Sorry, you can see the script below:
Thanks
//******************** Index Method
******************************************/
public void index(DoubleMap doubleMap, String dirPath, String originalPath)
throws IOException
{
File f = new File(dirPath);
IndexWriter writer = null;
if(f.exists())
{
writer = new IndexWriter(dirPath, new WhitespaceAnalyzer(), false);
}
else
{
writer = new IndexWriter(dirPath, new WhitespaceAnalyzer(), true);
}
writer.setSimilarity(new WordsSimilarity());
Iterator it = doubleMap.getMap().entrySet().iterator();
int count = 0;
int size = doubleMap.getMap().size();
while(it.hasNext())
{
count++;
Map.Entry entry = (Map.Entry) it.next();
String word = entry.getKey().toString();
Word w = new Word();
w.word = word;
Date date = new Date();
System.out.println(date.toString() + " : Updateing word " + word + " ( "
+ count + " out of " + size + ") " + " FROM " + originalPath);
Map<Long, Double> innerMap = (Map<Long, Double>) entry.getValue();
Document doc = WordIndex.getDoc(word, dirPath);
if(doc != null)
{
doc = WordIndex.addToDoc(doc, innerMap);
/// delete the document and then add it
writer.deleteDocuments(new Term(WordIndex.FIELD_WORD, word));
writer.addDocument(doc);
}
else
{
w.worldsMap = innerMap;
WordIndex wi = new WordIndex(w);
wi.createDocument();
writer.addDocument(wi.getDocument());
}
}
System.out.println("Optimizing " + dirPath + " ...");
writer.optimize();
writer.close();
}
//******************** WordIndex class
******************************************/
public class WordIndex extends Index
{
protected Word w;
public static String FIELD_WORD = "word";
public static String FIELD_WORLDS = "worlds";
public WordIndex(Word w)
{
this.w = w;
}
public void createDocument() throws java.io.FileNotFoundException
{
// make a new, empty document
doc = new Document();
// Add the id of the patent
// indexed (i.e. searchable), but don't tokenize the field into words.
doc.add(new Field(FIELD_WORD, w.word, Field.Store.YES,
Field.Index.UN_TOKENIZED));
doc.add(new Field(FIELD_WORLDS, String.valueOf(w.getWorldIds()),
Field.Store.YES, Field.Index.TOKENIZED));
// Iterator iter = w.worldsMap.entrySet().iterator();
// while(iter.hasNext())
// {
// Map.Entry entry = (Map.Entry) iter.next();
// doc.add(new Field(entry.getKey().toString(),
String.valueOf(entry.getValue()), Field.Store.YES,
Field.Index.UN_TOKENIZED));
// }
}
public static Document addToDoc(Document doc, Map<Long, Double> map)
{
Iterator iter = map.entrySet().iterator();
String worlds = doc.getField(WordIndex.FIELD_WORLDS).stringValue();
doc.removeField(FIELD_WORLDS);
while(iter.hasNext())
{
Map.Entry entry = (Map.Entry) iter.next();
String worldId = entry.getKey().toString();
if(doc.getField(worldId) == null)
{
// doc.add(new Field(entry.getKey().toString(),
String.valueOf(entry.getValue()), Field.Store.YES,
Field.Index.UN_TOKENIZED));
// also add to the field of worlds the current world
worlds += entry.getKey().toString() + " ";
}
}
System.out.println(worlds);
doc.add(new Field(FIELD_WORLDS, String.valueOf(worlds), Field.Store.YES,
Field.Index.TOKENIZED));
return doc;
}
public static Document getDoc(String word, String indexPath) throws
IOException
{
IndexSearcher mapSearcher = new IndexSearcher(indexPath);
TermQuery mapQuery = new TermQuery(new Term(FIELD_WORD, word));
Hits mapHits = mapSearcher.search(mapQuery);
if(mapHits.length() != 0)
{
Document doc = mapHits.doc(0);
return doc;
}
return null;
}
}
2009/4/21 Chris Hostetter <[email protected]>
>
> Erick means we need to see *all* of your code (inlcuding how you get the
> score and the Explanation you are printing) to understand why they don't
> match.
>
> All you've shown is the output of your program and the generation of a
> Hits object.
>
>
>
> -Hoss
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: [email protected]
> For additional commands, e-mail: [email protected]
>
>
