<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT>    /**<a name="line.1"></a>
<FONT color="green">002</FONT>     * Licensed to the Apache Software Foundation (ASF) under one<a name="line.2"></a>
<FONT color="green">003</FONT>     * or more contributor license agreements.  See the NOTICE file<a name="line.3"></a>
<FONT color="green">004</FONT>     * distributed with this work for additional information<a name="line.4"></a>
<FONT color="green">005</FONT>     * regarding copyright ownership.  The ASF licenses this file<a name="line.5"></a>
<FONT color="green">006</FONT>     * to you under the Apache License, Version 2.0 (the<a name="line.6"></a>
<FONT color="green">007</FONT>     * "License"); you may not use this file except in compliance<a name="line.7"></a>
<FONT color="green">008</FONT>     * with the License.  You may obtain a copy of the License at<a name="line.8"></a>
<FONT color="green">009</FONT>     *<a name="line.9"></a>
<FONT color="green">010</FONT>     *     http://www.apache.org/licenses/LICENSE-2.0<a name="line.10"></a>
<FONT color="green">011</FONT>     *<a name="line.11"></a>
<FONT color="green">012</FONT>     * Unless required by applicable law or agreed to in writing, software<a name="line.12"></a>
<FONT color="green">013</FONT>     * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.13"></a>
<FONT color="green">014</FONT>     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.14"></a>
<FONT color="green">015</FONT>     * See the License for the specific language governing permissions and<a name="line.15"></a>
<FONT color="green">016</FONT>     * limitations under the License.<a name="line.16"></a>
<FONT color="green">017</FONT>     */<a name="line.17"></a>
<FONT color="green">018</FONT>    <a name="line.18"></a>
<FONT color="green">019</FONT>    package org.apache.hadoop.mapreduce.lib.db;<a name="line.19"></a>
<FONT color="green">020</FONT>    <a name="line.20"></a>
<FONT color="green">021</FONT>    import java.io.DataInput;<a name="line.21"></a>
<FONT color="green">022</FONT>    import java.io.DataOutput;<a name="line.22"></a>
<FONT color="green">023</FONT>    import java.io.IOException;<a name="line.23"></a>
<FONT color="green">024</FONT>    import java.sql.Connection;<a name="line.24"></a>
<FONT color="green">025</FONT>    import java.sql.DatabaseMetaData;<a name="line.25"></a>
<FONT color="green">026</FONT>    import java.sql.PreparedStatement;<a name="line.26"></a>
<FONT color="green">027</FONT>    import java.sql.ResultSet;<a name="line.27"></a>
<FONT color="green">028</FONT>    import java.sql.SQLException;<a name="line.28"></a>
<FONT color="green">029</FONT>    import java.sql.Statement;<a name="line.29"></a>
<FONT color="green">030</FONT>    import java.sql.Types;<a name="line.30"></a>
<FONT color="green">031</FONT>    import java.util.ArrayList;<a name="line.31"></a>
<FONT color="green">032</FONT>    import java.util.List;<a name="line.32"></a>
<FONT color="green">033</FONT>    <a name="line.33"></a>
<FONT color="green">034</FONT>    import org.apache.commons.logging.Log;<a name="line.34"></a>
<FONT color="green">035</FONT>    import org.apache.commons.logging.LogFactory;<a name="line.35"></a>
<FONT color="green">036</FONT>    <a name="line.36"></a>
<FONT color="green">037</FONT>    import org.apache.hadoop.io.LongWritable;<a name="line.37"></a>
<FONT color="green">038</FONT>    import org.apache.hadoop.io.Text;<a name="line.38"></a>
<FONT color="green">039</FONT>    import org.apache.hadoop.io.Writable;<a name="line.39"></a>
<FONT color="green">040</FONT>    import org.apache.hadoop.mapreduce.InputFormat;<a name="line.40"></a>
<FONT color="green">041</FONT>    import org.apache.hadoop.mapreduce.InputSplit;<a name="line.41"></a>
<FONT color="green">042</FONT>    import org.apache.hadoop.mapreduce.Job;<a name="line.42"></a>
