Lucene中Index源代码 | DataLearnerAI

加载中...
public IndexWriter(Directory d, IndexWriterConfig conf) throws IOException {

	// 检查当前目录下是否存在有待删除且挂起的文件，如果有，则执行删除操作，删除失败抛出异常，停止执行。
    if (d instanceof FSDirectory && ((FSDirectory) d).checkPendingDeletions()) {
      throw new IllegalArgumentException("Directory " + d + " still has pending deleted files; cannot initialize IndexWriter");
    }

    conf.setIndexWriter(this); // prevent reuse by other instances
    config = conf;
    infoStream = config.getInfoStream();

    // obtain the write.lock. If the user configured a timeout,
    // we wrap with a sleeper and this might take some time.
    writeLock = d.obtainLock(WRITE_LOCK_NAME);

    boolean success = false;
    try {
      directoryOrig = d;
      directory = new LockValidatingDirectoryWrapper(d, writeLock);

      // Directory we use for merging, so we can abort running merges, and so
      // merge schedulers can optionally rate-limit per-merge IO:
      mergeDirectory = addMergeRateLimiters(directory);

      analyzer = config.getAnalyzer();
      mergeScheduler = config.getMergeScheduler();
      mergeScheduler.setInfoStream(infoStream);
      codec = config.getCodec();

      bufferedUpdatesStream = new BufferedUpdatesStream(infoStream);
      poolReaders = config.getReaderPooling();

      OpenMode mode = config.getOpenMode();
      boolean create;
      if (mode == OpenMode.CREATE) {
        create = true;
      } else if (mode == OpenMode.APPEND) {
        create = false;
      } else {
        // CREATE_OR_APPEND - create only if an index does not exist
        create = !DirectoryReader.indexExists(directory);
      }

      // If index is too old, reading the segments will throw
      // IndexFormatTooOldException.

      boolean initialIndexExists = true;

      String[] files = directory.listAll();

      // Set up our initial SegmentInfos:
      IndexCommit commit = config.getIndexCommit();

      // Set up our initial SegmentInfos:
      StandardDirectoryReader reader;
      if (commit == null) {
        reader = null;
      } else {
        reader = commit.getReader();
      }

      if (create) {

        if (config.getIndexCommit() != null) {
          // We cannot both open from a commit point and create:
          if (mode == OpenMode.CREATE) {
            throw new IllegalArgumentException("cannot use IndexWriterConfig.setIndexCommit() with OpenMode.CREATE");
          } else {
            throw new IllegalArgumentException("cannot use IndexWriterConfig.setIndexCommit() when index has no commit");
          }
        }

        // Try to read first.  This is to allow create
        // against an index that's currently open for
        // searching.  In this case we write the next
        // segments_N file with no segments:
        SegmentInfos sis = null;
        try {
          sis = SegmentInfos.readLatestCommit(directory);
          sis.clear();
        } catch (IOException e) {
          // Likely this means it's a fresh directory
          initialIndexExists = false;
          sis = new SegmentInfos();
        }

        segmentInfos = sis;

        rollbackSegments = segmentInfos.createBackupSegmentInfos();

        // Record that we have a change (zero out all
        // segments) pending:
        changed();

      } else if (reader != null) {
        // Init from an existing already opened NRT or non-NRT reader:

        if (reader.directory() != commit.getDirectory()) {
          throw new IllegalArgumentException("IndexCommit's reader must have the same directory as the IndexCommit");
        }

        if (reader.directory() != directoryOrig) {
          throw new IllegalArgumentException("IndexCommit's reader must have the same directory passed to IndexWriter");
        }

        if (reader.segmentInfos.getLastGeneration() == 0) {
          // TODO: maybe we could allow this?  It's tricky...
          throw new IllegalArgumentException("index must already have an initial commit to open from reader");
        }

        // Must clone because we don't want the incoming NRT reader to "see" any changes this writer now makes:
        segmentInfos = reader.segmentInfos.clone();

        SegmentInfos lastCommit;
        try {
          lastCommit = SegmentInfos.readCommit(directoryOrig, segmentInfos.getSegmentsFileName());
        } catch (IOException ioe) {
          throw new IllegalArgumentException("the provided reader is stale: its prior commit file \"" + segmentInfos.getSegmentsFileName() + "\" is missing from index");
        }

        if (reader.writer != null) {

          // The old writer better be closed (we have the write lock now!):
          assert reader.writer.closed;

