Save This Page
Home » lucene-2.3.2-src » org.apache » lucene » document » [javadoc | source]
    1   package org.apache.lucene.document;
    2   
    3   /**
    4    * Licensed to the Apache Software Foundation (ASF) under one or more
    5    * contributor license agreements.  See the NOTICE file distributed with
    6    * this work for additional information regarding copyright ownership.
    7    * The ASF licenses this file to You under the Apache License, Version 2.0
    8    * (the "License"); you may not use this file except in compliance with
    9    * the License.  You may obtain a copy of the License at
   10    *
   11    *     http://www.apache.org/licenses/LICENSE-2.0
   12    *
   13    * Unless required by applicable law or agreed to in writing, software
   14    * distributed under the License is distributed on an "AS IS" BASIS,
   15    * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   16    * See the License for the specific language governing permissions and
   17    * limitations under the License.
   18    */
   19   
   20   import org.apache.lucene.index.IndexReader;
   21   import org.apache.lucene.search.Hits;
   22   import org.apache.lucene.search.Searcher;
   23   
   24   import java.util.*;             // for javadoc
   25   
   26   /** Documents are the unit of indexing and search.
   27    *
   28    * A Document is a set of fields.  Each field has a name and a textual value.
   29    * A field may be {@link Fieldable#isStored() stored} with the document, in which
   30    * case it is returned with search hits on the document.  Thus each document
   31    * should typically contain one or more stored fields which uniquely identify
   32    * it.
   33    *
   34    * <p>Note that fields which are <i>not</i> {@link Fieldable#isStored() stored} are
   35    * <i>not</i> available in documents retrieved from the index, e.g. with {@link
   36    * Hits#doc(int)}, {@link Searcher#doc(int)} or {@link
   37    * IndexReader#document(int)}.
   38    */
   39   
   40   public final class Document implements java.io.Serializable {
   41     List fields = new ArrayList();
   42     private float boost = 1.0f;
   43   
   44     /** Constructs a new document with no fields. */
   45     public Document() {}
   46   
   47   
   48     /** Sets a boost factor for hits on any field of this document.  This value
   49      * will be multiplied into the score of all hits on this document.
   50      *
   51      * <p>The default value is 1.0.
   52      * 
   53      * <p>Values are multiplied into the value of {@link Fieldable#getBoost()} of
   54      * each field in this document.  Thus, this method in effect sets a default
   55      * boost for the fields of this document.
   56      *
   57      * @see Fieldable#setBoost(float)
   58      */
   59     public void setBoost(float boost) {
   60       this.boost = boost;
   61     }
   62   
   63     /** Returns, at indexing time, the boost factor as set by {@link #setBoost(float)}. 
   64      *
   65      * <p>Note that once a document is indexed this value is no longer available
   66      * from the index.  At search time, for retrieved documents, this method always 
   67      * returns 1. This however does not mean that the boost value set at  indexing 
   68      * time was ignored - it was just combined with other indexing time factors and 
   69      * stored elsewhere, for better indexing and search performance. (For more 
   70      * information see the "norm(t,d)" part of the scoring formula in 
   71      * {@link org.apache.lucene.search.Similarity Similarity}.)
   72      *
   73      * @see #setBoost(float)
   74      */
   75     public float getBoost() {
   76       return boost;
   77     }
   78   
   79     /**
   80      * <p>Adds a field to a document.  Several fields may be added with
   81      * the same name.  In this case, if the fields are indexed, their text is
   82      * treated as though appended for the purposes of search.</p>
   83      * <p> Note that add like the removeField(s) methods only makes sense 
   84      * prior to adding a document to an index. These methods cannot
   85      * be used to change the content of an existing index! In order to achieve this,
   86      * a document has to be deleted from an index and a new changed version of that
   87      * document has to be added.</p>
   88      */
   89     public final void add(Fieldable field) {
   90       fields.add(field);
   91     }
   92     
   93     /**
   94      * <p>Removes field with the specified name from the document.
   95      * If multiple fields exist with this name, this method removes the first field that has been added.
