You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@commons.apache.org by gg...@apache.org on 2013/03/21 16:20:21 UTC
svn commit: r855435 [8/45] - in
/websites/production/commons/content/proper/commons-csv: ./ apidocs/
apidocs/org/apache/commons/csv/ apidocs/org/apache/commons/csv/class-use/
apidocs/org/apache/commons/csv/writer/
apidocs/src-html/org/apache/commons/cs...
Modified: websites/production/commons/content/proper/commons-csv/apidocs/src-html/org/apache/commons/csv/CSVParser.html
==============================================================================
--- websites/production/commons/content/proper/commons-csv/apidocs/src-html/org/apache/commons/csv/CSVParser.html (original)
+++ websites/production/commons/content/proper/commons-csv/apidocs/src-html/org/apache/commons/csv/CSVParser.html Thu Mar 21 15:20:15 2013
@@ -8,9 +8,9 @@
<FONT color="green">005</FONT> * The ASF licenses this file to You under the Apache License, Version 2.0<a name="line.5"></a>
<FONT color="green">006</FONT> * (the "License"); you may not use this file except in compliance with<a name="line.6"></a>
<FONT color="green">007</FONT> * the License. You may obtain a copy of the License at<a name="line.7"></a>
-<FONT color="green">008</FONT> * <a name="line.8"></a>
+<FONT color="green">008</FONT> *<a name="line.8"></a>
<FONT color="green">009</FONT> * http://www.apache.org/licenses/LICENSE-2.0<a name="line.9"></a>
-<FONT color="green">010</FONT> * <a name="line.10"></a>
+<FONT color="green">010</FONT> *<a name="line.10"></a>
<FONT color="green">011</FONT> * Unless required by applicable law or agreed to in writing, software<a name="line.11"></a>
<FONT color="green">012</FONT> * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.12"></a>
<FONT color="green">013</FONT> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.13"></a>
@@ -20,531 +20,286 @@
<FONT color="green">017</FONT> <a name="line.17"></a>
<FONT color="green">018</FONT> package org.apache.commons.csv;<a name="line.18"></a>
<FONT color="green">019</FONT> <a name="line.19"></a>
-<FONT color="green">020</FONT> import java.io.IOException;<a name="line.20"></a>
-<FONT color="green">021</FONT> import java.io.Reader;<a name="line.21"></a>
-<FONT color="green">022</FONT> import java.io.StringReader;<a name="line.22"></a>
-<FONT color="green">023</FONT> import java.util.ArrayList;<a name="line.23"></a>
-<FONT color="green">024</FONT> import java.util.Iterator;<a name="line.24"></a>
-<FONT color="green">025</FONT> import java.util.List;<a name="line.25"></a>
-<FONT color="green">026</FONT> import java.util.NoSuchElementException;<a name="line.26"></a>
-<FONT color="green">027</FONT> <a name="line.27"></a>
-<FONT color="green">028</FONT> import org.apache.commons.csv.CSVLexer.Token;<a name="line.28"></a>
-<FONT color="green">029</FONT> <a name="line.29"></a>
-<FONT color="green">030</FONT> import static org.apache.commons.csv.CSVLexer.Token.Type.*;<a name="line.30"></a>
+<FONT color="green">020</FONT> import static org.apache.commons.csv.Token.Type.TOKEN;<a name="line.20"></a>
+<FONT color="green">021</FONT> <a name="line.21"></a>
+<FONT color="green">022</FONT> import java.io.IOException;<a name="line.22"></a>
+<FONT color="green">023</FONT> import java.io.Reader;<a name="line.23"></a>
+<FONT color="green">024</FONT> import java.io.StringReader;<a name="line.24"></a>
+<FONT color="green">025</FONT> import java.util.ArrayList;<a name="line.25"></a>
+<FONT color="green">026</FONT> import java.util.Iterator;<a name="line.26"></a>
+<FONT color="green">027</FONT> import java.util.LinkedHashMap;<a name="line.27"></a>
+<FONT color="green">028</FONT> import java.util.List;<a name="line.28"></a>
+<FONT color="green">029</FONT> import java.util.Map;<a name="line.29"></a>
+<FONT color="green">030</FONT> import java.util.NoSuchElementException;<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> * Parses CSV files according to the specified configuration.<a name="line.33"></a>
<FONT color="green">034</FONT> *<a name="line.34"></a>
-<FONT color="green">035</FONT> * Because CSV appears in many different dialects, the parser supports many<a name="line.35"></a>
-<FONT color="green">036</FONT> * configuration settings by allowing the specification of a {@link CSVFormat}.<a name="line.36"></a>
+<FONT color="green">035</FONT> * Because CSV appears in many different dialects, the parser supports many configuration settings by allowing the<a name="line.35"></a>
+<FONT color="green">036</FONT> * specification of a {@link CSVFormat}.<a name="line.36"></a>
<FONT color="green">037</FONT> *<a name="line.37"></a>
-<FONT color="green">038</FONT> * <p>Parsing of a csv-string having tabs as separators,<a name="line.38"></a>
-<FONT color="green">039</FONT> * '"' as an optional value encapsulator, and comments starting with '#':</p><a name="line.39"></a>
-<FONT color="green">040</FONT> * <pre><a name="line.40"></a>
-<FONT color="green">041</FONT> * CSVFormat format = new CSVFormat('\t', '"', '#');<a name="line.41"></a>
-<FONT color="green">042</FONT> * Reader in = new StringReader("a\tb\nc\td");<a name="line.42"></a>
-<FONT color="green">043</FONT> * String[][] records = new CSVParser(in, format).getRecords();<a name="line.43"></a>
-<FONT color="green">044</FONT> * </pre><a name="line.44"></a>
-<FONT color="green">045</FONT> *<a name="line.45"></a>
-<FONT color="green">046</FONT> * <p>Parsing of a csv-string in Excel CSV format, using a for-each loop:</p><a name="line.46"></a>
-<FONT color="green">047</FONT> * <pre><a name="line.47"></a>
-<FONT color="green">048</FONT> * Reader in = new StringReader("a;b\nc;d");<a name="line.48"></a>
-<FONT color="green">049</FONT> * CSVParser parser = new CSVParser(in, CSVFormat.EXCEL);<a name="line.49"></a>
-<FONT color="green">050</FONT> * for (String[] record : parser) {<a name="line.50"></a>
-<FONT color="green">051</FONT> * ...<a name="line.51"></a>
-<FONT color="green">052</FONT> * }<a name="line.52"></a>
-<FONT color="green">053</FONT> * </pre><a name="line.53"></a>
-<FONT color="green">054</FONT> *<a name="line.54"></a>
-<FONT color="green">055</FONT> * <p><a name="line.55"></a>
-<FONT color="green">056</FONT> * Internal parser state is completely covered by the format<a name="line.56"></a>
-<FONT color="green">057</FONT> * and the reader-state.</p><a name="line.57"></a>
-<FONT color="green">058</FONT> *<a name="line.58"></a>
-<FONT color="green">059</FONT> * <p>see <a href="package-summary.html">package documentation</a><a name="line.59"></a>
-<FONT color="green">060</FONT> * for more details</p><a name="line.60"></a>
-<FONT color="green">061</FONT> */<a name="line.61"></a>
-<FONT color="green">062</FONT> public class CSVParser implements Iterable<String[]> {<a name="line.62"></a>
-<FONT color="green">063</FONT> <a name="line.63"></a>
-<FONT color="green">064</FONT> /** Immutable empty String array. */<a name="line.64"></a>
-<FONT color="green">065</FONT> private static final String[] EMPTY_STRING_ARRAY = new String[0];<a name="line.65"></a>
-<FONT color="green">066</FONT> <a name="line.66"></a>
-<FONT color="green">067</FONT> private final CSVLexer lexer;<a name="line.67"></a>
-<FONT color="green">068</FONT> <a name="line.68"></a>
-<FONT color="green">069</FONT> // the following objects are shared to reduce garbage<a name="line.69"></a>
-<FONT color="green">070</FONT> <a name="line.70"></a>
-<FONT color="green">071</FONT> /** A record buffer for getRecord(). Grows as necessary and is reused. */<a name="line.71"></a>
-<FONT color="green">072</FONT> private final List<String> record = new ArrayList<String>();<a name="line.72"></a>
-<FONT color="green">073</FONT> private final Token reusableToken = new Token();<a name="line.73"></a>
-<FONT color="green">074</FONT> <a name="line.74"></a>
-<FONT color="green">075</FONT> /**<a name="line.75"></a>
-<FONT color="green">076</FONT> * CSV parser using the default {@link CSVFormat}.<a name="line.76"></a>
