欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

lucene4.7 (1)全文检索之根据数据库内容创建索引

程序员文章站 2022-07-09 11:51:53
...
package org.apache.lucene.demo;

/*
 * 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.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;
import java.util.List;
import java.util.Map;

import org.apache.commons.dbutils.DbUtils;
import org.apache.lucene.analysis.cn.ChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.poi.util.IntegerField;

import thtf.ebuilder.website.search.DBIndex;
import thtf.ebuilder.website.services.HTMLServices;

/** Index all text files under a directory.
 * <p>
 * This is a command-line application demonstrating simple Lucene indexing.
 * Run it with no command-line arguments for usage information.
 */
public class IndexFiles {
  
  private IndexFiles() {}

  /** Index all text files under a directory. */
  public static void main(String[] args) {
    String indexPath = DBIndex._$.getIndexFile().toString();
    boolean add = true;
    
    Date start = new Date();
    try {
      Directory dir = FSDirectory.open(new File(indexPath));
      IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_47, DBIndex._$.analyzer);
      if (add) {
        iwc.setOpenMode(OpenMode.CREATE);
      } else {
        iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
      }
      IndexWriter writer = new IndexWriter(dir, iwc);
      indexDocs(writer);

      // NOTE: if you want to maximize search performance,
      // you can optionally call forceMerge here.  This can be
      // a terribly costly operation, so generally it's only
      // worth it when your index is relatively static (ie
      // you're done adding documents to it):
      //
      // writer.forceMerge(1);

      writer.close();

      Date end = new Date();
      System.out.println(end.getTime() - start.getTime() + " total milliseconds");

    } catch (IOException e) {
      System.out.println(" caught a " + e.getClass() +
       "\n with message: " + e.getMessage());
    }
  }

  /**
   * Indexes the given file using the given writer, or if a directory is given,
   * recurses over files and directories found under the given directory.
   * 
   * NOTE: This method indexes one document per input file.  This is slow.  For good
   * throughput, put multiple documents into your input file(s).  An example of this is
   * in the benchmark module, which can create "line doc" files, one document per line,
   * using the
   * <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html"
   * >WriteLineDocTask</a>.
   *  
   * @param writer Writer to the index where the given file/dir info will be stored
   * @param file The file to index, or the directory to recurse into to find files to index
   * @throws IOException If there is a low-level I/O error
   */
  static void indexDocs(IndexWriter writer)
    throws IOException {
        try {
          // make a new, empty document
          
          List list=new DbUtils().queryToMapList("select info_id,info_title,info_content from up_info limit 500");
          for(int i=0;i<list.size();i++){
        	  Map map=(Map)list.get(i);
        	  Document doc = new Document();
        	  
        	  Field info_id = new IntField("info_id",Integer.valueOf(String.valueOf(map.get("info_id"))), Field.Store.YES);
              doc.add(info_id);
        	  
              Field info_title = new StringField("info_title", map.get("info_title")==null?"": map.get("info_title").toString(), Field.Store.YES);
              doc.add(info_title);
              
              Field info_content = new TextField("info_content", map.get("info_content")==null?"": HTMLServices.clearHTMLToString(map.get("info_content").toString()), Field.Store.YES);
              doc.add(info_content);
              
              if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
                writer.addDocument(doc);
              } else {
                writer.updateDocument(new Term("info_id",map.get("info_id")==null?"1": map.get("info_id").toString() ), doc);
              }
          }
          writer.commit();
//          // Add the path of the file as a field named "path".  Use a
//          // field that is indexed (i.e. searchable), but don't tokenize 
//          // the field into separate words and don't index term frequency
//          // or positional information:
//          Field pathField = new StringField("path", file.getPath(), Field.Store.YES);
//          doc.add(pathField);
//
//          // Add the last modified date of the file a field named "modified".
//          // Use a LongField that is indexed (i.e. efficiently filterable with
//          // NumericRangeFilter).  This indexes to milli-second resolution, which
//          // is often too fine.  You could instead create a number based on
//          // year/month/day/hour/minutes/seconds, down the resolution you require.
//          // For example the long value 2011021714 would mean
//          // February 17, 2011, 2-3 PM.
//          doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));
//
//          // Add the contents of the file to a field named "contents".  Specify a Reader,
//          // so that the text of the file is tokenized and indexed, but not stored.
//          // Note that FileReader expects the file to be in UTF-8 encoding.
//          // If that's not the case searching for special characters will fail.
//          BufferedReader _content=new BufferedReader(new InputStreamReader(fis, "UTF-8"));
//          System.out.println(_content);
//          doc.add(new TextField("contents", _content));
//
//          if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
//            // New index, so we just add the document (no old document can be there):
//            System.out.println("adding " + file);
//            writer.addDocument(doc);
//          } else {
//            // Existing index (an old copy of this document may have been indexed) so 
//            // we use updateDocument instead to replace the old one matching the exact 
//            // path, if present:
//            System.out.println("updating " + file);
//            writer.updateDocument(new Term("path", file.getPath()), doc);
//          }
        }catch (Exception e) {
        	e.printStackTrace();
        }
  }
}