   96      * If there is no field with the specified name, the document remains unchanged.</p>
   97      * <p> Note that the removeField(s) methods like the add method only make sense 
   98      * prior to adding a document to an index. These methods cannot
   99      * be used to change the content of an existing index! In order to achieve this,
  100      * a document has to be deleted from an index and a new changed version of that
  101      * document has to be added.</p>
  102      */
  103     public final void removeField(String name) {
  104       Iterator it = fields.iterator();
  105       while (it.hasNext()) {
  106         Fieldable field = (Fieldable)it.next();
  107         if (field.name().equals(name)) {
  108           it.remove();
  109           return;
  110         }
  111       }
  112     }
  113     
  114     /**
  115      * <p>Removes all fields with the given name from the document.
  116      * If there is no field with the specified name, the document remains unchanged.</p>
  117      * <p> Note that the removeField(s) methods like the add method only make sense 
  118      * prior to adding a document to an index. These methods cannot
  119      * be used to change the content of an existing index! In order to achieve this,
  120      * a document has to be deleted from an index and a new changed version of that
  121      * document has to be added.</p>
  122      */
  123     public final void removeFields(String name) {
  124       Iterator it = fields.iterator();
  125       while (it.hasNext()) {
  126         Fieldable field = (Fieldable)it.next();
  127         if (field.name().equals(name)) {
  128           it.remove();
  129         }
  130       }
  131     }
  132   
  133     /** Returns a field with the given name if any exist in this document, or
  134      * null.  If multiple fields exists with this name, this method returns the
  135      * first value added.
  136      * Do not use this method with lazy loaded fields.
  137      */
  138     public final Field getField(String name) {
  139       for (int i = 0; i < fields.size(); i++) {
  140         Field field = (Field)fields.get(i);
  141         if (field.name().equals(name))
  142           return field;
  143       }
  144       return null;
  145     }
  146   
  147   
  148    /** Returns a field with the given name if any exist in this document, or
  149      * null.  If multiple fields exists with this name, this method returns the
  150      * first value added.
  151      */
  152    public Fieldable getFieldable(String name) {
  153      for (int i = 0; i < fields.size(); i++) {
  154        Fieldable field = (Fieldable)fields.get(i);
  155        if (field.name().equals(name))
  156          return field;
  157      }
  158      return null;
  159    }
  160   
  161     /** Returns the string value of the field with the given name if any exist in
  162      * this document, or null.  If multiple fields exist with this name, this
  163      * method returns the first value added. If only binary fields with this name
  164      * exist, returns null.
  165      */
  166     public final String get(String name) {
  167       for (int i = 0; i < fields.size(); i++) {
  168         Fieldable field = (Fieldable)fields.get(i);
  169         if (field.name().equals(name) && (!field.isBinary()))
  170           return field.stringValue();
  171       }
  172       return null;
  173     }
  174   
  175     /** Returns an Enumeration of all the fields in a document.
  176      * @deprecated use {@link #getFields()} instead
  177      */
  178     public final Enumeration fields() {
  179       return new Enumeration() {
  180         final Iterator iter = fields.iterator();
  181         public boolean hasMoreElements() {
  182           return iter.hasNext();
  183         }
  184         public Object nextElement() {
  185           return iter.next();
  186         }
  187       };
  188     }
  189   
  190     /** Returns a List of all the fields in a document.
  191      * <p>Note that fields which are <i>not</i> {@link Fieldable#isStored() stored} are
  192      * <i>not</i> available in documents retrieved from the index, e.g. with {@link
  193      * Hits#doc(int)}, {@link Searcher#doc(int)} or {@link IndexReader#document(int)}.
  194      */
  195     public final List getFields() {
  196       return fields;
  197     }
  198   
  199     /**
  200      * Returns an array of {@link Field}s with the given name.
  201      * This method can return <code>null</code>.
  202      * Do not use with lazy loaded fields.
