<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT> package org.maltparser.core.syntaxgraph.writer;<a name="line.1"></a>
<FONT color="green">002</FONT> <a name="line.2"></a>
<FONT color="green">003</FONT> import java.io.BufferedWriter;<a name="line.3"></a>
<FONT color="green">004</FONT> import java.io.FileNotFoundException;<a name="line.4"></a>
<FONT color="green">005</FONT> import java.io.FileOutputStream;<a name="line.5"></a>
<FONT color="green">006</FONT> import java.io.IOException;<a name="line.6"></a>
<FONT color="green">007</FONT> import java.io.OutputStream;<a name="line.7"></a>
<FONT color="green">008</FONT> import java.io.OutputStreamWriter;<a name="line.8"></a>
<FONT color="green">009</FONT> import java.io.UnsupportedEncodingException;<a name="line.9"></a>
<FONT color="green">010</FONT> import java.util.SortedMap;<a name="line.10"></a>
<FONT color="green">011</FONT> import java.util.TreeMap;<a name="line.11"></a>
<FONT color="green">012</FONT> import java.util.regex.PatternSyntaxException;<a name="line.12"></a>
<FONT color="green">013</FONT> <a name="line.13"></a>
<FONT color="green">014</FONT> import org.maltparser.core.exception.MaltChainedException;<a name="line.14"></a>
<FONT color="green">015</FONT> <a name="line.15"></a>
<FONT color="green">016</FONT> import org.maltparser.core.helper.Util;<a name="line.16"></a>
<FONT color="green">017</FONT> import org.maltparser.core.io.dataformat.ColumnDescription;<a name="line.17"></a>
<FONT color="green">018</FONT> import org.maltparser.core.io.dataformat.DataFormatException;<a name="line.18"></a>
<FONT color="green">019</FONT> import org.maltparser.core.io.dataformat.DataFormatInstance;<a name="line.19"></a>
<FONT color="green">020</FONT> import org.maltparser.core.syntaxgraph.PhraseStructure;<a name="line.20"></a>
<FONT color="green">021</FONT> import org.maltparser.core.syntaxgraph.TokenStructure;<a name="line.21"></a>
<FONT color="green">022</FONT> import org.maltparser.core.syntaxgraph.node.NonTerminalNode;<a name="line.22"></a>
<FONT color="green">023</FONT> import org.maltparser.core.syntaxgraph.node.PhraseStructureNode;<a name="line.23"></a>
<FONT color="green">024</FONT> import org.maltparser.core.syntaxgraph.node.TokenNode;<a name="line.24"></a>
<FONT color="green">025</FONT> import org.maltparser.core.syntaxgraph.reader.TigerXMLHeader;<a name="line.25"></a>
<FONT color="green">026</FONT> import org.maltparser.ml.libsvm.LibsvmException;<a name="line.26"></a>
<FONT color="green">027</FONT> /**<a name="line.27"></a>
<FONT color="green">028</FONT> *<a name="line.28"></a>
<FONT color="green">029</FONT> *<a name="line.29"></a>
<FONT color="green">030</FONT> * @author Johan Hall<a name="line.30"></a>
<FONT color="green">031</FONT> */<a name="line.31"></a>
<FONT color="green">032</FONT> public class TigerXMLWriter implements SyntaxGraphWriter {<a name="line.32"></a>
<FONT color="green">033</FONT> private enum RootHandling {<a name="line.33"></a>
<FONT color="green">034</FONT> TALBANKEN, NORMAL <a name="line.34"></a>
<FONT color="green">035</FONT> };<a name="line.35"></a>
<FONT color="green">036</FONT> <a name="line.36"></a>
<FONT color="green">037</FONT> private BufferedWriter writer;<a name="line.37"></a>
<FONT color="green">038</FONT> private DataFormatInstance dataFormatInstance;<a name="line.38"></a>
<FONT color="green">039</FONT> private String optionString;<a name="line.39"></a>
<FONT color="green">040</FONT> private int sentenceCount;<a name="line.40"></a>
<FONT color="green">041</FONT> private TigerXMLHeader header;<a name="line.41"></a>
<FONT color="green">042</FONT> // private boolean hasWriteTigerXMLHeader = false;<a name="line.42"></a>
<FONT color="green">043</FONT> private RootHandling rootHandling;<a name="line.43"></a>
<FONT color="green">044</FONT> private String sentencePrefix = "s";<a name="line.44"></a>
<FONT color="green">045</FONT> private StringBuilder sentenceID;<a name="line.45"></a>
<FONT color="green">046</FONT> private StringBuilder tmpID;<a name="line.46"></a>
<FONT color="green">047</FONT> private StringBuilder rootID;<a name="line.47"></a>
