`
liuxinglanyue
  • 浏览: 565265 次
  • 性别: Icon_minigender_1
  • 来自: 杭州
社区版块
存档分类
最新评论

Lucene 3.0.2 源码 - abstract class AbstractField

阅读更多

package org.apache.lucene.document;
/**
 * Copyright 2006 The Apache Software Foundation
 *
 * Licensed 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.search.PhraseQuery; // for javadocs
import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.util.StringHelper; // for javadocs


/**
 *
 *
 **/
public abstract class AbstractField implements Fieldable {

  protected String name = "body";
  protected boolean storeTermVector = false;
  protected boolean storeOffsetWithTermVector = false;
  protected boolean storePositionWithTermVector = false;
  protected boolean omitNorms = false;
  protected boolean isStored = false;
  protected boolean isIndexed = true;
  protected boolean isTokenized = true;
  protected boolean isBinary = false;
  protected boolean lazy = false;
  protected boolean omitTermFreqAndPositions = false;
  protected float boost = 1.0f;
  // the data object for all different kind of field values
  protected Object fieldsData = null;
  // pre-analyzed tokenStream for indexed fields
  protected TokenStream tokenStream;
  // length/offset for all primitive types
  protected int binaryLength;
  protected int binaryOffset;

  protected AbstractField()
  {
  }

  protected AbstractField(String name, Field.Store store, Field.Index index, Field.TermVector termVector) {
    if (name == null)
      throw new NullPointerException("name cannot be null");
    this.name = StringHelper.intern(name);        // field names are interned

    this.isStored = store.isStored();
    this.isIndexed = index.isIndexed();
    this.isTokenized = index.isAnalyzed();
    this.omitNorms = index.omitNorms();

    this.isBinary = false;

    setStoreTermVector(termVector);
  }

  /** Sets the boost factor hits on this field.  This value will be
   * multiplied into the score of all hits on this this field of this
   * document.
   *
   * <p>The boost is multiplied by {@link org.apache.lucene.document.Document#getBoost()} of the document
   * containing this field.  If a document has multiple fields with the same
   * name, all such values are multiplied together.  This product is then
   * used to compute the norm factor for the field.  By
   * default, in the {@link
   * org.apache.lucene.search.Similarity#computeNorm(String,
   * FieldInvertState)} method, the boost value is multipled
   * by the {@link
   * org.apache.lucene.search.Similarity#lengthNorm(String,
   * int)} and then
   * rounded by {@link org.apache.lucene.search.Similarity#encodeNorm(float)} before it is stored in the
   * index.  One should attempt to ensure that this product does not overflow
   * the range of that encoding.
   *
   * @see org.apache.lucene.document.Document#setBoost(float)
   * @see org.apache.lucene.search.Similarity#computeNorm(String, org.apache.lucene.index.FieldInvertState)
   * @see org.apache.lucene.search.Similarity#encodeNorm(float)
   */
  public void setBoost(float boost) {
    this.boost = boost;
  }

  /** Returns the boost factor for hits for this field.
   *
   * <p>The default value is 1.0.
   *
   * <p>Note: this value is not stored directly with the document in the index.
   * Documents returned from {@link org.apache.lucene.index.IndexReader#document(int)} and
   * {@link org.apache.lucene.search.Searcher#doc(int)} may thus not have the same value present as when
   * this field was indexed.
   *
   * @see #setBoost(float)
   */
  public float getBoost() {
    return boost;
  }

  /** Returns the name of the field as an interned string.
   * For example "date", "title", "body", ...
   */
  public String name()    { return name; }

  protected void setStoreTermVector(Field.TermVector termVector) {
    this.storeTermVector = termVector.isStored();
    this.storePositionWithTermVector = termVector.withPositions();
    this.storeOffsetWithTermVector = termVector.withOffsets();
  }

  /** True iff the value of the field is to be stored in the index for return
    with search hits.  It is an error for this to be true if a field is
    Reader-valued. */
  public final boolean  isStored()  { return isStored; }

  /** True iff the value of the field is to be indexed, so that it may be
    searched on. */
  public final boolean  isIndexed()   { return isIndexed; }

  /** True iff the value of the field should be tokenized as text prior to
    indexing.  Un-tokenized fields are indexed as a single word and may not be
    Reader-valued. */
  public final boolean  isTokenized()   { return isTokenized; }

  /** True iff the term or terms used to index this field are stored as a term
   *  vector, available from {@link org.apache.lucene.index.IndexReader#getTermFreqVector(int,String)}.
   *  These methods do not provide access to the original content of the field,
   *  only to terms used to index it. If the original content must be
   *  preserved, use the <code>stored</code> attribute instead.
   *
   * @see org.apache.lucene.index.IndexReader#getTermFreqVector(int, String)
   */
  public final boolean isTermVectorStored() { return storeTermVector; }

