<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT> package org.maltparser.core.syntaxgraph.reader;<a name="line.1"></a>
<FONT color="green">002</FONT> <a name="line.2"></a>
<FONT color="green">003</FONT> import java.io.BufferedReader;<a name="line.3"></a>
<FONT color="green">004</FONT> import java.io.FileInputStream;<a name="line.4"></a>
<FONT color="green">005</FONT> import java.io.FileNotFoundException;<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.InputStream;<a name="line.7"></a>
<FONT color="green">008</FONT> import java.io.InputStreamReader;<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.net.URL;<a name="line.10"></a>
<FONT color="green">011</FONT> import java.util.SortedMap;<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 javax.xml.stream.XMLInputFactory;<a name="line.14"></a>
<FONT color="green">015</FONT> import javax.xml.stream.XMLStreamConstants;<a name="line.15"></a>
<FONT color="green">016</FONT> import javax.xml.stream.XMLStreamException;<a name="line.16"></a>
<FONT color="green">017</FONT> import javax.xml.stream.XMLStreamReader;<a name="line.17"></a>
<FONT color="green">018</FONT> <a name="line.18"></a>
<FONT color="green">019</FONT> import org.maltparser.core.exception.MaltChainedException;<a name="line.19"></a>
<FONT color="green">020</FONT> import org.maltparser.core.io.dataformat.DataFormatException;<a name="line.20"></a>
<FONT color="green">021</FONT> import org.maltparser.core.io.dataformat.DataFormatInstance;<a name="line.21"></a>
<FONT color="green">022</FONT> import org.maltparser.core.symbol.SymbolTable;<a name="line.22"></a>
<FONT color="green">023</FONT> import org.maltparser.core.syntaxgraph.MappablePhraseStructureGraph;<a name="line.23"></a>
<FONT color="green">024</FONT> import org.maltparser.core.syntaxgraph.PhraseStructure;<a name="line.24"></a>
<FONT color="green">025</FONT> import org.maltparser.core.syntaxgraph.SyntaxGraphException;<a name="line.25"></a>
<FONT color="green">026</FONT> import org.maltparser.core.syntaxgraph.TokenStructure;<a name="line.26"></a>
<FONT color="green">027</FONT> import org.maltparser.core.syntaxgraph.edge.Edge;<a name="line.27"></a>
<FONT color="green">028</FONT> import org.maltparser.core.syntaxgraph.node.NonTerminalNode;<a name="line.28"></a>
<FONT color="green">029</FONT> import org.maltparser.core.syntaxgraph.node.PhraseStructureNode;<a name="line.29"></a>
<FONT color="green">030</FONT> <a name="line.30"></a>
<FONT color="green">031</FONT> /**<a name="line.31"></a>
<FONT color="green">032</FONT> *<a name="line.32"></a>
<FONT color="green">033</FONT> *<a name="line.33"></a>
<FONT color="green">034</FONT> * @author Johan Hall<a name="line.34"></a>
<FONT color="green">035</FONT> */<a name="line.35"></a>
<FONT color="green">036</FONT> public class TigerXMLReader implements SyntaxGraphReader {<a name="line.36"></a>
<FONT color="green">037</FONT> // private TigerXMLHeader header;<a name="line.37"></a>
<FONT color="green">038</FONT> private XMLStreamReader reader;<a name="line.38"></a>
<FONT color="green">039</FONT> private int sentenceCount;<a name="line.39"></a>
<FONT color="green">040</FONT> private DataFormatInstance dataFormatInstance;<a name="line.40"></a>
<FONT color="green">041</FONT> private StringBuffer ntid;<a name="line.41"></a>
<FONT color="green">042</FONT> private final StringBuilder graphRootID;<a name="line.42"></a>
<FONT color="green">043</FONT> // private StringBuilder elementContent; <a name="line.43"></a>
<FONT color="green">044</FONT> // private StringBuilder valueName;<a name="line.44"></a>
<FONT color="green">045</FONT> // private StringBuilder currentFeatureName;<a name="line.45"></a>
<FONT color="green">046</FONT> // private Domain domain;<a name="line.46"></a>
<FONT color="green">047</FONT> // private boolean collectChar = false;<a name="line.47"></a>
<FONT color="green">048</FONT> private String optionString;<a name="line.48"></a>
<FONT color="green">049</FONT> private String fileName = null;<a name="line.49"></a>
<FONT color="green">050</FONT> private URL url = null;<a name="line.50"></a>
<FONT color="green">051</FONT> private String charsetName;<a name="line.51"></a>
<FONT color="green">052</FONT> private int nIterations;<a name="line.52"></a>
<FONT color="green">053</FONT> private int cIterations;<a name="line.53"></a>
<FONT color="green">054</FONT> private int START_ID_OF_NONTERMINALS = 500;<a name="line.54"></a>
<FONT color="green">055</FONT> private boolean closeStream = true;<a name="line.55"></a>
<FONT color="green">056</FONT> <a name="line.56"></a>
<FONT color="green">057</FONT> public TigerXMLReader() {<a name="line.57"></a>
<FONT color="green">058</FONT> this.ntid = new StringBuffer();<a name="line.58"></a>
<FONT color="green">059</FONT> // elementContent = new StringBuilder();<a name="line.59"></a>
<FONT color="green">060</FONT> // valueName = new StringBuilder();<a name="line.60"></a>
<FONT color="green">061</FONT> // currentFeatureName = new StringBuilder(); <a name="line.61"></a>
<FONT color="green">062</FONT> graphRootID = new StringBuilder(); <a name="line.62"></a>
<FONT color="green">063</FONT> nIterations = 1;<a name="line.63"></a>
<FONT color="green">064</FONT> cIterations = 1;<a name="line.64"></a>
