span id="line-106"> }</span> |
| <span class="source-line-no">107</span><span id="line-107"> }</span> |
| <span class="source-line-no">108</span><span id="line-108"> }</span> |
| <span class="source-line-no">109</span><span id="line-109"> if (foundList.size() == numCols) {</span> |
| <span class="source-line-no">110</span><span id="line-110"> keyVals = foundList.toArray(new byte[numCols][]);</span> |
| <span class="source-line-no">111</span><span id="line-111"> }</span> |
| <span class="source-line-no">112</span><span id="line-112"> }</span> |
| <span class="source-line-no">113</span><span id="line-113"> return keyVals;</span> |
| <span class="source-line-no">114</span><span id="line-114"> }</span> |
| <span class="source-line-no">115</span><span id="line-115"></span> |
| <span class="source-line-no">116</span><span id="line-116"> /**</span> |
| <span class="source-line-no">117</span><span id="line-117"> * Create a key by concatenating multiple column values. Override this function in order to</span> |
| <span class="source-line-no">118</span><span id="line-118"> * produce different types of keys.</span> |
| <span class="source-line-no">119</span><span id="line-119"> * @return key generated by concatenating multiple column values</span> |
| <span class="source-line-no">120</span><span id="line-120"> */</span> |
| <span class="source-line-no">121</span><span id="line-121"> protected ImmutableBytesWritable createGroupKey(byte[][] vals) {</span> |
| <span class="source-line-no">122</span><span id="line-122"> if (vals == null) {</span> |
| <span class="source-line-no">123</span><span id="line-123"> return null;</span> |
| <span class="source-line-no">124</span><span id="line-124"> }</span> |
| <span class="source-line-no">125</span><span id="line-125"> StringBuilder sb = new StringBuilder();</span> |
| <span class="source-line-no">126</span><span id="line-126"> for (int i = 0; i < vals.length; i++) {</span> |
| <span class="source-line-no">127</span><span id="line-127"> if (i > 0) {</span> |
| <span class="source-line-no">128</span><span id="line-128"> sb.append(" ");</span> |
| <span class="source-line-no">129</span><span id="line-129"> }</span> |
| <span class="source-line-no">130</span><span id="line-130"> sb.append(Bytes.toString(vals[i]));</span> |
| <span class="source-line-no">131</span><span id="line-131"> }</span> |
| <span class="source-line-no">132</span><span id="line-132"> return new ImmutableBytesWritable(Bytes.toBytesBinary(sb.toString()));</span> |
| <span class="source-line-no">133</span><span id="line-133"> }</span> |
| <span class="source-line-no">134</span><span id="line-134">}</span> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </pre> |
| </div> |
| </main> |
| </body> |
| </html> |