<FONT color="green">043</FONT>    import org.apache.hadoop.mapreduce.JobContext;<a name="line.43"></a>
<FONT color="green">044</FONT>    import org.apache.hadoop.mapreduce.MRJobConfig;<a name="line.44"></a>
<FONT color="green">045</FONT>    import org.apache.hadoop.mapreduce.RecordReader;<a name="line.45"></a>
<FONT color="green">046</FONT>    import org.apache.hadoop.mapreduce.TaskAttemptContext;<a name="line.46"></a>
<FONT color="green">047</FONT>    import org.apache.hadoop.util.ReflectionUtils;<a name="line.47"></a>
<FONT color="green">048</FONT>    import org.apache.hadoop.classification.InterfaceAudience;<a name="line.48"></a>
<FONT color="green">049</FONT>    import org.apache.hadoop.classification.InterfaceStability;<a name="line.49"></a>
<FONT color="green">050</FONT>    import org.apache.hadoop.conf.Configurable;<a name="line.50"></a>
<FONT color="green">051</FONT>    import org.apache.hadoop.conf.Configuration;<a name="line.51"></a>
<FONT color="green">052</FONT>    <a name="line.52"></a>
<FONT color="green">053</FONT>    /**<a name="line.53"></a>
<FONT color="green">054</FONT>     * A InputFormat that reads input data from an SQL table.<a name="line.54"></a>
<FONT color="green">055</FONT>     * Operates like DBInputFormat, but instead of using LIMIT and OFFSET to demarcate<a name="line.55"></a>
<FONT color="green">056</FONT>     * splits, it tries to generate WHERE clauses which separate the data into roughly<a name="line.56"></a>
<FONT color="green">057</FONT>     * equivalent shards.<a name="line.57"></a>
<FONT color="green">058</FONT>     */<a name="line.58"></a>
<FONT color="green">059</FONT>    @InterfaceAudience.Public<a name="line.59"></a>
<FONT color="green">060</FONT>    @InterfaceStability.Evolving<a name="line.60"></a>
<FONT color="green">061</FONT>    public class DataDrivenDBInputFormat&lt;T extends DBWritable&gt;<a name="line.61"></a>
<FONT color="green">062</FONT>        extends DBInputFormat&lt;T&gt; implements Configurable {<a name="line.62"></a>
<FONT color="green">063</FONT>    <a name="line.63"></a>
<FONT color="green">064</FONT>      private static final Log LOG = LogFactory.getLog(DataDrivenDBInputFormat.class);<a name="line.64"></a>
<FONT color="green">065</FONT>    <a name="line.65"></a>
<FONT color="green">066</FONT>      /** If users are providing their own query, the following string is expected to<a name="line.66"></a>
<FONT color="green">067</FONT>          appear in the WHERE clause, which will be substituted with a pair of conditions<a name="line.67"></a>
<FONT color="green">068</FONT>          on the input to allow input splits to parallelise the import. */<a name="line.68"></a>
<FONT color="green">069</FONT>      public static final String SUBSTITUTE_TOKEN = "$CONDITIONS";<a name="line.69"></a>
<FONT color="green">070</FONT>    <a name="line.70"></a>
<FONT color="green">071</FONT>      /**<a name="line.71"></a>
<FONT color="green">072</FONT>       * A InputSplit that spans a set of rows<a name="line.72"></a>
<FONT color="green">073</FONT>       */<a name="line.73"></a>
<FONT color="green">074</FONT>      @InterfaceStability.Evolving<a name="line.74"></a>
<FONT color="green">075</FONT>      public static class DataDrivenDBInputSplit extends DBInputFormat.DBInputSplit {<a name="line.75"></a>
<FONT color="green">076</FONT>    <a name="line.76"></a>
<FONT color="green">077</FONT>        private String lowerBoundClause;<a name="line.77"></a>
<FONT color="green">078</FONT>        private String upperBoundClause;<a name="line.78"></a>
<FONT color="green">079</FONT>    <a name="line.79"></a>
<FONT color="green">080</FONT>        /**<a name="line.80"></a>
<FONT color="green">081</FONT>         * Default Constructor<a name="line.81"></a>
