Did a clone of the AddIndexes method.
See code below. Anybody seeing any problems with using the
AddIndexesWithoutOptimize method ?
// Original
public virtual void AddIndexes(Directory[] dirs)
{
lock (this)
{
Optimize(); // start with zero or 1 seg
for (int i = 0; i < dirs.Length; i++)
{
SegmentInfos sis = new SegmentInfos();
// read infos from dir
sis.Read(dirs[i]);
for (int j = 0; j < sis.Count; j++)
{
segmentInfos.Add(sis.Info(j));
// add each info
}
}
Optimize(); // final cleanup
}
}
// new without optimize calls
public virtual void AddIndexesWithoutOptimize(Directory[] dirs)
{
lock (this)
{
for (int i = 0; i < dirs.Length; i++)
{
SegmentInfos sis = new SegmentInfos(); // read infos from
dir
sis.Read(dirs[i]);
for (int j = 0; j < sis.Count; j++)
{
segmentInfos.Add(sis.Info(j)); // add each info
}
}
MaybeMergeSegments();
}
}
-----Ursprungligt meddelande-----
Från: Marcus Falck [mailto:[EMAIL PROTECTED]
Skickat: den 28 juni 2006 11:46
Till: java-user@lucene.apache.org
Ämne: Flushing RAMDir into FSDir
Hi,
I got a lucene based host application that retrieves content for
indexing from fetcher applications.
Since I get fresh content all the time I wanted to have full control
over the disc write process.
So I ended up using a RAMDirectory and a FSDirectory.
When the content arrives to the application a representation of the
content is written to the disc and the content itself are added as a
Lucene document into the RAMDirectory. When the amount of documents in
the RAMDirectory exceeds my limit I flush the RAMDirectory into the
FSDirectory (using the same limit as minMergeDocs).
This works fine as long as I use the
fsIndexWriter.AddIndexes(new Directory[] { myRamDir } );
approach. However this approach seems to add the newly content to a new
large file (as long as maxMergeDocs hasn't been exceed).
For example if I got 5000 as minMergeDocs and 15000 as maxMergeDocs and
I flush the interval 5001-10000 from the ramdir to disc I will end up
with 1 file containing docs 1 - 10000 rather than 2 files ( 1 - 5000 and
5001 - 10000 ).
Is there any way to get it to add the new indexes as a new file instead?
Since this severely affects my indexing in a negative way.
/
Regards
Marcus Falck
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
