http://git-wip-us.apache.org/repos/asf/hbase-site/blob/387c1112/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSerialization.html ---------------------------------------------------------------------- diff --git a/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSerialization.html b/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSerialization.html new file mode 100644 index 0000000..2f94a75 --- /dev/null +++ b/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSerialization.html @@ -0,0 +1,165 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> +<html lang="en"> +<head> +<title>Source code</title> +<link rel="stylesheet" type="text/css" href="../../../../../../stylesheet.css" title="Style"> +</head> +<body> +<div class="sourceContainer"> +<pre><span class="sourceLineNo">001</span>/**<a name="line.1"></a> +<span class="sourceLineNo">002</span> * Licensed to the Apache Software Foundation (ASF) under one<a name="line.2"></a> +<span class="sourceLineNo">003</span> * or more contributor license agreements. See the NOTICE file<a name="line.3"></a> +<span class="sourceLineNo">004</span> * distributed with this work for additional information<a name="line.4"></a> +<span class="sourceLineNo">005</span> * regarding copyright ownership. The ASF licenses this file<a name="line.5"></a> +<span class="sourceLineNo">006</span> * to you under the Apache License, Version 2.0 (the<a name="line.6"></a> +<span class="sourceLineNo">007</span> * "License"); you may not use this file except in compliance<a name="line.7"></a> +<span class="sourceLineNo">008</span> * with the License. You may obtain a copy of the License at<a name="line.8"></a> +<span class="sourceLineNo">009</span> *<a name="line.9"></a> +<span class="sourceLineNo">010</span> * http://www.apache.org/licenses/LICENSE-2.0<a name="line.10"></a> +<span class="sourceLineNo">011</span> *<a name="line.11"></a> +<span class="sourceLineNo">012</span> * Unless required by applicable law or agreed to in writing, software<a name="line.12"></a> +<span class="sourceLineNo">013</span> * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.13"></a> +<span class="sourceLineNo">014</span> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.14"></a> +<span class="sourceLineNo">015</span> * See the License for the specific language governing permissions and<a name="line.15"></a> +<span class="sourceLineNo">016</span> * limitations under the License.<a name="line.16"></a> +<span class="sourceLineNo">017</span> */<a name="line.17"></a> +<span class="sourceLineNo">018</span>package org.apache.hadoop.hbase.mapreduce;<a name="line.18"></a> +<span class="sourceLineNo">019</span><a name="line.19"></a> +<span class="sourceLineNo">020</span>import java.io.DataInputStream;<a name="line.20"></a> +<span class="sourceLineNo">021</span>import java.io.DataOutputStream;<a name="line.21"></a> +<span class="sourceLineNo">022</span>import java.io.IOException;<a name="line.22"></a> +<span class="sourceLineNo">023</span>import java.io.InputStream;<a name="line.23"></a> +<span class="sourceLineNo">024</span>import java.io.OutputStream;<a name="line.24"></a> +<span class="sourceLineNo">025</span><a name="line.25"></a> +<span class="sourceLineNo">026</span>import org.apache.hadoop.hbase.Cell;<a name="line.26"></a> +<span class="sourceLineNo">027</span>import org.apache.hadoop.hbase.CellUtil;<a name="line.27"></a> +<span class="sourceLineNo">028</span>import org.apache.hadoop.hbase.ExtendedCell;<a name="line.28"></a> +<span class="sourceLineNo">029</span>import org.apache.hadoop.hbase.KeyValue;<a name="line.29"></a> +<span class="sourceLineNo">030</span>import org.apache.hadoop.hbase.KeyValueUtil;<a name="line.30"></a> +<span class="sourceLineNo">031</span>import org.apache.hadoop.hbase.util.Bytes;<a name="line.31"></a> +<span class="sourceLineNo">032</span>import org.apache.yetus.audience.InterfaceAudience;<a name="line.32"></a> +<span class="sourceLineNo">033</span>import org.apache.hadoop.io.serializer.Deserializer;<a name="line.33"></a> +<span class="sourceLineNo">034</span>import org.apache.hadoop.io.serializer.Serialization;<a name="line.34"></a> +<span class="sourceLineNo">035</span>import org.apache.hadoop.io.serializer.Serializer;<a name="line.35"></a> +<span class="sourceLineNo">036</span><a name="line.36"></a> +<span class="sourceLineNo">037</span>@InterfaceAudience.Public<a name="line.37"></a> +<span class="sourceLineNo">038</span>public class CellSerialization implements Serialization<Cell> {<a name="line.38"></a> +<span class="sourceLineNo">039</span> @Override<a name="line.39"></a> +<span class="sourceLineNo">040</span> public boolean accept(Class<?