<FONT color="green">082</FONT>         */<a name="line.82"></a>
<FONT color="green">083</FONT>        public DataDrivenDBInputSplit() {<a name="line.83"></a>
<FONT color="green">084</FONT>        }<a name="line.84"></a>
<FONT color="green">085</FONT>    <a name="line.85"></a>
<FONT color="green">086</FONT>        /**<a name="line.86"></a>
<FONT color="green">087</FONT>         * Convenience Constructor<a name="line.87"></a>
<FONT color="green">088</FONT>         * @param lower the string to be put in the WHERE clause to guard on the 'lower' end<a name="line.88"></a>
<FONT color="green">089</FONT>         * @param upper the string to be put in the WHERE clause to guard on the 'upper' end<a name="line.89"></a>
<FONT color="green">090</FONT>         */<a name="line.90"></a>
<FONT color="green">091</FONT>        public DataDrivenDBInputSplit(final String lower, final String upper) {<a name="line.91"></a>
<FONT color="green">092</FONT>          this.lowerBoundClause = lower;<a name="line.92"></a>
<FONT color="green">093</FONT>          this.upperBoundClause = upper;<a name="line.93"></a>
<FONT color="green">094</FONT>        }<a name="line.94"></a>
<FONT color="green">095</FONT>    <a name="line.95"></a>
<FONT color="green">096</FONT>    <a name="line.96"></a>
<FONT color="green">097</FONT>        /**<a name="line.97"></a>
<FONT color="green">098</FONT>         * @return The total row count in this split<a name="line.98"></a>
<FONT color="green">099</FONT>         */<a name="line.99"></a>
<FONT color="green">100</FONT>        public long getLength() throws IOException {<a name="line.100"></a>
<FONT color="green">101</FONT>          return 0; // unfortunately, we don't know this.<a name="line.101"></a>
<FONT color="green">102</FONT>        }<a name="line.102"></a>
<FONT color="green">103</FONT>    <a name="line.103"></a>
<FONT color="green">104</FONT>        /** {@inheritDoc} */<a name="line.104"></a>
<FONT color="green">105</FONT>        public void readFields(DataInput input) throws IOException {<a name="line.105"></a>
<FONT color="green">106</FONT>          this.lowerBoundClause = Text.readString(input);<a name="line.106"></a>
<FONT color="green">107</FONT>          this.upperBoundClause = Text.readString(input);<a name="line.107"></a>
<FONT color="green">108</FONT>        }<a name="line.108"></a>
<FONT color="green">109</FONT>    <a name="line.109"></a>
<FONT color="green">110</FONT>        /** {@inheritDoc} */<a name="line.110"></a>
<FONT color="green">111</FONT>        public void write(DataOutput output) throws IOException {<a name="line.111"></a>
<FONT color="green">112</FONT>          Text.writeString(output, this.lowerBoundClause);<a name="line.112"></a>
<FONT color="green">113</FONT>          Text.writeString(output, this.upperBoundClause);<a name="line.113"></a>
<FONT color="green">114</FONT>        }<a name="line.114"></a>
<FONT color="green">115</FONT>    <a name="line.115"></a>
<FONT color="green">116</FONT>        public String getLowerClause() {<a name="line.116"></a>
<FONT color="green">117</FONT>          return lowerBoundClause;<a name="line.117"></a>
<FONT color="green">118</FONT>        }<a name="line.118"></a>
<FONT color="green">119</FONT>    <a name="line.119"></a>
<FONT color="green">120</FONT>        public String getUpperClause() {<a name="line.120"></a>
<FONT color="green">121</FONT>          return upperBoundClause;<a name="line.121"></a>
<FONT color="green">122</FONT>        }<a name="line.122"></a>
<FONT color="green">123</FONT>      }<a name="line.123"></a>
<FONT color="green">124</FONT>    <a name="line.124"></a>
<FONT color="green">125</FONT>      /**<a name="line.125"></a>
<FONT color="green">126</FONT>       * @return the DBSplitter implementation to use to divide the table/query into InputSplits.<a name="line.126"></a>