  203      *
  204      * @param name the name of the field
  205      * @return a <code>Field[]</code> array
  206      */
  207      public final Field[] getFields(String name) {
  208        List result = new ArrayList();
  209        for (int i = 0; i < fields.size(); i++) {
  210          Field field = (Field)fields.get(i);
  211          if (field.name().equals(name)) {
  212            result.add(field);
  213          }
  214        }
  215   
  216        if (result.size() == 0)
  217          return null;
  218   
  219        return (Field[])result.toArray(new Field[result.size()]);
  220      }
  221   
  222   
  223     /**
  224      * Returns an array of {@link Fieldable}s with the given name.
  225      * This method can return <code>null</code>.
  226      *
  227      * @param name the name of the field
  228      * @return a <code>Fieldable[]</code> array or <code>null</code>
  229      */
  230      public Fieldable[] getFieldables(String name) {
  231        List result = new ArrayList();
  232        for (int i = 0; i < fields.size(); i++) {
  233          Fieldable field = (Fieldable)fields.get(i);
  234          if (field.name().equals(name)) {
  235            result.add(field);
  236          }
  237        }
  238   
  239        if (result.size() == 0)
  240          return null;
  241   
  242        return (Fieldable[])result.toArray(new Fieldable[result.size()]);
  243      }
  244   
  245   
  246     /**
  247      * Returns an array of values of the field specified as the method parameter.
  248      * This method can return <code>null</code>.
  249      *
  250      * @param name the name of the field
  251      * @return a <code>String[]</code> of field values or <code>null</code>
  252      */
  253     public final String[] getValues(String name) {
  254       List result = new ArrayList();
  255       for (int i = 0; i < fields.size(); i++) {
  256         Fieldable field = (Fieldable)fields.get(i);
  257         if (field.name().equals(name) && (!field.isBinary()))
  258           result.add(field.stringValue());
  259       }
  260       
  261       if (result.size() == 0)
  262         return null;
  263       
  264       return (String[])result.toArray(new String[result.size()]);
  265     }
  266   
  267     /**
  268     * Returns an array of byte arrays for of the fields that have the name specified
  269     * as the method parameter. This method will return <code>null</code> if no
  270     * binary fields with the specified name are available.
  271     *
  272     * @param name the name of the field
  273     * @return a  <code>byte[][]</code> of binary field values or <code>null</code>
  274     */
  275     public final byte[][] getBinaryValues(String name) {
  276       List result = new ArrayList();
  277       for (int i = 0; i < fields.size(); i++) {
  278         Fieldable field = (Fieldable)fields.get(i);
  279         if (field.name().equals(name) && (field.isBinary()))
  280           result.add(field.binaryValue());
  281       }
  282     
  283       if (result.size() == 0)
  284         return null;
  285     
  286       return (byte[][])result.toArray(new byte[result.size()][]);
  287     }
  288     
  289     /**
  290     * Returns an array of bytes for the first (or only) field that has the name
  291     * specified as the method parameter. This method will return <code>null</code>
  292     * if no binary fields with the specified name are available.
  293     * There may be non-binary fields with the same name.
  294     *
  295     * @param name the name of the field.
  296     * @return a <code>byte[]</code> containing the binary field value or <code>null</code>
  297     */
  298     public final byte[] getBinaryValue(String name) {
  299       for (int i=0; i < fields.size(); i++) {
  300         Fieldable field = (Fieldable)fields.get(i);
  301         if (field.name().equals(name) && (field.isBinary()))
  302           return field.binaryValue();
  303       }
  304       return null;
  305     }
  306     
  307     /** Prints the fields of a document for human consumption. */
  308     public final String toString() {
  309       StringBuffer buffer = new StringBuffer();
  310       buffer.append("Document<");
  311       for (int i = 0; i < fields.size(); i++) {
  312         Fieldable field = (Fieldable)fields.get(i);
  313         buffer.append(field.toString());
  314         if (i != fields.size()-1)
  315           buffer.append(" ");
  316       }
  317       buffer.append(">");
  318       return buffer.toString();
  319     }
  320   }

Save This Page
Home » lucene-2.3.2-src » org.apache » lucene » document » [javadoc | source]