The Perl Toolchain Summit needs more sponsors. If your company depends on Perl, please support this very important event.
<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT>    package org.maltparser;<a name="line.1"></a>
<FONT color="green">002</FONT>    <a name="line.2"></a>
<FONT color="green">003</FONT>    import java.net.MalformedURLException;<a name="line.3"></a>
<FONT color="green">004</FONT>    import java.net.URL;<a name="line.4"></a>
<FONT color="green">005</FONT>    import java.util.Iterator;<a name="line.5"></a>
<FONT color="green">006</FONT>    <a name="line.6"></a>
<FONT color="green">007</FONT>    import org.maltparser.core.exception.MaltChainedException;<a name="line.7"></a>
<FONT color="green">008</FONT>    import org.maltparser.core.flow.FlowChartInstance;<a name="line.8"></a>
<FONT color="green">009</FONT>    import org.maltparser.core.helper.SystemInfo;<a name="line.9"></a>
<FONT color="green">010</FONT>    import org.maltparser.core.helper.Util;<a name="line.10"></a>
<FONT color="green">011</FONT>    import org.maltparser.core.io.dataformat.ColumnDescription;<a name="line.11"></a>
<FONT color="green">012</FONT>    import org.maltparser.core.io.dataformat.DataFormatInstance;<a name="line.12"></a>
<FONT color="green">013</FONT>    import org.maltparser.core.options.OptionManager;<a name="line.13"></a>
<FONT color="green">014</FONT>    import org.maltparser.core.syntaxgraph.DependencyGraph;<a name="line.14"></a>
<FONT color="green">015</FONT>    import org.maltparser.core.syntaxgraph.DependencyStructure;<a name="line.15"></a>
<FONT color="green">016</FONT>    import org.maltparser.core.syntaxgraph.node.DependencyNode;<a name="line.16"></a>
<FONT color="green">017</FONT>    import org.maltparser.parser.SingleMalt;<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>     * The purpose of MaltParserService is to easily write third-party programs that uses MaltParser. <a name="line.20"></a>
<FONT color="green">021</FONT>     * <a name="line.21"></a>
<FONT color="green">022</FONT>     *  There are two ways to call the MaltParserService:<a name="line.22"></a>
<FONT color="green">023</FONT>     *  1. By running experiments, which allow other programs to train a parser model or parse with a parser model. IO-handling is done by MaltParser.<a name="line.23"></a>
<FONT color="green">024</FONT>     *  2. By first initialize a parser model and then call the method parse() with an array of tokens that MaltParser parses. IO-handling of the sentence is<a name="line.24"></a>
<FONT color="green">025</FONT>     *  done by the third-party program.<a name="line.25"></a>
<FONT color="green">026</FONT>     *  <a name="line.26"></a>
<FONT color="green">027</FONT>     *  How to use MaltParserService, please see the examples provided in the directory 'examples/apiexamples/srcex'<a name="line.27"></a>
<FONT color="green">028</FONT>     * <a name="line.28"></a>
<FONT color="green">029</FONT>     * @author Johan Hall<a name="line.29"></a>
<FONT color="green">030</FONT>     */<a name="line.30"></a>
<FONT color="green">031</FONT>    public class MaltParserService {<a name="line.31"></a>
<FONT color="green">032</FONT>            private URL urlMaltJar;<a name="line.32"></a>
<FONT color="green">033</FONT>            private Engine engine;<a name="line.33"></a>
<FONT color="green">034</FONT>            private FlowChartInstance flowChartInstance;<a name="line.34"></a>
<FONT color="green">035</FONT>            private DataFormatInstance dataFormatInstance;<a name="line.35"></a>
<FONT color="green">036</FONT>            private SingleMalt singleMalt;<a name="line.36"></a>
<FONT color="green">037</FONT>            private int optionContainer;<a name="line.37"></a>
<FONT color="green">038</FONT>            private boolean initialized = false;<a name="line.38"></a>
<FONT color="green">039</FONT>            <a name="line.39"></a>
<FONT color="green">040</FONT>            /**<a name="line.40"></a>
<FONT color="green">041</FONT>             * Creates a MaltParserService with the option container 0<a name="line.41"></a>
<FONT color="green">042</FONT>             * <a name="line.42"></a>
