<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.Iterator;<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.io.dataformat.ColumnDescription;<a name="line.13"></a>
<FONT color="green">014</FONT> import org.maltparser.core.io.dataformat.DataFormatException;<a name="line.14"></a>
<FONT color="green">015</FONT> import org.maltparser.core.io.dataformat.DataFormatInstance;<a name="line.15"></a>
<FONT color="green">016</FONT> import org.maltparser.core.syntaxgraph.DependencyStructure;<a name="line.16"></a>
<FONT color="green">017</FONT> import org.maltparser.core.syntaxgraph.TokenStructure;<a name="line.17"></a>
<FONT color="green">018</FONT> import org.maltparser.core.syntaxgraph.node.TokenNode;<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> * @author Johan Hall<a name="line.22"></a>
<FONT color="green">023</FONT> */<a name="line.23"></a>
<FONT color="green">024</FONT> public class TabWriter implements SyntaxGraphWriter {<a name="line.24"></a>
<FONT color="green">025</FONT> private BufferedWriter writer;<a name="line.25"></a>
<FONT color="green">026</FONT> private DataFormatInstance dataFormatInstance;<a name="line.26"></a>
<FONT color="green">027</FONT> private final StringBuilder output;<a name="line.27"></a>
<FONT color="green">028</FONT> private boolean closeStream = true;<a name="line.28"></a>
<FONT color="green">029</FONT> // private String ID = "ID";<a name="line.29"></a>
<FONT color="green">030</FONT> // private String IGNORE_COLUMN_SIGN = "_";<a name="line.30"></a>
<FONT color="green">031</FONT> private final char TAB = '\t';<a name="line.31"></a>
<FONT color="green">032</FONT> private final char NEWLINE = '\n';<a name="line.32"></a>
<FONT color="green">033</FONT> <a name="line.33"></a>
<FONT color="green">034</FONT> <a name="line.34"></a>
<FONT color="green">035</FONT> public TabWriter() { <a name="line.35"></a>
<FONT color="green">036</FONT> output = new StringBuilder();<a name="line.36"></a>
<FONT color="green">037</FONT> }<a name="line.37"></a>
<FONT color="green">038</FONT> <a name="line.38"></a>
<FONT color="green">039</FONT> public void open(String fileName, String charsetName) throws MaltChainedException {<a name="line.39"></a>
<FONT color="green">040</FONT> try {<a name="line.40"></a>
<FONT color="green">041</FONT> open(new OutputStreamWriter(new FileOutputStream(fileName),charsetName));<a name="line.41"></a>
<FONT color="green">042</FONT> } catch (FileNotFoundException e) {<a name="line.42"></a>
<FONT color="green">043</FONT> throw new DataFormatException("The output file '"+fileName+"' cannot be found.", e);<a name="line.43"></a>
<FONT color="green">044</FONT> } catch (UnsupportedEncodingException e) {<a name="line.44"></a>
<FONT color="green">045</FONT> throw new DataFormatException("The character encoding set '"+charsetName+"' isn't supported.", e);<a name="line.45"></a>
<FONT color="green">046</FONT> } <a name="line.46"></a>
<FONT color="green">047</FONT> }<a name="line.47"></a>
<FONT color="green">048</FONT> <a name="line.48"></a>
<FONT color="green">049</FONT> public void open(OutputStream os, String charsetName) throws MaltChainedException {<a name="line.49"></a>
<FONT color="green">050</FONT> try {<a name="line.50"></a>
<FONT color="green">051</FONT> if (os == System.out || os == System.err) {<a name="line.51"></a>
<FONT color="green">052</FONT> closeStream = false;<a name="line.52"></a>
<FONT color="green">053</FONT> }<a name="line.53"></a>
<FONT color="green">054</FONT> open(new OutputStreamWriter(os, charsetName));<a name="line.54"></a>
<FONT color="green">055</FONT> } catch (UnsupportedEncodingException e) {<a name="line.55"></a>
<FONT color="green">056</FONT> throw new DataFormatException("The character encoding set '"+charsetName+"' isn't supported.", e);<a name="line.56"></a>
<FONT color="green">057</FONT> }<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> private void open(OutputStreamWriter osw) throws MaltChainedException {<a name="line.60"></a>
<FONT color="green">061</FONT> setWriter(new BufferedWriter(osw));<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 writeProlog() throws MaltChainedException {<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> <a name="line.67"></a>