          // In case the old writer wrote further segments (which we are now dropping),
          // update SIS metadata so we remain write-once:
          segmentInfos.updateGenerationVersionAndCounter(reader.writer.segmentInfos);
          lastCommit.updateGenerationVersionAndCounter(reader.writer.segmentInfos);
        }

        rollbackSegments = lastCommit.createBackupSegmentInfos();

        if (infoStream.isEnabled("IW")) {
          infoStream.message("IW", "init from reader " + reader);
          messageState();
        }
      } else {
        // Init from either the latest commit point, or an explicit prior commit point:

        String lastSegmentsFile = SegmentInfos.getLastCommitSegmentsFileName(files);
        if (lastSegmentsFile == null) {
          throw new IndexNotFoundException("no segments* file found in " + directory + ": files: " + Arrays.toString(files));
        }

        // Do not use SegmentInfos.read(Directory) since the spooky
        // retrying it does is not necessary here (we hold the write lock):
        segmentInfos = SegmentInfos.readCommit(directoryOrig, lastSegmentsFile);

        if (commit != null) {
          // Swap out all segments, but, keep metadata in
          // SegmentInfos, like version & generation, to
          // preserve write-once.  This is important if
          // readers are open against the future commit
          // points.
          if (commit.getDirectory() != directoryOrig) {
            throw new IllegalArgumentException("IndexCommit's directory doesn't match my directory, expected=" + directoryOrig + ", got=" + commit.getDirectory());
          }

          SegmentInfos oldInfos = SegmentInfos.readCommit(directoryOrig, commit.getSegmentsFileName());
          segmentInfos.replace(oldInfos);
          changed();

          if (infoStream.isEnabled("IW")) {
            infoStream.message("IW", "init: loaded commit \"" + commit.getSegmentsFileName() + "\"");
          }
        }

        rollbackSegments = segmentInfos.createBackupSegmentInfos();
      }

      pendingNumDocs.set(segmentInfos.totalMaxDoc());

      // start with previous field numbers, but new FieldInfos
      // NOTE: this is correct even for an NRT reader because we'll pull FieldInfos even for the un-committed segments:
      globalFieldNumberMap = getFieldNumberMap();

      config.getFlushPolicy().init(config);
      docWriter = new DocumentsWriter(this, config, directoryOrig, directory);
      eventQueue = docWriter.eventQueue();

      // Default deleter (for backwards compatibility) is
      // KeepOnlyLastCommitDeleter:

      // Sync'd is silly here, but IFD asserts we sync'd on the IW instance:
      synchronized(this) {
        deleter = new IndexFileDeleter(files, directoryOrig, directory,
                config.getIndexDeletionPolicy(),
                segmentInfos, infoStream, this,
                initialIndexExists, reader != null);

        // We incRef all files when we return an NRT reader from IW, so all files must exist even in the NRT case:
        assert create || filesExist(segmentInfos);
      }

      if (deleter.startingCommitDeleted) {
        // Deletion policy deleted the "head" commit point.
        // We have to mark ourself as changed so that if we
        // are closed w/o any further changes we write a new
        // segments_N file.
        changed();
      }

      if (reader != null) {
        // Pre-enroll all segment readers into the reader pool; this is necessary so
        // any in-memory NRT live docs are correctly carried over, and so NRT readers
        // pulled from this IW share the same segment reader:
        List<LeafReaderContext> leaves = reader.leaves();
        assert segmentInfos.size() == leaves.size();

        for (int i=0;i<leaves.size();i++) {
          LeafReaderContext leaf = leaves.get(i);
          SegmentReader segReader = (SegmentReader) leaf.reader();
          SegmentReader newReader = new SegmentReader(segmentInfos.info(i), segReader, segReader.getLiveDocs(), segReader.numDocs());
          readerPool.readerMap.put(newReader.getSegmentInfo(), new ReadersAndUpdates(this, newReader));
        }

        // We always assume we are carrying over incoming changes when opening from reader:
        segmentInfos.changed();
        changed();
      }

      if (infoStream.isEnabled("IW")) {
        infoStream.message("IW", "init: create=" + create);
        messageState();
      }

      success = true;

    } finally {
      if (!success) {
        if (infoStream.isEnabled("IW")) {
          infoStream.message("IW", "init: hit exception on init; releasing write lock");
        }
        IOUtils.closeWhileHandlingException(writeLock);
        writeLock = null;
      }
    }
  }
DataLearner WeChat
