You are viewing a plain text version of this content. The canonical link for it is here.
Posted to site-dev@james.apache.org by rd...@apache.org on 2011/05/08 18:41:14 UTC

svn commit: r1100766 [5/7] - in /james/site/trunk/www/mailet/ai: ./ apidocs/ apidocs/org/ apidocs/org/apache/ apidocs/org/apache/james/ apidocs/org/apache/james/ai/ apidocs/org/apache/james/ai/classic/ apidocs/org/apache/james/ai/classic/class-use/ api...

Added: james/site/trunk/www/mailet/ai/apidocs/src-html/org/apache/james/ai/classic/BayesianAnalysisFeeder.html
URL: http://svn.apache.org/viewvc/james/site/trunk/www/mailet/ai/apidocs/src-html/org/apache/james/ai/classic/BayesianAnalysisFeeder.html?rev=1100766&view=auto
==============================================================================
--- james/site/trunk/www/mailet/ai/apidocs/src-html/org/apache/james/ai/classic/BayesianAnalysisFeeder.html (added)
+++ james/site/trunk/www/mailet/ai/apidocs/src-html/org/apache/james/ai/classic/BayesianAnalysisFeeder.html Sun May  8 16:41:13 2011
@@ -0,0 +1,410 @@
+<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,   *<a name="line.12"></a>
+<FONT color="green">013</FONT>     * software distributed under the License is distributed on an  *<a name="line.13"></a>
+<FONT color="green">014</FONT>     * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY       *<a name="line.14"></a>
+<FONT color="green">015</FONT>     * KIND, either express or implied.  See the License for the    *<a name="line.15"></a>
+<FONT color="green">016</FONT>     * specific language governing permissions and limitations      *<a name="line.16"></a>
+<FONT color="green">017</FONT>     * under the License.                                           *<a name="line.17"></a>
+<FONT color="green">018</FONT>     ****************************************************************/<a name="line.18"></a>
+<FONT color="green">019</FONT>    <a name="line.19"></a>
+<FONT color="green">020</FONT>    package org.apache.james.ai.classic;<a name="line.20"></a>
+<FONT color="green">021</FONT>    <a name="line.21"></a>
+<FONT color="green">022</FONT>    import java.io.BufferedReader;<a name="line.22"></a>
+<FONT color="green">023</FONT>    import java.io.ByteArrayOutputStream;<a name="line.23"></a>
+<FONT color="green">024</FONT>    import java.io.StringReader;<a name="line.24"></a>
+<FONT color="green">025</FONT>    import java.sql.Connection;<a name="line.25"></a>
+<FONT color="green">026</FONT>    import java.util.Enumeration;<a name="line.26"></a>
+<FONT color="green">027</FONT>    <a name="line.27"></a>
+<FONT color="green">028</FONT>    import javax.annotation.Resource;<a name="line.28"></a>
+<FONT color="green">029</FONT>    import javax.mail.Header;<a name="line.29"></a>
+<FONT color="green">030</FONT>    import javax.mail.MessagingException;<a name="line.30"></a>
+<FONT color="green">031</FONT>    import javax.mail.internet.MimeMessage;<a name="line.31"></a>
+<FONT color="green">032</FONT>    import javax.sql.DataSource;<a name="line.32"></a>
+<FONT color="green">033</FONT>    <a name="line.33"></a>
+<FONT color="green">034</FONT>    import org.apache.mailet.Mail;<a name="line.34"></a>
+<FONT color="green">035</FONT>    import org.apache.mailet.base.GenericMailet;<a name="line.35"></a>
+<FONT color="green">036</FONT>    <a name="line.36"></a>
+<FONT color="green">037</FONT>    /**<a name="line.37"></a>
+<FONT color="green">038</FONT>     * &lt;p&gt;<a name="line.38"></a>
+<FONT color="green">039</FONT>     * Feeds ham OR spam messages to train the {@link BayesianAnalysis} mailet.<a name="line.39"></a>
+<FONT color="green">040</FONT>     * &lt;/p&gt;<a name="line.40"></a>
+<FONT color="green">041</FONT>     * <a name="line.41"></a>
+<FONT color="green">042</FONT>     * &lt;p&gt;<a name="line.42"></a>
