lucene 3.0.2 search 各种各样的Query类型

http://blog.sina.com.cn/s/blog_61d2047c010195mo.html

 

 

lucene的这种各种各样的查询类型

1、TermQuery 

     最简单的Query类型，某一个field是否含有一个term的value

 

2、TermRangeQuery 

     由于term在index中是按照字典顺序排列的，可以使用TermRangeQuery查询一个范围内的Term

例如

Query query = new TermRangeQuery("city", "aa", "am", true, true);

TopDocs hits = searcher.search(query, 20);

 

可以查血从aa* ab* ..... am*的term。 后面的true和false代表是否包括aa和am

 

3、NumericRangeQuery 

查询一个数值的范围。 这个必须查血NumericFiled

Query query = NumericRangeQuery.newIntRange("intID", from, to, true,true);

TopDocs hits = searcher.search(query, 20);

 

4、PrefixQuery 前缀查询

      查询一个term是否满足一个前缀。

     比如 prefix =“bri” bridge和“bright”都可以满足

Term t = new Term(field, prefix);

Query query = new PrefixQuery(t);

TopDocs hits = searcher.search(query, 20);

 

5、BooleanQuery 联合多个查找

Term t = new Term("contents", "bri");

Query query1 = new PrefixQuery(t);

Query query2 = NumericRangeQuery.newIntRange("intID", 1, 3, true, true);

 

// create a boolean query

BooleanQuery query = new BooleanQuery();

query.add(query1, BooleanClause.Occur.SHOULD);

query.add(query2, BooleanClause.Occur.MUST);

 

TopDocs hits = searcher.search(query, 20);

注意BooleanClause.Occur.MUST是and的意思，BooleanClause.Occur.SHOULD是or的意思，BooleanClause.Occur.MUST_NOT是not的意思

 

6、PhraseQuery 短语查询

     我们想查询一个短语  fox quick 或者 quick fox 或者quick brown fox，或者quick red fox。

     可以使用phraseQuery,  PhraseQuery使用Edit distance（编辑距离） 来量度，编辑距离是一个字符串变化到另一个字符串需要的替换，删除，插入的次数总和。每一次这种操作叫做一次slop。可以使用setSlop来限制短语slop的最大值。

edit distance如下图

 

    

 

比如： quick fox 到quick [xxx] fox 需要 1 slop

fox quick 到 quick [xxx] fox 需要 3 slop 先用quick替换 fox，再用fox替换quick，再插入一个xxx 总共3次。

     PhraseQuery query = new PhraseQuery();

 

// set max slop to 10

query.setSlop(10);

query.add(new Term("contents", " quick " ));

query.add(new Term("contents", " fox"));

TopDocs hits = searcher.search(query, 20);

 

7、WildcardQuery通配符查询

     PrefixQuery是WildcardQuery 的特殊形式

     *代表一个或者多个，？代表0个或者一个

                // use wildchard "?ridg*"

WildcardQuery query = new WildcardQuery(new Term("contents", "?ridg*"));

TopDocs hits = searcher.search(query, 20);

 

8、FuzzyQuery  模糊查询

    FuzzyQuery与PhraseQury 一类似都是以Edit distance 来做的，只不过 FuzzyQuery是在term内部，而PhraseQuery是在term之间。   

 例如    FuzzyQuery query = new FuzzyQuery(new Term("contents", "Amsteedam")); 可以查出 Amsterdam,他们之间的编辑距离是1。

如下

 IndexSearcher searcher = new IndexSearcher(dir);

// "Amsterdam" is similar to "Amsteedam"

FuzzyQuery query = new FuzzyQuery(new Term("contents", "Amsteedam"));

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

 

package charpter3;

 

import java.io.File;

import java.io.IOException;

 