-<FONT color="green">077</FONT> *<a name="line.77"></a>
-<FONT color="green">078</FONT> * @param input a Reader containing "csv-formatted" input<a name="line.78"></a>
-<FONT color="green">079</FONT> * @throws IllegalArgumentException thrown if the parameters of the format are inconsistent<a name="line.79"></a>
-<FONT color="green">080</FONT> */<a name="line.80"></a>
-<FONT color="green">081</FONT> public CSVParser(Reader input) {<a name="line.81"></a>
-<FONT color="green">082</FONT> this(input, CSVFormat.DEFAULT);<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> * Customized CSV parser using the given {@link CSVFormat}<a name="line.86"></a>
-<FONT color="green">087</FONT> *<a name="line.87"></a>
-<FONT color="green">088</FONT> * @param input a Reader containing "csv-formatted" input<a name="line.88"></a>
-<FONT color="green">089</FONT> * @param format the CSVFormat used for CSV parsing<a name="line.89"></a>
-<FONT color="green">090</FONT> * @throws IllegalArgumentException thrown if the parameters of the format are inconsistent<a name="line.90"></a>
-<FONT color="green">091</FONT> */<a name="line.91"></a>
-<FONT color="green">092</FONT> public CSVParser(Reader input, CSVFormat format) {<a name="line.92"></a>
-<FONT color="green">093</FONT> format.validate();<a name="line.93"></a>
-<FONT color="green">094</FONT> <a name="line.94"></a>
-<FONT color="green">095</FONT> if (format.isUnicodeEscapesInterpreted()) {<a name="line.95"></a>
-<FONT color="green">096</FONT> input = new UnicodeUnescapeReader(input);<a name="line.96"></a>
-<FONT color="green">097</FONT> }<a name="line.97"></a>
-<FONT color="green">098</FONT> <a name="line.98"></a>
-<FONT color="green">099</FONT> this.lexer = new CSVLexer(format, new ExtendedBufferedReader(input));<a name="line.99"></a>
-<FONT color="green">100</FONT> }<a name="line.100"></a>
-<FONT color="green">101</FONT> <a name="line.101"></a>
-<FONT color="green">102</FONT> /**<a name="line.102"></a>
-<FONT color="green">103</FONT> * Customized CSV parser using the given {@link CSVFormat}<a name="line.103"></a>
-<FONT color="green">104</FONT> *<a name="line.104"></a>
-<FONT color="green">105</FONT> * @param input a String containing "csv-formatted" input<a name="line.105"></a>
-<FONT color="green">106</FONT> * @param format the CSVFormat used for CSV parsing<a name="line.106"></a>
-<FONT color="green">107</FONT> * @throws IllegalArgumentException thrown if the parameters of the format are inconsistent<a name="line.107"></a>
-<FONT color="green">108</FONT> */<a name="line.108"></a>
-<FONT color="green">109</FONT> public CSVParser(String input, CSVFormat format) {<a name="line.109"></a>
-<FONT color="green">110</FONT> this(new StringReader(input), format);<a name="line.110"></a>
-<FONT color="green">111</FONT> }<a name="line.111"></a>
-<FONT color="green">112</FONT> <a name="line.112"></a>
-<FONT color="green">113</FONT> <a name="line.113"></a>
-<FONT color="green">114</FONT> /**<a name="line.114"></a>
-<FONT color="green">115</FONT> * Parses the CSV input according to the given format and returns the content<a name="line.115"></a>
-<FONT color="green">116</FONT> * as an array of records (whereas records are arrays of single values).<a name="line.116"></a>
-<FONT color="green">117</FONT> * <p/><a name="line.117"></a>
-<FONT color="green">118</FONT> * The returned content starts at the current parse-position in the stream.<a name="line.118"></a>
-<FONT color="green">119</FONT> *<a name="line.119"></a>
-<FONT color="green">120</FONT> * @return matrix of records x values ('null' when end of file)<a name="line.120"></a>
-<FONT color="green">121</FONT> * @throws IOException on parse error or input read-failure<a name="line.121"></a>
-<FONT color="green">122</FONT> */<a name="line.122"></a>
-<FONT color="green">123</FONT> public String[][] getRecords() throws IOException {<a name="line.123"></a>
-<FONT color="green">124</FONT> List<String[]> records = new ArrayList<String[]>();<a name="line.124"></a>
-<FONT color="green">125</FONT> String[] record;<a name="line.125"></a>
-<FONT color="green">126</FONT> while ((record = getRecord()) != null) {<a name="line.126"></a>
-<FONT color="green">127</FONT> records.add(record);<a name="line.127"></a>
-<FONT color="green">128</FONT> }<a name="line.128"></a>
-<FONT color="green">129</FONT> <a name="line.129"></a>
-<FONT color="green">130</FONT> if (!records.isEmpty()) {<a name="line.130"></a>
-<FONT color="green">131</FONT> return records.toArray(new String[records.size()][]);<a name="line.131"></a>
-<FONT color="green">132</FONT> } else {<a name="line.132"></a>
-<FONT color="green">133</FONT> return null;<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> * Parses the next record from the current point in the stream.<a name="line.138"></a>
-<FONT color="green">139</FONT> *<a name="line.139"></a>
-<FONT color="green">140</FONT> * @return the record as an array of values, or <tt>null</tt> if the end of the stream has been reached<a name="line.140"></a>
-<FONT color="green">141</FONT> * @throws IOException on parse error or input read-failure<a name="line.141"></a>
+<FONT color="green">038</FONT> * <p><a name="line.38"></a>
+<FONT color="green">039</FONT> * Parsing of a csv-string having tabs as separators, '"' as an optional value encapsulator, and comments starting with<a name="line.39"></a>
+<FONT color="green">040</FONT> * '#':<a name="line.40"></a>
+<FONT color="green">041</FONT> * </p><a name="line.41"></a>
+<FONT color="green">042</FONT> *<a name="line.42"></a>
+<FONT color="green">043</FONT> * <pre><a name="line.43"></a>
+<FONT color="green">044</FONT> * CSVFormat format = new CSVFormat('\t', '&quot;', '#');<a name="line.44"></a>
+<FONT color="green">045</FONT> * Reader in = new StringReader(&quot;a\tb\nc\td&quot;);<a name="line.45"></a>
+<FONT color="green">046</FONT> * List&lt;CSVRecord&gt; records = new CSVParser(in, format).getRecords();<a name="line.46"></a>
+<FONT color="green">047</FONT> * </pre><a name="line.47"></a>
+<FONT color="green">048</FONT> *<a name="line.48"></a>
+<FONT color="green">049</FONT> * <p><a name="line.49"></a>
+<FONT color="green">050</FONT> * Parsing of a csv-string in Excel CSV format, using a for-each loop:<a name="line.50"></a>
+<FONT color="green">051</FONT> * </p><a name="line.51"></a>
+<FONT color="green">052</FONT> *<a name="line.52"></a>
+<FONT color="green">053</FONT> * <pre><a name="line.53"></a>
+<FONT color="green">054</FONT> * Reader in = new StringReader("a;b\nc;d");<a name="line.54"></a>
+<FONT color="green">055</FONT> * CSVParser parser = new CSVParser(in, CSVFormat.EXCEL);<a name="line.55"></a>
+<FONT color="green">056</FONT> * for (CSVRecord record : parser) {<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> * </pre><a name="line.59"></a>
+<FONT color="green">060</FONT> *<a name="line.60"></a>
+<FONT color="green">061</FONT> * <p><a name="line.61"></a>
+<FONT color="green">062</FONT> * Internal parser state is completely covered by the format and the reader-state.<a name="line.62"></a>
+<FONT color="green">063</FONT> * </p><a name="line.63"></a>
+<FONT color="green">064</FONT> *<a name="line.64"></a>
+<FONT color="green">065</FONT> * <p><a name="line.65"></a>
+<FONT color="green">066</FONT> * see <a href="package-summary.html">package documentation</a> for more details<a name="line.66"></a>
+<FONT color="green">067</FONT> * </p><a name="line.67"></a>
+<FONT color="green">068</FONT> *<a name="line.68"></a>
+<FONT color="green">069</FONT> * @version $Id: CSVParser.java 1458683 2013-03-20 08:31:14Z britter $<a name="line.69"></a>
+<FONT color="green">070</FONT> */<a name="line.70"></a>
+<FONT color="green">071</FONT> public class CSVParser implements Iterable<CSVRecord> {<a name="line.71"></a>
+<FONT color="green">072</FONT> <a name="line.72"></a>
+<FONT color="green">073</FONT> private final Lexer lexer;<a name="line.73"></a>