<FONT color="green">127</FONT>       */<a name="line.127"></a>
<FONT color="green">128</FONT>      protected DBSplitter getSplitter(int sqlDataType) {<a name="line.128"></a>
<FONT color="green">129</FONT>        switch (sqlDataType) {<a name="line.129"></a>
<FONT color="green">130</FONT>        case Types.NUMERIC:<a name="line.130"></a>
<FONT color="green">131</FONT>        case Types.DECIMAL:<a name="line.131"></a>
<FONT color="green">132</FONT>          return new BigDecimalSplitter();<a name="line.132"></a>
<FONT color="green">133</FONT>    <a name="line.133"></a>
<FONT color="green">134</FONT>        case Types.BIT:<a name="line.134"></a>
<FONT color="green">135</FONT>        case Types.BOOLEAN:<a name="line.135"></a>
<FONT color="green">136</FONT>          return new BooleanSplitter();<a name="line.136"></a>
<FONT color="green">137</FONT>    <a name="line.137"></a>
<FONT color="green">138</FONT>        case Types.INTEGER:<a name="line.138"></a>
<FONT color="green">139</FONT>        case Types.TINYINT:<a name="line.139"></a>
<FONT color="green">140</FONT>        case Types.SMALLINT:<a name="line.140"></a>
<FONT color="green">141</FONT>        case Types.BIGINT:<a name="line.141"></a>
<FONT color="green">142</FONT>          return new IntegerSplitter();<a name="line.142"></a>
<FONT color="green">143</FONT>    <a name="line.143"></a>
<FONT color="green">144</FONT>        case Types.REAL:<a name="line.144"></a>
<FONT color="green">145</FONT>        case Types.FLOAT:<a name="line.145"></a>
<FONT color="green">146</FONT>        case Types.DOUBLE:<a name="line.146"></a>
<FONT color="green">147</FONT>          return new FloatSplitter();<a name="line.147"></a>
<FONT color="green">148</FONT>    <a name="line.148"></a>
<FONT color="green">149</FONT>        case Types.CHAR:<a name="line.149"></a>
<FONT color="green">150</FONT>        case Types.VARCHAR:<a name="line.150"></a>
<FONT color="green">151</FONT>        case Types.LONGVARCHAR:<a name="line.151"></a>
<FONT color="green">152</FONT>          return new TextSplitter();<a name="line.152"></a>
<FONT color="green">153</FONT>    <a name="line.153"></a>
<FONT color="green">154</FONT>        case Types.DATE:<a name="line.154"></a>
<FONT color="green">155</FONT>        case Types.TIME:<a name="line.155"></a>
<FONT color="green">156</FONT>        case Types.TIMESTAMP:<a name="line.156"></a>
<FONT color="green">157</FONT>          return new DateSplitter();<a name="line.157"></a>
<FONT color="green">158</FONT>    <a name="line.158"></a>
<FONT color="green">159</FONT>        default:<a name="line.159"></a>
<FONT color="green">160</FONT>          // TODO: Support BINARY, VARBINARY, LONGVARBINARY, DISTINCT, CLOB, BLOB, ARRAY<a name="line.160"></a>
<FONT color="green">161</FONT>          // STRUCT, REF, DATALINK, and JAVA_OBJECT.<a name="line.161"></a>
<FONT color="green">162</FONT>          return null;<a name="line.162"></a>
<FONT color="green">163</FONT>        }<a name="line.163"></a>
<FONT color="green">164</FONT>      }<a name="line.164"></a>
<FONT color="green">165</FONT>    <a name="line.165"></a>
<FONT color="green">166</FONT>      /** {@inheritDoc} */<a name="line.166"></a>
<FONT color="green">167</FONT>      public List&lt;InputSplit&gt; getSplits(JobContext job) throws IOException {<a name="line.167"></a>
<FONT color="green">168</FONT>    <a name="line.168"></a>
<FONT color="green">169</FONT>        int targetNumTasks = job.getConfiguration().getInt(MRJobConfig.NUM_MAPS, 1);<a name="line.169"></a>
<FONT color="green">170</FONT>        if (1 == targetNumTasks) {<a name="line.170"></a>
<FONT color="green">171</FONT>          // There's no need to run a bounding vals query; just return a split<a name="line.171"></a>
<FONT color="green">172</FONT>          // that separates nothing. This can be considerably more optimal for a<a name="line.172"></a>