<FONT color="green">065</FONT> }<a name="line.65"></a>
<FONT color="green">066</FONT> <a name="line.66"></a>
<FONT color="green">067</FONT> private void reopen() throws MaltChainedException {<a name="line.67"></a>
<FONT color="green">068</FONT> close();<a name="line.68"></a>
<FONT color="green">069</FONT> if (fileName != null) {<a name="line.69"></a>
<FONT color="green">070</FONT> open(fileName, charsetName);<a name="line.70"></a>
<FONT color="green">071</FONT> } else if (url != null) {<a name="line.71"></a>
<FONT color="green">072</FONT> open(url, charsetName);<a name="line.72"></a>
<FONT color="green">073</FONT> } else {<a name="line.73"></a>
<FONT color="green">074</FONT> throw new DataFormatException("The input stream cannot be reopen. ");<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> public void open(String fileName, String charsetName) throws MaltChainedException {<a name="line.78"></a>
<FONT color="green">079</FONT> setFileName(fileName);<a name="line.79"></a>
<FONT color="green">080</FONT> setCharsetName(charsetName);<a name="line.80"></a>
<FONT color="green">081</FONT> try {<a name="line.81"></a>
<FONT color="green">082</FONT> open(new FileInputStream(fileName), charsetName);<a name="line.82"></a>
<FONT color="green">083</FONT> }catch (FileNotFoundException e) {<a name="line.83"></a>
<FONT color="green">084</FONT> throw new DataFormatException("The input file '"+fileName+"' cannot be found. ", e);<a name="line.84"></a>
<FONT color="green">085</FONT> }<a name="line.85"></a>
<FONT color="green">086</FONT> }<a name="line.86"></a>
<FONT color="green">087</FONT> public void open(URL url, String charsetName) throws MaltChainedException {<a name="line.87"></a>
<FONT color="green">088</FONT> setUrl(url);<a name="line.88"></a>
<FONT color="green">089</FONT> setCharsetName(charsetName);<a name="line.89"></a>
<FONT color="green">090</FONT> try {<a name="line.90"></a>
<FONT color="green">091</FONT> open(url.openStream(), charsetName);<a name="line.91"></a>
<FONT color="green">092</FONT> } catch (IOException e) {<a name="line.92"></a>
<FONT color="green">093</FONT> throw new DataFormatException("The URL '"+url.toString()+"' cannot be opened. ", e);<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 open(InputStream is, String charsetName) throws MaltChainedException {<a name="line.97"></a>
<FONT color="green">098</FONT> try {<a name="line.98"></a>
<FONT color="green">099</FONT> if (is == System.in) {<a name="line.99"></a>
<FONT color="green">100</FONT> closeStream = false;<a name="line.100"></a>
<FONT color="green">101</FONT> }<a name="line.101"></a>
<FONT color="green">102</FONT> open(new InputStreamReader(is, charsetName));<a name="line.102"></a>
<FONT color="green">103</FONT> } catch (UnsupportedEncodingException e) {<a name="line.103"></a>
<FONT color="green">104</FONT> throw new DataFormatException("The character encoding set '"+charsetName+"' isn't supported. ", e);<a name="line.104"></a>
<FONT color="green">105</FONT> }<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> private void open(InputStreamReader isr) throws MaltChainedException {<a name="line.108"></a>
<FONT color="green">109</FONT> try {<a name="line.109"></a>
<FONT color="green">110</FONT> XMLInputFactory factory = XMLInputFactory.newInstance();<a name="line.110"></a>
<FONT color="green">111</FONT> setReader(factory.createXMLStreamReader(new BufferedReader(isr)));<a name="line.111"></a>
<FONT color="green">112</FONT> } catch (XMLStreamException e) {<a name="line.112"></a>
<FONT color="green">113</FONT> throw new DataFormatException("XML input file could be opened. ", e);<a name="line.113"></a>
<FONT color="green">114</FONT> } <a name="line.114"></a>
<FONT color="green">115</FONT> setSentenceCount(0);<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> public void readProlog() throws MaltChainedException {<a name="line.118"></a>
<FONT color="green">119</FONT> <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 boolean readSentence(TokenStructure syntaxGraph) throws MaltChainedException {<a name="line.122"></a>
<FONT color="green">123</FONT> if (syntaxGraph == null || !(syntaxGraph instanceof PhraseStructure)) {<a name="line.123"></a>
<FONT color="green">124</FONT> return false;<a name="line.124"></a>
<FONT color="green">125</FONT> }<a name="line.125"></a>
<FONT color="green">126</FONT> syntaxGraph.clear();<a name="line.126"></a>
<FONT color="green">127</FONT> final PhraseStructure phraseStructure = (PhraseStructure)syntaxGraph;<a name="line.127"></a>
<FONT color="green">128</FONT> PhraseStructureNode parent = null;<a name="line.128"></a>
<FONT color="green">129</FONT> PhraseStructureNode child = null;<a name="line.129"></a>
<FONT color="green">130</FONT> // if (header == null) {<a name="line.130"></a>
<FONT color="green">131</FONT> // header = new TigerXMLHeader(syntaxGraph.getSymbolTables());<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> try {<a name="line.134"></a>
<FONT color="green">135</FONT> while (true) {<a name="line.135"></a>
<FONT color="green">136</FONT> int event = reader.next();<a name="line.136"></a>
<FONT color="green">137</FONT> if (event == XMLStreamConstants.START_ELEMENT) {<a name="line.137"></a>
