fieldsreader.java

一套java版本的搜索引擎源码

package org.apache.lucene.index;

/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import org.apache.lucene.document.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IndexInput;

import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.Reader;
import java.util.zip.DataFormatException;
import java.util.zip.Inflater;

/**
 * Class responsible for access to stored document fields.
 * <p/>
 * It uses &lt;segment&gt;.fdt and &lt;segment&gt;.fdx; files.
 *
 * @version $Id: FieldsReader.java 507009 2007-02-13 14:06:52Z gsingers $
 */
final class FieldsReader {
  private final FieldInfos fieldInfos;

  // The main fieldStream, used only for cloning.
  private final IndexInput cloneableFieldsStream;

  // This is a clone of cloneableFieldsStream used for reading documents.
  // It should not be cloned outside of a synchronized context.
  private final IndexInput fieldsStream;

  private final IndexInput indexStream;
  private int size;

  private ThreadLocal fieldsStreamTL = new ThreadLocal();

  FieldsReader(Directory d, String segment, FieldInfos fn) throws IOException {
    fieldInfos = fn;

    cloneableFieldsStream = d.openInput(segment + ".fdt");
    fieldsStream = (IndexInput)cloneableFieldsStream.clone();
    indexStream = d.openInput(segment + ".fdx");
    size = (int) (indexStream.length() / 8);
  }

  /**
   * Closes the underlying {@link org.apache.lucene.store.IndexInput} streams, including any ones associated with a
   * lazy implementation of a Field.  This means that the Fields values will not be accessible.
   *
   * @throws IOException
   */
  final void close() throws IOException {
    fieldsStream.close();
    cloneableFieldsStream.close();
    indexStream.close();
    IndexInput localFieldsStream = (IndexInput) fieldsStreamTL.get();
    if (localFieldsStream != null) {
      localFieldsStream.close();
      fieldsStreamTL.set(null);
    }
  }

  final int size() {
    return size;
  }

  final Document doc(int n, FieldSelector fieldSelector) throws IOException {
    indexStream.seek(n * 8L);
    long position = indexStream.readLong();
    fieldsStream.seek(position);

    Document doc = new Document();
    int numFields = fieldsStream.readVInt();
    for (int i = 0; i < numFields; i++) {
      int fieldNumber = fieldsStream.readVInt();
      FieldInfo fi = fieldInfos.fieldInfo(fieldNumber);
      FieldSelectorResult acceptField = fieldSelector == null ? FieldSelectorResult.LOAD : fieldSelector.accept(fi.name);
      
      byte bits = fieldsStream.readByte();
      boolean compressed = (bits & FieldsWriter.FIELD_IS_COMPRESSED) != 0;
      boolean tokenize = (bits & FieldsWriter.FIELD_IS_TOKENIZED) != 0;
      boolean binary = (bits & FieldsWriter.FIELD_IS_BINARY) != 0;
      //TODO: Find an alternative approach here if this list continues to grow beyond the
      //list of 5 or 6 currently here.  See Lucene 762 for discussion
      if (acceptField.equals(FieldSelectorResult.LOAD)) {
        addField(doc, fi, binary, compressed, tokenize);
      }
      else if (acceptField.equals(FieldSelectorResult.LOAD_FOR_MERGE)) {
        addFieldForMerge(doc, fi, binary, compressed, tokenize);
      }
      else if (acceptField.equals(FieldSelectorResult.LOAD_AND_BREAK)){
        addField(doc, fi, binary, compressed, tokenize);
        break;//Get out of this loop
      }
      else if (acceptField.equals(FieldSelectorResult.LAZY_LOAD)) {
        addFieldLazy(doc, fi, binary, compressed, tokenize);
      }
      else if (acceptField.equals(FieldSelectorResult.SIZE)){
        skipField(binary, compressed, addFieldSize(doc, fi, binary, compressed));
      }
      else if (acceptField.equals(FieldSelectorResult.SIZE_AND_BREAK)){
        addFieldSize(doc, fi, binary, compressed);
        break;
      }
      else {
        skipField(binary, compressed);
      }
    }