+<FONT color="green">074</FONT> private final Map<String, Integer> headerMap;<a name="line.74"></a>
+<FONT color="green">075</FONT> private long recordNumber;<a name="line.75"></a>
+<FONT color="green">076</FONT> <a name="line.76"></a>
+<FONT color="green">077</FONT> // the following objects are shared to reduce garbage<a name="line.77"></a>
+<FONT color="green">078</FONT> <a name="line.78"></a>
+<FONT color="green">079</FONT> /** A record buffer for getRecord(). Grows as necessary and is reused. */<a name="line.79"></a>
+<FONT color="green">080</FONT> private final List<String> record = new ArrayList<String>();<a name="line.80"></a>
+<FONT color="green">081</FONT> private final Token reusableToken = new Token();<a name="line.81"></a>
+<FONT color="green">082</FONT> <a name="line.82"></a>
+<FONT color="green">083</FONT> /**<a name="line.83"></a>
+<FONT color="green">084</FONT> * CSV parser using the default {@link CSVFormat}.<a name="line.84"></a>
+<FONT color="green">085</FONT> *<a name="line.85"></a>
+<FONT color="green">086</FONT> * @param input<a name="line.86"></a>
+<FONT color="green">087</FONT> * a Reader containing "csv-formatted" input<a name="line.87"></a>
+<FONT color="green">088</FONT> * @throws IllegalArgumentException<a name="line.88"></a>
+<FONT color="green">089</FONT> * thrown if the parameters of the format are inconsistent<a name="line.89"></a>
+<FONT color="green">090</FONT> */<a name="line.90"></a>
+<FONT color="green">091</FONT> public CSVParser(final Reader input) throws IOException {<a name="line.91"></a>
+<FONT color="green">092</FONT> this(input, CSVFormat.DEFAULT);<a name="line.92"></a>
+<FONT color="green">093</FONT> }<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> * Customized CSV parser using the given {@link CSVFormat}<a name="line.96"></a>
+<FONT color="green">097</FONT> *<a name="line.97"></a>
+<FONT color="green">098</FONT> * @param input<a name="line.98"></a>
+<FONT color="green">099</FONT> * a Reader containing "csv-formatted" input<a name="line.99"></a>
+<FONT color="green">100</FONT> * @param format<a name="line.100"></a>
+<FONT color="green">101</FONT> * the CSVFormat used for CSV parsing<a name="line.101"></a>
+<FONT color="green">102</FONT> * @throws IllegalArgumentException<a name="line.102"></a>
+<FONT color="green">103</FONT> * thrown if the parameters of the format are inconsistent<a name="line.103"></a>
+<FONT color="green">104</FONT> */<a name="line.104"></a>
+<FONT color="green">105</FONT> public CSVParser(final Reader input, final CSVFormat format) throws IOException {<a name="line.105"></a>
+<FONT color="green">106</FONT> this.lexer = new CSVLexer(format, new ExtendedBufferedReader(input));<a name="line.106"></a>
+<FONT color="green">107</FONT> this.headerMap = initializeHeader(format);<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> /**<a name="line.110"></a>
+<FONT color="green">111</FONT> * Customized CSV parser using the given {@link CSVFormat}<a name="line.111"></a>
+<FONT color="green">112</FONT> *<a name="line.112"></a>
+<FONT color="green">113</FONT> * @param input<a name="line.113"></a>
+<FONT color="green">114</FONT> * a String containing "csv-formatted" input<a name="line.114"></a>
+<FONT color="green">115</FONT> * @param format<a name="line.115"></a>
+<FONT color="green">116</FONT> * the CSVFormat used for CSV parsing<a name="line.116"></a>
+<FONT color="green">117</FONT> * @throws IllegalArgumentException<a name="line.117"></a>
+<FONT color="green">118</FONT> * thrown if the parameters of the format are inconsistent<a name="line.118"></a>
+<FONT color="green">119</FONT> */<a name="line.119"></a>
+<FONT color="green">120</FONT> public CSVParser(final String input, final CSVFormat format) throws IOException {<a name="line.120"></a>
+<FONT color="green">121</FONT> this(new StringReader(input), format);<a name="line.121"></a>
+<FONT color="green">122</FONT> }<a name="line.122"></a>
+<FONT color="green">123</FONT> <a name="line.123"></a>
+<FONT color="green">124</FONT> /**<a name="line.124"></a>
+<FONT color="green">125</FONT> * Returns a copy of the header map that iterates in column order.<a name="line.125"></a>
+<FONT color="green">126</FONT> * <p><a name="line.126"></a>
+<FONT color="green">127</FONT> * The map keys are column names.<a name="line.127"></a>
+<FONT color="green">128</FONT> * The map values are 0-based indices.<a name="line.128"></a>
+<FONT color="green">129</FONT> *<a name="line.129"></a>
+<FONT color="green">130</FONT> * @return a copy of the header map that iterates in column order.<a name="line.130"></a>
+<FONT color="green">131</FONT> */<a name="line.131"></a>
+<FONT color="green">132</FONT> public Map<String, Integer> getHeaderMap() {<a name="line.132"></a>
+<FONT color="green">133</FONT> return new LinkedHashMap<String, Integer>(headerMap);<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> * Returns the current line number in the input stream.<a name="line.137"></a>
+<FONT color="green">138</FONT> * <p/><a name="line.138"></a>
+<FONT color="green">139</FONT> * ATTENTION: If your CSV input has multi-line values, the returned number does not correspond to the record number.<a name="line.139"></a>
+<FONT color="green">140</FONT> *<a name="line.140"></a>
+<FONT color="green">141</FONT> * @return current line number<a name="line.141"></a>
<FONT color="green">142</FONT> */<a name="line.142"></a>
-<FONT color="green">143</FONT> String[] getRecord() throws IOException {<a name="line.143"></a>
-<FONT color="green">144</FONT> String[] result = EMPTY_STRING_ARRAY;<a name="line.144"></a>
-<FONT color="green">145</FONT> record.clear();<a name="line.145"></a>
-<FONT color="green">146</FONT> while (true) {<a name="line.146"></a>
-<FONT color="green">147</FONT> reusableToken.reset();<a name="line.147"></a>
-<FONT color="green">148</FONT> lexer.nextToken(reusableToken);<a name="line.148"></a>
-<FONT color="green">149</FONT> switch (reusableToken.type) {<a name="line.149"></a>
-<FONT color="green">150</FONT> case TOKEN:<a name="line.150"></a>
-<FONT color="green">151</FONT> record.add(reusableToken.content.toString());<a name="line.151"></a>
-<FONT color="green">152</FONT> break;<a name="line.152"></a>
-<FONT color="green">153</FONT> case EORECORD:<a name="line.153"></a>
-<FONT color="green">154</FONT> record.add(reusableToken.content.toString());<a name="line.154"></a>
-<FONT color="green">155</FONT> break;<a name="line.155"></a>
-<FONT color="green">156</FONT> case EOF:<a name="line.156"></a>
-<FONT color="green">157</FONT> if (reusableToken.isReady) {<a name="line.157"></a>
-<FONT color="green">158</FONT> record.add(reusableToken.content.toString());<a name="line.158"></a>
-<FONT color="green">159</FONT> } else {<a name="line.159"></a>
-<FONT color="green">160</FONT> result = null;<a name="line.160"></a>
-<FONT color="green">161</FONT> }<a name="line.161"></a>
-<FONT color="green">162</FONT> break;<a name="line.162"></a>
-<FONT color="green">163</FONT> case INVALID:<a name="line.163"></a>
-<FONT color="green">164</FONT> // error: throw IOException<a name="line.164"></a>
-<FONT color="green">165</FONT> throw new IOException("(line " + getLineNumber() + ") invalid parse sequence");<a name="line.165"></a>
-<FONT color="green">166</FONT> // unreachable: break;<a name="line.166"></a>
-<FONT color="green">167</FONT> }<a name="line.167"></a>
-<FONT color="green">168</FONT> if (reusableToken.type != TOKEN) {<a name="line.168"></a>
-<FONT color="green">169</FONT> break;<a name="line.169"></a>
-<FONT color="green">170</FONT> }<a name="line.170"></a>
-<FONT color="green">171</FONT> }<a name="line.171"></a>
-<FONT color="green">172</FONT> if (!record.isEmpty()) {<a name="line.172"></a>
-<FONT color="green">173</FONT> result = record.toArray(new String[record.size()]);<a name="line.173"></a>
-<FONT color="green">174</FONT> }<a name="line.174"></a>