<FONT color="green">138</FONT> if (reader.getLocalName().length() == 0) {<a name="line.138"></a>
<FONT color="green">139</FONT> continue;<a name="line.139"></a>
<FONT color="green">140</FONT> }<a name="line.140"></a>
<FONT color="green">141</FONT> if (reader.getLocalName().charAt(0) == 'e') {<a name="line.141"></a>
<FONT color="green">142</FONT> // e -> edge, edgelabel<a name="line.142"></a>
<FONT color="green">143</FONT> if (reader.getLocalName().length() == 4) { //edge<a name="line.143"></a>
<FONT color="green">144</FONT> int childid = -1;<a name="line.144"></a>
<FONT color="green">145</FONT> int indexSep = reader.getAttributeValue(null, "idref").indexOf('_');<a name="line.145"></a>
<FONT color="green">146</FONT> <a name="line.146"></a>
<FONT color="green">147</FONT> try {<a name="line.147"></a>
<FONT color="green">148</FONT> if (indexSep != -1) {<a name="line.148"></a>
<FONT color="green">149</FONT> childid = Integer.parseInt(reader.getAttributeValue(null, "idref").substring(indexSep+1));<a name="line.149"></a>
<FONT color="green">150</FONT> } else {<a name="line.150"></a>
<FONT color="green">151</FONT> childid = Integer.parseInt(reader.getAttributeValue(null, "idref"));<a name="line.151"></a>
<FONT color="green">152</FONT> }<a name="line.152"></a>
<FONT color="green">153</FONT> if (childid == -1) {<a name="line.153"></a>
<FONT color="green">154</FONT> throw new SyntaxGraphException("The tiger reader couldn't recognize the idref attribute '"+reader.getAttributeValue(null, "idref")+"' of the edge element. ");<a name="line.154"></a>
<FONT color="green">155</FONT> }<a name="line.155"></a>
<FONT color="green">156</FONT> } catch (NumberFormatException e) {<a name="line.156"></a>
<FONT color="green">157</FONT> throw new SyntaxGraphException("The tiger reader couldn't recognize the idref attribute '"+reader.getAttributeValue(null, "idref")+"' of the edge element. ");<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> if (childid < START_ID_OF_NONTERMINALS) {<a name="line.160"></a>
<FONT color="green">161</FONT> child = phraseStructure.getTokenNode(childid);<a name="line.161"></a>
<FONT color="green">162</FONT> } else {<a name="line.162"></a>
<FONT color="green">163</FONT> <a name="line.163"></a>
<FONT color="green">164</FONT> child = phraseStructure.getNonTerminalNode(childid-START_ID_OF_NONTERMINALS+1);<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> Edge e = phraseStructure.addPhraseStructureEdge(parent, child);<a name="line.167"></a>
<FONT color="green">168</FONT> SortedMap<String, SymbolTable> inputTables = dataFormatInstance.getPhraseStructureEdgeLabelSymbolTables();<a name="line.168"></a>
<FONT color="green">169</FONT> for (String name : inputTables.keySet()) {<a name="line.169"></a>
<FONT color="green">170</FONT> e.addLabel(inputTables.get(name), reader.getAttributeValue(null, name.toLowerCase()));<a name="line.170"></a>
<FONT color="green">171</FONT> }<a name="line.171"></a>
<FONT color="green">172</FONT> } else if (reader.getLocalName().equals("edgelabel")) { // edgelabel<a name="line.172"></a>
<FONT color="green">173</FONT> // domain = Domain.EL;<a name="line.173"></a>
<FONT color="green">174</FONT> }<a name="line.174"></a>
<FONT color="green">175</FONT> } else if (reader.getLocalName().charAt(0) == 'n') {<a name="line.175"></a>
<FONT color="green">176</FONT> // n -> nt, nonterminals, name<a name="line.176"></a>
<FONT color="green">177</FONT> if (reader.getLocalName().length() == 2) { // nt<a name="line.177"></a>
<FONT color="green">178</FONT> final String id = reader.getAttributeValue(null, "id");<a name="line.178"></a>
<FONT color="green">179</FONT> if (graphRootID.length() == id.length() && graphRootID.toString().equals(id)) {<a name="line.179"></a>
<FONT color="green">180</FONT> parent = phraseStructure.getPhraseStructureRoot();<a name="line.180"></a>
<FONT color="green">181</FONT> } else {<a name="line.181"></a>
<FONT color="green">182</FONT> int index = id.indexOf('_');<a name="line.182"></a>
<FONT color="green">183</FONT> if (index != -1) {<a name="line.183"></a>
<FONT color="green">184</FONT> parent = phraseStructure.addNonTerminalNode(Integer.parseInt(id.substring(index+1))-START_ID_OF_NONTERMINALS+1);<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> SortedMap<String, SymbolTable> inputTables = dataFormatInstance.getPhraseStructureNodeLabelSymbolTables();<a name="line.187"></a>
<FONT color="green">188</FONT> for (String name : inputTables.keySet()) {<a name="line.188"></a>
<FONT color="green">189</FONT> parent.addLabel(inputTables.get(name), reader.getAttributeValue(null, name.toLowerCase()));<a name="line.189"></a>
<FONT color="green">190</FONT> }<a name="line.190"></a>
<FONT color="green">191</FONT> } else if (reader.getLocalName().equals("name")) { // name<a name="line.191"></a>
<FONT color="green">192</FONT> // elementContent.setLength(0);<a name="line.192"></a>
<FONT color="green">193</FONT> // collectChar = true;<a name="line.193"></a>
<FONT color="green">194</FONT> }<a name="line.194"></a>
<FONT color="green">195</FONT> } else if (reader.getLocalName().charAt(0) == 't') {<a name="line.195"></a>
<FONT color="green">196</FONT> // t -> t, terminals<a name="line.196"></a>
