<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT> package org.maltparser.core.io.dataformat;<a name="line.1"></a>
<FONT color="green">002</FONT> <a name="line.2"></a>
<FONT color="green">003</FONT> import java.net.URL;<a name="line.3"></a>
<FONT color="green">004</FONT> import java.util.HashSet;<a name="line.4"></a>
<FONT color="green">005</FONT> import java.util.SortedMap;<a name="line.5"></a>
<FONT color="green">006</FONT> import java.util.TreeMap;<a name="line.6"></a>
<FONT color="green">007</FONT> <a name="line.7"></a>
<FONT color="green">008</FONT> import javax.xml.parsers.DocumentBuilder;<a name="line.8"></a>
<FONT color="green">009</FONT> import javax.xml.parsers.DocumentBuilderFactory;<a name="line.9"></a>
<FONT color="green">010</FONT> import javax.xml.parsers.ParserConfigurationException;<a name="line.10"></a>
<FONT color="green">011</FONT> <a name="line.11"></a>
<FONT color="green">012</FONT> import org.maltparser.core.exception.MaltChainedException;<a name="line.12"></a>
<FONT color="green">013</FONT> import org.maltparser.core.helper.SystemLogger;<a name="line.13"></a>
<FONT color="green">014</FONT> import org.maltparser.core.helper.Util;<a name="line.14"></a>
<FONT color="green">015</FONT> import org.maltparser.core.symbol.SymbolTableHandler;<a name="line.15"></a>
<FONT color="green">016</FONT> import org.w3c.dom.Element;<a name="line.16"></a>
<FONT color="green">017</FONT> import org.w3c.dom.NodeList;<a name="line.17"></a>
<FONT color="green">018</FONT> import org.xml.sax.SAXException;<a name="line.18"></a>
<FONT color="green">019</FONT> <a name="line.19"></a>
<FONT color="green">020</FONT> /**<a name="line.20"></a>
<FONT color="green">021</FONT> * <a name="line.21"></a>
<FONT color="green">022</FONT> *<a name="line.22"></a>
<FONT color="green">023</FONT> * @author Johan Hall<a name="line.23"></a>
<FONT color="green">024</FONT> * @since 1.0<a name="line.24"></a>
<FONT color="green">025</FONT> **/<a name="line.25"></a>
<FONT color="green">026</FONT> public class DataFormatSpecification { <a name="line.26"></a>
<FONT color="green">027</FONT> public enum DataStructure {<a name="line.27"></a>
<FONT color="green">028</FONT> DEPENDENCY, // Dependency structure<a name="line.28"></a>
<FONT color="green">029</FONT> PHRASE, // Phrase structure<a name="line.29"></a>
<FONT color="green">030</FONT> };<a name="line.30"></a>
<FONT color="green">031</FONT> private int entryPositionCounter;<a name="line.31"></a>
<FONT color="green">032</FONT> private String dataFormatName;<a name="line.32"></a>
<FONT color="green">033</FONT> private DataStructure dataStructure;<a name="line.33"></a>
<FONT color="green">034</FONT> private final SortedMap<String, DataFormatEntry> entries;<a name="line.34"></a>
<FONT color="green">035</FONT> private final HashSet<Dependency> dependencies;<a name="line.35"></a>
<FONT color="green">036</FONT> // private final HashSet<SyntaxGraphReader> supportedReaders;<a name="line.36"></a>
<FONT color="green">037</FONT> // private final HashSet<SyntaxGraphWriter> supportedWriters;<a name="line.37"></a>
<FONT color="green">038</FONT> <a name="line.38"></a>
<FONT color="green">039</FONT> public DataFormatSpecification() {<a name="line.39"></a>
<FONT color="green">040</FONT> entries = new TreeMap<String, DataFormatEntry>();<a name="line.40"></a>
<FONT color="green">041</FONT> entryPositionCounter = 0;<a name="line.41"></a>
<FONT color="green">042</FONT> dependencies = new HashSet<Dependency>();<a name="line.42"></a>
<FONT color="green">043</FONT> // supportedReaders = new HashSet<SyntaxGraphReader>();<a name="line.43"></a>
<FONT color="green">044</FONT> // supportedWriters = new HashSet<SyntaxGraphWriter>();<a name="line.44"></a>
<FONT color="green">045</FONT> }<a name="line.45"></a>