-<FONT color="green">175</FONT> return result;<a name="line.175"></a>
-<FONT color="green">176</FONT> }<a name="line.176"></a>
-<FONT color="green">177</FONT> <a name="line.177"></a>
-<FONT color="green">178</FONT> /**<a name="line.178"></a>
-<FONT color="green">179</FONT> * Returns an iterator on the records. IOExceptions occuring<a name="line.179"></a>
-<FONT color="green">180</FONT> * during the iteration are wrapped in a RuntimeException.<a name="line.180"></a>
-<FONT color="green">181</FONT> */<a name="line.181"></a>
-<FONT color="green">182</FONT> public Iterator<String[]> iterator() {<a name="line.182"></a>
-<FONT color="green">183</FONT> return new Iterator<String[]>() {<a name="line.183"></a>
-<FONT color="green">184</FONT> String[] current;<a name="line.184"></a>
-<FONT color="green">185</FONT> <a name="line.185"></a>
-<FONT color="green">186</FONT> public boolean hasNext() {<a name="line.186"></a>
-<FONT color="green">187</FONT> if (current == null) {<a name="line.187"></a>
-<FONT color="green">188</FONT> current = getNextLine();<a name="line.188"></a>
-<FONT color="green">189</FONT> }<a name="line.189"></a>
-<FONT color="green">190</FONT> <a name="line.190"></a>
-<FONT color="green">191</FONT> return current != null;<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> public String[] next() {<a name="line.194"></a>
-<FONT color="green">195</FONT> String[] next = current;<a name="line.195"></a>
-<FONT color="green">196</FONT> current = null;<a name="line.196"></a>
+<FONT color="green">143</FONT> public long getLineNumber() {<a name="line.143"></a>
+<FONT color="green">144</FONT> return lexer.getLineNumber();<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> /**<a name="line.147"></a>
+<FONT color="green">148</FONT> * Returns the current record number in the input stream.<a name="line.148"></a>
+<FONT color="green">149</FONT> * <p/><a name="line.149"></a>
+<FONT color="green">150</FONT> * ATTENTION: If your CSV input has multi-line values, the returned number does not correspond to the line number.<a name="line.150"></a>
+<FONT color="green">151</FONT> *<a name="line.151"></a>
+<FONT color="green">152</FONT> * @return current line number<a name="line.152"></a>
+<FONT color="green">153</FONT> */<a name="line.153"></a>
+<FONT color="green">154</FONT> public long getRecordNumber() {<a name="line.154"></a>
+<FONT color="green">155</FONT> return recordNumber;<a name="line.155"></a>
+<FONT color="green">156</FONT> }<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> * Parses the next record from the current point in the stream.<a name="line.159"></a>
+<FONT color="green">160</FONT> *<a name="line.160"></a>
+<FONT color="green">161</FONT> * @return the record as an array of values, or <tt>null</tt> if the end of the stream has been reached<a name="line.161"></a>
+<FONT color="green">162</FONT> * @throws IOException<a name="line.162"></a>
+<FONT color="green">163</FONT> * on parse error or input read-failure<a name="line.163"></a>
+<FONT color="green">164</FONT> */<a name="line.164"></a>
+<FONT color="green">165</FONT> CSVRecord nextRecord() throws IOException {<a name="line.165"></a>
+<FONT color="green">166</FONT> CSVRecord result = null;<a name="line.166"></a>
+<FONT color="green">167</FONT> record.clear();<a name="line.167"></a>
+<FONT color="green">168</FONT> StringBuilder sb = null;<a name="line.168"></a>
+<FONT color="green">169</FONT> do {<a name="line.169"></a>
+<FONT color="green">170</FONT> reusableToken.reset();<a name="line.170"></a>
+<FONT color="green">171</FONT> lexer.nextToken(reusableToken);<a name="line.171"></a>
+<FONT color="green">172</FONT> switch (reusableToken.type) {<a name="line.172"></a>
+<FONT color="green">173</FONT> case TOKEN:<a name="line.173"></a>
+<FONT color="green">174</FONT> record.add(reusableToken.content.toString());<a name="line.174"></a>
+<FONT color="green">175</FONT> break;<a name="line.175"></a>
+<FONT color="green">176</FONT> case EORECORD:<a name="line.176"></a>
+<FONT color="green">177</FONT> record.add(reusableToken.content.toString());<a name="line.177"></a>
+<FONT color="green">178</FONT> break;<a name="line.178"></a>
+<FONT color="green">179</FONT> case EOF:<a name="line.179"></a>
+<FONT color="green">180</FONT> if (reusableToken.isReady) {<a name="line.180"></a>
+<FONT color="green">181</FONT> record.add(reusableToken.content.toString());<a name="line.181"></a>
+<FONT color="green">182</FONT> }<a name="line.182"></a>
+<FONT color="green">183</FONT> break;<a name="line.183"></a>
+<FONT color="green">184</FONT> case INVALID:<a name="line.184"></a>
+<FONT color="green">185</FONT> throw new IOException("(line " + getLineNumber() + ") invalid parse sequence");<a name="line.185"></a>
+<FONT color="green">186</FONT> case COMMENT: // Ignored currently<a name="line.186"></a>
+<FONT color="green">187</FONT> if (sb == null) { // first comment for this record<a name="line.187"></a>
+<FONT color="green">188</FONT> sb = new StringBuilder();<a name="line.188"></a>
+<FONT color="green">189</FONT> } else {<a name="line.189"></a>
+<FONT color="green">190</FONT> sb.append("\n");<a name="line.190"></a>
+<FONT color="green">191</FONT> }<a name="line.191"></a>
+<FONT color="green">192</FONT> sb.append(reusableToken.content);<a name="line.192"></a>
+<FONT color="green">193</FONT> reusableToken.type = TOKEN; // Read another token<a name="line.193"></a>
+<FONT color="green">194</FONT> break;<a name="line.194"></a>
+<FONT color="green">195</FONT> }<a name="line.195"></a>
+<FONT color="green">196</FONT> } while (reusableToken.type == TOKEN);<a name="line.196"></a>
<FONT color="green">197</FONT> <a name="line.197"></a>
-<FONT color="green">198</FONT> if (next == null) {<a name="line.198"></a>
-<FONT color="green">199</FONT> // hasNext() wasn't called before<a name="line.199"></a>
-<FONT color="green">200</FONT> next = getNextLine();<a name="line.200"></a>
-<FONT color="green">201</FONT> if (next == null) {<a name="line.201"></a>
-<FONT color="green">202</FONT> throw new NoSuchElementException("No more CSV records available");<a name="line.202"></a>
-<FONT color="green">203</FONT> }<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> return next;<a name="line.206"></a>
-<FONT color="green">207</FONT> }<a name="line.207"></a>
-<FONT color="green">208</FONT> <a name="line.208"></a>
-<FONT color="green">209</FONT> private String[] getNextLine() {<a name="line.209"></a>
-<FONT color="green">210</FONT> try {<a name="line.210"></a>
-<FONT color="green">211</FONT> return getRecord();<a name="line.211"></a>
-<FONT color="green">212</FONT> } catch (IOException e) {<a name="line.212"></a>
-<FONT color="green">213</FONT> throw new RuntimeException(e);<a name="line.213"></a>
-<FONT color="green">214</FONT> }<a name="line.214"></a>
-<FONT color="green">215</FONT> }<a name="line.215"></a>
-<FONT color="green">216</FONT> <a name="line.216"></a>
-<FONT color="green">217</FONT> public void remove() { }<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> <a name="line.220"></a>
-<FONT color="green">221</FONT> /**<a name="line.221"></a>
-<FONT color="green">222</FONT> * Returns the current line number in the input stream.<a name="line.222"></a>
-<FONT color="green">223</FONT> * <p/><a name="line.223"></a>
-<FONT color="green">224</FONT> * ATTENTION: in case your csv has multiline-values the returned<a name="line.224"></a>
-<FONT color="green">225</FONT> * number does not correspond to the record-number<a name="line.225"></a>
-<FONT color="green">226</FONT> *<a name="line.226"></a>
-<FONT color="green">227</FONT> * @return current line number<a name="line.227"></a>
-<FONT color="green">228</FONT> */<a name="line.228"></a>
-<FONT color="green">229</FONT> public int getLineNumber() {<a name="line.229"></a>
-<FONT color="green">230</FONT> return lexer.getLineNumber();<a name="line.230"></a>
-<FONT color="green">231</FONT> }<a name="line.231"></a>
