Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

don't skip the reader of the huge linedocs file, skip the inputstream instead 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1336904 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2012-05-10 21:26:13 +00:00
parent 54a5e34d35
commit a41f0ca63b
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
lucene/test-framework/src/java/org/apache/lucene/util/LineFileDocs.java
View File

@ -24,6 +24,9 @@ import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CodingErrorAction;
import java.util.Random;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.zip.GZIPInputStream;
@ -88,8 +91,6 @@ public class LineFileDocs implements Closeable {
size *= 2.8;
}
reader = new BufferedReader(new InputStreamReader(is, "UTF-8"), BUFFER_SIZE);
// Override sizes for currently "known" line files:
if (path.equals("europarl.lines.txt.gz")) {
size = 15129506L;
@ -103,7 +104,11 @@ public class LineFileDocs implements Closeable {
if (LuceneTestCase.VERBOSE) {
System.out.println("TEST: LineFileDocs: seek to fp=" + seekTo + " on open");
}
reader.skip(seekTo);
is.skip(seekTo);
CharsetDecoder decoder = Charset.forName("UTF-8").newDecoder()
.onMalformedInput(CodingErrorAction.IGNORE)
.onUnmappableCharacter(CodingErrorAction.IGNORE);
reader = new BufferedReader(new InputStreamReader(is, decoder), BUFFER_SIZE);
reader.readLine();
}
}