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.document.Field.TermVector;

import org.apache.lucene.document.NumericField;

import org.apache.lucene.index.CorruptIndexException;

import org.apache.lucene.index.IndexReader;

import org.apache.lucene.index.IndexWriter;

import org.apache.lucene.index.Term;

import org.apache.lucene.queryParser.ParseException;

import org.apache.lucene.queryParser.QueryParser;

import org.apache.lucene.search.BooleanClause;

import org.apache.lucene.search.BooleanQuery;

import org.apache.lucene.search.FuzzyQuery;

import org.apache.lucene.search.IndexSearcher;

import org.apache.lucene.search.NumericRangeQuery;

import org.apache.lucene.search.PhraseQuery;

import org.apache.lucene.search.PrefixQuery;

import org.apache.lucene.search.Query;

import org.apache.lucene.search.ScoreDoc;

import org.apache.lucene.search.TermQuery;

import org.apache.lucene.search.TermRangeQuery;

import org.apache.lucene.search.TopDocs;

import org.apache.lucene.search.WildcardQuery;

import org.apache.lucene.store.Directory;

import org.apache.lucene.store.FSDirectory;

import org.apache.lucene.util.Version;

 

public class Querys {

private IndexWriter writer;

protected String[] ids = { "1", "2", "3" };

protected String[] unindexed = { "Netherlands", "Italy", "China" };

protected String[] unstored = { "Amsterdam has a lot of bridge",

"Venice has lots of canals", "Amsterddam bridges are a lot" };

protected String[] text = { "Amsterdam", "Venice", "Aeijing" };

 

private Directory dir = null;

private IndexReader indexReader = null;

 

public Querys(String indexDir) throws IOException {

dir = FSDirectory.open(new File(indexDir));

this.writer = new IndexWriter(dir, new StandardAnalyzer(

Version.LUCENE_36), true, IndexWriter.MaxFieldLength.UNLIMITED);

this.writer.setInfoStream(System.out);

 

// create a index reader instance

indexReader = IndexReader.open(dir);

}

 

 

public void addDocuments() throws CorruptIndexException, IOException {

for (int i = 0; i < ids.length; i++) {

Document doc = new Document();

 

NumericField nfield = new NumericField("intID", 10);

nfield.setIntValue(i);

doc.add(nfield);

 

doc.add(new Field("id", ids[i], Field.Store.YES,

Field.Index.NOT_ANALYZED));

doc.add(new Field("country", unindexed[i], Field.Store.YES,

Field.Index.NO));

doc.add(new Field("contents", unstored[i], Field.Store.YES,

Field.Index.ANALYZED));

doc.add(new Field("city", text[i], Field.Store.YES,

Field.Index.ANALYZED));

writer.addDocument(doc);

 

}

 

System.out.println("docs = " + writer.numDocs());

 

}

 

public void index() throws CorruptIndexException, IOException {

this.addDocuments();

this.commit();

}

 

 

public void expressionQuery() throws CorruptIndexException, IOException,

ParseException {

 

IndexSearcher searcher = new IndexSearcher(this.indexReader);

 

QueryParser praser = new QueryParser(Version.LUCENE_CURRENT,

"contents", new StandardAnalyzer(Version.LUCENE_CURRENT));

 

// note

Query query = praser.parse("+bridge -Amsterdam");

System.out.println("query = " + query.toString());

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

 

}

 

 

public void termQuery(String fieldName, String q)

throws CorruptIndexException, IOException, ParseException {

// IndexSearcher searcher = new IndexSearcher(dir);

 

// build a indexSearch on a indexReader

IndexSearcher searcher = new IndexSearcher(this.indexReader);

 

Term t = new Term(fieldName, q.toLowerCase());

Query query = new TermQuery(t);

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

}

 

 

public void termRangeQuery(String fieldName, String q)

throws CorruptIndexException, IOException, ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

 

Query query = new TermRangeQuery("city", "aa", "am", true, true);

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

}

 

 

public void numericRangeQuery(int from, int to)

throws CorruptIndexException, IOException, ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

 

Query query = NumericRangeQuery.newIntRange("intID", from, to, true,true);

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

}

 

 

public void prefixQuery(String field, String prefix)

throws CorruptIndexException, IOException, ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

 

Term t = new Term(field, prefix);

Query query = new PrefixQuery(t);

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

}

 

 

public void booleanQuery() throws CorruptIndexException, IOException,

ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

 

Term t = new Term("contents", "bri");

Query query1 = new PrefixQuery(t);

 

Query query2 = NumericRangeQuery.newIntRange("intID", 1, 3, true, true);

 

// create a boolean query

BooleanQuery query = new BooleanQuery();

query.add(query1, BooleanClause.Occur.SHOULD);

query.add(query2, BooleanClause.Occur.MUST);

