You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lenya.apache.org by mi...@apache.org on 2004/02/19 14:18:45 UTC
cvs commit: cocoon-lenya/src/java/org/apache/lenya/lucene/index AbstractIndexer.java DefaultIndexer.java Index.java IndexInformation.java Indexer.java
michi 2004/02/19 05:18:45
Modified: src/java/org/apache/lenya/lucene/index AbstractIndexer.java
DefaultIndexer.java Index.java
IndexInformation.java Indexer.java
Log:
Indexing improved
Revision Changes Path
1.12 +22 -19 cocoon-lenya/src/java/org/apache/lenya/lucene/index/AbstractIndexer.java
Index: AbstractIndexer.java
===================================================================
RCS file: /home/cvs/cocoon-lenya/src/java/org/apache/lenya/lucene/index/AbstractIndexer.java,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -r1.11 -r1.12
--- AbstractIndexer.java 17 Feb 2004 10:07:12 -0000 1.11
+++ AbstractIndexer.java 19 Feb 2004 13:18:45 -0000 1.12
@@ -61,6 +61,7 @@
import org.apache.log4j.Category;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.analysis.de.GermanAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
@@ -85,7 +86,9 @@
private Element indexer;
private String configFileName;
- /** Creates a new instance of AbstractIndexer */
+ /**
+ * Creates a new instance of AbstractIndexer
+ */
public AbstractIndexer() {
}
@@ -126,7 +129,7 @@
* <li>new documents, to be indexed.</li>
* </ol>
*/
- public void updateIndex(File dumpDirectory, String index)
+ public void updateIndex(File dumpDirectory, File index)
throws Exception {
deleteStaleDocuments(dumpDirectory, index);
doIndex(dumpDirectory, index, false);
@@ -135,24 +138,25 @@
/**
* Creates a new index.
*/
- public void createIndex(File dumpDirectory, String index)
+ public void createIndex(File dumpDirectory, File index)
throws Exception {
doIndex(dumpDirectory, index, true);
}
/**
- * DOCUMENT ME!
+ * Index files
*
- * @param dumpDirectory DOCUMENT ME!
- * @param index DOCUMENT ME!
- * @param create DOCUMENT ME!
+ * @param dumpDirectory Directory where the files to be indexed are located
+ * @param index Directory where the index shall be located
+ * @param create <b>true</b> means the index will be created from scratch, <b>false</b> means it will be indexed incrementally
*/
- public void doIndex(File dumpDirectory, String index, boolean create) {
+ public void doIndex(File dumpDirectory, File index, boolean create) {
try {
- IndexWriter writer = new IndexWriter(index, new StandardAnalyzer(), create);
+ //IndexWriter writer = new IndexWriter(index.getAbsolutePath(), new GermanAnalyzer(), create);
+ IndexWriter writer = new IndexWriter(index.getAbsolutePath(), new StandardAnalyzer(), create);
writer.maxFieldLength = 1000000;
- IndexInformation info = new IndexInformation(index, dumpDirectory, getFilter(indexer, configFileName), create);
+ IndexInformation info = new IndexInformation(index.getAbsolutePath(), dumpDirectory, getFilter(indexer, configFileName), create);
IndexHandler handler;
@@ -162,7 +166,7 @@
handler = new UpdateIndexHandler(dumpDirectory, info, writer);
}
- IndexIterator iterator = new IndexIterator(index, getFilter(indexer, configFileName));
+ IndexIterator iterator = new IndexIterator(index.getAbsolutePath(), getFilter(indexer, configFileName));
iterator.addHandler(handler);
iterator.iterate(dumpDirectory);
@@ -176,11 +180,11 @@
/**
* Delete the stale documents.
*/
- protected void deleteStaleDocuments(File dumpDirectory, String index)
+ protected void deleteStaleDocuments(File dumpDirectory, File index)
throws Exception {
log.debug("Deleting stale documents");
- IndexIterator iterator = new IndexIterator(index, getFilter(indexer, configFileName));
+ IndexIterator iterator = new IndexIterator(index.getAbsolutePath(), getFilter(indexer, configFileName));
iterator.addHandler(new DeleteHandler());
iterator.iterate(dumpDirectory);
log.debug("Deleting stale documents finished");
@@ -312,15 +316,14 @@
}
info.increase();
- log.debug(info.printProgress());
+ log.info(info.printProgress());
}
}
/**
* DOCUMENT ME!