<FONT color="green">197</FONT> if (reader.getLocalName().length() == 1) { // t<a name="line.197"></a>
<FONT color="green">198</FONT> SortedMap<String, SymbolTable> inputTables = dataFormatInstance.getInputSymbolTables();<a name="line.198"></a>
<FONT color="green">199</FONT> child = syntaxGraph.addTokenNode();<a name="line.199"></a>
<FONT color="green">200</FONT> for (String name : inputTables.keySet()) {<a name="line.200"></a>
<FONT color="green">201</FONT> child.addLabel(inputTables.get(name), reader.getAttributeValue(null, name.toLowerCase()));<a name="line.201"></a>
<FONT color="green">202</FONT> }<a name="line.202"></a>
<FONT color="green">203</FONT> }<a name="line.203"></a>
<FONT color="green">204</FONT> } else if (reader.getLocalName().charAt(0) == 's') {<a name="line.204"></a>
<FONT color="green">205</FONT> // s -> subcorpus, secedge, s, secedgelabel<a name="line.205"></a>
<FONT color="green">206</FONT> if (reader.getLocalName().length() == 1) { // s<a name="line.206"></a>
<FONT color="green">207</FONT> String id = reader.getAttributeValue(null, "id");<a name="line.207"></a>
<FONT color="green">208</FONT> boolean indexable = false;<a name="line.208"></a>
<FONT color="green">209</FONT> int index = -1;<a name="line.209"></a>
<FONT color="green">210</FONT> if (id != null && id.length() > 0) {<a name="line.210"></a>
<FONT color="green">211</FONT> for (int i = 0, n = id.length(); i < n; i++) {<a name="line.211"></a>
<FONT color="green">212</FONT> if (Character.isDigit(id.charAt(i))) {<a name="line.212"></a>
<FONT color="green">213</FONT> if (index == -1) { <a name="line.213"></a>
<FONT color="green">214</FONT> index = i;<a name="line.214"></a>
<FONT color="green">215</FONT> }<a name="line.215"></a>
<FONT color="green">216</FONT> indexable = true;<a name="line.216"></a>
<FONT color="green">217</FONT> }<a name="line.217"></a>
<FONT color="green">218</FONT> }<a name="line.218"></a>
<FONT color="green">219</FONT> }<a name="line.219"></a>
<FONT color="green">220</FONT> if (indexable) {<a name="line.220"></a>
<FONT color="green">221</FONT> phraseStructure.setSentenceID(Integer.parseInt(id.substring(index)));<a name="line.221"></a>
<FONT color="green">222</FONT> } else {<a name="line.222"></a>
<FONT color="green">223</FONT> phraseStructure.setSentenceID(sentenceCount+1);<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> } else if (reader.getLocalName().charAt(0) == 'v') {<a name="line.226"></a>
<FONT color="green">227</FONT> // v -> variable, value<a name="line.227"></a>
<FONT color="green">228</FONT> // if (reader.getLocalName().equals("value")) {<a name="line.228"></a>
<FONT color="green">229</FONT> // valueName.setLength(0);<a name="line.229"></a>
<FONT color="green">230</FONT> // valueName.append(reader.getAttributeValue(null, "name"));<a name="line.230"></a>
<FONT color="green">231</FONT> // elementContent.setLength(0);<a name="line.231"></a>
<FONT color="green">232</FONT> // collectChar = true;<a name="line.232"></a>
<FONT color="green">233</FONT> // }<a name="line.233"></a>
<FONT color="green">234</FONT> } else {<a name="line.234"></a>
<FONT color="green">235</FONT> // a -> annotation, author<a name="line.235"></a>
<FONT color="green">236</FONT> // b -> body<a name="line.236"></a>
<FONT color="green">237</FONT> // c -> corpus<a name="line.237"></a>
<FONT color="green">238</FONT> // d -> date, description,<a name="line.238"></a>
<FONT color="green">239</FONT> // f -> feature, format<a name="line.239"></a>
<FONT color="green">240</FONT> // g -> graph<a name="line.240"></a>
<FONT color="green">241</FONT> // h -> head, history<a name="line.241"></a>
<FONT color="green">242</FONT> // m -> matches, match<a name="line.242"></a>
<FONT color="green">243</FONT> if (reader.getLocalName().equals("graph")) {<a name="line.243"></a>
<FONT color="green">244</FONT> graphRootID.setLength(0);<a name="line.244"></a>
<FONT color="green">245</FONT> graphRootID.append(reader.getAttributeValue(null, "root"));<a name="line.245"></a>
<FONT color="green">246</FONT> } else if (reader.getLocalName().equals("corpus")) {<a name="line.246"></a>
<FONT color="green">247</FONT> // header.setCorpusID(reader.getAttributeValue(null, "id"));<a name="line.247"></a>
<FONT color="green">248</FONT> // header.setCorpusID(reader.getAttributeValue(null, "version"));<a name="line.248"></a>
<FONT color="green">249</FONT> } else if (reader.getLocalName().equals("feature")) {<a name="line.249"></a>
<FONT color="green">250</FONT> // if (header != null) {<a name="line.250"></a>
<FONT color="green">251</FONT> // currentFeatureName.setLength(0);<a name="line.251"></a>
<FONT color="green">252</FONT> // currentFeatureName.append(reader.getAttributeValue(null, "name"));<a name="line.252"></a>
<FONT color="green">253</FONT> // header.addFeature(reader.getAttributeValue(null, "name"), reader.getAttributeValue(null, "domain"));<a name="line.253"></a>
<FONT color="green">254</FONT> // }<a name="line.254"></a>
<FONT color="green">255</FONT> // domain = Domain.valueOf(reader.getAttributeValue(null, "domain"));<a name="line.255"></a>
<FONT color="green">256</FONT> } else if (reader.getLocalName().equals("secedgelabel")) {<a name="line.256"></a>
<FONT color="green">257</FONT> // domain = Domain.SEL;<a name="line.257"></a>
