indexreader.cpp

clucene是c++版的全文检索引擎,完全移植于lucene,采用 stl 编写.

      return directory->fileExists("segments");
  }

  TermDocs* IndexReader::termDocs(Term* term) const {
  //Func - Returns an enumeration of all the documents which contain
  //       term. For each document, the document number, the frequency of
  //       the term in that document is also provided, for use in search scoring.
  //       Thus, this method implements the mapping: 
  //
  //       Term => <docNum, freq>*
  //	   The enumeration is ordered by document number.  Each document number
  //       is greater than all that precede it in the enumeration. 
  //Pre  - term != NULL
  //Post - A reference to TermDocs containing an enumeration of all found documents
  //       has been returned

      CND_PRECONDITION(term != NULL, "term is NULL");

      //Reference an instantiated TermDocs instance
      TermDocs* _termDocs = termDocs();
      //Seek all documents containing term
      _termDocs->seek(term);
      //return the enumaration
      return _termDocs;
  }

  TermPositions* IndexReader::termPositions(Term* term) const{
  //Func - Returns an enumeration of all the documents which contain  term. For each 
  //       document, in addition to the document number and frequency of the term in 
  //       that document, a list of all of the ordinal positions of the term in the document 
  //       is available.  Thus, this method implements the mapping:
  //
  //       Term => <docNum, freq,<pos 1, pos 2, ...pos freq-1>>*
  //
  //       This positional information faciliates phrase and proximity searching.
  //       The enumeration is ordered by document number.  Each document number is greater than 
  //       all that precede it in the enumeration. 
  //Pre  - term != NULL
  //Post - A reference to TermPositions containing an enumeration of all found documents
  //       has been returned

      CND_PRECONDITION(term != NULL, "term is NULL");

      //Reference an instantiated termPositions instance
      TermPositions* _termPositions = termPositions();
	  //Seek all documents containing term
      _termPositions->seek(term);
	  //return the enumeration
      return _termPositions;
  }

  void IndexReader::deleteDocument(const int32_t docNum) {
  //Func - Deletes the document numbered docNum.  Once a document is deleted it will not appear 
  //       in TermDocs or TermPostitions enumerations. Attempts to read its field with the document 
  //       method will result in an error.  The presence of this document may still be reflected in 
  //       the docFreq statistic, though this will be corrected eventually as the index is further modified.  
  //Pre  - docNum >= 0
  //Post - If successful the document identified by docNum has been deleted. If no writelock
  //       could be obtained an exception has been thrown stating that the index was locked or has no write access

	  SCOPED_LOCK_MUTEX(THIS_LOCK)

     CND_PRECONDITION(docNum >= 0, "docNum is negative");

      if (directoryOwner)
		  aquireWriteLock();

	  //Have the document identified by docNum deleted
      doDelete(docNum);
      hasChanges = true;
  }

  /**
   * Commit changes resulting from delete, undeleteAll, or setNorm operations
   * 
   * @throws IOException
   */
   void IndexReader::commit(){
    SCOPED_LOCK_MUTEX(THIS_LOCK)
    if(hasChanges){
      if(directoryOwner){
        {
	        SCOPED_LOCK_MUTEX(directory->THIS_LOCK)      // in- & inter-process sync
	
	        LuceneLock* commitLock = directory->makeLock("commit.lock");
	        IndexReaderCommitLockWith cl(commitLock,this);
	        cl.run();
			_CLDELETE(commitLock);
	
	    }
        if (writeLock != NULL) {
          writeLock->release();  // release write lock
          _CLDELETE(writeLock);
        }
      }else
        doCommit();
    }
    hasChanges = false;
  }


  void IndexReader::undeleteAll(){
     SCOPED_LOCK_MUTEX(THIS_LOCK)
    if(directoryOwner)
      aquireWriteLock();
    doUndeleteAll();
    hasChanges = true;
  }

  int32_t IndexReader::deleteDocuments(Term* term) {
  //Func - Deletes all documents containing term. This is useful if one uses a 
  //       document field to hold a unique ID string for the document.  Then to delete such  
  //       a document, one merely constructs a term with the appropriate field and the unique 
  //       ID string as its text and passes it to this method.  
  //Pre  - term != NULL
  //Post - All documents containing term have been deleted. The number of deleted documents
  //       has been returned

      CND_PRECONDITION(term != NULL, "term is NULL");

	  //Search for the documents contain term
      TermDocs* docs = termDocs(term);