-<FONT color="green">232</FONT> }<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> class CSVLexer {<a name="line.235"></a>
-<FONT color="green">236</FONT> <a name="line.236"></a>
-<FONT color="green">237</FONT> /** length of the initial token (content-)buffer */<a name="line.237"></a>
-<FONT color="green">238</FONT> private static final int INITIAL_TOKEN_LENGTH = 50;<a name="line.238"></a>
-<FONT color="green">239</FONT> <a name="line.239"></a>
-<FONT color="green">240</FONT> private final CharBuffer wsBuf = new CharBuffer();<a name="line.240"></a>
-<FONT color="green">241</FONT> <a name="line.241"></a>
-<FONT color="green">242</FONT> private final CSVFormat format;<a name="line.242"></a>
-<FONT color="green">243</FONT> <a name="line.243"></a>
-<FONT color="green">244</FONT> /** The input stream */<a name="line.244"></a>
-<FONT color="green">245</FONT> private final ExtendedBufferedReader in;<a name="line.245"></a>
-<FONT color="green">246</FONT> <a name="line.246"></a>
-<FONT color="green">247</FONT> /**<a name="line.247"></a>
-<FONT color="green">248</FONT> * Token is an internal token representation.<a name="line.248"></a>
-<FONT color="green">249</FONT> * <p/><a name="line.249"></a>
-<FONT color="green">250</FONT> * It is used as contract between the lexer and the parser.<a name="line.250"></a>
-<FONT color="green">251</FONT> */<a name="line.251"></a>
-<FONT color="green">252</FONT> static class Token {<a name="line.252"></a>
+<FONT color="green">198</FONT> if (!record.isEmpty()) {<a name="line.198"></a>
+<FONT color="green">199</FONT> recordNumber++;<a name="line.199"></a>
+<FONT color="green">200</FONT> final String comment = sb == null ? null : sb.toString();<a name="line.200"></a>
+<FONT color="green">201</FONT> result = new CSVRecord(record.toArray(new String[record.size()]), headerMap, comment, this.recordNumber);<a name="line.201"></a>
+<FONT color="green">202</FONT> }<a name="line.202"></a>
+<FONT color="green">203</FONT> return result;<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> * Parses the CSV input according to the given format and returns the content as an array of {@link CSVRecord}<a name="line.207"></a>
+<FONT color="green">208</FONT> * entries.<a name="line.208"></a>
+<FONT color="green">209</FONT> * <p/><a name="line.209"></a>
+<FONT color="green">210</FONT> * The returned content starts at the current parse-position in the stream.<a name="line.210"></a>
+<FONT color="green">211</FONT> *<a name="line.211"></a>
+<FONT color="green">212</FONT> * @return list of {@link CSVRecord} entries, may be empty<a name="line.212"></a>
+<FONT color="green">213</FONT> * @throws IOException<a name="line.213"></a>
+<FONT color="green">214</FONT> * on parse error or input read-failure<a name="line.214"></a>
+<FONT color="green">215</FONT> */<a name="line.215"></a>
+<FONT color="green">216</FONT> public List<CSVRecord> getRecords() throws IOException {<a name="line.216"></a>
+<FONT color="green">217</FONT> final List<CSVRecord> records = new ArrayList<CSVRecord>();<a name="line.217"></a>
+<FONT color="green">218</FONT> CSVRecord rec;<a name="line.218"></a>
+<FONT color="green">219</FONT> while ((rec = nextRecord()) != null) {<a name="line.219"></a>
+<FONT color="green">220</FONT> records.add(rec);<a name="line.220"></a>
+<FONT color="green">221</FONT> }<a name="line.221"></a>
+<FONT color="green">222</FONT> return records;<a name="line.222"></a>
+<FONT color="green">223</FONT> }<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> * Initializes the name to index mapping if the format defines a header.<a name="line.226"></a>
+<FONT color="green">227</FONT> */<a name="line.227"></a>
+<FONT color="green">228</FONT> private Map<String, Integer> initializeHeader(final CSVFormat format) throws IOException {<a name="line.228"></a>
+<FONT color="green">229</FONT> Map<String, Integer> hdrMap = null;<a name="line.229"></a>
+<FONT color="green">230</FONT> if (format.getHeader() != null) {<a name="line.230"></a>
+<FONT color="green">231</FONT> hdrMap = new LinkedHashMap<String, Integer>();<a name="line.231"></a>
+<FONT color="green">232</FONT> <a name="line.232"></a>
+<FONT color="green">233</FONT> String[] header = null;<a name="line.233"></a>
+<FONT color="green">234</FONT> if (format.getHeader().length == 0) {<a name="line.234"></a>
+<FONT color="green">235</FONT> // read the header from the first line of the file<a name="line.235"></a>
+<FONT color="green">236</FONT> final CSVRecord rec = nextRecord();<a name="line.236"></a>
+<FONT color="green">237</FONT> if (rec != null) {<a name="line.237"></a>
+<FONT color="green">238</FONT> header = rec.values();<a name="line.238"></a>
+<FONT color="green">239</FONT> }<a name="line.239"></a>
+<FONT color="green">240</FONT> } else {<a name="line.240"></a>
+<FONT color="green">241</FONT> header = format.getHeader();<a name="line.241"></a>
+<FONT color="green">242</FONT> }<a name="line.242"></a>
+<FONT color="green">243</FONT> <a name="line.243"></a>
+<FONT color="green">244</FONT> // build the name to index mappings<a name="line.244"></a>
+<FONT color="green">245</FONT> if (header != null) {<a name="line.245"></a>
+<FONT color="green">246</FONT> for (int i = 0; i < header.length; i++) {<a name="line.246"></a>
+<FONT color="green">247</FONT> hdrMap.put(header[i], Integer.valueOf(i));<a name="line.247"></a>
+<FONT color="green">248</FONT> }<a name="line.248"></a>
+<FONT color="green">249</FONT> }<a name="line.249"></a>
+<FONT color="green">250</FONT> }<a name="line.250"></a>
+<FONT color="green">251</FONT> return hdrMap;<a name="line.251"></a>
+<FONT color="green">252</FONT> }<a name="line.252"></a>
<FONT color="green">253</FONT> <a name="line.253"></a>
-<FONT color="green">254</FONT> enum Type {<a name="line.254"></a>
-<FONT color="green">255</FONT> /** Token has no valid content, i.e. is in its initialized state. */<a name="line.255"></a>
-<FONT color="green">256</FONT> INVALID,<a name="line.256"></a>
-<FONT color="green">257</FONT> <a name="line.257"></a>
-<FONT color="green">258</FONT> /** Token with content, at beginning or in the middle of a line. */<a name="line.258"></a>
-<FONT color="green">259</FONT> TOKEN,<a name="line.259"></a>
-<FONT color="green">260</FONT> <a name="line.260"></a>
-<FONT color="green">261</FONT> /** Token (which can have content) when end of file is reached. */<a name="line.261"></a>
-<FONT color="green">262</FONT> EOF,<a name="line.262"></a>
-<FONT color="green">263</FONT> <a name="line.263"></a>
-<FONT color="green">264</FONT> /** Token with content when end of a line is reached. */<a name="line.264"></a>
-<FONT color="green">265</FONT> EORECORD<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> /** Token type */<a name="line.268"></a>
-<FONT color="green">269</FONT> Type type = INVALID;<a name="line.269"></a>
-<FONT color="green">270</FONT> <a name="line.270"></a>
-<FONT color="green">271</FONT> /** The content buffer. */<a name="line.271"></a>
-<FONT color="green">272</FONT> CharBuffer content = new CharBuffer(INITIAL_TOKEN_LENGTH);<a name="line.272"></a>
-<FONT color="green">273</FONT> <a name="line.273"></a>
-<FONT color="green">274</FONT> /** Token ready flag: indicates a valid token with content (ready for the parser). */<a name="line.274"></a>
-<FONT color="green">275</FONT> boolean isReady;<a name="line.275"></a>
-<FONT color="green">276</FONT> <a name="line.276"></a>
-<FONT color="green">277</FONT> Token reset() {<a name="line.277"></a>
-<FONT color="green">278</FONT> content.clear();<a name="line.278"></a>
-<FONT color="green">279</FONT> type = INVALID;<a name="line.279"></a>
-<FONT color="green">280</FONT> isReady = false;<a name="line.280"></a>
-<FONT color="green">281</FONT> return this;<a name="line.281"></a>
-<FONT color="green">282</FONT> }<a name="line.282"></a>
-<FONT color="green">283</FONT> }<a name="line.283"></a>
-<FONT color="green">284</FONT> <a name="line.284"></a>