<FONT color="green">048</FONT> private int START_ID_OF_NONTERMINALS = 500;<a name="line.48"></a>
<FONT color="green">049</FONT> private boolean labeledTerminalID;<a name="line.49"></a>
<FONT color="green">050</FONT> private String VROOT_SYMBOL = "VROOT";<a name="line.50"></a>
<FONT color="green">051</FONT> private boolean useVROOT = false;<a name="line.51"></a>
<FONT color="green">052</FONT> // private String fileName = null;<a name="line.52"></a>
<FONT color="green">053</FONT> // private String charsetName = null;<a name="line.53"></a>
<FONT color="green">054</FONT> private boolean closeStream = true;<a name="line.54"></a>
<FONT color="green">055</FONT> <a name="line.55"></a>
<FONT color="green">056</FONT> public TigerXMLWriter() { <a name="line.56"></a>
<FONT color="green">057</FONT> sentenceID = new StringBuilder();<a name="line.57"></a>
<FONT color="green">058</FONT> tmpID = new StringBuilder();<a name="line.58"></a>
<FONT color="green">059</FONT> rootID = new StringBuilder();<a name="line.59"></a>
<FONT color="green">060</FONT> labeledTerminalID = false;<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> public void open(String fileName, String charsetName) throws MaltChainedException {<a name="line.63"></a>
<FONT color="green">064</FONT> try {<a name="line.64"></a>
<FONT color="green">065</FONT> // this.fileName = fileName;<a name="line.65"></a>
<FONT color="green">066</FONT> // this.charsetName = charsetName;<a name="line.66"></a>
<FONT color="green">067</FONT> open(new OutputStreamWriter(new FileOutputStream(fileName),charsetName));<a name="line.67"></a>
<FONT color="green">068</FONT> } catch (FileNotFoundException e) {<a name="line.68"></a>
<FONT color="green">069</FONT> throw new DataFormatException("The output file '"+fileName+"' cannot be found.", e);<a name="line.69"></a>
<FONT color="green">070</FONT> } catch (UnsupportedEncodingException e) {<a name="line.70"></a>
<FONT color="green">071</FONT> throw new DataFormatException("The character encoding set '"+charsetName+"' isn't supported.", e);<a name="line.71"></a>
<FONT color="green">072</FONT> } <a name="line.72"></a>
<FONT color="green">073</FONT> }<a name="line.73"></a>
<FONT color="green">074</FONT> <a name="line.74"></a>
<FONT color="green">075</FONT> public void open(OutputStream os, String charsetName) throws MaltChainedException {<a name="line.75"></a>
<FONT color="green">076</FONT> try {<a name="line.76"></a>
<FONT color="green">077</FONT> if (os == System.out || os == System.err) {<a name="line.77"></a>
<FONT color="green">078</FONT> closeStream = false;<a name="line.78"></a>
<FONT color="green">079</FONT> }<a name="line.79"></a>
<FONT color="green">080</FONT> open(new OutputStreamWriter(os, charsetName));<a name="line.80"></a>
<FONT color="green">081</FONT> } catch (UnsupportedEncodingException e) {<a name="line.81"></a>
<FONT color="green">082</FONT> throw new DataFormatException("The character encoding set '"+charsetName+"' isn't supported.", e);<a name="line.82"></a>
<FONT color="green">083</FONT> }<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> private void open(OutputStreamWriter osw) throws MaltChainedException {<a name="line.86"></a>
<FONT color="green">087</FONT> setWriter(new BufferedWriter(osw));<a name="line.87"></a>
<FONT color="green">088</FONT> setSentenceCount(0);<a name="line.88"></a>
<FONT color="green">089</FONT> }<a name="line.89"></a>
<FONT color="green">090</FONT> <a name="line.90"></a>
<FONT color="green">091</FONT> public void writeProlog() throws MaltChainedException { <a name="line.91"></a>
<FONT color="green">092</FONT> // if (fileName == null || charsetName == null) {<a name="line.92"></a>
<FONT color="green">093</FONT> writeHeader();<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> public void writeSentence(TokenStructure syntaxGraph) throws MaltChainedException {<a name="line.97"></a>
<FONT color="green">098</FONT> if (syntaxGraph == null || dataFormatInstance == null) {<a name="line.98"></a>
<FONT color="green">099</FONT> return;<a name="line.99"></a>