*
- * @author $author$
- * @version $Revision$
+ * @author Andreas Hartmann
*/
public class CreateIndexHandler extends IndexHandler {
/**
1.8 +2 -2 cocoon-lenya/src/java/org/apache/lenya/lucene/index/DefaultIndexer.java
Index: DefaultIndexer.java
===================================================================
RCS file: /home/cvs/cocoon-lenya/src/java/org/apache/lenya/lucene/index/DefaultIndexer.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -u -r1.7 -r1.8
--- DefaultIndexer.java 2 Dec 2003 22:24:57 -0000 1.7
+++ DefaultIndexer.java 19 Feb 2004 13:18:45 -0000 1.8
@@ -71,7 +71,7 @@
/**
* @param indexer Indexer
- * @param configFileName Licene Configuration File
+ * @param configFileName Lucene Configuration File
*
* @return DefaultDocumentCreator
*
1.13 +6 -7 cocoon-lenya/src/java/org/apache/lenya/lucene/index/Index.java
Index: Index.java
===================================================================
RCS file: /home/cvs/cocoon-lenya/src/java/org/apache/lenya/lucene/index/Index.java,v
retrieving revision 1.12
retrieving revision 1.13
diff -u -r1.12 -r1.13
--- Index.java 17 Feb 2004 10:07:12 -0000 1.12
+++ Index.java 19 Feb 2004 13:18:45 -0000 1.13
@@ -1,5 +1,4 @@
/*
-$Id$
<License>
============================================================================
@@ -66,14 +65,14 @@
/**
- *
- * @author hrt
+ * @author Andreas Hartmann
+ * @version $Id$
*/
public class Index {
/**
- * DOCUMENT ME!
+ * Command line interface
*
- * @param argv DOCUMENT ME!
+ * @param argv Lucene Index Configuration
*/
public static void main(String[] argv) {
try {
@@ -127,9 +126,9 @@
indexer.configure(du.getElement(config.getDocumentElement(), new XPath("indexer")), argv[0]);
if (create) {
- indexer.createIndex(root, index);
+ indexer.createIndex(root, new File(index));
} else {
- indexer.updateIndex(root, index);
+ indexer.updateIndex(root, new File(index));
}
Date end = new Date();
1.8 +6 -6 cocoon-lenya/src/java/org/apache/lenya/lucene/index/IndexInformation.java
Index: IndexInformation.java
===================================================================
RCS file: /home/cvs/cocoon-lenya/src/java/org/apache/lenya/lucene/index/IndexInformation.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -u -r1.7 -r1.8
--- IndexInformation.java 17 Feb 2004 10:07:12 -0000 1.7
+++ IndexInformation.java 19 Feb 2004 13:18:45 -0000 1.8
@@ -1,5 +1,4 @@
/*
-$Id$
<License>
============================================================================
@@ -73,7 +72,8 @@
/**
*
- * @author <a href="mailto:andreas@apache.org">Andreas Hartmann</a>
+ * @author Andreas Hartmann
+ * @version $Id$
*/
public class IndexInformation {
@@ -165,9 +165,9 @@
}
/**
- * DOCUMENT ME!
+ * Generate string which tells about the indexing progress
*
- * @return DOCUMENT ME!
+ * @return indexing progress
*/
public String printProgress() {
double percent = (double) currentFile / (double) getFileNumber();
1.9 +3 -3 cocoon-lenya/src/java/org/apache/lenya/lucene/index/Indexer.java
Index: Indexer.java
===================================================================
RCS file: /home/cvs/cocoon-lenya/src/java/org/apache/lenya/lucene/index/Indexer.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -u -r1.8 -r1.9
--- Indexer.java 2 Feb 2004 02:50:38 -0000 1.8
+++ Indexer.java 19 Feb 2004 13:18:45 -0000 1.9
@@ -73,12 +73,12 @@
/**
* Indexes the contents of a directory.
*/
- void createIndex(File dumpDirectory, String index)
+ void createIndex(File dumpDirectory, File index)
throws Exception;
/**
* Indexes the contents of a directory.
*/
- void updateIndex(File dumpDirectory, String index)
+ void updateIndex(File dumpDirectory, File index)
throws Exception;
}
---------------------------------------------------------------------
To unsubscribe, e-mail: lenya-cvs-unsubscribe@cocoon.apache.org
For additional commands, e-mail: lenya-cvs-help@cocoon.apache.org