import java.util.*;
import java.io.*;
-
+
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.*;
import org.apache.lucene.document.Document;
import mir.util.*;
+import mir.log.*;
import mir.producer.*;
//import mir.generator.*;
import mircoders.global.*;
public class IndexingProducerNode implements ProducerNode {
private String contentKey;
private String indexPath;
-
-
+
+
public IndexingProducerNode(String aContentKey, String pathToIndex) {
contentKey = aContentKey;
indexPath=pathToIndex;
}
-
- public void produce(Map aValueMap, String aVerb, PrintWriter aLogger) throws ProducerFailure {
+
+ public void produce(Map aValueMap, String aVerb, LoggerWrapper aLogger) throws ProducerFailure {
IndexReader indexReader = null;
IndexWriter indexWriter = null;
Object data;
Entity entity;
-
+
long startTime;
long endTime;
-
+
startTime = System.currentTimeMillis();
-
+
try {
data = ParameterExpander.findValueForKey( aValueMap, contentKey );
-
+
if (! (data instanceof EntityAdapter)) {
- throw new ProducerFailure("IndexingProducerNode: value of '"+contentKey+"' is not an EntityAdapter, but an " + data.getClass().getName(), null);
+ throw new ProducerFailure("IndexingProducerNode: value of '"+contentKey+"' is not an EntityAdapter, but an " + data.getClass().getName(), null);
}
-
+
entity = ((EntityAdapter) data).getEntity();
if (! (entity instanceof EntityContent)) {
- throw new ProducerFailure("IndexingProducerNode: value of '"+contentKey+"' is not a content EntityAdapter, but a " + entity.getClass().getName() + " adapter", null);
+ throw new ProducerFailure("IndexingProducerNode: value of '"+contentKey+"' is not a content EntityAdapter, but a " + entity.getClass().getName() + " adapter", null);
}
- aLogger.println("Indexing " + (String) entity.getValue("id") + " into " + indexPath);
- aLogger.flush();
-
+ aLogger.info("Indexing " + (String) entity.getValue("id") + " into " + indexPath);
+
indexReader = IndexReader.open(indexPath);
indexReader.delete(new Term("id",entity.getValue("id")));
indexReader.close();
-
+
indexWriter = new IndexWriter(indexPath, new StandardAnalyzer(), false);
Document theDoc = new Document();
-
+
// Keyword is stored and indexed, but not tokenized
// Text is tokenized,stored, indexed
// Unindexed is not tokenized or indexed, only stored
// Unstored is tokenized and indexed, but not stored
-
+
theDoc.add(Field.Keyword("id",entity.getValue("id")));
theDoc.add(Field.Keyword("where",entity.getValue("publish_path")+entity.getValue("id")+".shtml"));
theDoc.add(Field.Text("creator",entity.getValue("creator")));
theDoc.add(Field.Text("title",entity.getValue("title")));
theDoc.add(Field.Keyword("webdb_create",entity.getValue("webdb_create_formatted")));
theDoc.add(Field.UnStored("content_and_description",entity.getValue("description")+entity.getValue("content_data")));
-
+
//topics
TemplateModel topics=entity.get("to_topics");
- aLogger.println("THE CLASS NAME WAS: "+entity.get("to_topics").getClass().getName());
+ aLogger.debug("THE CLASS NAME WAS: "+entity.get("to_topics").getClass().getName());
while (((TemplateListModel)topics).hasNext()){
- theDoc.add(Field.UnStored("topic",((TemplateHashModel)((TemplateListModel)topics).next()).get("title").toString()));
+ theDoc.add(Field.UnStored("topic",((TemplateHashModel)((TemplateListModel)topics).next()).get("title").toString()));
}
-
-
+
+
//media
-
+
//images
TemplateModel images=entity.get("to_media_images");
if (images != null){
- //here we should really store a list of urls instead,
- //so we can thumbnail from another server
- theDoc.add(Field.UnStored("media","images"));
-
+ //here we should really store a list of urls instead,
+ //so we can thumbnail from another server
+ theDoc.add(Field.UnStored("media","images"));
+
}
//audio
TemplateModel audio=entity.get("to_media_audio");
if (audio != null){
- theDoc.add(Field.UnStored("media","audio"));
+ theDoc.add(Field.UnStored("media","audio"));
}
//video
TemplateModel video=entity.get("to_media_video");
if (video != null){
- theDoc.add(Field.UnStored("media","video"));
+ theDoc.add(Field.UnStored("media","video"));
}
//comments-just aggregate all relevant fields
String commentsAggregate = "";
TemplateModel comments=entity.get("to_comments");
if (comments != null){
- while (((TemplateListModel)comments).hasNext()){
- TemplateModel aComment = ((TemplateListModel)comments).next();
- commentsAggregate = commentsAggregate + " " + ((TemplateHashModel)aComment).get("title").toString()
- + " " + ((TemplateHashModel)aComment).get("creator").toString()
- + " " + ((TemplateHashModel)aComment).get("text").toString();
- }
+ while (((TemplateListModel)comments).hasNext()){
+ TemplateModel aComment = ((TemplateListModel)comments).next();
+ commentsAggregate = commentsAggregate + " " + ((TemplateHashModel)aComment).get("title").toString()
+ + " " + ((TemplateHashModel)aComment).get("creator").toString()
+ + " " + ((TemplateHashModel)aComment).get("text").toString();
+ }
}
theDoc.add(Field.UnStored("comments",commentsAggregate));
indexWriter.addDocument(theDoc);
-
+
}
catch (Throwable t) {
- aLogger.println("Error while indexing content: " + t.getMessage());
- t.printStackTrace(aLogger);
+ aLogger.error("Error while indexing content: " + t.getMessage());
+ t.printStackTrace(new PrintWriter(new LoggerToWriterAdapter(aLogger, LoggerWrapper.DEBUG_MESSAGE)));
//should remove index lock here.....jd
- throw new ProducerFailure(t.getMessage(), t);
}
finally {
if (indexReader != null){
- try{
- indexReader.close();
- }
- catch (Throwable t) {
- aLogger.println("Error while closing indexReader: " + t.getMessage());
- }
-
+ try{
+ indexReader.close();
+ }
+ catch (Throwable t) {
+ aLogger.warn("Error while closing indexReader: " + t.getMessage());
+ }
+
}
if (indexWriter != null){
- try{
- indexWriter.close();
- }
- catch (Throwable t) {
- aLogger.println("Error while closing indexWriter: " + t.getMessage());
- }
-
+ try{
+ indexWriter.close();
+ }
+ catch (Throwable t) {
+ aLogger.warn("Error while closing indexWriter: " + t.getMessage());
+ }
+
}
-
+
try{
- FSDirectory theIndexDir=FSDirectory.getDirectory(indexPath,false);
- if (indexReader.isLocked(theIndexDir)){
- indexReader.unlock(theIndexDir);
- }
+ FSDirectory theIndexDir=FSDirectory.getDirectory(indexPath,false);
+ if (indexReader.isLocked(theIndexDir)){
+ indexReader.unlock(theIndexDir);
+ }
}
catch (Throwable t) {
- aLogger.println("Error while unlocking index: " + t.getMessage());
+ aLogger.warn("Error while unlocking index: " + t.getMessage());
}
}
-
-
-
+
+
+
endTime = System.currentTimeMillis();
-
- aLogger.println(" IndexTime: " + (endTime-startTime) + " ms<br>");
- aLogger.flush();
+
+ aLogger.info(" IndexTime: " + (endTime-startTime) + " ms<br>");
}
}
projects / mir.git / blobdiff