<FONT color="green">100</FONT> }<a name="line.100"></a>
<FONT color="green">101</FONT> if (syntaxGraph.hasTokens()) {<a name="line.101"></a>
<FONT color="green">102</FONT> sentenceCount++;<a name="line.102"></a>
<FONT color="green">103</FONT> final PhraseStructure phraseStructure = (PhraseStructure)syntaxGraph;<a name="line.103"></a>
<FONT color="green">104</FONT> try {<a name="line.104"></a>
<FONT color="green">105</FONT> sentenceID.setLength(0);<a name="line.105"></a>
<FONT color="green">106</FONT> sentenceID.append(sentencePrefix);<a name="line.106"></a>
<FONT color="green">107</FONT> if (phraseStructure.getSentenceID() != 0) {<a name="line.107"></a>
<FONT color="green">108</FONT> sentenceID.append(Integer.toString(phraseStructure.getSentenceID()));<a name="line.108"></a>
<FONT color="green">109</FONT> } else {<a name="line.109"></a>
<FONT color="green">110</FONT> sentenceID.append(Integer.toString(sentenceCount));<a name="line.110"></a>
<FONT color="green">111</FONT> }<a name="line.111"></a>
<FONT color="green">112</FONT> writer.write(" <s id=\"");<a name="line.112"></a>
<FONT color="green">113</FONT> writer.write(sentenceID.toString()); <a name="line.113"></a>
<FONT color="green">114</FONT> writer.write("\">\n");<a name="line.114"></a>
<FONT color="green">115</FONT> <a name="line.115"></a>
<FONT color="green">116</FONT> setRootID(phraseStructure);<a name="line.116"></a>
<FONT color="green">117</FONT> writer.write(" <graph root=\"");<a name="line.117"></a>
<FONT color="green">118</FONT> writer.write(rootID.toString());<a name="line.118"></a>
<FONT color="green">119</FONT> writer.write("\" ");<a name="line.119"></a>
<FONT color="green">120</FONT> writer.write("discontinuous=\"");<a name="line.120"></a>
<FONT color="green">121</FONT> writer.write(Boolean.toString(!phraseStructure.isContinuous()));<a name="line.121"></a>
<FONT color="green">122</FONT> writer.write("\">\n");<a name="line.122"></a>
<FONT color="green">123</FONT> <a name="line.123"></a>
<FONT color="green">124</FONT> writeTerminals(phraseStructure);<a name="line.124"></a>
<FONT color="green">125</FONT> if (phraseStructure.nTokenNode() != 1 || rootHandling.equals(RootHandling.TALBANKEN)) {<a name="line.125"></a>
<FONT color="green">126</FONT> writeNonTerminals(phraseStructure);<a name="line.126"></a>
<FONT color="green">127</FONT> } else {<a name="line.127"></a>
<FONT color="green">128</FONT> writer.write(" <nonterminals/>\n");<a name="line.128"></a>
<FONT color="green">129</FONT> }<a name="line.129"></a>
<FONT color="green">130</FONT> writer.write(" </graph>\n");<a name="line.130"></a>
<FONT color="green">131</FONT> writer.write(" </s>\n");<a name="line.131"></a>
<FONT color="green">132</FONT> } catch (IOException e) {<a name="line.132"></a>
<FONT color="green">133</FONT> throw new DataFormatException("The TigerXML writer could not write to file. ", e);<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> private void setRootID(PhraseStructure phraseStructure) throws MaltChainedException {<a name="line.138"></a>
<FONT color="green">139</FONT> useVROOT = false;<a name="line.139"></a>
<FONT color="green">140</FONT> PhraseStructureNode root = phraseStructure.getPhraseStructureRoot();<a name="line.140"></a>
<FONT color="green">141</FONT> for (ColumnDescription column : dataFormatInstance.getPhraseStructureNodeLabelColumnDescriptionSet()) {<a name="line.141"></a>
<FONT color="green">142</FONT> if (root.hasLabel(column.getSymbolTable()) && root.getLabelSymbol(column.getSymbolTable()).equals(VROOT_SYMBOL)) {<a name="line.142"></a>
<FONT color="green">143</FONT> useVROOT = true;<a name="line.143"></a>
<FONT color="green">144</FONT> break;<a name="line.144"></a>
<FONT color="green">145</FONT> }<a name="line.145"></a>
<FONT color="green">146</FONT> }<a name="line.146"></a>
<FONT color="green">147</FONT> if (useVROOT) {<a name="line.147"></a>
<FONT color="green">148</FONT> rootID.setLength(0);<a name="line.148"></a>
<FONT color="green">149</FONT> rootID.append(sentenceID);<a name="line.149"></a>
<FONT color="green">150</FONT> rootID.append('_');<a name="line.150"></a>