<FONT color="green">258</FONT> } else if (reader.getLocalName().equals("author")) {<a name="line.258"></a>
<FONT color="green">259</FONT> // elementContent.setLength(0);<a name="line.259"></a>
<FONT color="green">260</FONT> // collectChar = true;<a name="line.260"></a>
<FONT color="green">261</FONT> } else if (reader.getLocalName().equals("date")) {<a name="line.261"></a>
<FONT color="green">262</FONT> // elementContent.setLength(0);<a name="line.262"></a>
<FONT color="green">263</FONT> // collectChar = true;<a name="line.263"></a>
<FONT color="green">264</FONT> } else if (reader.getLocalName().equals("description")) {<a name="line.264"></a>
<FONT color="green">265</FONT> // elementContent.setLength(0);<a name="line.265"></a>
<FONT color="green">266</FONT> // collectChar = true;<a name="line.266"></a>
<FONT color="green">267</FONT> } else if (reader.getLocalName().equals("format")) {<a name="line.267"></a>
<FONT color="green">268</FONT> // elementContent.setLength(0);<a name="line.268"></a>
<FONT color="green">269</FONT> // collectChar = true;<a name="line.269"></a>
<FONT color="green">270</FONT> } else if (reader.getLocalName().equals("history")) {<a name="line.270"></a>
<FONT color="green">271</FONT> // elementContent.setLength(0);<a name="line.271"></a>
<FONT color="green">272</FONT> // collectChar = true;<a name="line.272"></a>
<FONT color="green">273</FONT> } <a name="line.273"></a>
<FONT color="green">274</FONT> }<a name="line.274"></a>
<FONT color="green">275</FONT> } else if (event == XMLStreamConstants.END_ELEMENT) {<a name="line.275"></a>
<FONT color="green">276</FONT> if (reader.getLocalName().length() == 0) {<a name="line.276"></a>
<FONT color="green">277</FONT> continue;<a name="line.277"></a>
<FONT color="green">278</FONT> }<a name="line.278"></a>
<FONT color="green">279</FONT> if (reader.getLocalName().charAt(0) == 'e') {<a name="line.279"></a>
<FONT color="green">280</FONT> // e -> edge, edgelabel<a name="line.280"></a>
<FONT color="green">281</FONT> } else if (reader.getLocalName().charAt(0) == 'n') {<a name="line.281"></a>
<FONT color="green">282</FONT> // n -> nt, nonterminals, name<a name="line.282"></a>
<FONT color="green">283</FONT> if (reader.getLocalName().equals("nt")) {<a name="line.283"></a>
<FONT color="green">284</FONT> ntid.setLength(0);<a name="line.284"></a>
<FONT color="green">285</FONT> }<a name="line.285"></a>
<FONT color="green">286</FONT> else if (reader.getLocalName().equals("nonterminals")) {<a name="line.286"></a>
<FONT color="green">287</FONT> if (phraseStructure.nTokenNode() == 1 && phraseStructure.nNonTerminals() == 0 &&((NonTerminalNode)phraseStructure.getPhraseStructureRoot()).nChildren() == 0) {<a name="line.287"></a>
<FONT color="green">288</FONT> Edge e = phraseStructure.addPhraseStructureEdge(phraseStructure.getPhraseStructureRoot(), phraseStructure.getTokenNode(1));<a name="line.288"></a>
<FONT color="green">289</FONT> SortedMap<String, SymbolTable> inputTables = dataFormatInstance.getPhraseStructureEdgeLabelSymbolTables();<a name="line.289"></a>
<FONT color="green">290</FONT> for (String name : inputTables.keySet()) {<a name="line.290"></a>
<FONT color="green">291</FONT> e.addLabel(inputTables.get(name), "--");<a name="line.291"></a>
<FONT color="green">292</FONT> }<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> // else if (reader.getLocalName().equals("name")) {<a name="line.295"></a>
<FONT color="green">296</FONT> // if (header != null) {<a name="line.296"></a>
<FONT color="green">297</FONT> // header.setMetaName(elementContent.toString());<a name="line.297"></a>
<FONT color="green">298</FONT> // }<a name="line.298"></a>
<FONT color="green">299</FONT> // collectChar = false;<a name="line.299"></a>
<FONT color="green">300</FONT> // }<a name="line.300"></a>
<FONT color="green">301</FONT> } else if (reader.getLocalName().charAt(0) == 't') {<a name="line.301"></a>
<FONT color="green">302</FONT> // t -> t, terminals<a name="line.302"></a>
<FONT color="green">303</FONT> } else if (reader.getLocalName().charAt(0) == 's') {<a name="line.303"></a>
<FONT color="green">304</FONT> // s -> subcorpus, secedge, s, secedgelabel<a name="line.304"></a>
<FONT color="green">305</FONT> if (reader.getLocalName().equals("s")) {<a name="line.305"></a>
<FONT color="green">306</FONT> if (syntaxGraph.hasTokens()) {<a name="line.306"></a>
<FONT color="green">307</FONT> sentenceCount++;<a name="line.307"></a>
<FONT color="green">308</FONT> }<a name="line.308"></a>
<FONT color="green">309</FONT> if (syntaxGraph instanceof MappablePhraseStructureGraph) {<a name="line.309"></a>
<FONT color="green">310</FONT> ((MappablePhraseStructureGraph)syntaxGraph).getMapping().updateDependenyGraph(((MappablePhraseStructureGraph)syntaxGraph), ((PhraseStructure)syntaxGraph).getPhraseStructureRoot());<a name="line.310"></a>
<FONT color="green">311</FONT> }<a name="line.311"></a>
<FONT color="green">312</FONT> return true;<a name="line.312"></a>
<FONT color="green">313</FONT> }<a name="line.313"></a>
<FONT color="green">314</FONT> } else if (reader.getLocalName().charAt(0) == 'v') {<a name="line.314"></a>
<FONT color="green">315</FONT> // v -> variable, value<a name="line.315"></a>