> c) {<a name="line.40"></a> +<span class="sourceLineNo">041</span> return Cell.class.isAssignableFrom(c);<a name="line.41"></a> +<span class="sourceLineNo">042</span> }<a name="line.42"></a> +<span class="sourceLineNo">043</span><a name="line.43"></a> +<span class="sourceLineNo">044</span> @Override<a name="line.44"></a> +<span class="sourceLineNo">045</span> public CellDeserializer getDeserializer(Class<Cell> t) {<a name="line.45"></a> +<span class="sourceLineNo">046</span> return new CellDeserializer();<a name="line.46"></a> +<span class="sourceLineNo">047</span> }<a name="line.47"></a> +<span class="sourceLineNo">048</span><a name="line.48"></a> +<span class="sourceLineNo">049</span> @Override<a name="line.49"></a> +<span class="sourceLineNo">050</span> public CellSerializer getSerializer(Class<Cell> c) {<a name="line.50"></a> +<span class="sourceLineNo">051</span> return new CellSerializer();<a name="line.51"></a> +<span class="sourceLineNo">052</span> }<a name="line.52"></a> +<span class="sourceLineNo">053</span><a name="line.53"></a> +<span class="sourceLineNo">054</span> public static class CellDeserializer implements Deserializer<Cell> {<a name="line.54"></a> +<span class="sourceLineNo">055</span> private DataInputStream dis;<a name="line.55"></a> +<span class="sourceLineNo">056</span><a name="line.56"></a> +<span class="sourceLineNo">057</span> @Override<a name="line.57"></a> +<span class="sourceLineNo">058</span> public void close() throws IOException {<a name="line.58"></a> +<span class="sourceLineNo">059</span> this.dis.close();<a name="line.59"></a> +<span class="sourceLineNo">060</span> }<a name="line.60"></a> +<span class="sourceLineNo">061</span><a name="line.61"></a> +<span class="sourceLineNo">062</span> @Override<a name="line.62"></a> +<span class="sourceLineNo">063</span> public KeyValue deserialize(Cell ignore) throws IOException {<a name="line.63"></a> +<span class="sourceLineNo">064</span> // I can't overwrite the passed in KV, not from a proto kv, not just yet. TODO<a name="line.64"></a> +<span class="sourceLineNo">065</span> return KeyValueUtil.create(this.dis);<a name="line.65"></a> +<span class="sourceLineNo">066</span> }<a name="line.66"></a> +<span class="sourceLineNo">067</span><a name="line.67"></a> +<span class="sourceLineNo">068</span> @Override<a name="line.68"></a> +<span class="sourceLineNo">069</span> public void open(InputStream is) throws IOException {<a name="line.69"></a> +<span class="sourceLineNo">070</span> this.dis = new DataInputStream(is);<a name="line.70"></a> +<span class="sourceLineNo">071</span> }<a name="line.71"></a> +<span class="sourceLineNo">072</span> }<a name="line.72"></a> +<span class="sourceLineNo">073</span><a name="line.73"></a> +<span class="sourceLineNo">074</span> public static class CellSerializer implements Serializer<Cell> {<a name="line.74"></a> +<span class="sourceLineNo">075</span> private DataOutputStream dos;<a name="line.75"></a> +<span class="sourceLineNo">076</span><a name="line.76"></a> +<span class="sourceLineNo">077</span> @Override<a name="line.77"></a> +<span class="sourceLineNo">078</span> public void close() throws IOException {<a name="line.78"></a> +<span class="sourceLineNo">079</span> this.dos.close();<a name="line.79"></a> +<span class="sourceLineNo">080</span> }<a name="line.80"></a> +<span class="sourceLineNo">081</span><a name="line.81"></a> +<span class="sourceLineNo">082</span> @Override<a name="line.82"></a> +<span class="sourceLineNo">083</span> public void open(OutputStream os) throws IOException {<a name="line.83"></a> +<span class="sourceLineNo">084</span> this.dos = new DataOutputStream(os);<a name="line.84"></a> +<span class="sourceLineNo">085</span> }<a name="line.85"></a> +<span class="sourceLineNo">086</span><a name="line.86"></a> +<span class="sourceLineNo">087</span> @Override<a name="line.87"></a> +<span class="sourceLineNo">088</span> public void serialize(Cell kv) throws IOException {<a name="line.88"></a> +<span class="sourceLineNo">089</span> dos.writeInt(CellUtil.estimatedSerializedSizeOf(kv) - Bytes.SIZEOF_INT);<a name="line.89"></a> +<span class="sourceLineNo">090</span> CellUtil.writeCell(kv, dos, true);<a name="line.90"></a> +<span class="sourceLineNo">091</span> }<a name="line.91"></a> +<span class="sourceLineNo">092</span> }<a name="line.92"></a> +<span class="sourceLineNo">093</span>}<a name="line.93"></a> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +</pre> +</div> +</body> +</html>