<FONT color="green">151</FONT> rootID.append(VROOT_SYMBOL);<a name="line.151"></a>
<FONT color="green">152</FONT> } else if (phraseStructure.nTokenNode() == 1 && phraseStructure.nNonTerminals() == 0 && !root.isLabeled()) {<a name="line.152"></a>
<FONT color="green">153</FONT> rootID.setLength(0);<a name="line.153"></a>
<FONT color="green">154</FONT> rootID.append(sentenceID);<a name="line.154"></a>
<FONT color="green">155</FONT> rootID.append("_1");<a name="line.155"></a>
<FONT color="green">156</FONT> } else {<a name="line.156"></a>
<FONT color="green">157</FONT> rootID.setLength(0);<a name="line.157"></a>
<FONT color="green">158</FONT> rootID.append(sentenceID);<a name="line.158"></a>
<FONT color="green">159</FONT> rootID.append('_');<a name="line.159"></a>
<FONT color="green">160</FONT> // if (rootHandling.equals(RootHandling.NORMAL)) { <a name="line.160"></a>
<FONT color="green">161</FONT> rootID.append(Integer.toString(START_ID_OF_NONTERMINALS+phraseStructure.nNonTerminals()));<a name="line.161"></a>
<FONT color="green">162</FONT> // } else if (rootHandling.equals(RootHandling.TALBANKEN)) {<a name="line.162"></a>
<FONT color="green">163</FONT> // rootID.append(Integer.toString(START_ID_OF_NONTERMINALS+1));<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> <a name="line.166"></a>
<FONT color="green">167</FONT> }<a name="line.167"></a>
<FONT color="green">168</FONT> <a name="line.168"></a>
<FONT color="green">169</FONT> public void writeEpilog() throws MaltChainedException { <a name="line.169"></a>
<FONT color="green">170</FONT> writeTail();<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> public BufferedWriter getWriter() {<a name="line.173"></a>
<FONT color="green">174</FONT> return writer;<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> public void setWriter(BufferedWriter writer) {<a name="line.177"></a>
<FONT color="green">178</FONT> this.writer = writer;<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 void close() throws MaltChainedException {<a name="line.181"></a>
<FONT color="green">182</FONT> try {<a name="line.182"></a>
<FONT color="green">183</FONT> if (writer != null) {<a name="line.183"></a>
<FONT color="green">184</FONT> writer.flush();<a name="line.184"></a>
<FONT color="green">185</FONT> if (closeStream) {<a name="line.185"></a>
<FONT color="green">186</FONT> writer.close();<a name="line.186"></a>
<FONT color="green">187</FONT> }<a name="line.187"></a>
<FONT color="green">188</FONT> writer = null;<a name="line.188"></a>
<FONT color="green">189</FONT> }<a name="line.189"></a>
<FONT color="green">190</FONT> } catch (IOException e) {<a name="line.190"></a>
<FONT color="green">191</FONT> throw new DataFormatException("Could not close the output file. ", e);<a name="line.191"></a>
<FONT color="green">192</FONT> } <a name="line.192"></a>
<FONT color="green">193</FONT> }<a name="line.193"></a>
<FONT color="green">194</FONT> <a name="line.194"></a>
<FONT color="green">195</FONT> private void writeHeader() throws MaltChainedException {<a name="line.195"></a>
<FONT color="green">196</FONT> try {<a name="line.196"></a>
<FONT color="green">197</FONT> if (header == null) {<a name="line.197"></a>
<FONT color="green">198</FONT> header = new TigerXMLHeader(dataFormatInstance.getSymbolTables());<a name="line.198"></a>
<FONT color="green">199</FONT> }<a name="line.199"></a>
<FONT color="green">200</FONT> writer.write(header.toTigerXML());<a name="line.200"></a>
<FONT color="green">201</FONT> // hasWriteTigerXMLHeader = true;<a name="line.201"></a>
<FONT color="green">202</FONT> } catch (IOException e) {<a name="line.202"></a>
<FONT color="green">203</FONT> throw new DataFormatException("The TigerXML writer could not write to file. ", e);<a name="line.203"></a>
<FONT color="green">204</FONT> }<a name="line.204"></a>
<FONT color="green">205</FONT> }<a name="line.205"></a>
<FONT color="green">206</FONT> <a name="line.206"></a>
<FONT color="green">207</FONT> <a name="line.207"></a>
<FONT color="green">208</FONT> private void writeTerminals(PhraseStructure phraseStructure) throws MaltChainedException {<a name="line.208"></a>