<FONT color="green">316</FONT> // if (reader.getLocalName().equals("value")) {<a name="line.316"></a>
<FONT color="green">317</FONT> // if (header != null) {<a name="line.317"></a>
<FONT color="green">318</FONT> // if (domain == Domain.T || domain == Domain.NT || domain == Domain.FREC) {<a name="line.318"></a>
<FONT color="green">319</FONT> // header.addFeatureValue(currentFeatureName.toString(), valueName.toString(), elementContent.toString());<a name="line.319"></a>
<FONT color="green">320</FONT> // } else if (domain == Domain.EL) {<a name="line.320"></a>
<FONT color="green">321</FONT> // header.addEdgeLabelValue(valueName.toString(), elementContent.toString());<a name="line.321"></a>
<FONT color="green">322</FONT> // } else if (domain == Domain.SEL) {<a name="line.322"></a>
<FONT color="green">323</FONT> // header.addSecEdgeLabelValue(valueName.toString(), elementContent.toString());<a name="line.323"></a>
<FONT color="green">324</FONT> // }<a name="line.324"></a>
<FONT color="green">325</FONT> // }<a name="line.325"></a>
<FONT color="green">326</FONT> // collectChar = false;<a name="line.326"></a>
<FONT color="green">327</FONT> // }<a name="line.327"></a>
<FONT color="green">328</FONT> } else {<a name="line.328"></a>
<FONT color="green">329</FONT> // a -> annotation, author<a name="line.329"></a>
<FONT color="green">330</FONT> // b -> body<a name="line.330"></a>
<FONT color="green">331</FONT> // c -> corpus<a name="line.331"></a>
<FONT color="green">332</FONT> // d -> date, description,<a name="line.332"></a>
<FONT color="green">333</FONT> // f -> feature, format<a name="line.333"></a>
<FONT color="green">334</FONT> // g -> graph<a name="line.334"></a>
<FONT color="green">335</FONT> // h -> head, history<a name="line.335"></a>
<FONT color="green">336</FONT> // m -> matches, match<a name="line.336"></a>
<FONT color="green">337</FONT> if (reader.getLocalName().equals("body")) {<a name="line.337"></a>
<FONT color="green">338</FONT> //sentence = dataStructures.getSentence();<a name="line.338"></a>
<FONT color="green">339</FONT> //phraseTree = dataStructures.getInPhraseTree();<a name="line.339"></a>
<FONT color="green">340</FONT> //sentence.clear();<a name="line.340"></a>
<FONT color="green">341</FONT> //phraseTree.clear();<a name="line.341"></a>
<FONT color="green">342</FONT> //dataStructures.setLastProcessObject(true);<a name="line.342"></a>
<FONT color="green">343</FONT> } else if (reader.getLocalName().equals("author")) {<a name="line.343"></a>
<FONT color="green">344</FONT> // if (header != null) {<a name="line.344"></a>
<FONT color="green">345</FONT> // header.setMetaAuthor(elementContent.toString());<a name="line.345"></a>
<FONT color="green">346</FONT> // }<a name="line.346"></a>
<FONT color="green">347</FONT> // collectChar = false;<a name="line.347"></a>
<FONT color="green">348</FONT> } else if (reader.getLocalName().equals("date")) {<a name="line.348"></a>
<FONT color="green">349</FONT> // if (header != null) {<a name="line.349"></a>
<FONT color="green">350</FONT> // header.setMetaInDate(elementContent.toString());<a name="line.350"></a>
<FONT color="green">351</FONT> // }<a name="line.351"></a>
<FONT color="green">352</FONT> // collectChar = false;<a name="line.352"></a>
<FONT color="green">353</FONT> } else if (reader.getLocalName().equals("description")) {<a name="line.353"></a>
<FONT color="green">354</FONT> // if (header != null) {<a name="line.354"></a>
<FONT color="green">355</FONT> // header.setMetaDescription(elementContent.toString());<a name="line.355"></a>
<FONT color="green">356</FONT> // }<a name="line.356"></a>
<FONT color="green">357</FONT> // collectChar = false;<a name="line.357"></a>
<FONT color="green">358</FONT> } else if (reader.getLocalName().equals("format")) {<a name="line.358"></a>
<FONT color="green">359</FONT> // if (header != null) {<a name="line.359"></a>
<FONT color="green">360</FONT> // header.setMetaFormat(elementContent.toString());<a name="line.360"></a>
<FONT color="green">361</FONT> // }<a name="line.361"></a>
<FONT color="green">362</FONT> // collectChar = false;<a name="line.362"></a>
<FONT color="green">363</FONT> } else if (reader.getLocalName().equals("history")) {<a name="line.363"></a>
<FONT color="green">364</FONT> // if (header != null) {<a name="line.364"></a>
<FONT color="green">365</FONT> // header.setMetaHistory(elementContent.toString());<a name="line.365"></a>
<FONT color="green">366</FONT> // }<a name="line.366"></a>
<FONT color="green">367</FONT> // collectChar = false;<a name="line.367"></a>
<FONT color="green">368</FONT> } /* else if (reader.getLocalName().equals("annotation")) {<a name="line.368"></a>
<FONT color="green">369</FONT> if (header != null) {<a name="line.369"></a>
<FONT color="green">370</FONT> System.out.println(header.toTigerXML());<a name="line.370"></a>
<FONT color="green">371</FONT> }<a name="line.371"></a>
<FONT color="green">372</FONT> collectChar = false;<a name="line.372"></a>
<FONT color="green">373</FONT> } */<a name="line.373"></a>
<FONT color="green">374</FONT> } <a name="line.374"></a>
<FONT color="green">375</FONT> } else if (event == XMLStreamConstants.END_DOCUMENT) {<a name="line.375"></a>
<FONT color="green">376</FONT> if (syntaxGraph.hasTokens()) {<a name="line.376"></a>