	  //Check if documents have been found
	  if ( docs == NULL ){
          return 0;
	  }
    
	  //initialize
	  int32_t Counter = 0;
      try {
		  //iterate through the found documents
          while (docs->next()) {
			  //Delete the document
              deleteDocument(docs->doc());
              Counter++;
          }
      }_CLFINALLY(
		  //Close the enumeration
          docs->close();
          );

    //Delete the enumeration of found documents
    _CLVDELETE( docs ); //todo: not a clucene object... should be

	//Return the number of deleted documents
    return Counter;
  }

  void IndexReader::close() {
  //Func - Closes files associated with this index and also saves any new deletions to disk.
  //       No other methods should be called after this has been called.
  //Pre  - true
  //Post - All files associated with this index have been deleted and new deletions have been 
  //       saved to disk
    SCOPED_LOCK_MUTEX(THIS_LOCK)

	CloseCallbackMap::iterator iter = closeCallbacks.begin();
	for ( ;iter!=closeCallbacks.end();iter++){
		CloseCallback callback = *iter->first;
		callback(this,iter->second);
	}
	
    commit();
    doClose();

	if(closeDirectory){
      directory->close();
	  _CLDECDELETE(directory);
	}
  }
   
  bool IndexReader::isLocked(Directory* directory) {
  //Func - Static method 
  //       Checks if the index in the directory is currently locked.
  //Pre  - directory is a valid reference to a directory to check for a lock
  //Post - Returns true if the index in the named directory is locked otherwise false

	  //Check the existence of the file write.lock and return true when it does and false
	  //when it doesn't
     LuceneLock* l1 = directory->makeLock("write.lock");
     LuceneLock* l2 = directory->makeLock("commit.lock");

	 bool ret = l1->isLocked() || l2->isLocked();

     _CLDELETE(l1);
     _CLDELETE(l2);
     return ret;
  }

  bool IndexReader::isLocked(const char* directory) {
  //Func - Static method 
  //       Checks if the index in the named directory is currently locked.
  //Pre  - directory != NULL and contains the directory to check for a lock
  //Post - Returns true if the index in the named directory is locked otherwise false

      CND_PRECONDITION(directory != NULL, "directory is NULL");

	  //Create a buffer of length CL_MAXDIR
      char f[CL_MAX_PATH+12]; //add 12 in case that directory is already 260 long
	  //Copy the directory string to the buffer
      strcpy(f,directory);
	  //Cat the name of the write.lock file to buffer
      strcat ( f,"/write.lock" );

      Directory* dir = FSDirectory::getDirectory(directory,false);
      bool ret = isLocked(dir);
	  dir->close();
      _CLDECDELETE(dir);

	  return ret;
  }

  void IndexReader::unlock(const char* path){
	  FSDirectory* dir = FSDirectory::getDirectory(path,false);
	  unlock(dir);
	  dir->close();
	  _CLDECDELETE(dir);
  }
  void IndexReader::unlock(Directory* directory){
  //Func - Static method
  //       Forcibly unlocks the index in the named directory->
  //       Caution: this should only be used by failure recovery code,
  //       when it is known that no other process nor thread is in fact
  //       currently accessing this index.
  //Pre  - directory is a valid reference to a directory 
  //Post - The directory has been forcibly unlocked
      LuceneLock* lock;

	  lock = directory->makeLock("write.lock");
      lock->release();
      _CLDELETE(lock);

      lock = directory->makeLock("commit.lock");
      lock->release();
      _CLDELETE(lock);
  }

	void IndexReader::addCloseCallback(CloseCallback callback, void* parameter){
		closeCallbacks.put(callback, parameter);	
	}


	//Constructor	
    IndexReader::IndexReaderLockWith::IndexReaderLockWith(CL_NS(store)::LuceneLock* lock, CL_NS(store)::Directory* dir):
		CL_NS(store)::LuceneLockWith(lock,LUCENE_COMMIT_LOCK_TIMEOUT)
	{
		this->directory = dir;
	}	
	//Constructor	
	IndexReader::IndexReaderCommitLockWith::IndexReaderCommitLockWith( CL_NS(store)::LuceneLock* lock, IndexReader* r ):
		CL_NS(store)::LuceneLockWith(lock,LUCENE_COMMIT_LOCK_TIMEOUT),
		reader(r)
	{
	}
	void* IndexReader::IndexReaderCommitLockWith::doBody(){
		reader->doCommit();
		reader->segmentInfos->write(reader->getDirectory());
		return NULL;
	}

CL_NS_END