http://git-wip-us.apache.org/repos/asf/hbase-site/blob/387c1112/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSortReducer.html ---------------------------------------------------------------------- diff --git a/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSortReducer.html b/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSortReducer.html new file mode 100644 index 0000000..fb3bda4 --- /dev/null +++ b/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CellSortReducer.html @@ -0,0 +1,132 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> +<html lang="en"> +<head> +<title>Source code</title> +<link rel="stylesheet" type="text/css" href="../../../../../../stylesheet.css" title="Style"> +</head> +<body> +<div class="sourceContainer"> +<pre><span class="sourceLineNo">001</span>/**<a name="line.1"></a> +<span class="sourceLineNo">002</span> *<a name="line.2"></a> +<span class="sourceLineNo">003</span> * Licensed to the Apache Software Foundation (ASF) under one<a name="line.3"></a> +<span class="sourceLineNo">004</span> * or more contributor license agreements. See the NOTICE file<a name="line.4"></a> +<span class="sourceLineNo">005</span> * distributed with this work for additional information<a name="line.5"></a> +<span class="sourceLineNo">006</span> * regarding copyright ownership. The ASF licenses this file<a name="line.6"></a> +<span class="sourceLineNo">007</span> * to you under the Apache License, Version 2.0 (the<a name="line.7"></a> +<span class="sourceLineNo">008</span> * "License"); you may not use this file except in compliance<a name="line.8"></a> +<span class="sourceLineNo">009</span> * with the License. You may obtain a copy of the License at<a name="line.9"></a> +<span class="sourceLineNo">010</span> *<a name="line.10"></a> +<span class="sourceLineNo">011</span> * http://www.apache.org/licenses/LICENSE-2.0<a name="line.11"></a> +<span class="sourceLineNo">012</span> *<a name="line.12"></a> +<span class="sourceLineNo">013</span> * Unless required by applicable law or agreed to in writing, software<a name="line.13"></a> +<span class="sourceLineNo">014</span> * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.14"></a> +<span class="sourceLineNo">015</span> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.15"></a> +<span class="sourceLineNo">016</span> * See the License for the specific language governing permissions and<a name="line.16"></a> +<span class="sourceLineNo">017</span> * limitations under the License.<a name="line.17"></a> +<span class="sourceLineNo">018</span> */<a name="line.18"></a> +<span class="sourceLineNo">019</span>package org.apache.hadoop.hbase.mapreduce;<a name="line.19"></a> +<span class="sourceLineNo">020</span><a name="line.20"></a> +<span class="sourceLineNo">021</span>import java.io.IOException;<a name="line.21"></a> +<span class="sourceLineNo">022</span>import java.util.TreeSet;<a name="line.22"></a> +<span class="sourceLineNo">023</span><a name="line.23"></a> +<span class="sourceLineNo">024</span>import org.apache.hadoop.hbase.Cell;<a name="line.24"></a> +<span class="sourceLineNo">025</span>import org.apache.hadoop.hbase.CellComparator;<a name="line.25"></a> +<span class="sourceLineNo">026</span>import org.apache.hadoop.hbase.CellUtil;<a name="line.26"></a> +<span class="sourceLineNo">027</span>import org.apache.hadoop.hbase.io.ImmutableBytesWritable;<a name="line.27"></a> +<span class="sourceLineNo">028</span>import org.apache.hadoop.hbase.util.MapReduceCell;<a name="line.28"></a> +<span class="sourceLineNo">029</span>import org.apache.hadoop.mapreduce.Reducer;<a name="line.29"></a> +<span class="sourceLineNo">030</span>import org.apache.yetus.audience.InterfaceAudience;<a name="line.30"></a> +<span class="sourceLineNo">031</span><a name="line.31"></a> +<span class="sourceLineNo">032</span>/**<a name="line.32"></a> +<span class="sourceLineNo">033</span> * Emits sorted Cells.