<FONT color="green">377</FONT> sentenceCount++;<a name="line.377"></a>
<FONT color="green">378</FONT> }<a name="line.378"></a>
<FONT color="green">379</FONT> if (cIterations < nIterations) {<a name="line.379"></a>
<FONT color="green">380</FONT> cIterations++;<a name="line.380"></a>
<FONT color="green">381</FONT> reopen();<a name="line.381"></a>
<FONT color="green">382</FONT> return true;<a name="line.382"></a>
<FONT color="green">383</FONT> }<a name="line.383"></a>
<FONT color="green">384</FONT> return false;<a name="line.384"></a>
<FONT color="green">385</FONT> } else if (event == XMLStreamConstants.CHARACTERS) {<a name="line.385"></a>
<FONT color="green">386</FONT> // if (collectChar) {<a name="line.386"></a>
<FONT color="green">387</FONT> // char[] ch = reader.getTextCharacters();<a name="line.387"></a>
<FONT color="green">388</FONT> // final int size = reader.getTextStart()+reader.getTextLength();<a name="line.388"></a>
<FONT color="green">389</FONT> // for (int i = reader.getTextStart(); i < size; i++) {<a name="line.389"></a>
<FONT color="green">390</FONT> // elementContent.append(ch[i]);<a name="line.390"></a>
<FONT color="green">391</FONT> // }<a name="line.391"></a>
<FONT color="green">392</FONT> // }<a name="line.392"></a>
<FONT color="green">393</FONT> }<a name="line.393"></a>
<FONT color="green">394</FONT> }<a name="line.394"></a>
<FONT color="green">395</FONT> } catch (XMLStreamException e) {<a name="line.395"></a>
<FONT color="green">396</FONT> throw new DataFormatException("", e);<a name="line.396"></a>
<FONT color="green">397</FONT> }<a name="line.397"></a>
<FONT color="green">398</FONT> }<a name="line.398"></a>
<FONT color="green">399</FONT> <a name="line.399"></a>
<FONT color="green">400</FONT> public int getSentenceCount() {<a name="line.400"></a>
<FONT color="green">401</FONT> return sentenceCount;<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> public void setSentenceCount(int sentenceCount) {<a name="line.404"></a>
<FONT color="green">405</FONT> this.sentenceCount = sentenceCount;<a name="line.405"></a>
<FONT color="green">406</FONT> }<a name="line.406"></a>
<FONT color="green">407</FONT> <a name="line.407"></a>
<FONT color="green">408</FONT> public XMLStreamReader getReader() {<a name="line.408"></a>
<FONT color="green">409</FONT> return reader;<a name="line.409"></a>
<FONT color="green">410</FONT> }<a name="line.410"></a>
<FONT color="green">411</FONT> <a name="line.411"></a>
<FONT color="green">412</FONT> public void setReader(XMLStreamReader reader) {<a name="line.412"></a>
<FONT color="green">413</FONT> this.reader = reader;<a name="line.413"></a>
<FONT color="green">414</FONT> }<a name="line.414"></a>
<FONT color="green">415</FONT> <a name="line.415"></a>
<FONT color="green">416</FONT> public void readEpilog() throws MaltChainedException {<a name="line.416"></a>
<FONT color="green">417</FONT> <a name="line.417"></a>
<FONT color="green">418</FONT> }<a name="line.418"></a>
<FONT color="green">419</FONT> <a name="line.419"></a>
<FONT color="green">420</FONT> public void close() throws MaltChainedException {<a name="line.420"></a>
<FONT color="green">421</FONT> try {<a name="line.421"></a>
<FONT color="green">422</FONT> if (reader != null) {<a name="line.422"></a>
<FONT color="green">423</FONT> if (closeStream) {<a name="line.423"></a>
<FONT color="green">424</FONT> reader.close();<a name="line.424"></a>
<FONT color="green">425</FONT> }<a name="line.425"></a>
<FONT color="green">426</FONT> reader = null;<a name="line.426"></a>
<FONT color="green">427</FONT> }<a name="line.427"></a>
<FONT color="green">428</FONT> } catch (XMLStreamException e) {<a name="line.428"></a>
<FONT color="green">429</FONT> throw new DataFormatException("The XML input file could be closed. ", e);<a name="line.429"></a>
<FONT color="green">430</FONT> }<a name="line.430"></a>
<FONT color="green">431</FONT> }<a name="line.431"></a>
<FONT color="green">432</FONT> <a name="line.432"></a>
<FONT color="green">433</FONT> public DataFormatInstance getDataFormatInstance() {<a name="line.433"></a>
<FONT color="green">434</FONT> return dataFormatInstance;<a name="line.434"></a>
<FONT color="green">435</FONT> }<a name="line.435"></a>
<FONT color="green">436</FONT> <a name="line.436"></a>
<FONT color="green">437</FONT> public void setDataFormatInstance(DataFormatInstance inputDataFormatInstance) {<a name="line.437"></a>
<FONT color="green">438</FONT> this.dataFormatInstance = inputDataFormatInstance;<a name="line.438"></a>
<FONT color="green">439</FONT> }<a name="line.439"></a>
<FONT color="green">440</FONT> <a name="line.440"></a>
<FONT color="green">441</FONT> public String getOptions() {<a name="line.441"></a>
<FONT color="green">442</FONT> return optionString;<a name="line.442"></a>
<FONT color="green">443</FONT> }<a name="line.443"></a>
<FONT color="green">444</FONT> <a name="line.444"></a>
<FONT color="green">445</FONT> public void setOptions(String optionString) throws MaltChainedException {<a name="line.445"></a>
<FONT color="green">446</FONT> this.optionString = optionString;<a name="line.446"></a>
<FONT color="green">447</FONT> String[] argv;<a name="line.447"></a>
<FONT color="green">448</FONT> try {<a name="line.448"></a>