+<FONT color="green">043</FONT>     * The new token frequencies will be stored in a JDBC database.<a name="line.43"></a>
+<FONT color="green">044</FONT>     * &lt;/p&gt;<a name="line.44"></a>
+<FONT color="green">045</FONT>     * <a name="line.45"></a>
+<FONT color="green">046</FONT>     * &lt;p&gt;<a name="line.46"></a>
+<FONT color="green">047</FONT>     * Sample configuration:<a name="line.47"></a>
+<FONT color="green">048</FONT>     * &lt;/p&gt;<a name="line.48"></a>
+<FONT color="green">049</FONT>     * <a name="line.49"></a>
+<FONT color="green">050</FONT>     * &lt;pre&gt;<a name="line.50"></a>
+<FONT color="green">051</FONT>     * &lt;code&gt;<a name="line.51"></a>
+<FONT color="green">052</FONT>     * &amp;lt;processor name="root"&amp;gt;<a name="line.52"></a>
+<FONT color="green">053</FONT>     * <a name="line.53"></a>
+<FONT color="green">054</FONT>     *   &amp;lt;mailet match="RecipientIs=not.spam@thisdomain.com" class="BayesianAnalysisFeeder"&amp;gt;<a name="line.54"></a>
+<FONT color="green">055</FONT>     *     &amp;lt;repositoryPath&amp;gt; db://maildb &amp;lt;/repositoryPath&amp;gt;<a name="line.55"></a>
+<FONT color="green">056</FONT>     *     &amp;lt;feedType&amp;gt;ham&amp;lt;/feedType&amp;gt;<a name="line.56"></a>
+<FONT color="green">057</FONT>     *     &amp;lt;!--<a name="line.57"></a>
+<FONT color="green">058</FONT>     *       Set this to the maximum message size (in bytes) that a message may have<a name="line.58"></a>
+<FONT color="green">059</FONT>     *       to be analyzed (default is 100000).<a name="line.59"></a>
+<FONT color="green">060</FONT>     *     --&amp;gt;<a name="line.60"></a>
+<FONT color="green">061</FONT>     *     &amp;lt;maxSize&amp;gt;100000&amp;lt;/maxSize&amp;gt;<a name="line.61"></a>
+<FONT color="green">062</FONT>     *   &amp;lt;/mailet&amp;gt;<a name="line.62"></a>
+<FONT color="green">063</FONT>     * <a name="line.63"></a>
+<FONT color="green">064</FONT>     *   &amp;lt;mailet match="RecipientIs=spam@thisdomain.com" class="BayesianAnalysisFeeder"&amp;gt;<a name="line.64"></a>
+<FONT color="green">065</FONT>     *     &amp;lt;repositoryPath&amp;gt; db://maildb &amp;lt;/repositoryPath&amp;gt;<a name="line.65"></a>
+<FONT color="green">066</FONT>     *     &amp;lt;feedType&amp;gt;spam&amp;lt;/feedType&amp;gt;<a name="line.66"></a>
+<FONT color="green">067</FONT>     *     &amp;lt;!--<a name="line.67"></a>
+<FONT color="green">068</FONT>     *       Set this to the maximum message size (in bytes) that a message may have<a name="line.68"></a>
+<FONT color="green">069</FONT>     *       to be analyzed (default is 100000).<a name="line.69"></a>
+<FONT color="green">070</FONT>     *     --&amp;gt;<a name="line.70"></a>
+<FONT color="green">071</FONT>     *     &amp;lt;maxSize&amp;gt;100000&amp;lt;/maxSize&amp;gt;<a name="line.71"></a>
+<FONT color="green">072</FONT>     *   &amp;lt;/mailet&amp;gt;<a name="line.72"></a>
+<FONT color="green">073</FONT>     * <a name="line.73"></a>
+<FONT color="green">074</FONT>     * &amp;lt;processor&amp;gt;<a name="line.74"></a>
+<FONT color="green">075</FONT>     * &lt;/code&gt;<a name="line.75"></a>
+<FONT color="green">076</FONT>     * &lt;/pre&gt;<a name="line.76"></a>
+<FONT color="green">077</FONT>     * <a name="line.77"></a>
+<FONT color="green">078</FONT>     * &lt;p&gt;<a name="line.78"></a>
+<FONT color="green">079</FONT>     * The previous example will allow the user to send messages to the server and<a name="line.79"></a>
+<FONT color="green">080</FONT>     * use the recipient email address as the indicator for whether the message is<a name="line.80"></a>
+<FONT color="green">081</FONT>     * ham or spam.<a name="line.81"></a>
+<FONT color="green">082</FONT>     * &lt;/p&gt;<a name="line.82"></a>
+<FONT color="green">083</FONT>     * <a name="line.83"></a>
+<FONT color="green">084</FONT>     * &lt;p&gt;<a name="line.84"></a>