-<FONT color="green">285</FONT> CSVLexer(CSVFormat format, ExtendedBufferedReader in) {<a name="line.285"></a>
-<FONT color="green">286</FONT> this.format = format;<a name="line.286"></a>
-<FONT color="green">287</FONT> this.in = in;<a name="line.287"></a>
-<FONT color="green">288</FONT> }<a name="line.288"></a>
-<FONT color="green">289</FONT> <a name="line.289"></a>
-<FONT color="green">290</FONT> public int getLineNumber() {<a name="line.290"></a>
-<FONT color="green">291</FONT> return in.getLineNumber();<a name="line.291"></a>
-<FONT color="green">292</FONT> }<a name="line.292"></a>
+<FONT color="green">254</FONT> /**<a name="line.254"></a>
+<FONT color="green">255</FONT> * Returns an iterator on the records. IOExceptions occurring during the iteration are wrapped in a<a name="line.255"></a>
+<FONT color="green">256</FONT> * RuntimeException.<a name="line.256"></a>
+<FONT color="green">257</FONT> */<a name="line.257"></a>
+<FONT color="green">258</FONT> public Iterator<CSVRecord> iterator() {<a name="line.258"></a>
+<FONT color="green">259</FONT> return new Iterator<CSVRecord>() {<a name="line.259"></a>
+<FONT color="green">260</FONT> private CSVRecord current;<a name="line.260"></a>
+<FONT color="green">261</FONT> <a name="line.261"></a>
+<FONT color="green">262</FONT> private CSVRecord getNextRecord() {<a name="line.262"></a>
+<FONT color="green">263</FONT> try {<a name="line.263"></a>
+<FONT color="green">264</FONT> return nextRecord();<a name="line.264"></a>
+<FONT color="green">265</FONT> } catch (final IOException e) {<a name="line.265"></a>
+<FONT color="green">266</FONT> // TODO: This is not great, throw an ISE instead?<a name="line.266"></a>
+<FONT color="green">267</FONT> throw new RuntimeException(e);<a name="line.267"></a>
+<FONT color="green">268</FONT> }<a name="line.268"></a>
+<FONT color="green">269</FONT> }<a name="line.269"></a>
+<FONT color="green">270</FONT> <a name="line.270"></a>
+<FONT color="green">271</FONT> public boolean hasNext() {<a name="line.271"></a>
+<FONT color="green">272</FONT> if (current == null) {<a name="line.272"></a>
+<FONT color="green">273</FONT> current = getNextRecord();<a name="line.273"></a>
+<FONT color="green">274</FONT> }<a name="line.274"></a>
+<FONT color="green">275</FONT> <a name="line.275"></a>
+<FONT color="green">276</FONT> return current != null;<a name="line.276"></a>
+<FONT color="green">277</FONT> }<a name="line.277"></a>
+<FONT color="green">278</FONT> <a name="line.278"></a>
+<FONT color="green">279</FONT> public CSVRecord next() {<a name="line.279"></a>
+<FONT color="green">280</FONT> CSVRecord next = current;<a name="line.280"></a>
+<FONT color="green">281</FONT> current = null;<a name="line.281"></a>
+<FONT color="green">282</FONT> <a name="line.282"></a>
+<FONT color="green">283</FONT> if (next == null) {<a name="line.283"></a>
+<FONT color="green">284</FONT> // hasNext() wasn't called before<a name="line.284"></a>
+<FONT color="green">285</FONT> next = getNextRecord();<a name="line.285"></a>
+<FONT color="green">286</FONT> if (next == null) {<a name="line.286"></a>
+<FONT color="green">287</FONT> throw new NoSuchElementException("No more CSV records available");<a name="line.287"></a>
+<FONT color="green">288</FONT> }<a name="line.288"></a>
+<FONT color="green">289</FONT> }<a name="line.289"></a>
+<FONT color="green">290</FONT> <a name="line.290"></a>
+<FONT color="green">291</FONT> return next;<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> * Returns the next token.<a name="line.295"></a>
-<FONT color="green">296</FONT> * <p/><a name="line.296"></a>
-<FONT color="green">297</FONT> * A token corresponds to a term, a record change or an end-of-file indicator.<a name="line.297"></a>
-<FONT color="green">298</FONT> *<a name="line.298"></a>
-<FONT color="green">299</FONT> * @param tkn an existing Token object to reuse. The caller is responsible to initialize the Token.<a name="line.299"></a>
-<FONT color="green">300</FONT> * @return the next token found<a name="line.300"></a>
-<FONT color="green">301</FONT> * @throws IOException on stream access error<a name="line.301"></a>
-<FONT color="green">302</FONT> */<a name="line.302"></a>
-<FONT color="green">303</FONT> Token nextToken(Token tkn) throws IOException {<a name="line.303"></a>
-<FONT color="green">304</FONT> wsBuf.clear(); // reuse<a name="line.304"></a>
-<FONT color="green">305</FONT> <a name="line.305"></a>
-<FONT color="green">306</FONT> // get the last read char (required for empty line detection)<a name="line.306"></a>
-<FONT color="green">307</FONT> int lastChar = in.readAgain();<a name="line.307"></a>
-<FONT color="green">308</FONT> <a name="line.308"></a>
-<FONT color="green">309</FONT> // read the next char and set eol<a name="line.309"></a>
-<FONT color="green">310</FONT> /* note: unfortunately isEndOfLine may consumes a character silently.<a name="line.310"></a>
-<FONT color="green">311</FONT> * this has no effect outside of the method. so a simple workaround<a name="line.311"></a>
-<FONT color="green">312</FONT> * is to call 'readAgain' on the stream...<a name="line.312"></a>
-<FONT color="green">313</FONT> * uh: might using objects instead of base-types (jdk1.5 autoboxing!)<a name="line.313"></a>
-<FONT color="green">314</FONT> */<a name="line.314"></a>
-<FONT color="green">315</FONT> int c = in.read();<a name="line.315"></a>
-<FONT color="green">316</FONT> boolean eol = isEndOfLine(c);<a name="line.316"></a>
-<FONT color="green">317</FONT> c = in.readAgain();<a name="line.317"></a>
-<FONT color="green">318</FONT> <a name="line.318"></a>
-<FONT color="green">319</FONT> // empty line detection: eol AND (last char was EOL or beginning)<a name="line.319"></a>
-<FONT color="green">320</FONT> while (format.isEmptyLinesIgnored() && eol<a name="line.320"></a>
-<FONT color="green">321</FONT> && (lastChar == '\n'<a name="line.321"></a>
-<FONT color="green">322</FONT> || lastChar == '\r'<a name="line.322"></a>
-<FONT color="green">323</FONT> || lastChar == ExtendedBufferedReader.UNDEFINED)<a name="line.323"></a>
-<FONT color="green">324</FONT> && !isEndOfFile(lastChar)) {<a name="line.324"></a>
-<FONT color="green">325</FONT> // go on char ahead ...<a name="line.325"></a>
-<FONT color="green">326</FONT> lastChar = c;<a name="line.326"></a>
-<FONT color="green">327</FONT> c = in.read();<a name="line.327"></a>
-<FONT color="green">328</FONT> eol = isEndOfLine(c);<a name="line.328"></a>
-<FONT color="green">329</FONT> c = in.readAgain();<a name="line.329"></a>
-<FONT color="green">330</FONT> // reached end of file without any content (empty line at the end)<a name="line.330"></a>
-<FONT color="green">331</FONT> if (isEndOfFile(c)) {<a name="line.331"></a>
-<FONT color="green">332</FONT> tkn.type = EOF;<a name="line.332"></a>
-<FONT color="green">333</FONT> return tkn;<a name="line.333"></a>
-<FONT color="green">334</FONT> }<a name="line.334"></a>
-<FONT color="green">335</FONT> }<a name="line.335"></a>
-<FONT color="green">336</FONT> <a name="line.336"></a>
-<FONT color="green">337</FONT> // did we reach eof during the last iteration already ? EOF<a name="line.337"></a>
-<FONT color="green">338</FONT> if (isEndOfFile(lastChar) || (lastChar != format.getDelimiter() && isEndOfFile(c))) {<a name="line.338"></a>
-<FONT color="green">339</FONT> tkn.type = EOF;<a name="line.339"></a>
-<FONT color="green">340</FONT> return tkn;<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> // important: make sure a new char gets consumed in each iteration<a name="line.343"></a>
-<FONT color="green">344</FONT> while (!tkn.isReady && tkn.type != EOF) {<a name="line.344"></a>
-<FONT color="green">345</FONT> // ignore whitespaces at beginning of a token<a name="line.345"></a>
-<FONT color="green">346</FONT> while (format.isLeadingSpacesIgnored() && isWhitespace(c) && !eol) {<a name="line.346"></a>
-<FONT color="green">347</FONT> wsBuf.append((char) c);<a name="line.347"></a>