<FONT color="green">209</FONT> try {<a name="line.209"></a>
<FONT color="green">210</FONT> writer.write(" <terminals>\n");<a name="line.210"></a>
<FONT color="green">211</FONT> for (int index : phraseStructure.getTokenIndices()) {<a name="line.211"></a>
<FONT color="green">212</FONT> final PhraseStructureNode t = phraseStructure.getTokenNode(index);<a name="line.212"></a>
<FONT color="green">213</FONT> writer.write(" <t ");<a name="line.213"></a>
<FONT color="green">214</FONT> if (!labeledTerminalID) {<a name="line.214"></a>
<FONT color="green">215</FONT> tmpID.setLength(0);<a name="line.215"></a>
<FONT color="green">216</FONT> tmpID.append(sentenceID);<a name="line.216"></a>
<FONT color="green">217</FONT> tmpID.append('_');<a name="line.217"></a>
<FONT color="green">218</FONT> tmpID.append(Integer.toString(t.getIndex()));<a name="line.218"></a>
<FONT color="green">219</FONT> writer.write("id=\"");writer.write(tmpID.toString());writer.write("\" ");<a name="line.219"></a>
<FONT color="green">220</FONT> }<a name="line.220"></a>
<FONT color="green">221</FONT> <a name="line.221"></a>
<FONT color="green">222</FONT> for (ColumnDescription column : dataFormatInstance.getInputColumnDescriptionSet()) {<a name="line.222"></a>
<FONT color="green">223</FONT> writer.write(column.getName().toLowerCase());<a name="line.223"></a>
<FONT color="green">224</FONT> writer.write("=\"");<a name="line.224"></a>
<FONT color="green">225</FONT> writer.write(Util.xmlEscape(t.getLabelSymbol(column.getSymbolTable())));<a name="line.225"></a>
<FONT color="green">226</FONT> writer.write("\" "); <a name="line.226"></a>
<FONT color="green">227</FONT> }<a name="line.227"></a>
<FONT color="green">228</FONT> writer.write("/>\n");<a name="line.228"></a>
<FONT color="green">229</FONT> }<a name="line.229"></a>
<FONT color="green">230</FONT> writer.write(" </terminals>\n");<a name="line.230"></a>
<FONT color="green">231</FONT> } catch (IOException e) {<a name="line.231"></a>
<FONT color="green">232</FONT> throw new DataFormatException("The TigerXML writer is not able to write. ", e);<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> public void writeNonTerminals(PhraseStructure phraseStructure) throws MaltChainedException {<a name="line.236"></a>
<FONT color="green">237</FONT> try {<a name="line.237"></a>
<FONT color="green">238</FONT> SortedMap<Integer,Integer> heights = new TreeMap<Integer,Integer>();<a name="line.238"></a>
<FONT color="green">239</FONT> for (int index : phraseStructure.getNonTerminalIndices()) {<a name="line.239"></a>
<FONT color="green">240</FONT> heights.put(index, ((NonTerminalNode)phraseStructure.getNonTerminalNode(index)).getHeight());<a name="line.240"></a>
<FONT color="green">241</FONT> }<a name="line.241"></a>
<FONT color="green">242</FONT> writer.write(" <nonterminals>\n");<a name="line.242"></a>
<FONT color="green">243</FONT> boolean done = false;<a name="line.243"></a>
<FONT color="green">244</FONT> int h = 1;<a name="line.244"></a>
<FONT color="green">245</FONT> while (!done) {<a name="line.245"></a>
<FONT color="green">246</FONT> done = true;<a name="line.246"></a>
<FONT color="green">247</FONT> for (int index : phraseStructure.getNonTerminalIndices()) {<a name="line.247"></a>
<FONT color="green">248</FONT> if (heights.get(index) == h) {<a name="line.248"></a>
<FONT color="green">249</FONT> NonTerminalNode nt = (NonTerminalNode)phraseStructure.getNonTerminalNode(index);<a name="line.249"></a>
<FONT color="green">250</FONT> tmpID.setLength(0);<a name="line.250"></a>
<FONT color="green">251</FONT> tmpID.append(sentenceID);<a name="line.251"></a>
<FONT color="green">252</FONT> tmpID.append('_');<a name="line.252"></a>
<FONT color="green">253</FONT> tmpID.append(Integer.toString(nt.getIndex()+START_ID_OF_NONTERMINALS-1));<a name="line.253"></a>
<FONT color="green">254</FONT> writeNonTerminal(nt, tmpID.toString());<a name="line.254"></a>
<FONT color="green">255</FONT> done = false;<a name="line.255"></a>
<FONT color="green">256</FONT> }<a name="line.256"></a>