<FONT color="green">173</FONT>          // large table with no index.<a name="line.173"></a>
<FONT color="green">174</FONT>          List&lt;InputSplit&gt; singletonSplit = new ArrayList&lt;InputSplit&gt;();<a name="line.174"></a>
<FONT color="green">175</FONT>          singletonSplit.add(new DataDrivenDBInputSplit("1=1", "1=1"));<a name="line.175"></a>
<FONT color="green">176</FONT>          return singletonSplit;<a name="line.176"></a>
<FONT color="green">177</FONT>        }<a name="line.177"></a>
<FONT color="green">178</FONT>    <a name="line.178"></a>
<FONT color="green">179</FONT>        ResultSet results = null;<a name="line.179"></a>
<FONT color="green">180</FONT>        Statement statement = null;<a name="line.180"></a>
<FONT color="green">181</FONT>        Connection connection = getConnection();<a name="line.181"></a>
<FONT color="green">182</FONT>        try {<a name="line.182"></a>
<FONT color="green">183</FONT>          statement = connection.createStatement();<a name="line.183"></a>
<FONT color="green">184</FONT>    <a name="line.184"></a>
<FONT color="green">185</FONT>          results = statement.executeQuery(getBoundingValsQuery());<a name="line.185"></a>
<FONT color="green">186</FONT>          results.next();<a name="line.186"></a>
<FONT color="green">187</FONT>    <a name="line.187"></a>
<FONT color="green">188</FONT>          // Based on the type of the results, use a different mechanism<a name="line.188"></a>
<FONT color="green">189</FONT>          // for interpolating split points (i.e., numeric splits, text splits,<a name="line.189"></a>
<FONT color="green">190</FONT>          // dates, etc.)<a name="line.190"></a>
<FONT color="green">191</FONT>          int sqlDataType = results.getMetaData().getColumnType(1);<a name="line.191"></a>
<FONT color="green">192</FONT>          DBSplitter splitter = getSplitter(sqlDataType);<a name="line.192"></a>
<FONT color="green">193</FONT>          if (null == splitter) {<a name="line.193"></a>
<FONT color="green">194</FONT>            throw new IOException("Unknown SQL data type: " + sqlDataType);<a name="line.194"></a>
<FONT color="green">195</FONT>          }<a name="line.195"></a>
<FONT color="green">196</FONT>    <a name="line.196"></a>
<FONT color="green">197</FONT>          return splitter.split(job.getConfiguration(), results, getDBConf().getInputOrderBy());<a name="line.197"></a>
<FONT color="green">198</FONT>        } catch (SQLException e) {<a name="line.198"></a>
<FONT color="green">199</FONT>          throw new IOException(e.getMessage());<a name="line.199"></a>
<FONT color="green">200</FONT>        } finally {<a name="line.200"></a>
<FONT color="green">201</FONT>          // More-or-less ignore SQL exceptions here, but log in case we need it.<a name="line.201"></a>
<FONT color="green">202</FONT>          try {<a name="line.202"></a>
<FONT color="green">203</FONT>            if (null != results) {<a name="line.203"></a>
<FONT color="green">204</FONT>              results.close();<a name="line.204"></a>
<FONT color="green">205</FONT>            }<a name="line.205"></a>
<FONT color="green">206</FONT>          } catch (SQLException se) {<a name="line.206"></a>
<FONT color="green">207</FONT>            LOG.debug("SQLException closing resultset: " + se.toString());<a name="line.207"></a>
<FONT color="green">208</FONT>          }<a name="line.208"></a>
<FONT color="green">209</FONT>    <a name="line.209"></a>
<FONT color="green">210</FONT>          try {<a name="line.210"></a>
<FONT color="green">211</FONT>            if (null != statement) {<a name="line.211"></a>
<FONT color="green">212</FONT>              statement.close();<a name="line.212"></a>
<FONT color="green">213</FONT>            }<a name="line.213"></a>
