lucene4.7索引源码研究之域元文件

package org.apache.lucene.codecs.lucene46;

/*
 * 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 java.io.IOException;
import java.util.Collections;
import java.util.Map;

import org.apache.lucene.codecs.CodecUtil;
import org.apache.lucene.codecs.FieldInfosReader;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.FieldInfo;
import org.apache.lucene.index.FieldInfos;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.FieldInfo.DocValuesType;
import org.apache.lucene.index.FieldInfo.IndexOptions;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.util.IOUtils;

/**
 * Lucene 4.6 FieldInfos reader.
 * 
 * @lucene.experimental
 * @see Lucene46FieldInfosFormat
 */
final class Lucene46FieldInfosReader extends FieldInfosReader {

  /** Sole constructor. */
  public Lucene46FieldInfosReader() {
  }

  @Override
  public FieldInfos read(Directory directory, String segmentName, String segmentSuffix, IOContext context) throws IOException {
    final String fileName = IndexFileNames.segmentFileName(segmentName, segmentSuffix, Lucene46FieldInfosFormat.EXTENSION);
    IndexInput input = directory.openInput(fileName, context);
    
    boolean success = false;
    try {
      CodecUtil.checkHeader(input, Lucene46FieldInfosFormat.CODEC_NAME, 
                                   Lucene46FieldInfosFormat.FORMAT_START, 
                                   Lucene46FieldInfosFormat.FORMAT_CURRENT);//检查头信息，包括magic，codecname，version

      final int size = input.readVInt(); //read in the size  域数量
      FieldInfo infos[] = new FieldInfo[size];

      for (int i = 0; i < size; i++) {
        String name = input.readString();//域名称
        final int fieldNumber = input.readVInt();//域的编号
        byte bits = input.readByte();//域标志位，表示该域的特性
　　
        boolean isIndexed = (bits & Lucene46FieldInfosFormat.IS_INDEXED) != 0;// bits & 0000 0001 最低位表示是否索引   
        boolean storeTermVector = (bits & Lucene46FieldInfosFormat.STORE_TERMVECTOR) != 0;// bits & 0000 0010 倒数第二位表示是否存储词向量
        boolean omitNorms = (bits & Lucene46FieldInfosFormat.OMIT_NORMS) != 0;// bits & 0001 0000 第四位表示是否保存标准化因子
        boolean storePayloads = (bits & Lucene46FieldInfosFormat.STORE_PAYLOADS) != 0;// bits & 0010 0000 第三位表示是否存储payload
        final IndexOptions indexOptions;
        if (!isIndexed) {
          indexOptions = null;
        } else if ((bits & Lucene46FieldInfosFormat.OMIT_TERM_FREQ_AND_POSITIONS) != 0) {// bits & 0100 0000 第二位表示是否保存词频和位置信息 1为不存储
          //只索引
          indexOptions = IndexOptions.DOCS_ONLY;
        } else if ((bits & Lucene46FieldInfosFormat.OMIT_POSITIONS) != 0) {// bits & 1000 0000 最高位表是否保存位置信息 1为不存储
          //索引和词频
          indexOptions = IndexOptions.DOCS_AND_FREQS;
        } else if ((bits & Lucene46FieldInfosFormat.STORE_OFFSETS_IN_POSTINGS) != 0) {// bits & 0000 0100 是否存储偏移量
          //索引、词频、位置、偏移量
          indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
        } else {
    　　　　//默认情况，索引、词频、位置
          indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
        }

        // DV Types are packed in one byte
        // docValue

        byte val = input.readByte();
        final DocValuesType docValuesType = getDocValuesType(input, (byte) (val & 0x0F));//低4位表示DocValus类型
        final DocValuesType normsType = getDocValuesType(input, (byte) ((val >>> 4) & 0x0F));//高4位表示标准类型
        final long dvGen = input.readLong();//docValues版本号
        final Map<String,String> attributes = input.readStringStringMap();
        infos[i] = new FieldInfo(name, isIndexed, fieldNumber, storeTermVector, 
          omitNorms, storePayloads, indexOptions, docValuesType, normsType, Collections.unmodifiableMap(attributes));
        infos[i].setDocValuesGen(dvGen);
      }

      if (input.getFilePointer() != input.length()) {
        throw new CorruptIndexException("did not read all bytes from file \"" + fileName + "\": read " + input.getFilePointer() + " vs size " + input.length() + " (resource: " + input + ")");
      }
      FieldInfos fieldInfos = new FieldInfos(infos);
      success = true;
      return fieldInfos;
    } finally {
      if (success) {
        input.close();
      } else {
        IOUtils.closeWhileHandlingException(input);
      }
    }
  }
  
  private static DocValuesType getDocValuesType(IndexInput input, byte b) throws IOException {
    if (b == 0) {
      return null;
    } else if (b == 1) {
      return DocValuesType.NUMERIC;
    } else if (b == 2) {
      return DocValuesType.BINARY;
    } else if (b == 3) {
      return DocValuesType.SORTED;
    } else if (b == 4) {
      return DocValuesType.SORTED_SET;
    } else {
      throw new CorruptIndexException("invalid docvalues byte: " + b + " (resource=" + input + ")");
    }
  }
}