-<FONT color="green">348</FONT> c = in.read();<a name="line.348"></a>
-<FONT color="green">349</FONT> eol = isEndOfLine(c);<a name="line.349"></a>
-<FONT color="green">350</FONT> }<a name="line.350"></a>
-<FONT color="green">351</FONT> // ok, start of token reached: comment, encapsulated, or token<a name="line.351"></a>
-<FONT color="green">352</FONT> if (c == format.getCommentStart()) {<a name="line.352"></a>
-<FONT color="green">353</FONT> // ignore everything till end of line and continue (incr linecount)<a name="line.353"></a>
-<FONT color="green">354</FONT> in.readLine();<a name="line.354"></a>
-<FONT color="green">355</FONT> tkn = nextToken(tkn.reset());<a name="line.355"></a>
-<FONT color="green">356</FONT> } else if (c == format.getDelimiter()) {<a name="line.356"></a>
-<FONT color="green">357</FONT> // empty token return TOKEN("")<a name="line.357"></a>
-<FONT color="green">358</FONT> tkn.type = TOKEN;<a name="line.358"></a>
-<FONT color="green">359</FONT> tkn.isReady = true;<a name="line.359"></a>
-<FONT color="green">360</FONT> } else if (eol) {<a name="line.360"></a>
-<FONT color="green">361</FONT> // empty token return EORECORD("")<a name="line.361"></a>
-<FONT color="green">362</FONT> //noop: tkn.content.append("");<a name="line.362"></a>
-<FONT color="green">363</FONT> tkn.type = EORECORD;<a name="line.363"></a>
-<FONT color="green">364</FONT> tkn.isReady = true;<a name="line.364"></a>
-<FONT color="green">365</FONT> } else if (c == format.getEncapsulator()) {<a name="line.365"></a>
-<FONT color="green">366</FONT> // consume encapsulated token<a name="line.366"></a>
-<FONT color="green">367</FONT> encapsulatedTokenLexer(tkn, c);<a name="line.367"></a>
-<FONT color="green">368</FONT> } else if (isEndOfFile(c)) {<a name="line.368"></a>
-<FONT color="green">369</FONT> // end of file return EOF()<a name="line.369"></a>
-<FONT color="green">370</FONT> //noop: tkn.content.append("");<a name="line.370"></a>
-<FONT color="green">371</FONT> tkn.type = EOF;<a name="line.371"></a>
-<FONT color="green">372</FONT> tkn.isReady = true;<a name="line.372"></a>
-<FONT color="green">373</FONT> } else {<a name="line.373"></a>
-<FONT color="green">374</FONT> // next token must be a simple token<a name="line.374"></a>
-<FONT color="green">375</FONT> // add removed blanks when not ignoring whitespace chars...<a name="line.375"></a>
-<FONT color="green">376</FONT> if (!format.isLeadingSpacesIgnored()) {<a name="line.376"></a>
-<FONT color="green">377</FONT> tkn.content.append(wsBuf);<a name="line.377"></a>
-<FONT color="green">378</FONT> }<a name="line.378"></a>
-<FONT color="green">379</FONT> simpleTokenLexer(tkn, c);<a name="line.379"></a>
-<FONT color="green">380</FONT> }<a name="line.380"></a>
-<FONT color="green">381</FONT> }<a name="line.381"></a>
-<FONT color="green">382</FONT> return tkn;<a name="line.382"></a>
-<FONT color="green">383</FONT> }<a name="line.383"></a>
-<FONT color="green">384</FONT> <a name="line.384"></a>
-<FONT color="green">385</FONT> /**<a name="line.385"></a>
-<FONT color="green">386</FONT> * A simple token lexer<a name="line.386"></a>
-<FONT color="green">387</FONT> * <p/><a name="line.387"></a>
-<FONT color="green">388</FONT> * Simple token are tokens which are not surrounded by encapsulators.<a name="line.388"></a>
-<FONT color="green">389</FONT> * A simple token might contain escaped delimiters (as \, or \;). The<a name="line.389"></a>
-<FONT color="green">390</FONT> * token is finished when one of the following conditions become true:<a name="line.390"></a>
-<FONT color="green">391</FONT> * <ul><a name="line.391"></a>
-<FONT color="green">392</FONT> * <li>end of line has been reached (EORECORD)</li><a name="line.392"></a>
-<FONT color="green">393</FONT> * <li>end of stream has been reached (EOF)</li><a name="line.393"></a>
-<FONT color="green">394</FONT> * <li>an unescaped delimiter has been reached (TOKEN)</li><a name="line.394"></a>
-<FONT color="green">395</FONT> * </ul><a name="line.395"></a>
-<FONT color="green">396</FONT> *<a name="line.396"></a>
-<FONT color="green">397</FONT> * @param tkn the current token<a name="line.397"></a>
-<FONT color="green">398</FONT> * @param c the current character<a name="line.398"></a>
-<FONT color="green">399</FONT> * @return the filled token<a name="line.399"></a>
-<FONT color="green">400</FONT> * @throws IOException on stream access error<a name="line.400"></a>
-<FONT color="green">401</FONT> */<a name="line.401"></a>
-<FONT color="green">402</FONT> private Token simpleTokenLexer(Token tkn, int c) throws IOException {<a name="line.402"></a>
-<FONT color="green">403</FONT> for (; ;) {<a name="line.403"></a>
-<FONT color="green">404</FONT> if (isEndOfLine(c)) {<a name="line.404"></a>
-<FONT color="green">405</FONT> // end of record<a name="line.405"></a>
-<FONT color="green">406</FONT> tkn.type = EORECORD;<a name="line.406"></a>
-<FONT color="green">407</FONT> tkn.isReady = true;<a name="line.407"></a>
-<FONT color="green">408</FONT> break;<a name="line.408"></a>
-<FONT color="green">409</FONT> } else if (isEndOfFile(c)) {<a name="line.409"></a>
-<FONT color="green">410</FONT> // end of file<a name="line.410"></a>
-<FONT color="green">411</FONT> tkn.type = EOF;<a name="line.411"></a>
-<FONT color="green">412</FONT> tkn.isReady = true;<a name="line.412"></a>
-<FONT color="green">413</FONT> break;<a name="line.413"></a>
-<FONT color="green">414</FONT> } else if (c == format.getDelimiter()) {<a name="line.414"></a>
-<FONT color="green">415</FONT> // end of token<a name="line.415"></a>
-<FONT color="green">416</FONT> tkn.type = TOKEN;<a name="line.416"></a>
-<FONT color="green">417</FONT> tkn.isReady = true;<a name="line.417"></a>
-<FONT color="green">418</FONT> break;<a name="line.418"></a>
-<FONT color="green">419</FONT> } else if (c == format.getEscape()) {<a name="line.419"></a>
-<FONT color="green">420</FONT> tkn.content.append((char) readEscape(c));<a name="line.420"></a>
-<FONT color="green">421</FONT> } else {<a name="line.421"></a>
-<FONT color="green">422</FONT> tkn.content.append((char) c);<a name="line.422"></a>
-<FONT color="green">423</FONT> }<a name="line.423"></a>
-<FONT color="green">424</FONT> <a name="line.424"></a>
-<FONT color="green">425</FONT> c = in.read();<a name="line.425"></a>
-<FONT color="green">426</FONT> }<a name="line.426"></a>
-<FONT color="green">427</FONT> <a name="line.427"></a>
-<FONT color="green">428</FONT> if (format.isTrailingSpacesIgnored()) {<a name="line.428"></a>
-<FONT color="green">429</FONT> tkn.content.trimTrailingWhitespace();<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> return tkn;<a name="line.432"></a>
-<FONT color="green">433</FONT> }<a name="line.433"></a>
-<FONT color="green">434</FONT> <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> * An encapsulated token lexer<a name="line.437"></a>
-<FONT color="green">438</FONT> * <p/><a name="line.438"></a>
-<FONT color="green">439</FONT> * Encapsulated tokens are surrounded by the given encapsulating-string.<a name="line.439"></a>
-<FONT color="green">440</FONT> * The encapsulator itself might be included in the token using a<a name="line.440"></a>
-<FONT color="green">441</FONT> * doubling syntax (as "", '') or using escaping (as in \", \').<a name="line.441"></a>
-<FONT color="green">442</FONT> * Whitespaces before and after an encapsulated token are ignored.<a name="line.442"></a>
-<FONT color="green">443</FONT> *<a name="line.443"></a>
-<FONT color="green">444</FONT> * @param tkn the current token<a name="line.444"></a>
-<FONT color="green">445</FONT> * @param c the current character<a name="line.445"></a>
-<FONT color="green">446</FONT> * @return a valid token object<a name="line.446"></a>
-<FONT color="green">447</FONT> * @throws IOException on invalid state<a name="line.447"></a>
-<FONT color="green">448</FONT> */<a name="line.448"></a>