<FONT color="green">214</FONT>          } catch (SQLException se) {<a name="line.214"></a>
<FONT color="green">215</FONT>            LOG.debug("SQLException closing statement: " + se.toString());<a name="line.215"></a>
<FONT color="green">216</FONT>          }<a name="line.216"></a>
<FONT color="green">217</FONT>    <a name="line.217"></a>
<FONT color="green">218</FONT>          try {<a name="line.218"></a>
<FONT color="green">219</FONT>            connection.commit();<a name="line.219"></a>
<FONT color="green">220</FONT>            closeConnection();<a name="line.220"></a>
<FONT color="green">221</FONT>          } catch (SQLException se) {<a name="line.221"></a>
<FONT color="green">222</FONT>            LOG.debug("SQLException committing split transaction: " + se.toString());<a name="line.222"></a>
<FONT color="green">223</FONT>          }<a name="line.223"></a>
<FONT color="green">224</FONT>        }<a name="line.224"></a>
<FONT color="green">225</FONT>      }<a name="line.225"></a>
<FONT color="green">226</FONT>    <a name="line.226"></a>
<FONT color="green">227</FONT>      /**<a name="line.227"></a>
<FONT color="green">228</FONT>       * @return a query which returns the minimum and maximum values for<a name="line.228"></a>
<FONT color="green">229</FONT>       * the order-by column.<a name="line.229"></a>
<FONT color="green">230</FONT>       *<a name="line.230"></a>
<FONT color="green">231</FONT>       * The min value should be in the first column, and the<a name="line.231"></a>
<FONT color="green">232</FONT>       * max value should be in the second column of the results.<a name="line.232"></a>
<FONT color="green">233</FONT>       */<a name="line.233"></a>
<FONT color="green">234</FONT>      protected String getBoundingValsQuery() {<a name="line.234"></a>
<FONT color="green">235</FONT>        // If the user has provided a query, use that instead.<a name="line.235"></a>
<FONT color="green">236</FONT>        String userQuery = getDBConf().getInputBoundingQuery();<a name="line.236"></a>
<FONT color="green">237</FONT>        if (null != userQuery) {<a name="line.237"></a>
<FONT color="green">238</FONT>          return userQuery;<a name="line.238"></a>
<FONT color="green">239</FONT>        }<a name="line.239"></a>
<FONT color="green">240</FONT>    <a name="line.240"></a>
<FONT color="green">241</FONT>        // Auto-generate one based on the table name we've been provided with.<a name="line.241"></a>
<FONT color="green">242</FONT>        StringBuilder query = new StringBuilder();<a name="line.242"></a>
<FONT color="green">243</FONT>    <a name="line.243"></a>
<FONT color="green">244</FONT>        String splitCol = getDBConf().getInputOrderBy();<a name="line.244"></a>
<FONT color="green">245</FONT>        query.append("SELECT MIN(").append(splitCol).append("), ");<a name="line.245"></a>
<FONT color="green">246</FONT>        query.append("MAX(").append(splitCol).append(") FROM ");<a name="line.246"></a>
<FONT color="green">247</FONT>        query.append(getDBConf().getInputTableName());<a name="line.247"></a>
<FONT color="green">248</FONT>        String conditions = getDBConf().getInputConditions();<a name="line.248"></a>
<FONT color="green">249</FONT>        if (null != conditions) {<a name="line.249"></a>
<FONT color="green">250</FONT>          query.append(" WHERE ( " + conditions + " )");<a name="line.250"></a>
<FONT color="green">251</FONT>        }<a name="line.251"></a>
<FONT color="green">252</FONT>    <a name="line.252"></a>
<FONT color="green">253</FONT>        return query.toString();<a name="line.253"></a>
<FONT color="green">254</FONT>      }<a name="line.254"></a>
<FONT color="green">255</FONT>    <a name="line.255"></a>
<FONT color="green">256</FONT>      /** Set the user-defined bounding query to use with a user-defined query.<a name="line.256"></a>
