Spellcheck是Lucene新版本的功能,在介绍spellcheck之前,我们需要弄清楚Spellcheck支持几种数据源。Spellcheck构造函数需要传入Dictionary接口:
package org.apache.lucene.search.spell;
/*
* 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 org.apache.lucene.search.suggest.InputIterator; /**
* A simple interface representing a Dictionary. A Dictionary
* here is a list of entries, where every entry consists of
* term, weight and payload.
*
*/
public interface Dictionary { /**
* Returns an iterator over all the entries
* @return Iterator
*/
InputIterator getEntryIterator() throws IOException;
}
常用的Dictionary主要有以下几种,常用的主要有基于文本型的和基于lucene索引构建的:
下面是我测试用的一段代码,代码包括索引构建和索引查询:
package com.tianditu.com.search; import java.io.File;
import java.io.IOException; import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.spell.LuceneDictionary;
import org.apache.lucene.search.spell.SpellChecker;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.MMapDirectory;
import org.apache.lucene.util.Version; public class GlobalSuggest { //拼写检查构建的索引
private final String SPELL_CHECK_FOLDER = "c:\\spellcheck\\"; //根据已有的索引
private final String GLOBAL_PINYIN_SUGGEST = "O:\\searchwork_custom\\data_index\\pinyin2008\\"; //构建索引
public void testIndexPinyin2008() throws IOException{ long start = System.currentTimeMillis();
//北京吉威时代软件股份有限公司
//String indexDir ="O:\\searchwork_custom\\data_index\\GlobalIndex\\";
Directory direct = new MMapDirectory(new File(GLOBAL_PINYIN_SUGGEST)); LuceneDictionary ld = new LuceneDictionary(DirectoryReader.open(direct), "name"); ld.getEntryIterator(); Directory spd = FSDirectory.open(new File(SPELL_CHECK_FOLDER)); SpellChecker sc = new SpellChecker(spd);
//sc.in IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_30,null); //往spellcheck目录下写索引--------------
sc.indexDictionary(ld, iwc, true); sc.close(); long end = System.currentTimeMillis();
System.out.println("索引完毕,耗时:"+(end-start)+"ms");
} public void testIndex() throws IOException{
long start = System.currentTimeMillis();
//北京吉威时代软件股份有限公司
String indexDir ="O:\\searchwork_custom\\data_index\\GlobalIndex\\";
Directory direct = new MMapDirectory(new File(indexDir)); LuceneDictionary ld = new LuceneDictionary(DirectoryReader.open(direct), "name"); ld.getEntryIterator(); Directory spd = FSDirectory.open(new File(SPELL_CHECK_FOLDER)); SpellChecker sc = new SpellChecker(spd);
//sc.in IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_30,null); sc.indexDictionary(ld, iwc, true); sc.close(); long end = System.currentTimeMillis();
System.out.println("索引完毕,耗时:"+(end-start)+"ms");
} public void testSearch(String wd) throws IOException{ //构建Directory
Directory spd = FSDirectory.open(new File(SPELL_CHECK_FOLDER)); //实例化 spellcheck组件 SpellChecker sc = new SpellChecker(spd); //根据输入关键字 获得N条最相近的几率 第三个鄙视精确度 越大越匹配 安装实际需要调整
String[] suggests = sc.suggestSimilar(wd, 10,0.6f);
if(suggests!=null){
for(String word:suggests){
System.out.println("Dou you mean:"+word);
}
}
}
/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException { GlobalSuggest spellcheck = new GlobalSuggest();
//spellcheck.testIndexPinyin2008();
spellcheck.testSearch("beijing京鸭"); //spellcheck.testSearch("beijng"); } }
其中索引构建处代码:
//构建索引
public void testIndexPinyin2008() throws IOException{ long start = System.currentTimeMillis();
//北京吉威时代软件股份有限公司
//String indexDir ="O:\\searchwork_custom\\data_index\\GlobalIndex\\";
Directory direct = new MMapDirectory(new File(GLOBAL_PINYIN_SUGGEST)); LuceneDictionary ld = new LuceneDictionary(DirectoryReader.open(direct), "name"); ld.getEntryIterator(); Directory spd = FSDirectory.open(new File(SPELL_CHECK_FOLDER)); SpellChecker sc = new SpellChecker(spd);
//sc.in IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_30,null); //往spellcheck目录下写索引--------------
sc.indexDictionary(ld, iwc, true); sc.close(); long end = System.currentTimeMillis();
System.out.println("索引完毕,耗时:"+(end-start)+"ms");
}
此处代码,就是根据已有的索引来构建Spellcheck所需的索引。
Spellcheck查询索引代码片段如下:
//构建Directory
Directory spd = FSDirectory.open(new File(SPELL_CHECK_FOLDER)); //实例化 spellcheck组件 SpellChecker sc = new SpellChecker(spd); //根据输入关键字 获得N条最相近的几率 第三个鄙视精确度 越大越匹配 安装实际需要调整
String[] suggests = sc.suggestSimilar(wd, 10,0.6f);
if(suggests!=null){
for(String word:suggests){
System.out.println("Dou you mean:"+word);
}
}
相关算法:默认是 LevensteinDistance 。
查询样例:
1、查询汉字,有错别字情况:
2、查询拼音:
3、拼音汉字夹杂:
(备注:发现问题了,拼音和汉字夹杂的情况不行,如果想使用,需要进行某种处理。)
4、如果处理一长串汉字,中间夹杂错别字:
总结:看来spellcheck能力还是有限,如果需要用还可能改造。