<FONT color="green">449</FONT> argv = optionString.split("[_\\p{Blank}]");<a name="line.449"></a>
<FONT color="green">450</FONT> } catch (PatternSyntaxException e) {<a name="line.450"></a>
<FONT color="green">451</FONT> throw new DataFormatException("Could not split the TigerXML reader option '"+optionString+"'. ", e);<a name="line.451"></a>
<FONT color="green">452</FONT> }<a name="line.452"></a>
<FONT color="green">453</FONT> for (int i=0; i < argv.length-1; i++) {<a name="line.453"></a>
<FONT color="green">454</FONT> if(argv[i].charAt(0) != '-') {<a name="line.454"></a>
<FONT color="green">455</FONT> throw new DataFormatException("The argument flag should start with the following character '-', not with "+argv[i].charAt(0));<a name="line.455"></a>
<FONT color="green">456</FONT> }<a name="line.456"></a>
<FONT color="green">457</FONT> if(++i>=argv.length) {<a name="line.457"></a>
<FONT color="green">458</FONT> throw new DataFormatException("The last argument does not have any value. ");<a name="line.458"></a>
<FONT color="green">459</FONT> }<a name="line.459"></a>
<FONT color="green">460</FONT> switch(argv[i-1].charAt(1)) {<a name="line.460"></a>
<FONT color="green">461</FONT> case 's': <a name="line.461"></a>
<FONT color="green">462</FONT> try {<a name="line.462"></a>
<FONT color="green">463</FONT> START_ID_OF_NONTERMINALS = Integer.parseInt(argv[i]);<a name="line.463"></a>
<FONT color="green">464</FONT> } catch (NumberFormatException e){<a name="line.464"></a>
<FONT color="green">465</FONT> throw new MaltChainedException("The TigerXML Reader option -s must be an integer value. ");<a name="line.465"></a>
<FONT color="green">466</FONT> }<a name="line.466"></a>
<FONT color="green">467</FONT> break;<a name="line.467"></a>
<FONT color="green">468</FONT> default:<a name="line.468"></a>
<FONT color="green">469</FONT> throw new DataFormatException("Unknown TigerXMLReader parameter: '"+argv[i-1]+"' with value '"+argv[i]+"'. "); <a name="line.469"></a>
<FONT color="green">470</FONT> }<a name="line.470"></a>
<FONT color="green">471</FONT> }<a name="line.471"></a>
<FONT color="green">472</FONT> }<a name="line.472"></a>
<FONT color="green">473</FONT> <a name="line.473"></a>
<FONT color="green">474</FONT> public String getFileName() {<a name="line.474"></a>
<FONT color="green">475</FONT> return fileName;<a name="line.475"></a>
<FONT color="green">476</FONT> }<a name="line.476"></a>
<FONT color="green">477</FONT> <a name="line.477"></a>
<FONT color="green">478</FONT> public void setFileName(String fileName) {<a name="line.478"></a>
<FONT color="green">479</FONT> this.fileName = fileName;<a name="line.479"></a>
<FONT color="green">480</FONT> }<a name="line.480"></a>
<FONT color="green">481</FONT> <a name="line.481"></a>
<FONT color="green">482</FONT> public URL getUrl() {<a name="line.482"></a>
<FONT color="green">483</FONT> return url;<a name="line.483"></a>
<FONT color="green">484</FONT> }<a name="line.484"></a>
<FONT color="green">485</FONT> <a name="line.485"></a>
<FONT color="green">486</FONT> public void setUrl(URL url) {<a name="line.486"></a>
<FONT color="green">487</FONT> this.url = url;<a name="line.487"></a>
<FONT color="green">488</FONT> }<a name="line.488"></a>
<FONT color="green">489</FONT> <a name="line.489"></a>
<FONT color="green">490</FONT> public String getCharsetName() {<a name="line.490"></a>
<FONT color="green">491</FONT> return charsetName;<a name="line.491"></a>
<FONT color="green">492</FONT> }<a name="line.492"></a>
<FONT color="green">493</FONT> <a name="line.493"></a>
<FONT color="green">494</FONT> public void setCharsetName(String charsetName) {<a name="line.494"></a>
<FONT color="green">495</FONT> this.charsetName = charsetName;<a name="line.495"></a>
<FONT color="green">496</FONT> }<a name="line.496"></a>
<FONT color="green">497</FONT> <a name="line.497"></a>
<FONT color="green">498</FONT> public int getNIterations() {<a name="line.498"></a>
<FONT color="green">499</FONT> return nIterations;<a name="line.499"></a>
<FONT color="green">500</FONT> }<a name="line.500"></a>
<FONT color="green">501</FONT> <a name="line.501"></a>
<FONT color="green">502</FONT> public void setNIterations(int iterations) {<a name="line.502"></a>
<FONT color="green">503</FONT> nIterations = iterations;<a name="line.503"></a>
<FONT color="green">504</FONT> }<a name="line.504"></a>
<FONT color="green">505</FONT> <a name="line.505"></a>
<FONT color="green">506</FONT> public int getIterationCounter() {<a name="line.506"></a>
<FONT color="green">507</FONT> return cIterations;<a name="line.507"></a>
<FONT color="green">508</FONT> }<a name="line.508"></a>
<FONT color="green">509</FONT> // public TigerXMLHeader getHeader() {<a name="line.509"></a>
<FONT color="green">510</FONT> // return header;<a name="line.510"></a>
<FONT color="green">511</FONT> // }<a name="line.511"></a>
<FONT color="green">512</FONT> // <a name="line.512"></a>
<FONT color="green">513</FONT> // public void setHeader(TigerXMLHeader header) {<a name="line.513"></a>
<FONT color="green">514</FONT> // this.header = header;<a name="line.514"></a>
<FONT color="green">515</FONT> // }<a name="line.515"></a>
<FONT color="green">516</FONT> }<a name="line.516"></a>
</PRE>
</BODY>
</HTML>