<FONT color="green">257</FONT> }<a name="line.257"></a>
<FONT color="green">258</FONT> h++;<a name="line.258"></a>
<FONT color="green">259</FONT> }<a name="line.259"></a>
<FONT color="green">260</FONT> <a name="line.260"></a>
<FONT color="green">261</FONT> writeNonTerminal((NonTerminalNode)phraseStructure.getPhraseStructureRoot(),rootID.toString());<a name="line.261"></a>
<FONT color="green">262</FONT> writer.write(" </nonterminals>\n");<a name="line.262"></a>
<FONT color="green">263</FONT> } catch (IOException e) {<a name="line.263"></a>
<FONT color="green">264</FONT> throw new DataFormatException("The TigerXML writer is not able to write. ", e);<a name="line.264"></a>
<FONT color="green">265</FONT> }<a name="line.265"></a>
<FONT color="green">266</FONT> }<a name="line.266"></a>
<FONT color="green">267</FONT> <a name="line.267"></a>
<FONT color="green">268</FONT> public void writeNonTerminal(NonTerminalNode nt, String id) throws MaltChainedException {<a name="line.268"></a>
<FONT color="green">269</FONT> try {<a name="line.269"></a>
<FONT color="green">270</FONT> writer.write(" <nt");<a name="line.270"></a>
<FONT color="green">271</FONT> writer.write(" id=\"");writer.write(id);writer.write("\" ");<a name="line.271"></a>
<FONT color="green">272</FONT> for (ColumnDescription column : dataFormatInstance.getPhraseStructureNodeLabelColumnDescriptionSet()) {<a name="line.272"></a>
<FONT color="green">273</FONT> if (nt.hasLabel(column.getSymbolTable())) {<a name="line.273"></a>
<FONT color="green">274</FONT> writer.write(column.getName().toLowerCase());<a name="line.274"></a>
<FONT color="green">275</FONT> writer.write("=");<a name="line.275"></a>
<FONT color="green">276</FONT> writer.write("\"");<a name="line.276"></a>
<FONT color="green">277</FONT> writer.write(Util.xmlEscape(nt.getLabelSymbol(column.getSymbolTable())));<a name="line.277"></a>
<FONT color="green">278</FONT> writer.write("\" ");<a name="line.278"></a>
<FONT color="green">279</FONT> }<a name="line.279"></a>
<FONT color="green">280</FONT> }<a name="line.280"></a>
<FONT color="green">281</FONT> writer.write(">\n");<a name="line.281"></a>
<FONT color="green">282</FONT> <a name="line.282"></a>
<FONT color="green">283</FONT> for (int i = 0, n = nt.nChildren(); i < n; i++) {<a name="line.283"></a>
<FONT color="green">284</FONT> PhraseStructureNode child = nt.getChild(i); <a name="line.284"></a>
<FONT color="green">285</FONT> writer.write(" <edge ");<a name="line.285"></a>
<FONT color="green">286</FONT> <a name="line.286"></a>
<FONT color="green">287</FONT> for (ColumnDescription column : dataFormatInstance.getPhraseStructureEdgeLabelColumnDescriptionSet()) {<a name="line.287"></a>
<FONT color="green">288</FONT> if (child.hasParentEdgeLabel(column.getSymbolTable())) {<a name="line.288"></a>
<FONT color="green">289</FONT> writer.write(column.getName().toLowerCase());<a name="line.289"></a>
<FONT color="green">290</FONT> writer.write("=\"");<a name="line.290"></a>
<FONT color="green">291</FONT> writer.write(Util.xmlEscape(child.getParentEdgeLabelSymbol(column.getSymbolTable())));<a name="line.291"></a>
<FONT color="green">292</FONT> writer.write("\" ");<a name="line.292"></a>
<FONT color="green">293</FONT> }<a name="line.293"></a>
<FONT color="green">294</FONT> }<a name="line.294"></a>
<FONT color="green">295</FONT> if (child instanceof TokenNode) {<a name="line.295"></a>
<FONT color="green">296</FONT> if (!labeledTerminalID) {<a name="line.296"></a>
<FONT color="green">297</FONT> tmpID.setLength(0);<a name="line.297"></a>
<FONT color="green">298</FONT> tmpID.append(sentenceID);<a name="line.298"></a>
<FONT color="green">299</FONT> tmpID.append('_');<a name="line.299"></a>
<FONT color="green">300</FONT> tmpID.append(Integer.toString(child.getIndex()));<a name="line.300"></a>
<FONT color="green">301</FONT> writer.write(" idref=\"");writer.write(tmpID.toString());writer.write("\"");<a name="line.301"></a>
<FONT color="green">302</FONT> } else {<a name="line.302"></a>