<FONT color="green">068</FONT> public void writeSentence(TokenStructure syntaxGraph) throws MaltChainedException {<a name="line.68"></a>
<FONT color="green">069</FONT> if (syntaxGraph == null || dataFormatInstance == null || !syntaxGraph.hasTokens()) {<a name="line.69"></a>
<FONT color="green">070</FONT> return;<a name="line.70"></a>
<FONT color="green">071</FONT> }<a name="line.71"></a>
<FONT color="green">072</FONT> Iterator<ColumnDescription> columns = dataFormatInstance.iterator();<a name="line.72"></a>
<FONT color="green">073</FONT> <a name="line.73"></a>
<FONT color="green">074</FONT> for (int i : syntaxGraph.getTokenIndices()) {<a name="line.74"></a>
<FONT color="green">075</FONT> try {<a name="line.75"></a>
<FONT color="green">076</FONT> ColumnDescription column = null;<a name="line.76"></a>
<FONT color="green">077</FONT> while (columns.hasNext()) {<a name="line.77"></a>
<FONT color="green">078</FONT> column = columns.next();<a name="line.78"></a>
<FONT color="green">079</FONT> <a name="line.79"></a>
<FONT color="green">080</FONT> if (column.getCategory() == ColumnDescription.INPUT && column.getType() != ColumnDescription.IGNORE) {<a name="line.80"></a>
<FONT color="green">081</FONT> TokenNode node = syntaxGraph.getTokenNode(i); <a name="line.81"></a>
<FONT color="green">082</FONT> if (!column.getName().equals("ID")) {<a name="line.82"></a>
<FONT color="green">083</FONT> if (node.hasLabel(column.getSymbolTable())) {<a name="line.83"></a>
<FONT color="green">084</FONT> output.append(node.getLabelSymbol(column.getSymbolTable()));<a name="line.84"></a>
<FONT color="green">085</FONT> if (output.length() != 0) {<a name="line.85"></a>
<FONT color="green">086</FONT> writer.write(output.toString());<a name="line.86"></a>
<FONT color="green">087</FONT> } else {<a name="line.87"></a>
<FONT color="green">088</FONT> writer.write('_');<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> writer.write('_');<a name="line.91"></a>
<FONT color="green">092</FONT> }<a name="line.92"></a>
<FONT color="green">093</FONT> } else {<a name="line.93"></a>
<FONT color="green">094</FONT> writer.write(Integer.toString(i));<a name="line.94"></a>
<FONT color="green">095</FONT> }<a name="line.95"></a>
<FONT color="green">096</FONT> } else if (column.getCategory() == ColumnDescription.HEAD && column.getType() != ColumnDescription.IGNORE && syntaxGraph instanceof DependencyStructure) {<a name="line.96"></a>
<FONT color="green">097</FONT> if (((DependencyStructure)syntaxGraph).getDependencyNode(i).hasHead()) {<a name="line.97"></a>
<FONT color="green">098</FONT> writer.write(Integer.toString(((DependencyStructure)syntaxGraph).getDependencyNode(i).getHead().getIndex()));<a name="line.98"></a>
<FONT color="green">099</FONT> } else {<a name="line.99"></a>
<FONT color="green">100</FONT> writer.write(Integer.toString(0));<a name="line.100"></a>
<FONT color="green">101</FONT> }<a name="line.101"></a>
<FONT color="green">102</FONT> <a name="line.102"></a>
<FONT color="green">103</FONT> } else if (column.getCategory() == ColumnDescription.DEPENDENCY_EDGE_LABEL && column.getType() != ColumnDescription.IGNORE && syntaxGraph instanceof DependencyStructure) {<a name="line.103"></a>
<FONT color="green">104</FONT> if (((DependencyStructure)syntaxGraph).getDependencyNode(i).hasHead() && ((DependencyStructure)syntaxGraph).getDependencyNode(i).hasHeadEdgeLabel(column.getSymbolTable())) {<a name="line.104"></a>
<FONT color="green">105</FONT> output.append(((DependencyStructure)syntaxGraph).getDependencyNode(i).getHeadEdgeLabelSymbol(column.getSymbolTable()));<a name="line.105"></a>
<FONT color="green">106</FONT> } else {<a name="line.106"></a>
<FONT color="green">107</FONT> output.append(((DependencyStructure)syntaxGraph).getDefaultRootEdgeLabelSymbol(column.getSymbolTable()));<a name="line.107"></a>
<FONT color="green">108</FONT> }<a name="line.108"></a>
<FONT color="green">109</FONT> <a name="line.109"></a>
<FONT color="green">110</FONT> if (output.length() != 0) {<a name="line.110"></a>
<FONT color="green">111</FONT> writer.write(output.toString());<a name="line.111"></a>
<FONT color="green">112</FONT> }<a name="line.112"></a>
<FONT color="green">113</FONT> } else {<a name="line.113"></a>