+<FONT color="green">085</FONT>     * Using the example above, send good messages (ham not spam) to the email<a name="line.85"></a>
+<FONT color="green">086</FONT>     * address "not.spam@thisdomain.com" to pump good messages into the feeder, and<a name="line.86"></a>
+<FONT color="green">087</FONT>     * send spam messages (spam not ham) to the email address "spam@thisdomain.com"<a name="line.87"></a>
+<FONT color="green">088</FONT>     * to pump spam messages into the feeder.<a name="line.88"></a>
+<FONT color="green">089</FONT>     * &lt;/p&gt;<a name="line.89"></a>
+<FONT color="green">090</FONT>     * <a name="line.90"></a>
+<FONT color="green">091</FONT>     * &lt;p&gt;<a name="line.91"></a>
+<FONT color="green">092</FONT>     * The bayesian database tables will be updated during the training reflecting<a name="line.92"></a>
+<FONT color="green">093</FONT>     * the new data<a name="line.93"></a>
+<FONT color="green">094</FONT>     * &lt;/p&gt;<a name="line.94"></a>
+<FONT color="green">095</FONT>     * <a name="line.95"></a>
+<FONT color="green">096</FONT>     * &lt;p&gt;<a name="line.96"></a>
+<FONT color="green">097</FONT>     * At the end the mail will be destroyed (ghosted).<a name="line.97"></a>
+<FONT color="green">098</FONT>     * &lt;/p&gt;<a name="line.98"></a>
+<FONT color="green">099</FONT>     * <a name="line.99"></a>
+<FONT color="green">100</FONT>     * &lt;p&gt;<a name="line.100"></a>
+<FONT color="green">101</FONT>     * &lt;b&gt;The correct approach is to send the original ham/spam message as an<a name="line.101"></a>
+<FONT color="green">102</FONT>     * attachment to another message sent to the feeder; all the headers of the<a name="line.102"></a>
+<FONT color="green">103</FONT>     * enveloping message will be removed and only the original message's tokens<a name="line.103"></a>
+<FONT color="green">104</FONT>     * will be analyzed.&lt;/b&gt;<a name="line.104"></a>
+<FONT color="green">105</FONT>     * &lt;/p&gt;<a name="line.105"></a>
+<FONT color="green">106</FONT>     * <a name="line.106"></a>
+<FONT color="green">107</FONT>     * &lt;p&gt;<a name="line.107"></a>
+<FONT color="green">108</FONT>     * After a training session, the frequency &lt;i&gt;Corpus&lt;/i&gt; used by<a name="line.108"></a>
+<FONT color="green">109</FONT>     * &lt;code&gt;BayesianAnalysis&lt;/code&gt; must be rebuilt from the database, in order to<a name="line.109"></a>
+<FONT color="green">110</FONT>     * take advantage of the new token frequencies. Every 10 minutes a special<a name="line.110"></a>
+<FONT color="green">111</FONT>     * thread in the &lt;code&gt;BayesianAnalysis&lt;/code&gt; mailet will check if any change<a name="line.111"></a>
+<FONT color="green">112</FONT>     * was made to the database, and rebuild the corpus if necessary.<a name="line.112"></a>
+<FONT color="green">113</FONT>     * &lt;/p&gt;<a name="line.113"></a>
+<FONT color="green">114</FONT>     * <a name="line.114"></a>
+<FONT color="green">115</FONT>     * &lt;p&gt;<a name="line.115"></a>
+<FONT color="green">116</FONT>     * Only one message at a time is scanned (the database update activity is<a name="line.116"></a>
+<FONT color="green">117</FONT>     * &lt;i&gt;synchronized&lt;/i&gt;) in order to avoid too much database locking, as<a name="line.117"></a>
+<FONT color="green">118</FONT>     * thousands of rows may be updated just for one message fed.<a name="line.118"></a>
+<FONT color="green">119</FONT>     * &lt;/p&gt;<a name="line.119"></a>
+<FONT color="green">120</FONT>     * <a name="line.120"></a>
+<FONT color="green">121</FONT>     * @see BayesianAnalysis<a name="line.121"></a>
+<FONT color="green">122</FONT>     * @see BayesianAnalyzer<a name="line.122"></a>
+<FONT color="green">123</FONT>     * @see JDBCBayesianAnalyzer<a name="line.123"></a>
+<FONT color="green">124</FONT>     * @since 2.3.0<a name="line.124"></a>