<FONT color="green">046</FONT> <a name="line.46"></a>
<FONT color="green">047</FONT> public DataFormatInstance createDataFormatInstance(SymbolTableHandler symbolTables, String nullValueStrategy, String rootLabel) throws MaltChainedException {<a name="line.47"></a>
<FONT color="green">048</FONT> return new DataFormatInstance(entries, symbolTables, nullValueStrategy, rootLabel, this);<a name="line.48"></a>
<FONT color="green">049</FONT> <a name="line.49"></a>
<FONT color="green">050</FONT> }<a name="line.50"></a>
<FONT color="green">051</FONT> <a name="line.51"></a>
<FONT color="green">052</FONT> public void parseDataFormatXMLfile(String fileName) throws MaltChainedException {<a name="line.52"></a>
<FONT color="green">053</FONT> URL url = Util.findURL(fileName);<a name="line.53"></a>
<FONT color="green">054</FONT> if (url == null) {<a name="line.54"></a>
<FONT color="green">055</FONT> throw new DataFormatException("The data format specifcation file '"+fileName+"'cannot be found. ");<a name="line.55"></a>
<FONT color="green">056</FONT> }<a name="line.56"></a>
<FONT color="green">057</FONT> parseDataFormatXMLfile(url);<a name="line.57"></a>
<FONT color="green">058</FONT> }<a name="line.58"></a>
<FONT color="green">059</FONT> <a name="line.59"></a>
<FONT color="green">060</FONT> public HashSet<Dependency> getDependencies() {<a name="line.60"></a>
<FONT color="green">061</FONT> return dependencies;<a name="line.61"></a>
<FONT color="green">062</FONT> }<a name="line.62"></a>
<FONT color="green">063</FONT> <a name="line.63"></a>
<FONT color="green">064</FONT> public void parseDataFormatXMLfile(URL url) throws MaltChainedException {<a name="line.64"></a>
<FONT color="green">065</FONT> if (url == null) {<a name="line.65"></a>
<FONT color="green">066</FONT> throw new DataFormatException("The data format specifcation file cannot be found. ");<a name="line.66"></a>
<FONT color="green">067</FONT> }<a name="line.67"></a>
<FONT color="green">068</FONT> <a name="line.68"></a>
<FONT color="green">069</FONT> if (SystemLogger.logger().isInfoEnabled()) {<a name="line.69"></a>
<FONT color="green">070</FONT> int index = url.toString().indexOf('!');<a name="line.70"></a>
<FONT color="green">071</FONT> if (index == -1) {<a name="line.71"></a>
<FONT color="green">072</FONT> SystemLogger.logger().debug(" Data Format : "+url.toString()+"\n");<a name="line.72"></a>
<FONT color="green">073</FONT> } else {<a name="line.73"></a>
<FONT color="green">074</FONT> SystemLogger.logger().debug(" Data Format : "+url.toString().substring(index+1)+"\n");<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> <a name="line.77"></a>
<FONT color="green">078</FONT> try {<a name="line.78"></a>
<FONT color="green">079</FONT> DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();<a name="line.79"></a>
<FONT color="green">080</FONT> DocumentBuilder db = dbf.newDocumentBuilder();<a name="line.80"></a>
<FONT color="green">081</FONT> <a name="line.81"></a>
<FONT color="green">082</FONT> Element root = db.parse(url.openStream()).getDocumentElement();<a name="line.82"></a>
<FONT color="green">083</FONT> if (root.getNodeName().equals("dataformat")) { <a name="line.83"></a>
<FONT color="green">084</FONT> dataFormatName = root.getAttribute("name");<a name="line.84"></a>
<FONT color="green">085</FONT> if (root.getAttribute("datastructure").length() > 0) {<a name="line.85"></a>
<FONT color="green">086</FONT> dataStructure = DataStructure.valueOf(root.getAttribute("datastructure").toUpperCase());<a name="line.86"></a>
<FONT color="green">087</FONT> } else {<a name="line.87"></a>
<FONT color="green">088</FONT> dataStructure = DataStructure.DEPENDENCY;<a name="line.88"></a>
<FONT color="green">089</FONT> }<a name="line.89"></a>
<FONT color="green">090</FONT> } else {<a name="line.90"></a>