  /**
   * True iff terms are stored as term vector together with their offsets 
   * (start and end position in source text).
   */
  public boolean isStoreOffsetWithTermVector(){
    return storeOffsetWithTermVector;
  }

  /**
   * True iff terms are stored as term vector together with their token positions.
   */
  public boolean isStorePositionWithTermVector(){
    return storePositionWithTermVector;
  }

  /** True iff the value of the filed is stored as binary */
  public final boolean  isBinary() {
    return isBinary;
  }


  /**
   * Return the raw byte[] for the binary field.  Note that
   * you must also call {@link #getBinaryLength} and {@link
   * #getBinaryOffset} to know which range of bytes in this
   * returned array belong to the field.
   * @return reference to the Field value as byte[].
   */
  public byte[] getBinaryValue() {
    return getBinaryValue(null);
  }
  
  public byte[] getBinaryValue(byte[] result){
    if (isBinary || fieldsData instanceof byte[])
      return (byte[]) fieldsData;
    else
      return null;
  }

  /**
   * Returns length of byte[] segment that is used as value, if Field is not binary
   * returned value is undefined
   * @return length of byte[] segment that represents this Field value
   */
  public int getBinaryLength() {
    if (isBinary) {
      return binaryLength;
    } else if (fieldsData instanceof byte[])
      return ((byte[]) fieldsData).length;
    else
      return 0;
  }

  /**
   * Returns offset into byte[] segment that is used as value, if Field is not binary
   * returned value is undefined
   * @return index of the first character in byte[] segment that represents this Field value
   */
  public int getBinaryOffset() {
    return binaryOffset;
  }

  /** True if norms are omitted for this indexed field */
  public boolean getOmitNorms() { return omitNorms; }

  /** @see #setOmitTermFreqAndPositions */
  public boolean getOmitTermFreqAndPositions() { return omitTermFreqAndPositions; }
  
  /** Expert:
   *
   * If set, omit normalization factors associated with this indexed field.
   * This effectively disables indexing boosts and length normalization for this field.
   */
  public void setOmitNorms(boolean omitNorms) { this.omitNorms=omitNorms; }

  /** Expert:
   *
   * If set, omit term freq, positions and payloads from
   * postings for this field.
   *
   * <p><b>NOTE</b>: While this option reduces storage space
   * required in the index, it also means any query
   * requiring positional information, such as {@link
   * PhraseQuery} or {@link SpanQuery} subclasses will
   * silently fail to find results.
   */
  public void setOmitTermFreqAndPositions(boolean omitTermFreqAndPositions) { this.omitTermFreqAndPositions=omitTermFreqAndPositions; }
 
  public boolean isLazy() {
    return lazy;
  }

  /** Prints a Field for human consumption. */
  @Override
  public final String toString() {
    StringBuilder result = new StringBuilder();
    if (isStored) {
      result.append("stored");
    }
    if (isIndexed) {
      if (result.length() > 0)
        result.append(",");
      result.append("indexed");
    }
    if (isTokenized) {
      if (result.length() > 0)
        result.append(",");
      result.append("tokenized");
    }
    if (storeTermVector) {
      if (result.length() > 0)
        result.append(",");
      result.append("termVector");
    }
    if (storeOffsetWithTermVector) {
      if (result.length() > 0)
        result.append(",");
      result.append("termVectorOffsets");
    }
    if (storePositionWithTermVector) {
      if (result.length() > 0)
        result.append(",");
      result.append("termVectorPosition");
    }
    if (isBinary) {
      if (result.length() > 0)
        result.append(",");
      result.append("binary");
    }
    if (omitNorms) {
      result.append(",omitNorms");
    }
    if (omitTermFreqAndPositions) {
      result.append(",omitTermFreqAndPositions");
    }
    if (lazy){
      result.append(",lazy");
    }
    result.append('<');
    result.append(name);
    result.append(':');

    if (fieldsData != null && lazy == false) {
      result.append(fieldsData);
    }

    result.append('>');
    return result.toString();
  }
}
 
分享到:
评论

相关推荐

    lucene-core-3.0.2.jar,lucene-demos-3.0.2.jar

    首先,我们来看看`lucene-core-3.0.2.jar`。这是Lucene的核心库,包含了所有用于创建、索引和搜索文档的基本组件。它提供了一个高效的倒排索引结构,使得文本搜索变得快速且高效。在3.0.2版本中,Lucene引入了诸多...