+<FONT color="green">125</FONT>     */<a name="line.125"></a>
+<FONT color="green">126</FONT>    <a name="line.126"></a>
+<FONT color="green">127</FONT>    public class BayesianAnalysisFeeder extends GenericMailet {<a name="line.127"></a>
+<FONT color="green">128</FONT>        /**<a name="line.128"></a>
+<FONT color="green">129</FONT>         * The JDBCUtil helper class<a name="line.129"></a>
+<FONT color="green">130</FONT>         */<a name="line.130"></a>
+<FONT color="green">131</FONT>        private final JDBCUtil theJDBCUtil = new JDBCUtil() {<a name="line.131"></a>
+<FONT color="green">132</FONT>            protected void delegatedLog(String logString) {<a name="line.132"></a>
+<FONT color="green">133</FONT>                log("BayesianAnalysisFeeder: " + logString);<a name="line.133"></a>
+<FONT color="green">134</FONT>            }<a name="line.134"></a>
+<FONT color="green">135</FONT>        };<a name="line.135"></a>
+<FONT color="green">136</FONT>    <a name="line.136"></a>
+<FONT color="green">137</FONT>        /**<a name="line.137"></a>
+<FONT color="green">138</FONT>         * The JDBCBayesianAnalyzer class that does all the work.<a name="line.138"></a>
+<FONT color="green">139</FONT>         */<a name="line.139"></a>
+<FONT color="green">140</FONT>        private JDBCBayesianAnalyzer analyzer = new JDBCBayesianAnalyzer() {<a name="line.140"></a>
+<FONT color="green">141</FONT>            protected void delegatedLog(String logString) {<a name="line.141"></a>
+<FONT color="green">142</FONT>                log("BayesianAnalysisFeeder: " + logString);<a name="line.142"></a>
+<FONT color="green">143</FONT>            }<a name="line.143"></a>
+<FONT color="green">144</FONT>        };<a name="line.144"></a>
+<FONT color="green">145</FONT>    <a name="line.145"></a>
+<FONT color="green">146</FONT>        private DataSource datasource;<a name="line.146"></a>
+<FONT color="green">147</FONT>        private String repositoryPath;<a name="line.147"></a>
+<FONT color="green">148</FONT>    <a name="line.148"></a>
+<FONT color="green">149</FONT>        private String feedType;<a name="line.149"></a>
+<FONT color="green">150</FONT>    <a name="line.150"></a>
+<FONT color="green">151</FONT>        /**<a name="line.151"></a>
+<FONT color="green">152</FONT>         * Return a string describing this mailet.<a name="line.152"></a>
+<FONT color="green">153</FONT>         * <a name="line.153"></a>
+<FONT color="green">154</FONT>         * @return a string describing this mailet<a name="line.154"></a>
+<FONT color="green">155</FONT>         */<a name="line.155"></a>
+<FONT color="green">156</FONT>        public String getMailetInfo() {<a name="line.156"></a>
+<FONT color="green">157</FONT>            return "BayesianAnalysisFeeder Mailet";<a name="line.157"></a>
+<FONT color="green">158</FONT>        }<a name="line.158"></a>
+<FONT color="green">159</FONT>    <a name="line.159"></a>
+<FONT color="green">160</FONT>        /**<a name="line.160"></a>
+<FONT color="green">161</FONT>         * Holds value of property maxSize.<a name="line.161"></a>
+<FONT color="green">162</FONT>         */<a name="line.162"></a>
+<FONT color="green">163</FONT>        private int maxSize = 100000;<a name="line.163"></a>
+<FONT color="green">164</FONT>    <a name="line.164"></a>
+<FONT color="green">165</FONT>        private SystemContext fs;<a name="line.165"></a>
+<FONT color="green">166</FONT>    <a name="line.166"></a>
+<FONT color="green">167</FONT>        /**<a name="line.167"></a>
+<FONT color="green">168</FONT>         * Getter for property maxSize.<a name="line.168"></a>
+<FONT color="green">169</FONT>         * <a name="line.169"></a>
+<FONT color="green">170</FONT>         * @return Value of property maxSize.<a name="line.170"></a>
+<FONT color="green">171</FONT>         */<a name="line.171"></a>
