`
liuxinglanyue
  • 浏览: 561428 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 - final class Document

阅读更多

package org.apache.lucene.document;

/**
 * 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.util.*;             // for javadoc
import org.apache.lucene.search.ScoreDoc; // for javadoc
import org.apache.lucene.search.Searcher;  // for javadoc
import org.apache.lucene.index.IndexReader;  // for javadoc

/** Documents are the unit of indexing and search.
 *
 * A Document is a set of fields.  Each field has a name and a textual value.
 * A field may be {@link Fieldable#isStored() stored} with the document, in which
 * case it is returned with search hits on the document.  Thus each document
 * should typically contain one or more stored fields which uniquely identify
 * it.
 *
 * <p>Note that fields which are <i>not</i> {@link Fieldable#isStored() stored} are
 * <i>not</i> available in documents retrieved from the index, e.g. with {@link
 * ScoreDoc#doc}, {@link Searcher#doc(int)} or {@link
 * IndexReader#document(int)}.
 */

public final class Document implements java.io.Serializable {
  List<Fieldable> fields = new ArrayList<Fieldable>();
  private float boost = 1.0f;

  /** Constructs a new document with no fields. */
  public Document() {}


  /** Sets a boost factor for hits on any field of this document.  This value
   * will be multiplied into the score of all hits on this document.
   *
   * <p>The default value is 1.0.
   * 
   * <p>Values are multiplied into the value of {@link Fieldable#getBoost()} of
   * each field in this document.  Thus, this method in effect sets a default
   * boost for the fields of this document.
   *
   * @see Fieldable#setBoost(float)
   */
  public void setBoost(float boost) {
    this.boost = boost;
  }

  /** Returns, at indexing time, the boost factor as set by {@link #setBoost(float)}. 
   *
   * <p>Note that once a document is indexed this value is no longer available
   * from the index.  At search time, for retrieved documents, this method always 
   * returns 1. This however does not mean that the boost value set at  indexing 
   * time was ignored - it was just combined with other indexing time factors and 
   * stored elsewhere, for better indexing and search performance. (For more 
   * information see the "norm(t,d)" part of the scoring formula in 
   * {@link org.apache.lucene.search.Similarity Similarity}.)
   *
   * @see #setBoost(float)
   */
  public float getBoost() {
    return boost;
  }

  /**
   * <p>Adds a field to a document.  Several fields may be added with
   * the same name.  In this case, if the fields are indexed, their text is
   * treated as though appended for the purposes of search.</p>
   * <p> Note that add like the removeField(s) methods only makes sense 
   * prior to adding a document to an index. These methods cannot
   * be used to change the content of an existing index! In order to achieve this,
   * a document has to be deleted from an index and a new changed version of that
   * document has to be added.</p>
   */
  public final void add(Fieldable field) {
    fields.add(field);
  }
  
  /**
   * <p>Removes field with the specified name from the document.
   * If multiple fields exist with this name, this method removes the first field that has been added.
   * If there is no field with the specified name, the document remains unchanged.</p>
   * <p> Note that the removeField(s) methods like the add method only make sense 
   * prior to adding a document to an index. These methods cannot
   * be used to change the content of an existing index! In order to achieve this,
   * a document has to be deleted from an index and a new changed version of that
   * document has to be added.</p>
   */
  public final void removeField(String name) {
    Iterator<Fieldable> it = fields.iterator();
    while (it.hasNext()) {
      Fieldable field = it.next();
      if (field.name().equals(name)) {
        it.remove();
        return;
      }
    }
  }
  
  /**
   * <p>Removes all fields with the given name from the document.
   * If there is no field with the specified name, the document remains unchanged.</p>
   * <p> Note that the removeField(s) methods like the add method only make sense 
   * prior to adding a document to an index. These methods cannot
   * be used to change the content of an existing index! In order to achieve this,
   * a document has to be deleted from an index and a new changed version of that
   * document has to be added.</p>
   */
  public final void removeFields(String name) {
    Iterator<Fieldable> it = fields.iterator();
    while (it.hasNext()) {
      Fieldable field = it.next();
      if (field.name().equals(name)) {
        it.remove();
      }
    }
  }

  /** Returns a field with the given name if any exist in this document, or
   * null.  If multiple fields exists with this name, this method returns the
   * first value added.
   * Do not use this method with lazy loaded fields.
   */
  public final Field getField(String name) {
    return (Field) getFieldable(name);
  }


 /** Returns a field with the given name if any exist in this document, or
   * null.  If multiple fields exists with this name, this method returns the
   * first value added.
   */
 public Fieldable getFieldable(String name) {
   for (Fieldable field : fields) {
     if (field.name().equals(name))
       return field;
   }
   return null;
 }

