mirror of https://github.com/apache/lucene.git
LUCENE-829: close done readers in contrib/benchmark.
git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@518822 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
parent
b9edb2867f
commit
977e729685
|
@ -79,6 +79,7 @@ public class ReutersDocMaker extends BasicDocMaker {
|
|||
while ((line = reader.readLine()) != null) {
|
||||
bodyBuf.append(line).append(' ');
|
||||
}
|
||||
reader.close();
|
||||
|
||||
addBytes(f.length());
|
||||
|
||||
|
|
|
@ -26,8 +26,10 @@ import java.io.InputStreamReader;
|
|||
import java.io.Reader;
|
||||
import java.io.StringReader;
|
||||
import java.text.DateFormat;
|
||||
import java.text.ParseException;
|
||||
import java.text.SimpleDateFormat;
|
||||
import java.util.ArrayList;
|
||||
import java.util.Date;
|
||||
import java.util.Locale;
|
||||
import java.util.Properties;
|
||||
import java.util.zip.GZIPInputStream;
|
||||
|
@ -159,7 +161,8 @@ public class TrecDocMaker extends BasicDocMaker {
|
|||
read("</DOCHDR>",null,false,false);
|
||||
// 6. collect until end of doc
|
||||
sb = read("</DOC>",null,false,true);
|
||||
// this is the next document, so parse it
|
||||
// this is the next document, so parse it
|
||||
// TODO use a more robust html parser (current one aborts parsing quite easily).
|
||||
HTMLParser p = new HTMLParser(new StringReader(sb.toString()));
|
||||
// title
|
||||
String title = p.getTitle();
|
||||
|
@ -175,11 +178,18 @@ public class TrecDocMaker extends BasicDocMaker {
|
|||
bodyBuf.append(c,0,n);
|
||||
}
|
||||
}
|
||||
r.close();
|
||||
addBytes(bodyBuf.length());
|
||||
|
||||
DocData dd = new DocData();
|
||||
|
||||
dd.date = dateFormat.parse(dateStr.trim());
|
||||
|
||||
try {
|
||||
dd.date = dateFormat.parse(dateStr.trim());
|
||||
} catch (ParseException e) {
|
||||
// do not fail test just because a date could not be parsed
|
||||
System.out.println("ignoring date parse exception (assigning 'now') for: "+dateStr);
|
||||
dd.date = new Date(); // now
|
||||
}
|
||||
dd.name = name;
|
||||
dd.title = title;
|
||||
dd.body = bodyBuf.toString();
|
||||
|
|
|
@ -275,6 +275,8 @@ public class StandardBenchmarker extends AbstractBenchmarker implements Benchmar
|
|||
{
|
||||
body.append(line).append(' ');
|
||||
}
|
||||
reader.close();
|
||||
|
||||
Date date = format.parse(dateStr.trim());
|
||||
|
||||
doc.add(new Field("date", DateTools.dateToString(date, DateTools.Resolution.SECOND), Field.Store.YES, Field.Index.UN_TOKENIZED));
|
||||
|
|
|
@ -135,6 +135,7 @@ public class ExtractReuters
|
|||
buffer.setLength(0);
|
||||
}
|
||||
}
|
||||
reader.close();
|
||||
}
|
||||
|
||||
catch (
|
||||
|
|
Loading…
Reference in New Issue