+<FONT color="green">172</FONT>        public int getMaxSize() {<a name="line.172"></a>
+<FONT color="green">173</FONT>    <a name="line.173"></a>
+<FONT color="green">174</FONT>            return this.maxSize;<a name="line.174"></a>
+<FONT color="green">175</FONT>        }<a name="line.175"></a>
+<FONT color="green">176</FONT>    <a name="line.176"></a>
+<FONT color="green">177</FONT>        @Resource(name = "datasource")<a name="line.177"></a>
+<FONT color="green">178</FONT>        public void setDataSource(DataSource datasource) {<a name="line.178"></a>
+<FONT color="green">179</FONT>            this.datasource = datasource;<a name="line.179"></a>
+<FONT color="green">180</FONT>        }<a name="line.180"></a>
+<FONT color="green">181</FONT>    <a name="line.181"></a>
+<FONT color="green">182</FONT>        /**<a name="line.182"></a>
+<FONT color="green">183</FONT>         * Setter for property maxSize.<a name="line.183"></a>
+<FONT color="green">184</FONT>         * <a name="line.184"></a>
+<FONT color="green">185</FONT>         * @param maxSize<a name="line.185"></a>
+<FONT color="green">186</FONT>         *            New value of property maxSize.<a name="line.186"></a>
+<FONT color="green">187</FONT>         */<a name="line.187"></a>
+<FONT color="green">188</FONT>        public void setMaxSize(int maxSize) {<a name="line.188"></a>
+<FONT color="green">189</FONT>    <a name="line.189"></a>
+<FONT color="green">190</FONT>            this.maxSize = maxSize;<a name="line.190"></a>
+<FONT color="green">191</FONT>        }<a name="line.191"></a>
+<FONT color="green">192</FONT>    <a name="line.192"></a>
+<FONT color="green">193</FONT>        @Resource(name = "filesystem")<a name="line.193"></a>
+<FONT color="green">194</FONT>        public void setFileSystem(SystemContext fs) {<a name="line.194"></a>
+<FONT color="green">195</FONT>            this.fs = fs;<a name="line.195"></a>
+<FONT color="green">196</FONT>        }<a name="line.196"></a>
+<FONT color="green">197</FONT>    <a name="line.197"></a>
+<FONT color="green">198</FONT>        /**<a name="line.198"></a>
+<FONT color="green">199</FONT>         * Mailet initialization routine.<a name="line.199"></a>
+<FONT color="green">200</FONT>         * <a name="line.200"></a>
+<FONT color="green">201</FONT>         * @throws MessagingException<a name="line.201"></a>
+<FONT color="green">202</FONT>         *             if a problem arises<a name="line.202"></a>
+<FONT color="green">203</FONT>         */<a name="line.203"></a>
+<FONT color="green">204</FONT>        public void init() throws MessagingException {<a name="line.204"></a>
+<FONT color="green">205</FONT>            repositoryPath = getInitParameter("repositoryPath");<a name="line.205"></a>
+<FONT color="green">206</FONT>    <a name="line.206"></a>
+<FONT color="green">207</FONT>            if (repositoryPath == null) {<a name="line.207"></a>
+<FONT color="green">208</FONT>                throw new MessagingException("repositoryPath is null");<a name="line.208"></a>
+<FONT color="green">209</FONT>            }<a name="line.209"></a>
+<FONT color="green">210</FONT>    <a name="line.210"></a>
+<FONT color="green">211</FONT>            feedType = getInitParameter("feedType");<a name="line.211"></a>
+<FONT color="green">212</FONT>            if (feedType == null) {<a name="line.212"></a>
+<FONT color="green">213</FONT>                throw new MessagingException("feedType is null");<a name="line.213"></a>
+<FONT color="green">214</FONT>            }<a name="line.214"></a>
+<FONT color="green">215</FONT>    <a name="line.215"></a>
+<FONT color="green">216</FONT>            String maxSizeParam = getInitParameter("maxSize");<a name="line.216"></a>
+<FONT color="green">217</FONT>            if (maxSizeParam != null) {<a name="line.217"></a>