<FONT color="green">091</FONT> throw new DataFormatException("Data format specification file must contain one 'dataformat' element. ");<a name="line.91"></a>
<FONT color="green">092</FONT> }<a name="line.92"></a>
<FONT color="green">093</FONT> NodeList cols = root.getElementsByTagName("column");<a name="line.93"></a>
<FONT color="green">094</FONT> Element col = null;<a name="line.94"></a>
<FONT color="green">095</FONT> for (int i = 0, n = cols.getLength(); i < n; i++) {<a name="line.95"></a>
<FONT color="green">096</FONT> col = (Element)cols.item(i);<a name="line.96"></a>
<FONT color="green">097</FONT> DataFormatEntry entry = new DataFormatEntry(i, col.getAttribute("name"), col.getAttribute("category"),col.getAttribute("type"), col.getAttribute("default"));<a name="line.97"></a>
<FONT color="green">098</FONT> entries.put(entry.getDataFormatEntryName(), entry);<a name="line.98"></a>
<FONT color="green">099</FONT> }<a name="line.99"></a>
<FONT color="green">100</FONT> NodeList deps = root.getElementsByTagName("dependencies");<a name="line.100"></a>
<FONT color="green">101</FONT> if (deps.getLength() > 0) {<a name="line.101"></a>
<FONT color="green">102</FONT> NodeList dep = ((Element)deps.item(0)).getElementsByTagName("dependency");<a name="line.102"></a>
<FONT color="green">103</FONT> for (int i = 0, n = dep.getLength(); i < n; i++) {<a name="line.103"></a>
<FONT color="green">104</FONT> Element e = (Element)dep.item(i);<a name="line.104"></a>
<FONT color="green">105</FONT> dependencies.add(new Dependency(e.getAttribute("name"), e.getAttribute("url"), e.getAttribute("map"), e.getAttribute("urlmap")));<a name="line.105"></a>
<FONT color="green">106</FONT> }<a name="line.106"></a>
<FONT color="green">107</FONT> }<a name="line.107"></a>
<FONT color="green">108</FONT> } catch (java.io.IOException e) {<a name="line.108"></a>
<FONT color="green">109</FONT> throw new DataFormatException("Cannot find the file "+url.toString()+". ", e);<a name="line.109"></a>
<FONT color="green">110</FONT> } catch (ParserConfigurationException e) {<a name="line.110"></a>
<FONT color="green">111</FONT> throw new DataFormatException("Problem parsing the file "+url.toString()+". ", e);<a name="line.111"></a>
<FONT color="green">112</FONT> } catch (SAXException e) {<a name="line.112"></a>
<FONT color="green">113</FONT> throw new DataFormatException("Problem parsing the file "+url.toString()+". ", e);<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> <a name="line.116"></a>
<FONT color="green">117</FONT> public void addEntry(String dataFormatEntryName, String category, String type, String defaultOutput) {<a name="line.117"></a>
<FONT color="green">118</FONT> DataFormatEntry entry = new DataFormatEntry(entryPositionCounter++, dataFormatEntryName, category, type, defaultOutput);<a name="line.118"></a>
<FONT color="green">119</FONT> entries.put(entry.getDataFormatEntryName(), entry);<a name="line.119"></a>
<FONT color="green">120</FONT> }<a name="line.120"></a>
<FONT color="green">121</FONT> <a name="line.121"></a>
<FONT color="green">122</FONT> public DataFormatEntry getEntry(String dataFormatEntryName) {<a name="line.122"></a>
<FONT color="green">123</FONT> return entries.get(dataFormatEntryName);<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> public String getDataFormatName() {<a name="line.126"></a>
<FONT color="green">127</FONT> return dataFormatName;<a name="line.127"></a>
<FONT color="green">128</FONT> }<a name="line.128"></a>
<FONT color="green">129</FONT> <a name="line.129"></a>
<FONT color="green">130</FONT> public DataStructure getDataStructure() {<a name="line.130"></a>
<FONT color="green">131</FONT> return dataStructure;<a name="line.131"></a>
<FONT color="green">132</FONT> }<a name="line.132"></a>
<FONT color="green">133</FONT> <a name="line.133"></a>
