Lucene学习

Lucene学习

public class LuenceIndex {
/**
* 1.首先创建索引关键类
* IndexWriter indexWrite=new IndexWriter(directory,indexWriterConfig);
* 2.Directory(索引的存储位置)
* Directory directory = FSDirectory.open(new File("D://index/testindex"));
* 3.Analyzer(标准的分词技术)
* Analyzer anlyzer=new StandardAnalyzer(Version.Lucene_43);
* 4.Document(一个文档有很多个域)
* Document document=new Document();
* 5.Field(域)
* doc.add(new TextField("fieldname","测试标题",Store.YES));
*/
public static void main(String[] args) {
//创建标准分词技术
Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_46);
//IndexWriter配置信息
IndexWriterConfig indexWriterConfig=new IndexWriterConfig(Version.LUCENE_46, analyzer);
//创建索引的打开方式(没有就新建，有就打开)
indexWriterConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
Directory directory=null;
IndexWriter indexWriter=null;
try {
directory=FSDirectory.open(new File("D://index/testindex"));
if(indexWriter.isLocked(directory)){
indexWriter.unlock(directory);
}
indexWriter=new IndexWriter(directory, indexWriterConfig);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
Document doc1=new Document();
doc1.add(new StringField("id", "adcns", Store.YES));
doc1.add(new TextField("content", "急速漂流",Store.YES));
doc1.add(new IntField("num", 1, Store.YES));
//写入索引
try {
indexWriter.addDocument(doc1);
} catch (IOException e) {
e.printStackTrace();
}

Document doc2=new Document();
doc2.add(new StringField("id", "abc", Store.YES));
doc2.add(new TextField("content", "开始了",Store.YES));
doc2.add(new IntField("num", 2, Store.YES));
//写入索引
try {
indexWriter.addDocument(doc2);
} catch (IOException e) {
e.printStackTrace();
}
try {
indexWriter.commit();
indexWriter.close();
directory.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}

public class LuceneRead {
/**
* 1.DirectoryReader(读取硬盘上的索引文件)
* DirectoryReader dReader=DirectoryReader.open(directory);
* 2.IndexSearcher(提供索引的检索方法)
* IndexSearcher indexSearcher=new IndexSearcher(dReader);
* 3.Query(查询条件的创建)
* QueryParser query=new QueryParser(Version.LUCENE_46, field, analyzer);
* Query query=parser.parse("空间向量");
* 4.TopDocs(保存检索的结果)
* TopDocs docs=indexSearcher.search(query, 10);
*
*/
public static void main(String[] args) {
Directory directory=null;
try {
directory=FSDirectory.open(new File("D://index/testindex"));
//读取这个索引文件
DirectoryReader dReader=DirectoryReader.open(directory);
//创建索引的检索方法
IndexSearcher indexSearcher=new IndexSearcher(dReader);
//创建分词技术，要和创建索引的一样
Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_46);
//创建查询字符串
//field（搜索域）
QueryParser parser=new QueryParser(Version.LUCENE_46, "content", analyzer);
//搜索词
Query query=parser.parse("开始");
//检索前十条
TopDocs docs=indexSearcher.search(query, 10);
//循环输出
if(docs!=null){
System.out.println("符合条件的总数为"+docs.totalHits);
for(int i=0;i<docs.scoreDocs.length;i++){
Document document=indexSearcher.doc(docs.scoreDocs[i].doc);
System.out.println("id="+document.get("id"));
System.out.println("content="+document.get("content"));
System.out.println("num="+document.get("num"));
}
}
directory.close();
dReader.close();
} catch (Exception e) {
e.printStackTrace();
}

}
}

public class AnalyzerStudy {
private static String str="武汉麦达，Lucence 学习";
/**
*
*/
public static void printAnalyzer(Analyzer analyzer){
StringReader reader=new StringReader(str);
try {
TokenStream ts=analyzer.tokenStream("", reader);
ts.reset();
//获取分词结果的CharTermAttribute
CharTermAttribute attribute=ts.getAttribute(CharTermAttribute.class);
//打印分词技术
System.out.println(analyzer.getClass());
//循环输出分词劫夺
while(ts.incrementToken()){
System.out.println(attribute.toString()+"|");
}
System.out.println();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}

}
public static void main(String[] args) {
//创建分词器
Analyzer analyzer=null;
//标准分词器
analyzer=new StandardAnalyzer(Version.LUCENE_46);
printAnalyzer(analyzer);

//空格分词
analyzer=new WhitespaceAnalyzer(Version.LUCENE_46);
printAnalyzer(analyzer);
//简单分词(一句话就是一个词，遇到标点，空格分开)

analyzer=new SimpleAnalyzer(Version.LUCENE_46);
printAnalyzer(analyzer);

//二分分词
analyzer=new CJKAnalyzer(Version.LUCENE_46);
printAnalyzer(analyzer);
//关键字分词

b9f2
analyzer=new KeywordAnalyzer();
printAnalyzer(analyzer);

//被忽略词分词器
analyzer=new StopAnalyzer(Version.LUCENE_46);
printAnalyzer(analyzer);
}
}

public class QueryStudy {
/**
* 1.QueryParser(使用单个域搜索时，指定具体的域名和分词方法)
* QueryParser parser =new QueryParser(Version.LUCENE_46, field,analyzer);
* Query query=parser.parse(key);
* 2.MultiFieldQueryParser（多个域搜索时）
* MultiFieldQueryParser parser=new MultiFieldQueryParser(Version.LUCENE_46, fields, analyzer);
* Query query=parser.parse(key);
*
* 3.TermQuery(按关键词搜索)
*  Query query=new TermQuery(new Term(field, key));
*
* 4.PrefixQuery(使用前缀搜索，前缀指定若干个相同)
* PrefixQuery query=query = new PrefixQuery(new Term(field, key);
*
* 5.PhraseQuery（短语搜索，可以指定关键词之间的最大距离）
*  PhraseQuery query = new PhraseQuery();
*  query.setSlop(2);//两个关键词之间的最大距离不能超过2
*  query.add(new Term("content","lucene"));
*  query.add(new Term("content","训练"));
* 6.WildcardQuery(通配符搜索)
* 表示0到多个字符
? 表示一个单一的字符
WildcardQuery query=new WildcardQuery(new Term(“content”,”?qq*”));
7.TermRangeQuery(在某一范围内搜索)
域的上限，域的下限，是否包含上限，是否包含下限
TermRangeQuery query=new TermRangeQuery(field, "ab", "af", true, false);
8.NumericRangeQuery（数据范围内搜索）
NumericRangeQuery query=NumericRangeQuery.newIntRange("start", 0, 3 ,false, false);
NumericRangeQuery query=NumericRangeQuery.newDoubleRange("start", 0.01, 0.62,false, false);

9.BooleanQuery(当需要把多个query对象组合成一个时，此query可以嵌套非常复杂的查询)
query=new BooleanQuery();
query.add(new Term("contetnt", "基于"),BooleanClause.Occur.MUST);
query.add(new Term("contetnt", "Lucene"),BooleanClause.Occur.MUST_NOT);
1.和 MUST与MUST_NOT
2.或 SHOULD与SHOULD
3.A与B的并集－B  MUST与MUST_NOT

IndexSearch(检索关键类)
主要用这两个方法
search(Query query,int n);
search(Query query,int n, Sort sort);

*/
public static void main(String[] args) {

}

}