lucene(索引的查询)

短命女 2022-06-17 03:48 294阅读 0赞

# lucene(索引的查询)    #

lucene查询的核心类：

IndexSearcher、Term、Query、TermQuery、TopDocs、ScoreDoc

# 搜索功能的简单实现 #

## 创建IndexReader ##

// 此处是创建索引存放的地址
    Directory driectory = FSDirectory.open(new File("D:/lucene/files2"));
    IndexReader reader = IndexReader.open(driectory);

## 创建IndexSearcher ##

IndexSearcher indexSearche=new IndexSearcher(reader);

## 创建Term和TermQuery ##

IndexSearcher indexSearcher = new IndexSearcher(reader);
    Query query=new TermQuery(new Term(field,name));

## 根据TermQuery获取TopDocs ##

TopDocs tds = searcher.search(query, num);
    System.out.println("一共查询了：" + tds.totalHits);

## 根据TopDocs获取ScoreDoc ##

for (ScoreDoc sd : tds.scoreDocs) {
    	Document doc = searcher.doc(sd.doc);//根据ScoreDoc获取相应的Document
    	System.out.println(doc.get("fieldName"));
    }

以上是基础核心代码，举例简单查询代码如下：

Directory dir = FSDirectory.open(new File("D:/lucene/files2"));
     IndexSearcher searcher = new IndexSearcher(reader);
     Query q = new TermQuery(new Term("fieldName", "keyWord"));
     TopDocs tds = searcher.search(q, 500);
     ScoreDoc[] sds = tds.scoreDocs;
     // 查询500个，从start开始，从end结束
     for (int i = start; i < end; i++) {
       Document doc = searcher.doc(sds[i].doc);
       System.out.println("path" + doc.get("path"));
     }

# 其他的Query #

## TermRangeQuery(段域范围查询) ##

![Center][]

## NumricRangeQuery（数字范围查询） ##

Query q =NumericRangeQuery.newIntRange(field,start,end,true,true);
    TopDocs tds = searcher.search(q, num);

## PrefixQuery（前缀查询） ##

//此时的value就是通过前缀来匹配的
    Query q =new PrefixQuery(new Term(field,value));

## WildcardQuery（通配符查询） ##

//此查询是查询filename以java开始的所有结果集
    Query q = new WildcardQuery(new Term("filename","java*"));

## BooleanQuery(多条件查询)【经常使用】 ##

![Center 1][]

## PhraseQuery(短语查询) ##

![Center 2][]

## FuzzyQuery模糊查询 ##

//调整相似读 允许有个别错误的查询 
    Query q = new FuzzyQuery(new Term("field", ""), 0.4f, 0);

# QueryParse（重点） #

## 创建queryParse ##

QueryParser parser = new QueryParser(Version.LUCENE_35,"content",new StandardAnalyzer(Version.LUCENE_35));

## 各种匹配方式 ##

![Center 3][]

## 分页查询 ##

Directory dir = FSDirectory.open(new File("D:/lucene/files2"));
    IndexReader reader = IndexReader.open(dir);
    IndexSearcher searcher = new IndexSearcher(reader);
    QueryParser parser = new QueryParser(Version.LUCENE_35, "content",new StandardAnalyzer(Version.LUCENE_35));
    Query q = parser.parse(query);
    TopDocs tds = searcher.search(q, 500);
    ScoreDoc[] sds = tds.scoreDocs;
    // 每次取出所有数据，从这写数据进行再查询
    int start = (pageIndex - 1) * pageSize;
    int end = pageIndex * pageSize;
    for (int i = start; i < end; i++) {
    	Document doc = searcher.doc(sds[i].doc);
    	System.out.println("filename=" + doc.get("filename"));
    }
    searcher.close();

# 高级搜索 #

## 搜索排序 ##

public class AnalyzerUtils {
    	public void searcher(String queryStr, Sort sort) {
    		try {
    			Directory dir = FSDirectory.open(new File("D:/lucene/files2"));
    			IndexReader reader = IndexReader.open(dir);
    			IndexSearcher searcher = new IndexSearcher(reader);
    			Version version = Version.LUCENE_35;
    			Analyzer analyzer = new StandardAnalyzer(version);
    			QueryParser parser = new QueryParser(version, "content", analyzer);
    			Query query = parser.parse(queryStr);
    			TopDocs tds = null;
    			if (sort == null) {
    				// 默认排序
    				tds = searcher.search(query, 50);
    			} else {
    				// 按照穿日的值进行排序
    				tds = searcher.search(query, 50, sort);
    			}
    			for (ScoreDoc sd : tds.scoreDocs) {
    				Document doc = searcher.doc(sd.doc);
    				System.out.println("评分：" + sd.score + "-->filename"
    						+ doc.get("filename"));
    			}
    			searcher.close();
    		} catch (Exception e) {
    			e.printStackTrace();
    		}
    	}
    }

## 按照分值排序 ##

// 先按大小再按评分排序
    		analyzerUtils.searcher("java", new Sort(new SortField("size",
    				SortField.INT), SortField.FIELD_SCORE));

## 按照索引序号排序 ##

// 按照id排序
    analyzerUtils.searcher("java", Sort.INDEXORDER);

## 按照不同的域进行排序 ##

AnalyzerUtils analyzerUtils = new AnalyzerUtils();
    // 先按大小再按评分排序
    analyzerUtils.searcher("java", new Sort(new SortField("size",SortField.INT), SortField.FIELD_SCORE));
    // 按照id排序
    analyzerUtils.searcher("java", Sort.INDEXORDER);
    // 按照默认评分排序
    analyzerUtils.searcher("java", null);
    // 按照文件的大小排序
    analyzerUtils.searcher("java", new Sort(new SortField("size",SortField.INT)));
    // 按照日期排序
    analyzerUtils.searcher("java", new Sort(new SortField("date",SortField.LONG)));
    // 通过设置一个最后一个参数booleanReverse是否反转的意思就是倒叙即DESC还是ASC
    analyzerUtils.searcher("java", new Sort(new SortField("date",SortField.LONG)));

[Center]: /images/20220617/307ca93ba03544e18c50d9ad8459cbee.png
[Center 1]: /images/20220617/00bb296cef5a465ea41c3b069721e016.png
[Center 2]: /images/20220617/e1c3eee13f2f4a7a832241d976d02cd6.png
[Center 3]: /images/20220617/43884d7a8cd8432db9d81e2bb20e8945.png