<FONT color="green">303</FONT> writer.write(" idref=\"");writer.write(child.getLabelSymbol(dataFormatInstance.getInputSymbolTables().get("ID")));writer.write("\"");<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> } else {<a name="line.306"></a>
<FONT color="green">307</FONT> tmpID.setLength(0);<a name="line.307"></a>
<FONT color="green">308</FONT> tmpID.append(sentenceID);<a name="line.308"></a>
<FONT color="green">309</FONT> tmpID.append('_');<a name="line.309"></a>
<FONT color="green">310</FONT> tmpID.append(Integer.toString(child.getIndex()+START_ID_OF_NONTERMINALS-1));<a name="line.310"></a>
<FONT color="green">311</FONT> writer.write(" idref=\"");writer.write(tmpID.toString());writer.write("\"");<a name="line.311"></a>
<FONT color="green">312</FONT> }<a name="line.312"></a>
<FONT color="green">313</FONT> writer.write(" />\n");<a name="line.313"></a>
<FONT color="green">314</FONT> }<a name="line.314"></a>
<FONT color="green">315</FONT> writer.write(" </nt>\n");<a name="line.315"></a>
<FONT color="green">316</FONT> } catch (IOException e) {<a name="line.316"></a>
<FONT color="green">317</FONT> throw new DataFormatException("The TigerXML writer is not able to write. ", e);<a name="line.317"></a>
<FONT color="green">318</FONT> }<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> <a name="line.321"></a>
<FONT color="green">322</FONT> private void writeTail() throws MaltChainedException {<a name="line.322"></a>
<FONT color="green">323</FONT> try {<a name="line.323"></a>
<FONT color="green">324</FONT> writer.write(" </body>\n");<a name="line.324"></a>
<FONT color="green">325</FONT> writer.write("</corpus>\n");<a name="line.325"></a>
<FONT color="green">326</FONT> writer.flush();<a name="line.326"></a>
<FONT color="green">327</FONT> // if (fileName != null && charsetName != null) {<a name="line.327"></a>
<FONT color="green">328</FONT> // writer.close();<a name="line.328"></a>
<FONT color="green">329</FONT> // writer = null;<a name="line.329"></a>
<FONT color="green">330</FONT> // BufferedWriter headerWriter = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(fileName+".header"),charsetName));<a name="line.330"></a>
<FONT color="green">331</FONT> // if (header == null) {<a name="line.331"></a>
<FONT color="green">332</FONT> // header = new TigerXMLHeader(dataFormatInstance.getSymbolTables());<a name="line.332"></a>
<FONT color="green">333</FONT> // }<a name="line.333"></a>
<FONT color="green">334</FONT> // <a name="line.334"></a>
<FONT color="green">335</FONT> // headerWriter.write(header.toTigerXML());<a name="line.335"></a>
<FONT color="green">336</FONT> // headerWriter.flush();<a name="line.336"></a>
<FONT color="green">337</FONT> // headerWriter.close();<a name="line.337"></a>
<FONT color="green">338</FONT> // }<a name="line.338"></a>
<FONT color="green">339</FONT> } catch (IOException e) {<a name="line.339"></a>
<FONT color="green">340</FONT> throw new DataFormatException("The TigerXML writer is not able to write. ", e);<a name="line.340"></a>
<FONT color="green">341</FONT> }<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> public int getSentenceCount() {<a name="line.344"></a>
<FONT color="green">345</FONT> return sentenceCount;<a name="line.345"></a>
<FONT color="green">346</FONT> }<a name="line.346"></a>
<FONT color="green">347</FONT> <a name="line.347"></a>
<FONT color="green">348</FONT> public void setSentenceCount(int sentenceCount) {<a name="line.348"></a>
<FONT color="green">349</FONT> this.sentenceCount = sentenceCount;<a name="line.349"></a>
<FONT color="green">350</FONT> }<a name="line.350"></a>
<FONT color="green">351</FONT> <a name="line.351"></a>
<FONT color="green">352</FONT> public DataFormatInstance getDataFormatInstance() {<a name="line.352"></a>
<FONT color="green">353</FONT> return dataFormatInstance;<a name="line.353"></a>
<FONT color="green">354</FONT> }<a name="line.354"></a>
<FONT color="green">355</FONT> <a name="line.355"></a>
<FONT color="green">356</FONT> public void setDataFormatInstance(DataFormatInstance dataFormatInstance) {<a name="line.356"></a>
<FONT color="green">357</FONT> this.dataFormatInstance = dataFormatInstance;<a name="line.357"></a>