  /** Returns the string value of the field with the given name if any exist in
   * this document, or null.  If multiple fields exist with this name, this
   * method returns the first value added. If only binary fields with this name
   * exist, returns null.
   */
  public final String get(String name) {
   for (Fieldable field : fields) {
      if (field.name().equals(name) && (!field.isBinary()))
        return field.stringValue();
    }
    return null;
  }

  /** Returns a List of all the fields in a document.
   * <p>Note that fields which are <i>not</i> {@link Fieldable#isStored() stored} are
   * <i>not</i> available in documents retrieved from the
   * index, e.g. {@link Searcher#doc(int)} or {@link
   * IndexReader#document(int)}.
   */
  public final List<Fieldable> getFields() {
    return fields;
  }

  private final static Field[] NO_FIELDS = new Field[0];
  
  /**
   * Returns an array of {@link Field}s with the given name.
   * Do not use with lazy loaded fields.
   * This method returns an empty array when there are no
   * matching fields.  It never returns null.
   *
   * @param name the name of the field
   * @return a <code>Field[]</code> array
   */
   public final Field[] getFields(String name) {
     List<Field> result = new ArrayList<Field>();
     for (Fieldable field : fields) {
       if (field.name().equals(name)) {
         result.add((Field) field);
       }
     }

     if (result.size() == 0)
       return NO_FIELDS;

     return result.toArray(new Field[result.size()]);
   }


   private final static Fieldable[] NO_FIELDABLES = new Fieldable[0];

   /**
   * Returns an array of {@link Fieldable}s with the given name.
   * This method returns an empty array when there are no
   * matching fields.  It never returns null.
   *
   * @param name the name of the field
   * @return a <code>Fieldable[]</code> array
   */
   public Fieldable[] getFieldables(String name) {
     List<Fieldable> result = new ArrayList<Fieldable>();
     for (Fieldable field : fields) {
       if (field.name().equals(name)) {
         result.add(field);
       }
     }

     if (result.size() == 0)
       return NO_FIELDABLES;

     return result.toArray(new Fieldable[result.size()]);
   }


   private final static String[] NO_STRINGS = new String[0];

  /**
   * Returns an array of values of the field specified as the method parameter.
   * This method returns an empty array when there are no
   * matching fields.  It never returns null.
   * @param name the name of the field
   * @return a <code>String[]</code> of field values
   */
  public final String[] getValues(String name) {
    List<String> result = new ArrayList<String>();
    for (Fieldable field : fields) {
      if (field.name().equals(name) && (!field.isBinary()))
        result.add(field.stringValue());
    }
    
    if (result.size() == 0)
      return NO_STRINGS;
    
    return result.toArray(new String[result.size()]);
  }

  private final static byte[][] NO_BYTES = new byte[0][];

  /**
  * Returns an array of byte arrays for of the fields that have the name specified
  * as the method parameter.  This method returns an empty
  * array when there are no matching fields.  It never
  * returns null.
  *
  * @param name the name of the field
  * @return a <code>byte[][]</code> of binary field values
  */
  public final byte[][] getBinaryValues(String name) {
    List<byte[]> result = new ArrayList<byte[]>();
    for (Fieldable field : fields) {
      if (field.name().equals(name) && (field.isBinary()))
        result.add(field.getBinaryValue());
    }
  
    if (result.size() == 0)
      return NO_BYTES;
  
    return result.toArray(new byte[result.size()][]);
  }
  
  /**
  * Returns an array of bytes for the first (or only) field that has the name
  * specified as the method parameter. This method will return <code>null</code>
  * if no binary fields with the specified name are available.
  * There may be non-binary fields with the same name.
  *
  * @param name the name of the field.
  * @return a <code>byte[]</code> containing the binary field value or <code>null</code>
  */
  public final byte[] getBinaryValue(String name) {
    for (Fieldable field : fields) {
      if (field.name().equals(name) && (field.isBinary()))
        return field.getBinaryValue();
    }
    return null;
  }
  
  /** Prints the fields of a document for human consumption. */
  @Override
  public final String toString() {
    StringBuilder buffer = new StringBuilder();
    buffer.append("Document<");
    for (int i = 0; i < fields.size(); i++) {
      Fieldable field = fields.get(i);
      buffer.append(field.toString());
      if (i != fields.size()-1)
        buffer.append(" ");
    }
    buffer.append(">");
    return buffer.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-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-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-...

    jakarta-lucene-1.9-final.zip_lucene_lucene 1.9 final j

    在“jakarta-lucene-1.9-final.zip”这个压缩包中,我们找到了Lucene 1.9最终版本的相关文件。Lucene自1.9以来,已经经历了多次迭代,每个版本都带来了性能和功能上的提升,但1.9版本仍具有其历史价值,尤其对于那些...

    lucene-demos-3.0.2.jar

    lucene-demos-3.0.2.jar 搜索引擎

    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-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-...

Global site tag (gtag.js) - Google Analytics