<FONT color="green">134</FONT> public String toString() {<a name="line.134"></a>
<FONT color="green">135</FONT> final StringBuilder sb = new StringBuilder();<a name="line.135"></a>
<FONT color="green">136</FONT> sb.append("Data format specification: ");<a name="line.136"></a>
<FONT color="green">137</FONT> sb.append(dataFormatName);<a name="line.137"></a>
<FONT color="green">138</FONT> sb.append('\n');<a name="line.138"></a>
<FONT color="green">139</FONT> for (DataFormatEntry dfe : entries.values()) {<a name="line.139"></a>
<FONT color="green">140</FONT> sb.append(dfe);<a name="line.140"></a>
<FONT color="green">141</FONT> sb.append('\n');<a name="line.141"></a>
<FONT color="green">142</FONT> }<a name="line.142"></a>
<FONT color="green">143</FONT> return sb.toString();<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> public class Dependency {<a name="line.146"></a>
<FONT color="green">147</FONT> protected String dependentOn;<a name="line.147"></a>
<FONT color="green">148</FONT> protected String urlString;<a name="line.148"></a>
<FONT color="green">149</FONT> protected String map;<a name="line.149"></a>
<FONT color="green">150</FONT> protected String mapUrl;<a name="line.150"></a>
<FONT color="green">151</FONT> <a name="line.151"></a>
<FONT color="green">152</FONT> public Dependency(String dependentOn, String urlString, String map, String mapUrl) {<a name="line.152"></a>
<FONT color="green">153</FONT> setDependentOn(dependentOn);<a name="line.153"></a>
<FONT color="green">154</FONT> setUrlString(urlString);<a name="line.154"></a>
<FONT color="green">155</FONT> setMap(map);<a name="line.155"></a>
<FONT color="green">156</FONT> setMapUrl(mapUrl);<a name="line.156"></a>
<FONT color="green">157</FONT> }<a name="line.157"></a>
<FONT color="green">158</FONT> <a name="line.158"></a>
<FONT color="green">159</FONT> public String getDependentOn() {<a name="line.159"></a>
<FONT color="green">160</FONT> return dependentOn;<a name="line.160"></a>
<FONT color="green">161</FONT> }<a name="line.161"></a>
<FONT color="green">162</FONT> protected void setDependentOn(String dependentOn) {<a name="line.162"></a>
<FONT color="green">163</FONT> this.dependentOn = dependentOn;<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> public String getUrlString() {<a name="line.166"></a>
<FONT color="green">167</FONT> return urlString;<a name="line.167"></a>
<FONT color="green">168</FONT> }<a name="line.168"></a>
<FONT color="green">169</FONT> <a name="line.169"></a>
<FONT color="green">170</FONT> public void setUrlString(String urlString) {<a name="line.170"></a>
<FONT color="green">171</FONT> this.urlString = urlString;<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> public String getMap() {<a name="line.174"></a>
<FONT color="green">175</FONT> return map;<a name="line.175"></a>
<FONT color="green">176</FONT> }<a name="line.176"></a>
<FONT color="green">177</FONT> protected void setMap(String map) {<a name="line.177"></a>
<FONT color="green">178</FONT> this.map = map;<a name="line.178"></a>
<FONT color="green">179</FONT> }<a name="line.179"></a>
<FONT color="green">180</FONT> <a name="line.180"></a>
<FONT color="green">181</FONT> public String getMapUrl() {<a name="line.181"></a>
<FONT color="green">182</FONT> return mapUrl;<a name="line.182"></a>
<FONT color="green">183</FONT> }<a name="line.183"></a>
<FONT color="green">184</FONT> <a name="line.184"></a>
<FONT color="green">185</FONT> public void setMapUrl(String mapUrl) {<a name="line.185"></a>
<FONT color="green">186</FONT> this.mapUrl = mapUrl;<a name="line.186"></a>
<FONT color="green">187</FONT> }<a name="line.187"></a>
<FONT color="green">188</FONT> }<a name="line.188"></a>
<FONT color="green">189</FONT> }<a name="line.189"></a>
</PRE>
</BODY>
</HTML>