<FONT color="green">043</FONT>             * @throws MaltChainedException<a name="line.43"></a>
<FONT color="green">044</FONT>             */<a name="line.44"></a>
<FONT color="green">045</FONT>            public MaltParserService() throws MaltChainedException {<a name="line.45"></a>
<FONT color="green">046</FONT>                    this(0);<a name="line.46"></a>
<FONT color="green">047</FONT>            }<a name="line.47"></a>
<FONT color="green">048</FONT>            <a name="line.48"></a>
<FONT color="green">049</FONT>            /**<a name="line.49"></a>
<FONT color="green">050</FONT>             * Creates a MaltParserService with the specified option container. To use different option containers allows the calling program <a name="line.50"></a>
<FONT color="green">051</FONT>             * to load several parser models or several experiments. The option management in MaltParser uses the singleton design pattern, which means that there can only<a name="line.51"></a>
<FONT color="green">052</FONT>             * be one instance of the option manager. To be able to have several parser models or experiments at same time please use different option containers.<a name="line.52"></a>
<FONT color="green">053</FONT>             * <a name="line.53"></a>
<FONT color="green">054</FONT>             * @param optionContainer an integer from 0 to max value of data type Integer<a name="line.54"></a>
<FONT color="green">055</FONT>             * @throws MaltChainedException<a name="line.55"></a>
<FONT color="green">056</FONT>             */<a name="line.56"></a>
<FONT color="green">057</FONT>            public MaltParserService(int optionContainer) throws MaltChainedException {<a name="line.57"></a>
<FONT color="green">058</FONT>                    initialize();<a name="line.58"></a>
<FONT color="green">059</FONT>                    setOptionContainer(optionContainer);<a name="line.59"></a>
<FONT color="green">060</FONT>            }<a name="line.60"></a>
<FONT color="green">061</FONT>            <a name="line.61"></a>
<FONT color="green">062</FONT>            /**<a name="line.62"></a>
<FONT color="green">063</FONT>             * Runs a MaltParser experiment. The experiment is controlled by a commandLine string, please see the documentation of MaltParser to see all available options.<a name="line.63"></a>
<FONT color="green">064</FONT>             * <a name="line.64"></a>
<FONT color="green">065</FONT>             * @param commandLine a commandLine string that controls the MaltParser.<a name="line.65"></a>
<FONT color="green">066</FONT>             * @throws MaltChainedException<a name="line.66"></a>
<FONT color="green">067</FONT>             */<a name="line.67"></a>
<FONT color="green">068</FONT>            public void runExperiment(String commandLine) throws MaltChainedException {<a name="line.68"></a>
<FONT color="green">069</FONT>                    OptionManager.instance().parseCommandLine(commandLine, optionContainer);<a name="line.69"></a>
<FONT color="green">070</FONT>                    engine = new Engine();<a name="line.70"></a>
<FONT color="green">071</FONT>                    engine.initialize(optionContainer);<a name="line.71"></a>
<FONT color="green">072</FONT>                    engine.process(optionContainer);<a name="line.72"></a>
<FONT color="green">073</FONT>                    engine.terminate(optionContainer);<a name="line.73"></a>
<FONT color="green">074</FONT>            }<a name="line.74"></a>
<FONT color="green">075</FONT>            <a name="line.75"></a>
<FONT color="green">076</FONT>            /**<a name="line.76"></a>
<FONT color="green">077</FONT>             * Initialize a parser model that later can by used to parse sentences. MaltParser is controlled by a commandLine string, please see the documentation of MaltParser to see all available options.<a name="line.77"></a>
<FONT color="green">078</FONT>             * <a name="line.78"></a>
<FONT color="green">079</FONT>             * @param commandLine a commandLine string that controls the MaltParser<a name="line.79"></a>