 

TopDocs hits = searcher.search(query, 20);

 

showResult(hits, searcher);

 

}

 

 

public void phraseQuery() throws CorruptIndexException, IOException,

ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

PhraseQuery query = new PhraseQuery();

 

// set max slop to 10

query.setSlop(10);

query.add(new Term("contents", "lot"));

query.add(new Term("contents", "bridges"));

TopDocs hits = searcher.search(query, 20);

 

showResult(hits, searcher);

 

}

 

 

public void wildCardQuery() throws CorruptIndexException, IOException,

ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

 

// use wildchard "?ridg*"

WildcardQuery query = new WildcardQuery(new Term("contents", "?ridg*"));

TopDocs hits = searcher.search(query, 20);

 

showResult(hits, searcher);

}

 

 

public void fuzzyQuery() throws CorruptIndexException, IOException,

ParseException {

IndexSearcher searcher = new IndexSearcher(dir);

 

// "Amsterdam" is similar to "Amsteedam"

FuzzyQuery query = new FuzzyQuery(new Term("contents", "Amsteedam"));

TopDocs hits = searcher.search(query, 20);

showResult(hits, searcher);

 

}

 

 

public void testReopen() throws ParseException, IOException {

 

IndexSearcher searcher = new IndexSearcher(this.indexReader);

 

QueryParser praser = new QueryParser(Version.LUCENE_CURRENT,

"contents", new StandardAnalyzer(Version.LUCENE_CURRENT));

 

// note

Query query = praser.parse("+bridge -Amsterdam");

System.out.println("query = " + query.toString());

 

TopDocs hits = searcher.search(query, 20);

 

// reopen a index and will cover current modification of index.

IndexReader newReader = indexReader.reopen();

if (indexReader != newReader) {

indexReader = newReader;

 

// if indexReader is changed , searcher must be constructed.

searcher.close();

searcher = null;

searcher = new IndexSearcher(this.indexReader);

}

 

hits = searcher.search(query, 20);

 

showResult(hits, searcher);

 

}

 

 

public void testTopDocs() throws CorruptIndexException, IOException {

IndexSearcher searcher = new IndexSearcher(dir);

 

// "Amsterdam" is similar to "Amsteedam"

FuzzyQuery query = new FuzzyQuery(new Term("contents", "Amsteedam"));

TopDocs hits = searcher.search(query, 20);

 

System.out.println("search result:");

 

for (ScoreDoc doc : hits.scoreDocs) {

// 閸欐牕绶遍崨鎴掕厬閻ㄥ嫭鏋冨锟�

Document d = searcher.doc(doc.doc);

System.out.println(d.get("contents"));

}

}

 

public void commit() throws CorruptIndexException, IOException {

this.writer.commit();

}

 

 

public void showResult(TopDocs hits, IndexSearcher searcher) {

 

try {

System.out.println("search result:");

 

for (ScoreDoc doc : hits.scoreDocs) {

// 閸欐牕绶遍崨鎴掕厬閻ㄥ嫭鏋冨锟�

Document d = searcher.doc(doc.doc);

System.out.println(d.get("contents"));

}

} catch (Exception e) {

e.printStackTrace();

}

}

 

 

public static void main(String[] args) throws IOException, ParseException {

// TODO Auto-generated method stub

Querys ci = new Querys("charpter2-1");

ci.index();

System.out.println("----------termQuery--------------");

ci.termQuery("city", "Venice");

 

System.out.println("----------termRangeQuery--------------");

ci.termRangeQuery(null, null);

 

System.out.println("----------numericRangeQuery--------------");

ci.numericRangeQuery(1, 5);

 

System.out.println("----------prefixQuery--------------");

ci.prefixQuery("contents", "bri");

 

System.out.println("----------booleanQuery--------------");

ci.booleanQuery();

 

System.out.println("----------phraseQuery--------------");

ci.phraseQuery();

 

System.out.println("----------wildCardQuery--------------");

ci.wildCardQuery();

 

System.out.println("----------fuzzyQuery--------------");

ci.fuzzyQuery();

 

System.out.println("----------expressionQuery--------------");

ci.expressionQuery();

 

System.out.println("----------test reopen--------------");

ci.testReopen();

 

}

 

}