<a name="line.33"></a> +<span class="sourceLineNo">034</span> * Reads in all Cells from passed Iterator, sorts them, then emits<a name="line.34"></a> +<span class="sourceLineNo">035</span> * Cells in sorted order. If lots of columns per row, it will use lots of<a name="line.35"></a> +<span class="sourceLineNo">036</span> * memory sorting.<a name="line.36"></a> +<span class="sourceLineNo">037</span> * @see HFileOutputFormat2<a name="line.37"></a> +<span class="sourceLineNo">038</span> */<a name="line.38"></a> +<span class="sourceLineNo">039</span>@InterfaceAudience.Public<a name="line.39"></a> +<span class="sourceLineNo">040</span>public class CellSortReducer<a name="line.40"></a> +<span class="sourceLineNo">041</span> extends Reducer<ImmutableBytesWritable, Cell, ImmutableBytesWritable, Cell> {<a name="line.41"></a> +<span class="sourceLineNo">042</span> protected void reduce(ImmutableBytesWritable row, Iterable<Cell> kvs,<a name="line.42"></a> +<span class="sourceLineNo">043</span> Reducer<ImmutableBytesWritable, Cell, ImmutableBytesWritable, Cell>.Context context)<a name="line.43"></a> +<span class="sourceLineNo">044</span> throws java.io.IOException, InterruptedException {<a name="line.44"></a> +<span class="sourceLineNo">045</span> TreeSet<Cell> map = new TreeSet<>(CellComparator.COMPARATOR);<a name="line.45"></a> +<span class="sourceLineNo">046</span> for (Cell kv : kvs) {<a name="line.46"></a> +<span class="sourceLineNo">047</span> try {<a name="line.47"></a> +<span class="sourceLineNo">048</span> map.add(CellUtil.deepClone(kv));<a name="line.48"></a> +<span class="sourceLineNo">049</span> } catch (CloneNotSupportedException e) {<a name="line.49"></a> +<span class="sourceLineNo">050</span> throw new IOException(e);<a name="line.50"></a> +<span class="sourceLineNo">051</span> }<a name="line.51"></a> +<span class="sourceLineNo">052</span> }<a name="line.52"></a> +<span class="sourceLineNo">053</span> context.setStatus("Read " + map.getClass());<a name="line.53"></a> +<span class="sourceLineNo">054</span> int index = 0;<a name="line.54"></a> +<span class="sourceLineNo">055</span> for (Cell kv: map) {<a name="line.55"></a> +<span class="sourceLineNo">056</span> context.write(row, new MapReduceCell(kv));<a name="line.56"></a> +<span class="sourceLineNo">057</span> if (++index % 100 == 0) context.setStatus("Wrote " + index);<a name="line.57"></a> +<span class="sourceLineNo">058</span> }<a name="line.58"></a> +<span class="sourceLineNo">059</span> }<a name="line.59"></a> +<span class="sourceLineNo">060</span>}<a name="line.60"></a> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +</pre> +</div> +</body> +</html> http://git-wip-us.apache.org/repos/asf/hbase-site/blob/387c1112/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CopyTable.html ---------------------------------------------------------------------- diff --git a/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CopyTable.html b/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CopyTable.html index d7da879..46fb016 100644 --- a/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CopyTable.html +++ b/apidocs/src-html/org/apache/hadoop/hbase/mapreduce/CopyTable.html @@ -147,7 +147,7 @@ <span class="sourceLineNo">139</span> job.setNumReduceTasks(0);<a name="line.139"></a> <span class="sourceLineNo">140</span><a name="line.140"></a> <span class="sourceLineNo">141</span> if (bulkload) {<a name="line.141"></a> -<span class="sourceLineNo">142</span> TableMapReduceUtil.initTableMapperJob(tableName, scan, Import.KeyValueImporter.class, null,<a name="line.142"></a> +<span class="sourceLineNo">142</span> TableMapReduceUtil.initTableMapperJob(tableName, scan, Import.CellImporter.class, null,<a name="line.142"></a> <span class="sourceLineNo">143</span> null, job);<a name="line.143"></a> <span class="sourceLineNo">144</span><a name="line.144"></a> <span class="sourceLineNo">145</span> // We need to split the inputs by destination tables so that output of Map can be bulk-loaded.<a name="line.145"></a>