<FONT color="green">257</FONT>          This *must* include the substring "$CONDITIONS"<a name="line.257"></a>
<FONT color="green">258</FONT>          (DataDrivenDBInputFormat.SUBSTITUTE_TOKEN) inside the WHERE clause,<a name="line.258"></a>
<FONT color="green">259</FONT>          so that DataDrivenDBInputFormat knows where to insert split clauses.<a name="line.259"></a>
<FONT color="green">260</FONT>          e.g., "SELECT foo FROM mytable WHERE $CONDITIONS"<a name="line.260"></a>
<FONT color="green">261</FONT>          This will be expanded to something like:<a name="line.261"></a>
<FONT color="green">262</FONT>            SELECT foo FROM mytable WHERE (id &amp;gt; 100) AND (id &amp;lt; 250)<a name="line.262"></a>
<FONT color="green">263</FONT>          inside each split.<a name="line.263"></a>
<FONT color="green">264</FONT>        */<a name="line.264"></a>
<FONT color="green">265</FONT>      public static void setBoundingQuery(Configuration conf, String query) {<a name="line.265"></a>
<FONT color="green">266</FONT>        if (null != query) {<a name="line.266"></a>
<FONT color="green">267</FONT>          // If the user's settng a query, warn if they don't allow conditions.<a name="line.267"></a>
<FONT color="green">268</FONT>          if (query.indexOf(SUBSTITUTE_TOKEN) == -1) {<a name="line.268"></a>
<FONT color="green">269</FONT>            LOG.warn("Could not find " + SUBSTITUTE_TOKEN + " token in query: " + query<a name="line.269"></a>
<FONT color="green">270</FONT>                + "; splits may not partition data.");<a name="line.270"></a>
<FONT color="green">271</FONT>          }<a name="line.271"></a>
<FONT color="green">272</FONT>        }<a name="line.272"></a>
<FONT color="green">273</FONT>    <a name="line.273"></a>
<FONT color="green">274</FONT>        conf.set(DBConfiguration.INPUT_BOUNDING_QUERY, query);<a name="line.274"></a>
<FONT color="green">275</FONT>      }<a name="line.275"></a>
<FONT color="green">276</FONT>    <a name="line.276"></a>
<FONT color="green">277</FONT>      protected RecordReader&lt;LongWritable, T&gt; createDBRecordReader(DBInputSplit split,<a name="line.277"></a>
<FONT color="green">278</FONT>          Configuration conf) throws IOException {<a name="line.278"></a>
<FONT color="green">279</FONT>    <a name="line.279"></a>
<FONT color="green">280</FONT>        DBConfiguration dbConf = getDBConf();<a name="line.280"></a>
<FONT color="green">281</FONT>        @SuppressWarnings("unchecked")<a name="line.281"></a>
<FONT color="green">282</FONT>        Class&lt;T&gt; inputClass = (Class&lt;T&gt;) (dbConf.getInputClass());<a name="line.282"></a>
<FONT color="green">283</FONT>        String dbProductName = getDBProductName();<a name="line.283"></a>
<FONT color="green">284</FONT>    <a name="line.284"></a>
<FONT color="green">285</FONT>        LOG.debug("Creating db record reader for db product: " + dbProductName);<a name="line.285"></a>
<FONT color="green">286</FONT>    <a name="line.286"></a>
<FONT color="green">287</FONT>        try {<a name="line.287"></a>
<FONT color="green">288</FONT>          // use database product name to determine appropriate record reader.<a name="line.288"></a>
<FONT color="green">289</FONT>          if (dbProductName.startsWith("MYSQL")) {<a name="line.289"></a>
<FONT color="green">290</FONT>            // use MySQL-specific db reader.<a name="line.290"></a>
<FONT color="green">291</FONT>            return new MySQLDataDrivenDBRecordReader&lt;T&gt;(split, inputClass,<a name="line.291"></a>
<FONT color="green">292</FONT>                conf, getConnection(), dbConf, dbConf.getInputConditions(),<a name="line.292"></a>
<FONT color="green">293</FONT>                dbConf.getInputFieldNames(), dbConf.getInputTableName());<a name="line.293"></a>