<FONT color="green">080</FONT>             * @throws MaltChainedException<a name="line.80"></a>
<FONT color="green">081</FONT>             */<a name="line.81"></a>
<FONT color="green">082</FONT>            public void initializeParserModel(String commandLine) throws MaltChainedException {<a name="line.82"></a>
<FONT color="green">083</FONT>                    OptionManager.instance().parseCommandLine(commandLine, optionContainer);<a name="line.83"></a>
<FONT color="green">084</FONT>                    // Creates an engine<a name="line.84"></a>
<FONT color="green">085</FONT>                    engine = new Engine();<a name="line.85"></a>
<FONT color="green">086</FONT>                    // Initialize the engine with option container and gets a flow chart instance<a name="line.86"></a>
<FONT color="green">087</FONT>                    flowChartInstance = engine.initialize(optionContainer);<a name="line.87"></a>
<FONT color="green">088</FONT>                    // Runs the preprocess chart items of the "parse" flow chart<a name="line.88"></a>
<FONT color="green">089</FONT>                    if (flowChartInstance.hasPreProcessChartItems()) {<a name="line.89"></a>
<FONT color="green">090</FONT>                            flowChartInstance.preprocess();<a name="line.90"></a>
<FONT color="green">091</FONT>                    }<a name="line.91"></a>
<FONT color="green">092</FONT>                    singleMalt = (SingleMalt)flowChartInstance.getFlowChartRegistry(org.maltparser.parser.SingleMalt.class, "singlemalt");<a name="line.92"></a>
<FONT color="green">093</FONT>                    singleMalt.getConfigurationDir().initDataFormat();<a name="line.93"></a>
<FONT color="green">094</FONT>                    dataFormatInstance = singleMalt.getConfigurationDir().getDataFormatManager().getInputDataFormatSpec().createDataFormatInstance(<a name="line.94"></a>
<FONT color="green">095</FONT>                                    singleMalt.getSymbolTables(),<a name="line.95"></a>
<FONT color="green">096</FONT>                                    OptionManager.instance().getOptionValueString(optionContainer, "singlemalt", "null_value"), <a name="line.96"></a>
<FONT color="green">097</FONT>                                    OptionManager.instance().getOptionValueString(optionContainer, "graph", "root_label"));<a name="line.97"></a>
<FONT color="green">098</FONT>                    initialized = true;<a name="line.98"></a>
<FONT color="green">099</FONT>            }<a name="line.99"></a>
<FONT color="green">100</FONT>            <a name="line.100"></a>
<FONT color="green">101</FONT>            /**<a name="line.101"></a>
<FONT color="green">102</FONT>             * Parses an array of tokens and returns a dependency structure. <a name="line.102"></a>
<FONT color="green">103</FONT>             * <a name="line.103"></a>
<FONT color="green">104</FONT>             * Note: To call this method requires that a parser model has been initialized by using the initializeParserModel(). <a name="line.104"></a>
<FONT color="green">105</FONT>             * <a name="line.105"></a>
<FONT color="green">106</FONT>             * @param tokens an array of tokens <a name="line.106"></a>
<FONT color="green">107</FONT>             * @return a dependency structure<a name="line.107"></a>
<FONT color="green">108</FONT>             * @throws MaltChainedException<a name="line.108"></a>
<FONT color="green">109</FONT>             */<a name="line.109"></a>
<FONT color="green">110</FONT>            public DependencyStructure parse(String[] tokens) throws MaltChainedException {<a name="line.110"></a>
<FONT color="green">111</FONT>                    if (!initialized) {<a name="line.111"></a>
<FONT color="green">112</FONT>                            throw new MaltChainedException("No parser model has been initialized. Please use the method initializeParserModel() before invoking this method.");<a name="line.112"></a>
<FONT color="green">113</FONT>                    }<a name="line.113"></a>
<FONT color="green">114</FONT>                    if (tokens == null || tokens.length == 0) {<a name="line.114"></a>