+<FONT color="green">218</FONT>                setMaxSize(Integer.parseInt(maxSizeParam));<a name="line.218"></a>
+<FONT color="green">219</FONT>            }<a name="line.219"></a>
+<FONT color="green">220</FONT>            log("maxSize: " + getMaxSize());<a name="line.220"></a>
+<FONT color="green">221</FONT>    <a name="line.221"></a>
+<FONT color="green">222</FONT>            initDb();<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>        private void initDb() throws MessagingException {<a name="line.226"></a>
+<FONT color="green">227</FONT>    <a name="line.227"></a>
+<FONT color="green">228</FONT>            try {<a name="line.228"></a>
+<FONT color="green">229</FONT>                analyzer.initSqlQueries(datasource.getConnection(), fs.readXml("sqlResources.xml"));<a name="line.229"></a>
+<FONT color="green">230</FONT>            } catch (Exception e) {<a name="line.230"></a>
+<FONT color="green">231</FONT>                throw new MessagingException("Exception initializing queries", e);<a name="line.231"></a>
+<FONT color="green">232</FONT>            }<a name="line.232"></a>
+<FONT color="green">233</FONT>    <a name="line.233"></a>
+<FONT color="green">234</FONT>        }<a name="line.234"></a>
+<FONT color="green">235</FONT>    <a name="line.235"></a>
+<FONT color="green">236</FONT>        /**<a name="line.236"></a>
+<FONT color="green">237</FONT>         * Scans the mail and updates the token frequencies in the database.<a name="line.237"></a>
+<FONT color="green">238</FONT>         * <a name="line.238"></a>
+<FONT color="green">239</FONT>         * The method is synchronized in order to avoid too much database locking,<a name="line.239"></a>
+<FONT color="green">240</FONT>         * as thousands of rows may be updated just for one message fed.<a name="line.240"></a>
+<FONT color="green">241</FONT>         * <a name="line.241"></a>
+<FONT color="green">242</FONT>         * @param mail<a name="line.242"></a>
+<FONT color="green">243</FONT>         *            The Mail message to be scanned.<a name="line.243"></a>
+<FONT color="green">244</FONT>         */<a name="line.244"></a>
+<FONT color="green">245</FONT>        public void service(Mail mail) {<a name="line.245"></a>
+<FONT color="green">246</FONT>            boolean dbUpdated = false;<a name="line.246"></a>
+<FONT color="green">247</FONT>    <a name="line.247"></a>
+<FONT color="green">248</FONT>            mail.setState(Mail.GHOST);<a name="line.248"></a>
+<FONT color="green">249</FONT>    <a name="line.249"></a>
+<FONT color="green">250</FONT>            ByteArrayOutputStream baos = new ByteArrayOutputStream();<a name="line.250"></a>
+<FONT color="green">251</FONT>    <a name="line.251"></a>
+<FONT color="green">252</FONT>            Connection conn = null;<a name="line.252"></a>
+<FONT color="green">253</FONT>    <a name="line.253"></a>
+<FONT color="green">254</FONT>            try {<a name="line.254"></a>
+<FONT color="green">255</FONT>    <a name="line.255"></a>
+<FONT color="green">256</FONT>                MimeMessage message = mail.getMessage();<a name="line.256"></a>
+<FONT color="green">257</FONT>    <a name="line.257"></a>
+<FONT color="green">258</FONT>                String messageId = message.getMessageID();<a name="line.258"></a>
+<FONT color="green">259</FONT>    <a name="line.259"></a>
+<FONT color="green">260</FONT>                if (message.getSize() &gt; getMaxSize()) {<a name="line.260"></a>
+<FONT color="green">261</FONT>                    log(messageId + " Feeding HAM/SPAM ignored because message size &gt; " + getMaxSize() + ": " + message.getSize());<a name="line.261"></a>
+<FONT color="green">262</FONT>                    return;<a name="line.262"></a>
+<FONT color="green">263</FONT>                }<a name="line.263"></a>
+<FONT color="green">264</FONT>    <a name="line.264"></a>
