docs/attachments/LUCENE-1537/LUCENE-1537.patch

Index: contrib/instantiated/src/test/org/apache/lucene/store/instantiated/TestIndicesEquals.java
===================================================================
--- contrib/instantiated/src/test/org/apache/lucene/store/instantiated/TestIndicesEquals.java	(revision 742818)
+++ contrib/instantiated/src/test/org/apache/lucene/store/instantiated/TestIndicesEquals.java	(working copy)
@@ -54,7 +54,30 @@
 //    testEquals(fsdir, ii);
 //  }
 
+  public void testClone() throws Exception {
+    RAMDirectory dir = new RAMDirectory();
 
+    // create dir data
+    IndexWriter indexWriter = new IndexWriter(dir, new StandardAnalyzer(), true);
+    for (int i = 0; i < 20; i++) {
+      Document document = new Document();
+      assembleDocument(document, i);
+      indexWriter.addDocument(document);
+    }
+    indexWriter.close();
+    
+    IndexReader ir = IndexReader.open(dir);
+    InstantiatedIndex ii = new InstantiatedIndex(ir);
+    
+    InstantiatedIndexReader r1 = new InstantiatedIndexReader(ii);
+    r1.deleteDocument(2);
+    r1.deleteDocument(5);
+    InstantiatedIndexReader r1cloned = (InstantiatedIndexReader)r1.clone();
+    assertEquals(18, r1cloned.numDocs());
+    // verify deleted docs are the same    
+    testEquals(r1, r1cloned);
+  }
+
   public void testLoadIndexReader() throws Exception {
     RAMDirectory dir = new RAMDirectory();
 
@@ -77,8 +100,6 @@
 
 
   public void testInstantiatedIndexWriter() throws Exception {
-
-
     RAMDirectory dir = new RAMDirectory();
     InstantiatedIndex ii = new InstantiatedIndex();
 
@@ -221,12 +242,14 @@
     // make sure they still equal
     testEquals(aprioriIndex,  testIndex);
   }
-
+  
   protected void testEquals(Directory aprioriIndex, InstantiatedIndex testIndex) throws Exception {
-
     IndexReader aprioriReader = IndexReader.open(aprioriIndex);
     IndexReader testReader = testIndex.indexReaderFactory();
-
+    testEquals(aprioriReader, testReader);
+  }
+  
+  protected void testEquals(IndexReader aprioriReader, IndexReader testReader) throws Exception {
     assertEquals(aprioriReader.numDocs(), testReader.numDocs());
 
     // assert field options
Index: contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexReader.java
===================================================================
--- contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexReader.java	(revision 742818)
+++ contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexReader.java	(working copy)
@@ -47,15 +47,31 @@
  * Consider using InstantiatedIndex as if it was immutable.
  */
 public class InstantiatedIndexReader extends IndexReader {
-
   private final InstantiatedIndex index;
 
   public InstantiatedIndexReader(InstantiatedIndex index) {
     super();
     this.index = index;
   }
-
+  
+  public Object clone() {
+    try {
+      doCommit();
+      InstantiatedIndex clonedIndex = index.cloneWithDeletesNorms();
+      return new InstantiatedIndexReader(clonedIndex);
+    } catch (IOException ioe) {
+      throw new RuntimeException("", ioe);
+    }
+  }
+  
   /**
+   * openReadOnly is ignored.
+   */
+  public IndexReader clone(boolean openReadOnly) {
+    return (IndexReader)clone();
+  }
+  
+  /**
    * @return always true.
    */
   public boolean isOptimized() {
@@ -116,7 +132,9 @@
   }
 
   public int numDocs() {
-    return getIndex().getDocumentsByNumber().length - index.getDeletedDocuments().size() - deletedDocuments.size();
+    int idd = index.getDeletedDocuments().size();
+    int dds = deletedDocuments.size();
+    return getIndex().getDocumentsByNumber().length - idd - dds;
   }
 
   public int maxDoc() {
Index: contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndex.java
===================================================================
--- contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndex.java	(revision 742818)
+++ contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndex.java	(working copy)
@@ -77,6 +77,18 @@
     initialize();
   }
   