    搜索引擎Lucene源码--官方3.0.2版本--Java

    Apache旗下的Lucene是一款用JAVA语言开发的最早的搜索引擎系统,对学习搜索引擎的朋友们有很大的帮助!

    lucene-analyzers-smartcn-7.7.0-API文档-中文版.zip

    赠送jar包:lucene-analyzers-smartcn-7.7.0.jar; 赠送原API文档:lucene-analyzers-smartcn-7.7.0-javadoc.jar; 赠送源代码:lucene-analyzers-smartcn-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-...

    lucene-3.0.2-src.zip 源码

    lucene-3.0.2-src.zip 源码

    lucene-core-2.9.4,lucene-core-3.0.2,lucene-core-3.0.3,lucene-core-3.4.0

    2. **Lucene 3.0.2和3.0.3** - **段合并优化**:这两个版本主要关注于索引段的合并策略,旨在减少磁盘I/O,提高检索速度。 - **文档处理增强**:引入了对PDF、HTML等更多文件格式的支持,使得Lucene可以处理更广泛...

    lucene-3.0.2-dev-src

    在`lucene-3.0.2-dev`源码中,`IndexWriter`类负责创建和更新索引,通过`Term`和`Document`对象来表示关键词和文档。索引的构建过程包括分词(Tokenization)、词项分析(Tokenization)和文档编码(Document ...

    lucene3.0.2

    lucene3.0.2包含lucene-analyzers-3.0.2.jar,lucene-core-3.0.2.jar,lucene-highlighter-3.0.2.jar,lucene-memory-3.0.2.jar等jar包使用lucene实现分词搜索

    lucene-core-7.7.0-API文档-中文版.zip

    赠送jar包:lucene-core-7.7.0.jar; 赠送原API文档:lucene-core-7.7.0-javadoc.jar; 赠送源代码:lucene-core-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-core-7.7.0.pom; 包含翻译后的API文档:lucene...

    lucene-analyzers-common-6.6.0-API文档-中文版.zip

    赠送jar包:lucene-analyzers-common-6.6.0.jar; 赠送原API文档:lucene-analyzers-common-6.6.0-javadoc.jar; 赠送源代码:lucene-analyzers-common-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-...

    lucene-memory-3.0.2.jar

    lucene-memory-3.0.2.jar,lucene高亮显示中不可少的jar包lucene-memory-*.jar

    lucene-suggest-6.6.0-API文档-中文版.zip

    赠送jar包:lucene-suggest-6.6.0.jar; 赠送原API文档:lucene-suggest-6.6.0-javadoc.jar; 赠送源代码:lucene-suggest-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-suggest-6.6.0.pom; 包含翻译后的API...

    lucene-demos-3.0.2.jar

    lucene-demos-3.0.2.jar 搜索引擎

    lucene-core-7.2.1-API文档-中文版.zip

    赠送jar包:lucene-core-7.2.1.jar; 赠送原API文档:lucene-core-7.2.1-javadoc.jar; 赠送源代码:lucene-core-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-core-7.2.1.pom; 包含翻译后的API文档:lucene...

    lucene-backward-codecs-7.3.1-API文档-中英对照版.zip

    赠送jar包:lucene-backward-codecs-7.3.1.jar; 赠送原API文档:lucene-backward-codecs-7.3.1-javadoc.jar; 赠送源代码:lucene-backward-codecs-7.3.1-sources.jar; 赠送Maven依赖信息文件:lucene-backward-...

    lucene-spatial-extras-7.3.1-API文档-中英对照版.zip

    赠送jar包:lucene-spatial-extras-7.3.1.jar; 赠送原API文档:lucene-spatial-extras-7.3.1-javadoc.jar; 赠送源代码:lucene-spatial-extras-7.3.1-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-extras...

    lucene-analyzers-smartcn-7.7.0-API文档-中英对照版.zip

    赠送jar包:lucene-analyzers-smartcn-7.7.0.jar; 赠送原API文档:lucene-analyzers-smartcn-7.7.0-javadoc.jar; 赠送源代码:lucene-analyzers-smartcn-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-...

    lucene-spatial-extras-7.2.1-API文档-中英对照版.zip

    赠送jar包:lucene-spatial-extras-7.2.1.jar; 赠送原API文档:lucene-spatial-extras-7.2.1-javadoc.jar; 赠送源代码:lucene-spatial-extras-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-extras...

    lucene-spatial-extras-6.6.0-API文档-中英对照版.zip

    赠送jar包:lucene-spatial-extras-6.6.0.jar; 赠送原API文档:lucene-spatial-extras-6.6.0-javadoc.jar; 赠送源代码:lucene-spatial-extras-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-extras...

    lucene-backward-codecs-7.2.1-API文档-中英对照版.zip

    赠送jar包:lucene-backward-codecs-7.2.1.jar; 赠送原API文档:lucene-backward-codecs-7.2.1-javadoc.jar; 赠送源代码:lucene-backward-codecs-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-backward-...

    lucene-sandbox-7.2.1-API文档-中文版.zip

    赠送jar包:lucene-sandbox-7.2.1.jar; 赠送原API文档:lucene-sandbox-7.2.1-javadoc.jar; 赠送源代码:lucene-sandbox-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-sandbox-7.2.1.pom; 包含翻译后的API...

Global site tag (gtag.js) - Google Analytics