-<FONT color="green">449</FONT> private Token encapsulatedTokenLexer(Token tkn, int c) throws IOException {<a name="line.449"></a>
-<FONT color="green">450</FONT> // save current line<a name="line.450"></a>
-<FONT color="green">451</FONT> int startLineNumber = getLineNumber();<a name="line.451"></a>
-<FONT color="green">452</FONT> // ignore the given delimiter<a name="line.452"></a>
-<FONT color="green">453</FONT> // assert c == delimiter;<a name="line.453"></a>
-<FONT color="green">454</FONT> for (; ;) {<a name="line.454"></a>
-<FONT color="green">455</FONT> c = in.read();<a name="line.455"></a>
-<FONT color="green">456</FONT> <a name="line.456"></a>
-<FONT color="green">457</FONT> if (c == format.getEscape()) {<a name="line.457"></a>
-<FONT color="green">458</FONT> tkn.content.append((char) readEscape(c));<a name="line.458"></a>
-<FONT color="green">459</FONT> } else if (c == format.getEncapsulator()) {<a name="line.459"></a>
-<FONT color="green">460</FONT> if (in.lookAhead() == format.getEncapsulator()) {<a name="line.460"></a>
-<FONT color="green">461</FONT> // double or escaped encapsulator -> add single encapsulator to token<a name="line.461"></a>
-<FONT color="green">462</FONT> c = in.read();<a name="line.462"></a>
-<FONT color="green">463</FONT> tkn.content.append((char) c);<a name="line.463"></a>
-<FONT color="green">464</FONT> } else {<a name="line.464"></a>
-<FONT color="green">465</FONT> // token finish mark (encapsulator) reached: ignore whitespace till delimiter<a name="line.465"></a>
-<FONT color="green">466</FONT> for (; ;) {<a name="line.466"></a>
-<FONT color="green">467</FONT> c = in.read();<a name="line.467"></a>
-<FONT color="green">468</FONT> if (c == format.getDelimiter()) {<a name="line.468"></a>
-<FONT color="green">469</FONT> tkn.type = TOKEN;<a name="line.469"></a>
-<FONT color="green">470</FONT> tkn.isReady = true;<a name="line.470"></a>
-<FONT color="green">471</FONT> return tkn;<a name="line.471"></a>
-<FONT color="green">472</FONT> } else if (isEndOfFile(c)) {<a name="line.472"></a>
-<FONT color="green">473</FONT> tkn.type = EOF;<a name="line.473"></a>
-<FONT color="green">474</FONT> tkn.isReady = true;<a name="line.474"></a>
-<FONT color="green">475</FONT> return tkn;<a name="line.475"></a>
-<FONT color="green">476</FONT> } else if (isEndOfLine(c)) {<a name="line.476"></a>
-<FONT color="green">477</FONT> // ok eo token reached<a name="line.477"></a>
-<FONT color="green">478</FONT> tkn.type = EORECORD;<a name="line.478"></a>
-<FONT color="green">479</FONT> tkn.isReady = true;<a name="line.479"></a>
-<FONT color="green">480</FONT> return tkn;<a name="line.480"></a>
-<FONT color="green">481</FONT> } else if (!isWhitespace(c)) {<a name="line.481"></a>
-<FONT color="green">482</FONT> // error invalid char between token and next delimiter<a name="line.482"></a>
-<FONT color="green">483</FONT> throw new IOException("(line " + getLineNumber() + ") invalid char between encapsulated token and delimiter");<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> }<a name="line.486"></a>
-<FONT color="green">487</FONT> } else if (isEndOfFile(c)) {<a name="line.487"></a>
-<FONT color="green">488</FONT> // error condition (end of file before end of token)<a name="line.488"></a>
-<FONT color="green">489</FONT> throw new IOException("(startline " + startLineNumber + ") EOF reached before encapsulated token finished");<a name="line.489"></a>
-<FONT color="green">490</FONT> } else {<a name="line.490"></a>
-<FONT color="green">491</FONT> // consume character<a name="line.491"></a>
-<FONT color="green">492</FONT> tkn.content.append((char) c);<a name="line.492"></a>
-<FONT color="green">493</FONT> }<a name="line.493"></a>
-<FONT color="green">494</FONT> }<a name="line.494"></a>
-<FONT color="green">495</FONT> }<a name="line.495"></a>
-<FONT color="green">496</FONT> <a name="line.496"></a>
-<FONT color="green">497</FONT> private int readEscape(int c) throws IOException {<a name="line.497"></a>
-<FONT color="green">498</FONT> // assume c is the escape char (normally a backslash)<a name="line.498"></a>
-<FONT color="green">499</FONT> c = in.read();<a name="line.499"></a>
-<FONT color="green">500</FONT> switch (c) {<a name="line.500"></a>
-<FONT color="green">501</FONT> case 'r':<a name="line.501"></a>
-<FONT color="green">502</FONT> return '\r';<a name="line.502"></a>
-<FONT color="green">503</FONT> case 'n':<a name="line.503"></a>
-<FONT color="green">504</FONT> return '\n';<a name="line.504"></a>
-<FONT color="green">505</FONT> case 't':<a name="line.505"></a>
-<FONT color="green">506</FONT> return '\t';<a name="line.506"></a>
-<FONT color="green">507</FONT> case 'b':<a name="line.507"></a>
-<FONT color="green">508</FONT> return '\b';<a name="line.508"></a>
-<FONT color="green">509</FONT> case 'f':<a name="line.509"></a>
-<FONT color="green">510</FONT> return '\f';<a name="line.510"></a>
-<FONT color="green">511</FONT> default:<a name="line.511"></a>
-<FONT color="green">512</FONT> return c;<a name="line.512"></a>
-<FONT color="green">513</FONT> }<a name="line.513"></a>
-<FONT color="green">514</FONT> }<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>
-<FONT color="green">517</FONT> * @return true if the given char is a whitespace character<a name="line.517"></a>
-<FONT color="green">518</FONT> */<a name="line.518"></a>
-<FONT color="green">519</FONT> private boolean isWhitespace(int c) {<a name="line.519"></a>
-<FONT color="green">520</FONT> return Character.isWhitespace((char) c) && (c != format.getDelimiter());<a name="line.520"></a>
-<FONT color="green">521</FONT> }<a name="line.521"></a>
-<FONT color="green">522</FONT> <a name="line.522"></a>
-<FONT color="green">523</FONT> /**<a name="line.523"></a>
-<FONT color="green">524</FONT> * Greedy - accepts \n, \r and \r\n<a name="line.524"></a>
-<FONT color="green">525</FONT> * This checker consumes silently the second control-character...<a name="line.525"></a>
-<FONT color="green">526</FONT> *<a name="line.526"></a>
-<FONT color="green">527</FONT> * @return true if the given character is a line-terminator<a name="line.527"></a>
-<FONT color="green">528</FONT> */<a name="line.528"></a>
-<FONT color="green">529</FONT> private boolean isEndOfLine(int c) throws IOException {<a name="line.529"></a>
-<FONT color="green">530</FONT> // check if we have \r\n...<a name="line.530"></a>
-<FONT color="green">531</FONT> if (c == '\r' && in.lookAhead() == '\n') {<a name="line.531"></a>
-<FONT color="green">532</FONT> // note: does not change c outside of this method !!<a name="line.532"></a>
-<FONT color="green">533</FONT> c = in.read();<a name="line.533"></a>
-<FONT color="green">534</FONT> }<a name="line.534"></a>
-<FONT color="green">535</FONT> return (c == '\n' || c == '\r');<a name="line.535"></a>
-<FONT color="green">536</FONT> }<a name="line.536"></a>
-<FONT color="green">537</FONT> <a name="line.537"></a>
-<FONT color="green">538</FONT> /**<a name="line.538"></a>
-<FONT color="green">539</FONT> * @return true if the given character indicates end of file<a name="line.539"></a>
-<FONT color="green">540</FONT> */<a name="line.540"></a>
-<FONT color="green">541</FONT> private boolean isEndOfFile(int c) {<a name="line.541"></a>
-<FONT color="green">542</FONT> return c == ExtendedBufferedReader.END_OF_STREAM;<a name="line.542"></a>
-<FONT color="green">543</FONT> }<a name="line.543"></a>
-<FONT color="green">544</FONT> }<a name="line.544"></a>
+<FONT color="green">294</FONT> public void remove() {<a name="line.294"></a>
+<FONT color="green">295</FONT> throw new UnsupportedOperationException();<a name="line.295"></a>
+<FONT color="green">296</FONT> }<a name="line.296"></a>
+<FONT color="green">297</FONT> };<a name="line.297"></a>
+<FONT color="green">298</FONT> }<a name="line.298"></a>
+<FONT color="green">299</FONT> }<a name="line.299"></a>
@@ -607,4 +362,4 @@
</PRE>
</BODY>
-</HTML>
+</HTML>
\ No newline at end of file