<FONT color="green">115</FONT>                            throw new MaltChainedException("Nothing to parse. ");<a name="line.115"></a>
<FONT color="green">116</FONT>                    }<a name="line.116"></a>
<FONT color="green">117</FONT>    <a name="line.117"></a>
<FONT color="green">118</FONT>                    DependencyStructure outputGraph = new DependencyGraph(singleMalt.getSymbolTables());<a name="line.118"></a>
<FONT color="green">119</FONT>                    <a name="line.119"></a>
<FONT color="green">120</FONT>                    for (int i = 0; i &lt; tokens.length; i++) {<a name="line.120"></a>
<FONT color="green">121</FONT>                            Iterator&lt;ColumnDescription&gt; columns = dataFormatInstance.iterator();<a name="line.121"></a>
<FONT color="green">122</FONT>                            DependencyNode node = outputGraph.addDependencyNode(i+1);<a name="line.122"></a>
<FONT color="green">123</FONT>                            String[] items = tokens[i].split("\t");<a name="line.123"></a>
<FONT color="green">124</FONT>                            for (int j = 0; j &lt; items.length; j++) {<a name="line.124"></a>
<FONT color="green">125</FONT>                                    if (columns.hasNext()) {<a name="line.125"></a>
<FONT color="green">126</FONT>                                            ColumnDescription column = columns.next();<a name="line.126"></a>
<FONT color="green">127</FONT>                                            if (column.getCategory() == ColumnDescription.INPUT &amp;&amp; node != null) {<a name="line.127"></a>
<FONT color="green">128</FONT>                                                    outputGraph.addLabel(node, column.getName(), items[j]);<a name="line.128"></a>
<FONT color="green">129</FONT>                                            }<a name="line.129"></a>
<FONT color="green">130</FONT>                                    }<a name="line.130"></a>
<FONT color="green">131</FONT>                            }<a name="line.131"></a>
<FONT color="green">132</FONT>                    }<a name="line.132"></a>
<FONT color="green">133</FONT>                    outputGraph.setDefaultRootEdgeLabel(outputGraph.getSymbolTables().getSymbolTable("DEPREL"), "ROOT");<a name="line.133"></a>
<FONT color="green">134</FONT>                    // Invoke parse with the output graph<a name="line.134"></a>
<FONT color="green">135</FONT>                    singleMalt.parse(outputGraph);<a name="line.135"></a>
<FONT color="green">136</FONT>                    return outputGraph;<a name="line.136"></a>
<FONT color="green">137</FONT>            }<a name="line.137"></a>
<FONT color="green">138</FONT>            <a name="line.138"></a>
<FONT color="green">139</FONT>            /**<a name="line.139"></a>
<FONT color="green">140</FONT>             * Terminates the parser model.<a name="line.140"></a>
<FONT color="green">141</FONT>             * <a name="line.141"></a>
<FONT color="green">142</FONT>             * @throws MaltChainedException<a name="line.142"></a>
<FONT color="green">143</FONT>             */<a name="line.143"></a>
<FONT color="green">144</FONT>            public void terminateParserModel() throws MaltChainedException {<a name="line.144"></a>
<FONT color="green">145</FONT>                    // Runs the postprocess chart items of the "parse" flow chart<a name="line.145"></a>
<FONT color="green">146</FONT>                    if (flowChartInstance.hasPostProcessChartItems()) {<a name="line.146"></a>
<FONT color="green">147</FONT>                            flowChartInstance.postprocess();<a name="line.147"></a>
<FONT color="green">148</FONT>                    }<a name="line.148"></a>
<FONT color="green">149</FONT>                    <a name="line.149"></a>
<FONT color="green">150</FONT>                    // Terminate the flow chart with an option container<a name="line.150"></a>
<FONT color="green">151</FONT>                    engine.terminate(optionContainer);<a name="line.151"></a>
<FONT color="green">152</FONT>            }<a name="line.152"></a>
<FONT color="green">153</FONT>            <a name="line.153"></a>