<FONT color="green">114</FONT> writer.write(column.getDefaultOutput());<a name="line.114"></a>
<FONT color="green">115</FONT> }<a name="line.115"></a>
<FONT color="green">116</FONT> if (columns.hasNext()) {<a name="line.116"></a>
<FONT color="green">117</FONT> writer.write(TAB);<a name="line.117"></a>
<FONT color="green">118</FONT> }<a name="line.118"></a>
<FONT color="green">119</FONT> output.setLength(0);<a name="line.119"></a>
<FONT color="green">120</FONT> }<a name="line.120"></a>
<FONT color="green">121</FONT> writer.write(NEWLINE);<a name="line.121"></a>
<FONT color="green">122</FONT> columns = dataFormatInstance.iterator();<a name="line.122"></a>
<FONT color="green">123</FONT> } catch (IOException e) {<a name="line.123"></a>
<FONT color="green">124</FONT> close();<a name="line.124"></a>
<FONT color="green">125</FONT> throw new DataFormatException("Could not write to the output file. ", e);<a name="line.125"></a>
<FONT color="green">126</FONT> }<a name="line.126"></a>
<FONT color="green">127</FONT> }<a name="line.127"></a>
<FONT color="green">128</FONT> <a name="line.128"></a>
<FONT color="green">129</FONT> try {<a name="line.129"></a>
<FONT color="green">130</FONT> writer.write('\n');<a name="line.130"></a>
<FONT color="green">131</FONT> writer.flush();<a name="line.131"></a>
<FONT color="green">132</FONT> } catch (IOException e) {<a name="line.132"></a>
<FONT color="green">133</FONT> close();<a name="line.133"></a>
<FONT color="green">134</FONT> throw new DataFormatException("Could not write to the output file. ", e);<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> public void writeEpilog() throws MaltChainedException {<a name="line.138"></a>
<FONT color="green">139</FONT> <a name="line.139"></a>
<FONT color="green">140</FONT> }<a name="line.140"></a>
<FONT color="green">141</FONT> <a name="line.141"></a>
<FONT color="green">142</FONT> public BufferedWriter getWriter() {<a name="line.142"></a>
<FONT color="green">143</FONT> return writer;<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 void setWriter(BufferedWriter writer) throws MaltChainedException {<a name="line.146"></a>
<FONT color="green">147</FONT> close();<a name="line.147"></a>
<FONT color="green">148</FONT> this.writer = writer;<a name="line.148"></a>
<FONT color="green">149</FONT> }<a name="line.149"></a>
<FONT color="green">150</FONT> <a name="line.150"></a>
<FONT color="green">151</FONT> public DataFormatInstance getDataFormatInstance() {<a name="line.151"></a>
<FONT color="green">152</FONT> return dataFormatInstance;<a name="line.152"></a>
<FONT color="green">153</FONT> }<a name="line.153"></a>
<FONT color="green">154</FONT> <a name="line.154"></a>
<FONT color="green">155</FONT> public void setDataFormatInstance(DataFormatInstance dataFormatInstance) {<a name="line.155"></a>
<FONT color="green">156</FONT> this.dataFormatInstance = dataFormatInstance;<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 getOptions() {<a name="line.159"></a>
<FONT color="green">160</FONT> return null;<a name="line.160"></a>
<FONT color="green">161</FONT> }<a name="line.161"></a>
<FONT color="green">162</FONT> <a name="line.162"></a>
<FONT color="green">163</FONT> public void setOptions(String optionString) throws MaltChainedException {<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> public void close() throws MaltChainedException {<a name="line.167"></a>
<FONT color="green">168</FONT> try {<a name="line.168"></a>
<FONT color="green">169</FONT> if (writer != null) {<a name="line.169"></a>
<FONT color="green">170</FONT> writer.flush();<a name="line.170"></a>
<FONT color="green">171</FONT> if (closeStream) {<a name="line.171"></a>
<FONT color="green">172</FONT> writer.close();<a name="line.172"></a>
<FONT color="green">173</FONT> }<a name="line.173"></a>
<FONT color="green">174</FONT> writer = null;<a name="line.174"></a>
<FONT color="green">175</FONT> }<a name="line.175"></a>
<FONT color="green">176</FONT> } catch (IOException e) {<a name="line.176"></a>
<FONT color="green">177</FONT> throw new DataFormatException("Could not close the output file. ", e);<a name="line.177"></a>
<FONT color="green">178</FONT> } <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> }<a name="line.181"></a>
</PRE>
</BODY>
</HTML>