+<FONT color="green">265</FONT>                clearAllHeaders(message);<a name="line.265"></a>
+<FONT color="green">266</FONT>    <a name="line.266"></a>
+<FONT color="green">267</FONT>                message.writeTo(baos);<a name="line.267"></a>
+<FONT color="green">268</FONT>    <a name="line.268"></a>
+<FONT color="green">269</FONT>                BufferedReader br = new BufferedReader(new StringReader(baos.toString()));<a name="line.269"></a>
+<FONT color="green">270</FONT>    <a name="line.270"></a>
+<FONT color="green">271</FONT>                // this is synchronized to avoid concurrent update of the corpus<a name="line.271"></a>
+<FONT color="green">272</FONT>                synchronized (JDBCBayesianAnalyzer.DATABASE_LOCK) {<a name="line.272"></a>
+<FONT color="green">273</FONT>    <a name="line.273"></a>
+<FONT color="green">274</FONT>                    conn = datasource.getConnection();<a name="line.274"></a>
+<FONT color="green">275</FONT>    <a name="line.275"></a>
+<FONT color="green">276</FONT>                    if (conn.getAutoCommit()) {<a name="line.276"></a>
+<FONT color="green">277</FONT>                        conn.setAutoCommit(false);<a name="line.277"></a>
+<FONT color="green">278</FONT>                    }<a name="line.278"></a>
+<FONT color="green">279</FONT>    <a name="line.279"></a>
+<FONT color="green">280</FONT>                    dbUpdated = true;<a name="line.280"></a>
+<FONT color="green">281</FONT>    <a name="line.281"></a>
+<FONT color="green">282</FONT>                    // Clear out any existing word/counts etc..<a name="line.282"></a>
+<FONT color="green">283</FONT>                    analyzer.clear();<a name="line.283"></a>
+<FONT color="green">284</FONT>    <a name="line.284"></a>
+<FONT color="green">285</FONT>                    if ("ham".equalsIgnoreCase(feedType)) {<a name="line.285"></a>
+<FONT color="green">286</FONT>                        log(messageId + " Feeding HAM");<a name="line.286"></a>
+<FONT color="green">287</FONT>                        // Process the stream as ham (not spam).<a name="line.287"></a>
+<FONT color="green">288</FONT>                        analyzer.addHam(br);<a name="line.288"></a>
+<FONT color="green">289</FONT>    <a name="line.289"></a>
+<FONT color="green">290</FONT>                        // Update storage statistics.<a name="line.290"></a>
+<FONT color="green">291</FONT>                        analyzer.updateHamTokens(conn);<a name="line.291"></a>
+<FONT color="green">292</FONT>                    } else {<a name="line.292"></a>
+<FONT color="green">293</FONT>                        log(messageId + " Feeding SPAM");<a name="line.293"></a>
+<FONT color="green">294</FONT>                        // Process the stream as spam.<a name="line.294"></a>
+<FONT color="green">295</FONT>                        analyzer.addSpam(br);<a name="line.295"></a>
+<FONT color="green">296</FONT>    <a name="line.296"></a>
+<FONT color="green">297</FONT>                        // Update storage statistics.<a name="line.297"></a>
+<FONT color="green">298</FONT>                        analyzer.updateSpamTokens(conn);<a name="line.298"></a>
+<FONT color="green">299</FONT>                    }<a name="line.299"></a>
+<FONT color="green">300</FONT>    <a name="line.300"></a>
+<FONT color="green">301</FONT>                    // Commit our changes if necessary.<a name="line.301"></a>
+<FONT color="green">302</FONT>                    if (conn != null &amp;&amp; dbUpdated &amp;&amp; !conn.getAutoCommit()) {<a name="line.302"></a>
+<FONT color="green">303</FONT>                        conn.commit();<a name="line.303"></a>
+<FONT color="green">304</FONT>                        dbUpdated = false;<a name="line.304"></a>
+<FONT color="green">305</FONT>                        log(messageId + " Training ended successfully");<a name="line.305"></a>