+  InstantiatedIndex cloneWithDeletesNorms() {
+    InstantiatedIndex clone = new InstantiatedIndex();
+    clone.version = System.currentTimeMillis();
+    clone.documentsByNumber = documentsByNumber;
+    clone.deletedDocuments = new HashSet<Integer>(deletedDocuments);
+    clone.termsByFieldAndText = termsByFieldAndText;
+    clone.orderedTerms = orderedTerms;
+    clone.normsByFieldNameAndDocumentNumber = new HashMap<String, byte[]>(normsByFieldNameAndDocumentNumber);
+    clone.fieldSettings = fieldSettings;
+    return clone;
+  }
+  
   void initialize() {
     // todo: clear index without loosing memory (uncouple stuff)
     termsByFieldAndText = new HashMap<String, Map<String, InstantiatedTerm>>();
@@ -170,7 +182,7 @@
     }
 
 
-    documentsByNumber = new InstantiatedDocument[sourceIndexReader.numDocs()];
+    documentsByNumber = new InstantiatedDocument[sourceIndexReader.maxDoc()];
 
     // create documents
     for (int i = 0; i < sourceIndexReader.numDocs(); i++) {
@@ -248,7 +260,7 @@
         InstantiatedTermDocumentInformation termDocumentInformation = new InstantiatedTermDocumentInformation(term, document, positions, payloads);
         term.getAssociatedDocuments()[position++] = termDocumentInformation;
 
-        if (document.getVectorSpace() != null
+        if (document != null && document.getVectorSpace() != null
             && document.getVectorSpace().containsKey(term.field())) {
           document.getVectorSpace().get(term.field()).add(termDocumentInformation);
         }
@@ -258,7 +270,8 @@
     }
 
     // load offsets to term-document informations
-    for (InstantiatedDocument document : getDocumentsByNumber()) {
+    //for (InstantiatedDocument document : getDocumentsByNumber()) {
+    for (InstantiatedDocument document : getDocumentsNotDeleted()) {
       for (Field field : (List<Field>) document.getDocument().getFields()) {
         if (field.isTermVectorStored() && field.isStoreOffsetWithTermVector()) {
           TermPositionVector termPositionVector = (TermPositionVector) sourceIndexReader.getTermFreqVector(document.getDocumentNumber(), field.name());
@@ -312,7 +325,15 @@
   public InstantiatedDocument[] getDocumentsByNumber() {
     return documentsByNumber;
   }
-
+  
+  public List<InstantiatedDocument> getDocumentsNotDeleted() {
+    List<InstantiatedDocument> list = new ArrayList<InstantiatedDocument>(documentsByNumber.length-deletedDocuments.size());
+    for (int x=0; x < documentsByNumber.length; x++) {
+      if (!deletedDocuments.contains(x)) list.add(documentsByNumber[x]);
+    }
+    return list;
+  } 
+  
   public Map<String, byte[]> getNormsByFieldNameAndDocumentNumber() {
     return normsByFieldNameAndDocumentNumber;
   }
Index: contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedTerm.java
===================================================================
--- contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedTerm.java	(revision 742818)
+++ contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedTerm.java	(working copy)
@@ -165,7 +165,10 @@
     }
     int min = offset, max = offset + length - 1;
     int minVal = getAssociatedDocuments()[min].getDocument().getDocumentNumber();
-    int maxVal = getAssociatedDocuments()[max].getDocument().getDocumentNumber();
+    InstantiatedTermDocumentInformation itdi = getAssociatedDocuments()[max];
+    InstantiatedDocument id = itdi.getDocument();
+    int maxVal = id.getDocumentNumber();
+    //int maxVal = getAssociatedDocuments()[max].getDocument().getDocumentNumber();
 
 
     int nPreviousSteps = 0;