<FONT color="green">294</FONT>          } else {<a name="line.294"></a>
<FONT color="green">295</FONT>            // Generic reader.<a name="line.295"></a>
<FONT color="green">296</FONT>            return new DataDrivenDBRecordReader&lt;T&gt;(split, inputClass,<a name="line.296"></a>
<FONT color="green">297</FONT>                conf, getConnection(), dbConf, dbConf.getInputConditions(),<a name="line.297"></a>
<FONT color="green">298</FONT>                dbConf.getInputFieldNames(), dbConf.getInputTableName(),<a name="line.298"></a>
<FONT color="green">299</FONT>                dbProductName);<a name="line.299"></a>
<FONT color="green">300</FONT>          }<a name="line.300"></a>
<FONT color="green">301</FONT>        } catch (SQLException ex) {<a name="line.301"></a>
<FONT color="green">302</FONT>          throw new IOException(ex.getMessage());<a name="line.302"></a>
<FONT color="green">303</FONT>        }<a name="line.303"></a>
<FONT color="green">304</FONT>      }<a name="line.304"></a>
<FONT color="green">305</FONT>    <a name="line.305"></a>
<FONT color="green">306</FONT>      // Configuration methods override superclass to ensure that the proper<a name="line.306"></a>
<FONT color="green">307</FONT>      // DataDrivenDBInputFormat gets used.<a name="line.307"></a>
<FONT color="green">308</FONT>    <a name="line.308"></a>
<FONT color="green">309</FONT>      /** Note that the "orderBy" column is called the "splitBy" in this version.<a name="line.309"></a>
<FONT color="green">310</FONT>        * We reuse the same field, but it's not strictly ordering it -- just partitioning<a name="line.310"></a>
<FONT color="green">311</FONT>        * the results.<a name="line.311"></a>
<FONT color="green">312</FONT>        */<a name="line.312"></a>
<FONT color="green">313</FONT>      public static void setInput(Job job, <a name="line.313"></a>
<FONT color="green">314</FONT>          Class&lt;? extends DBWritable&gt; inputClass,<a name="line.314"></a>
<FONT color="green">315</FONT>          String tableName,String conditions, <a name="line.315"></a>
<FONT color="green">316</FONT>          String splitBy, String... fieldNames) {<a name="line.316"></a>
<FONT color="green">317</FONT>        DBInputFormat.setInput(job, inputClass, tableName, conditions, splitBy, fieldNames);<a name="line.317"></a>
<FONT color="green">318</FONT>        job.setInputFormatClass(DataDrivenDBInputFormat.class);<a name="line.318"></a>
<FONT color="green">319</FONT>      }<a name="line.319"></a>
<FONT color="green">320</FONT>    <a name="line.320"></a>
<FONT color="green">321</FONT>      /** setInput() takes a custom query and a separate "bounding query" to use<a name="line.321"></a>
<FONT color="green">322</FONT>          instead of the custom "count query" used by DBInputFormat.<a name="line.322"></a>
<FONT color="green">323</FONT>        */<a name="line.323"></a>
<FONT color="green">324</FONT>      public static void setInput(Job job,<a name="line.324"></a>
<FONT color="green">325</FONT>          Class&lt;? extends DBWritable&gt; inputClass,<a name="line.325"></a>
<FONT color="green">326</FONT>          String inputQuery, String inputBoundingQuery) {<a name="line.326"></a>
<FONT color="green">327</FONT>        DBInputFormat.setInput(job, inputClass, inputQuery, "");<a name="line.327"></a>
<FONT color="green">328</FONT>        job.getConfiguration().set(DBConfiguration.INPUT_BOUNDING_QUERY, inputBoundingQuery);<a name="line.328"></a>
<FONT color="green">329</FONT>        job.setInputFormatClass(DataDrivenDBInputFormat.class);<a name="line.329"></a>
<FONT color="green">330</FONT>      }<a name="line.330"></a>
<FONT color="green">331</FONT>    }<a name="line.331"></a>




























































</PRE>
</BODY>
</HTML>