+<FONT color="green">306</FONT>                        JDBCBayesianAnalyzer.touchLastDatabaseUpdateTime();<a name="line.306"></a>
+<FONT color="green">307</FONT>                    }<a name="line.307"></a>
+<FONT color="green">308</FONT>    <a name="line.308"></a>
+<FONT color="green">309</FONT>                }<a name="line.309"></a>
+<FONT color="green">310</FONT>    <a name="line.310"></a>
+<FONT color="green">311</FONT>            } catch (java.sql.SQLException se) {<a name="line.311"></a>
+<FONT color="green">312</FONT>                log("SQLException: " + se.getMessage());<a name="line.312"></a>
+<FONT color="green">313</FONT>            } catch (java.io.IOException ioe) {<a name="line.313"></a>
+<FONT color="green">314</FONT>                log("IOException: " + ioe.getMessage());<a name="line.314"></a>
+<FONT color="green">315</FONT>            } catch (javax.mail.MessagingException me) {<a name="line.315"></a>
+<FONT color="green">316</FONT>                log("MessagingException: " + me.getMessage());<a name="line.316"></a>
+<FONT color="green">317</FONT>            } finally {<a name="line.317"></a>
+<FONT color="green">318</FONT>                // Rollback our changes if necessary.<a name="line.318"></a>
+<FONT color="green">319</FONT>                try {<a name="line.319"></a>
+<FONT color="green">320</FONT>                    if (conn != null &amp;&amp; dbUpdated &amp;&amp; !conn.getAutoCommit()) {<a name="line.320"></a>
+<FONT color="green">321</FONT>                        conn.rollback();<a name="line.321"></a>
+<FONT color="green">322</FONT>                        dbUpdated = false;<a name="line.322"></a>
+<FONT color="green">323</FONT>                    }<a name="line.323"></a>
+<FONT color="green">324</FONT>                } catch (Exception e) {<a name="line.324"></a>
+<FONT color="green">325</FONT>                }<a name="line.325"></a>
+<FONT color="green">326</FONT>                theJDBCUtil.closeJDBCConnection(conn);<a name="line.326"></a>
+<FONT color="green">327</FONT>            }<a name="line.327"></a>
+<FONT color="green">328</FONT>        }<a name="line.328"></a>
+<FONT color="green">329</FONT>    <a name="line.329"></a>
+<FONT color="green">330</FONT>        private void clearAllHeaders(MimeMessage message) throws javax.mail.MessagingException {<a name="line.330"></a>
+<FONT color="green">331</FONT>            @SuppressWarnings("rawtypes")<a name="line.331"></a>
+<FONT color="green">332</FONT>            Enumeration headers = message.getAllHeaders();<a name="line.332"></a>
+<FONT color="green">333</FONT>    <a name="line.333"></a>
+<FONT color="green">334</FONT>            while (headers.hasMoreElements()) {<a name="line.334"></a>
+<FONT color="green">335</FONT>                Header header = (Header) headers.nextElement();<a name="line.335"></a>
+<FONT color="green">336</FONT>                try {<a name="line.336"></a>
+<FONT color="green">337</FONT>                    message.removeHeader(header.getName());<a name="line.337"></a>
+<FONT color="green">338</FONT>                } catch (javax.mail.MessagingException me) {<a name="line.338"></a>
+<FONT color="green">339</FONT>                }<a name="line.339"></a>
+<FONT color="green">340</FONT>            }<a name="line.340"></a>
+<FONT color="green">341</FONT>            message.saveChanges();<a name="line.341"></a>
+<FONT color="green">342</FONT>        }<a name="line.342"></a>
+<FONT color="green">343</FONT>    <a name="line.343"></a>
+<FONT color="green">344</FONT>    }<a name="line.344"></a>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+</PRE>
+</BODY>
+</HTML>

Propchange: james/site/trunk/www/mailet/ai/apidocs/src-html/org/apache/james/ai/classic/BayesianAnalysisFeeder.html
------------------------------------------------------------------------------
    svn:eol-style = native