<FONT color="green">154</FONT>            private void initialize() throws MaltChainedException {<a name="line.154"></a>
<FONT color="green">155</FONT>                    if (OptionManager.instance().getOptionDescriptions().getOptionGroupNameSet().size() &gt; 0) {<a name="line.155"></a>
<FONT color="green">156</FONT>                            return; // OptionManager is already initialized<a name="line.156"></a>
<FONT color="green">157</FONT>                    }<a name="line.157"></a>
<FONT color="green">158</FONT>                    String maltpath = getMaltJarPath();<a name="line.158"></a>
<FONT color="green">159</FONT>                    if (maltpath == null) {<a name="line.159"></a>
<FONT color="green">160</FONT>                            new MaltChainedException("malt.jar could not be found. ");<a name="line.160"></a>
<FONT color="green">161</FONT>                    }<a name="line.161"></a>
<FONT color="green">162</FONT>                    urlMaltJar = Util.findURL(maltpath);<a name="line.162"></a>
<FONT color="green">163</FONT>                    try {<a name="line.163"></a>
<FONT color="green">164</FONT>                            OptionManager.instance().loadOptionDescriptionFile(new URL("jar:"+urlMaltJar.toString()+"!/appdata/options.xml"));<a name="line.164"></a>
<FONT color="green">165</FONT>                            <a name="line.165"></a>
<FONT color="green">166</FONT>                    } catch (MalformedURLException e) {<a name="line.166"></a>
<FONT color="green">167</FONT>                            throw new MaltChainedException("MaltParser couldn't find its options 'malt.jar!/appdata/options.xml'", e);<a name="line.167"></a>
<FONT color="green">168</FONT>                    }<a name="line.168"></a>
<FONT color="green">169</FONT>                    OptionManager.instance().generateMaps();<a name="line.169"></a>
<FONT color="green">170</FONT>            }<a name="line.170"></a>
<FONT color="green">171</FONT>            <a name="line.171"></a>
<FONT color="green">172</FONT>            <a name="line.172"></a>
<FONT color="green">173</FONT>            /**<a name="line.173"></a>
<FONT color="green">174</FONT>             * Returns the option container index<a name="line.174"></a>
<FONT color="green">175</FONT>             * <a name="line.175"></a>
<FONT color="green">176</FONT>             * @return the option container index<a name="line.176"></a>
<FONT color="green">177</FONT>             */<a name="line.177"></a>
<FONT color="green">178</FONT>            public int getOptionContainer() {<a name="line.178"></a>
<FONT color="green">179</FONT>                    return optionContainer;<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>            private void setOptionContainer(int optionContainer) {<a name="line.182"></a>
<FONT color="green">183</FONT>                    this.optionContainer = optionContainer;<a name="line.183"></a>
<FONT color="green">184</FONT>            }<a name="line.184"></a>
<FONT color="green">185</FONT>    <a name="line.185"></a>
<FONT color="green">186</FONT>            /**<a name="line.186"></a>
<FONT color="green">187</FONT>             * Returns the path of malt.jar file<a name="line.187"></a>
<FONT color="green">188</FONT>             * <a name="line.188"></a>
<FONT color="green">189</FONT>             * @return the path of malt.jar file<a name="line.189"></a>
<FONT color="green">190</FONT>             */<a name="line.190"></a>
<FONT color="green">191</FONT>            public static String getMaltJarPath() {<a name="line.191"></a>
<FONT color="green">192</FONT>                    if (SystemInfo.getMaltJarPath() != null) {<a name="line.192"></a>
<FONT color="green">193</FONT>                            return SystemInfo.getMaltJarPath().toString();<a name="line.193"></a>
<FONT color="green">194</FONT>                    }<a name="line.194"></a>
<FONT color="green">195</FONT>                    return null;<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>    }<a name="line.199"></a>




























































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