<FONT color="green">358</FONT> labeledTerminalID = (dataFormatInstance.getInputColumnDescriptions().containsKey("id") || dataFormatInstance.getInputColumnDescriptions().containsKey("ID"));<a name="line.358"></a>
<FONT color="green">359</FONT> }<a name="line.359"></a>
<FONT color="green">360</FONT> <a name="line.360"></a>
<FONT color="green">361</FONT> public String getOptions() {<a name="line.361"></a>
<FONT color="green">362</FONT> return optionString;<a name="line.362"></a>
<FONT color="green">363</FONT> }<a name="line.363"></a>
<FONT color="green">364</FONT> <a name="line.364"></a>
<FONT color="green">365</FONT> public void setOptions(String optionString) throws MaltChainedException {<a name="line.365"></a>
<FONT color="green">366</FONT> this.optionString = optionString;<a name="line.366"></a>
<FONT color="green">367</FONT> rootHandling = RootHandling.NORMAL;<a name="line.367"></a>
<FONT color="green">368</FONT> <a name="line.368"></a>
<FONT color="green">369</FONT> String[] argv;<a name="line.369"></a>
<FONT color="green">370</FONT> try {<a name="line.370"></a>
<FONT color="green">371</FONT> argv = optionString.split("[_\\p{Blank}]");<a name="line.371"></a>
<FONT color="green">372</FONT> } catch (PatternSyntaxException e) {<a name="line.372"></a>
<FONT color="green">373</FONT> throw new DataFormatException("Could not split the TigerXML writer option '"+optionString+"'. ", e);<a name="line.373"></a>
<FONT color="green">374</FONT> }<a name="line.374"></a>
<FONT color="green">375</FONT> for (int i=0; i < argv.length-1; i++) {<a name="line.375"></a>
<FONT color="green">376</FONT> if(argv[i].charAt(0) != '-') {<a name="line.376"></a>
<FONT color="green">377</FONT> throw new DataFormatException("The argument flag should start with the following character '-', not with "+argv[i].charAt(0));<a name="line.377"></a>
<FONT color="green">378</FONT> }<a name="line.378"></a>
<FONT color="green">379</FONT> if(++i>=argv.length) {<a name="line.379"></a>
<FONT color="green">380</FONT> throw new DataFormatException("The last argument does not have any value. ");<a name="line.380"></a>
<FONT color="green">381</FONT> }<a name="line.381"></a>
<FONT color="green">382</FONT> switch(argv[i-1].charAt(1)) {<a name="line.382"></a>
<FONT color="green">383</FONT> case 'r': <a name="line.383"></a>
<FONT color="green">384</FONT> if (argv[i].equals("n")) {<a name="line.384"></a>
<FONT color="green">385</FONT> rootHandling = RootHandling.NORMAL;<a name="line.385"></a>
<FONT color="green">386</FONT> } else if (argv[i].equals("tal")) {<a name="line.386"></a>
<FONT color="green">387</FONT> rootHandling = RootHandling.TALBANKEN;<a name="line.387"></a>
<FONT color="green">388</FONT> }<a name="line.388"></a>
<FONT color="green">389</FONT> break;<a name="line.389"></a>
<FONT color="green">390</FONT> case 's': <a name="line.390"></a>
<FONT color="green">391</FONT> try {<a name="line.391"></a>
<FONT color="green">392</FONT> START_ID_OF_NONTERMINALS = Integer.parseInt(argv[i]);<a name="line.392"></a>
<FONT color="green">393</FONT> } catch (NumberFormatException e){<a name="line.393"></a>
<FONT color="green">394</FONT> throw new MaltChainedException("The TigerXML writer option -s must be an integer value. ");<a name="line.394"></a>
<FONT color="green">395</FONT> }<a name="line.395"></a>
<FONT color="green">396</FONT> break;<a name="line.396"></a>
<FONT color="green">397</FONT> case 'v': <a name="line.397"></a>
<FONT color="green">398</FONT> VROOT_SYMBOL = argv[i];<a name="line.398"></a>
<FONT color="green">399</FONT> break; <a name="line.399"></a>
<FONT color="green">400</FONT> default:<a name="line.400"></a>
<FONT color="green">401</FONT> throw new LibsvmException("Unknown TigerXML writer option: '"+argv[i-1]+"' with value '"+argv[i]+"'. "); <a name="line.401"></a>
<FONT color="green">402</FONT> }<a name="line.402"></a>
<FONT color="green">403</FONT> } <a name="line.403"></a>
<FONT color="green">404</FONT> }<a name="line.404"></a>
<FONT color="green">405</FONT> }<a name="line.405"></a>
</PRE>
</BODY>
</HTML>