    return doc;
  }

  /**
   * Skip the field.  We still have to read some of the information about the field, but can skip past the actual content.
   * This will have the most payoff on large fields.
   */
  private void skipField(boolean binary, boolean compressed) throws IOException {
    skipField(binary, compressed, fieldsStream.readVInt());
  }
  
  private void skipField(boolean binary, boolean compressed, int toRead) throws IOException {
    if (binary || compressed) {
      long pointer = fieldsStream.getFilePointer();
      fieldsStream.seek(pointer + toRead);
    } else {
      //We need to skip chars.  This will slow us down, but still better
      fieldsStream.skipChars(toRead);
    }
  }

  private void addFieldLazy(Document doc, FieldInfo fi, boolean binary, boolean compressed, boolean tokenize) throws IOException {
    if (binary == true) {
      int toRead = fieldsStream.readVInt();
      long pointer = fieldsStream.getFilePointer();
      if (compressed) {
        //was: doc.add(new Fieldable(fi.name, uncompress(b), Fieldable.Store.COMPRESS));
        doc.add(new LazyField(fi.name, Field.Store.COMPRESS, toRead, pointer));
      } else {
        //was: doc.add(new Fieldable(fi.name, b, Fieldable.Store.YES));
        doc.add(new LazyField(fi.name, Field.Store.YES, toRead, pointer));
      }
      //Need to move the pointer ahead by toRead positions
      fieldsStream.seek(pointer + toRead);
    } else {
      Field.Store store = Field.Store.YES;
      Field.Index index = getIndexType(fi, tokenize);
      Field.TermVector termVector = getTermVectorType(fi);

      Fieldable f;
      if (compressed) {
        store = Field.Store.COMPRESS;
        int toRead = fieldsStream.readVInt();
        long pointer = fieldsStream.getFilePointer();
        f = new LazyField(fi.name, store, toRead, pointer);
        //skip over the part that we aren't loading
        fieldsStream.seek(pointer + toRead);
        f.setOmitNorms(fi.omitNorms);
      } else {
        int length = fieldsStream.readVInt();
        long pointer = fieldsStream.getFilePointer();
        //Skip ahead of where we are by the length of what is stored
        fieldsStream.skipChars(length);
        f = new LazyField(fi.name, store, index, termVector, length, pointer);
        f.setOmitNorms(fi.omitNorms);
      }
      doc.add(f);
    }

  }

  // in merge mode we don't uncompress the data of a compressed field
  private void addFieldForMerge(Document doc, FieldInfo fi, boolean binary, boolean compressed, boolean tokenize) throws IOException {
    Object data;
      
    if (binary || compressed) {
      int toRead = fieldsStream.readVInt();
      final byte[] b = new byte[toRead];
      fieldsStream.readBytes(b, 0, b.length);
      data = b;
    } else {
      data = fieldsStream.readString();
    }
      
    doc.add(new FieldForMerge(data, fi, binary, compressed, tokenize));
  }
  
  private void addField(Document doc, FieldInfo fi, boolean binary, boolean compressed, boolean tokenize) throws IOException {

    //we have a binary stored field, and it may be compressed
    if (binary) {
      int toRead = fieldsStream.readVInt();
      final byte[] b = new byte[toRead];
      fieldsStream.readBytes(b, 0, b.length);
      if (compressed)
        doc.add(new Field(fi.name, uncompress(b), Field.Store.COMPRESS));
      else
        doc.add(new Field(fi.name, b, Field.Store.YES));

    } else {
      Field.Store store = Field.Store.YES;
      Field.Index index = getIndexType(fi, tokenize);
      Field.TermVector termVector = getTermVectorType(fi);

      Fieldable f;
      if (compressed) {
        store = Field.Store.COMPRESS;
        int toRead = fieldsStream.readVInt();

        final byte[] b = new byte[toRead];
        fieldsStream.readBytes(b, 0, b.length);
        f = new Field(fi.name,      // field name
                new String(uncompress(b), "UTF-8"), // uncompress the value and add as string
                store,
                index,
                termVector);
        f.setOmitNorms(fi.omitNorms);