Lucene知识小总结8:索引查询
对于IndexReader而言，反复使用Index.open打开会有很大的开销，所以一般在整个程序的生命周期中只会打开一个IndexReader,通过这个IndexReader来创建不同的IndexSearcher,如果使用单例模式，可能出现的问题有：
1、当使用Writer修改了索引之后不会更新信息，所以需要使用IndexReader.openIfChange方法操作
如果IndexWriter在创建完成之后，没有关闭，需要进行commit操作之后才能提交
public IndexSearcher getSearcher() {
try {
if(reader==null) {
reader = IndexReader.open(directory);
} else {
IndexReader tr = IndexReader.openIfChanged(reader);
if(tr!=null) {
reader.close();
reader = tr;
}
}
return new IndexSearcher(reader);
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return null;
}
2、TermQuery查询
public void searchByTerm(String field,String name,int num) {
try {
IndexSearcher searcher = getSearcher();
Query query = new TermQuery(new Term(field,name));
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByTerm() {
su.searchByTerm("content","i",3);
}
3、TermRangeQuery查询
public void searchByTermRange(String field,String start,String end,int num) {
try {
IndexSearcher searcher = getSearcher();
Query query = new TermRangeQuery(field,start,end,true, true);
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByTermRange() {
//查询name以a开头和s结尾的
su.searchByTermRange("name","a","s",10);
//由于attachs是数字类型，使用TermRange无法查询
//su.searchByTermRange("attach","2","10", 5);
}
4、NumericRangeQuery查询
public void searchByNumricRange(String field,int start,int end,int num) {
try {
IndexSearcher searcher = getSearcher();
Query query = NumericRangeQuery.newIntRange(field,start, end,true,true);
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByNumRange() {
su.searchByNumricRange("attach",2,10, 5);
}
5、PrefixQuery查询
public void searchByPrefix(String field,String value,int num) {
try {
IndexSearcher searcher = getSearcher();
Query query = new PrefixQuery(new Term(field,value));
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByPrefix() {
su.searchByPrefix("content", "s", 10);
}
注：我们在添加索引的时候的content是Field.Store.NO的
doc.add(new Field("content",contents[i],Field.Store.NO,Field.Index.ANALYZED));
6、WildcardQuery查询
public void searchByWildcard(String field,String value,int num) {
try {
IndexSearcher searcher = getSearcher();
//在传入的value中可以使用通配符:?和*,?表示匹配一个字符，*表示匹配任意多个字符
Query query = new WildcardQuery(new Term(field,value));
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByWildcard() {
//匹配@itat.org结尾的所有字符
su.searchByWildcard("email", "*@itat.org", 10);
System.out.println("=======================================");
//匹配j开头的有三个字符的name
su.searchByWildcard("name", "j???", 10);
}
7、BooleanQuery查询
public void searchByBoolean(int num) {
try {
IndexSearcher searcher = getSearcher();
BooleanQuery query = new BooleanQuery();
/*
* BooleanQuery可以连接多个子查询
* Occur.MUST表示必须出现
* Occur.SHOULD表示可以出现
* Occur.MUSE_NOT表示不能出现
*/
query.add(new TermQuery(new Term("name","zhangsan")), Occur.MUST_NOT);
query.add(new TermQuery(new Term("content","game")),Occur.SHOULD);
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByBoolean() {
su.searchByBoolean(10);
}
将query.add(new TermQuery(new Term("name","zhangsan")), Occur.MUST_NOT);设置为query.add(new TermQuery(new Term("name","zhangsan")), Occur.SHOULD);
8、PhraseQuery查询
private String[] contents = {
"welcome to visited the space,I like book",
"hello boy, I like pingpeng ball",
"my name is cc I like game",
"I like football",
"I like football and I like basketball too",
"I like movie and swim"
};
public void searchByPhrase(int num) {
try {
IndexSearcher searcher = getSearcher();
PhraseQuery query = new PhraseQuery();
query.setSlop(3);
query.add(new Term("content","pingpeng"));
//第一个Term
query.add(new Term("content","i"));
//产生距离之后的第二个Term
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByPhrase() {
su.searchByPhrase(10);
}
9、FuzzyQuery查询
public void searchByFuzzy(int num) {
try {
IndexSearcher searcher = getSearcher();
FuzzyQuery query = new FuzzyQuery(new Term("name","mase"),0.4f,0);
System.out.println(query.getPrefixLength());
System.out.println(query.getMinSimilarity());
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date"));
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByFuzzy() {
su.searchByFuzzy(10);
}
10、QueryParse查询
public void searchByQueryParse(Query query,int num) {
try {
IndexSearcher searcher = getSearcher();
TopDocs tds = searcher.search(query, num);
System.out.println("一共查询了:"+tds.totalHits);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(doc.get("id")+"---->"+
doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
doc.get("attach")+","+doc.get("date")+"=="+sd.score);
}
searcher.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//测试方法
@Test
public void searchByQueryParse() throws ParseException {
//1、创建QueryParser对象,默认搜索域为content
QueryParser parser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
//改变空格的默认操作符，以下可以改成AND
//parser.setDefaultOperator(Operator.AND);
//开启第一个字符的通配符匹配，默认关闭因为效率不高
parser.setAllowLeadingWildcard(true);
//搜索content中包含有like的
Query query = parser.parse("like");
//有basketball或者football的，空格默认就是OR
query = parser.parse("basketball football");
//改变搜索域为name为mike
//query = parser.parse("content:like");
//同样可以使用*和?来进行通配符匹配
// query = parser.parse("name:j*");
//通配符默认不能放在首位
// query = parser.parse("email:*@itat.org");
//匹配name中没有mike但是content中必须有football的，+和-要放置到域说明前面
query = parser.parse("- name:mike + like");
//匹配一个区间，注意:TO必须是大写
//query = parser.parse("id:[1 TO 6]");
//闭区间匹配只会匹配到2
//query = parser.parse("id:{1 TO 3}");
//完全匹配I Like Football的
//query = parser.parse("\"I like football\"");
//匹配I 和football之间有一个单词距离的
//query = parser.parse("\"I football\"~1");
//模糊查询
//query = parser.parse("name:make~");
//没有办法匹配数字范围（自己扩展Parser）
//query = parser.parse("attach:[2 TO 10]");
su.searchByQueryParse(query, 10);
}
11、分页查询
/**
* 根据页码和分页大小获取上一次的最后一个ScoreDoc
*/
private ScoreDoc getLastScoreDoc(int pageIndex,int pageSize,Query query,IndexSearcher searcher) throws IOException {
if(pageIndex==1)return null;//如果是第一页就返回空
int num = pageSize*(pageIndex-1);//获取上一页的数量
TopDocs tds = searcher.search(query, num);
return tds.scoreDocs[num-1];
}
public void searchPageByAfter(String query,int pageIndex,int pageSize) {
try {
Directory dir = FileIndexUtils.getDirectory();
IndexSearcher searcher = getSearcher(dir);
QueryParser parser = new QueryParser(Version.LUCENE_35,"content",new StandardAnalyzer(Version.LUCENE_35));
Query q = parser.parse(query);
//先获取上一页的最后一个元素
ScoreDoc lastSd = getLastScoreDoc(pageIndex, pageSize, q, searcher);
//通过最后一个元素搜索下页的pageSize个元素
TopDocs tds = searcher.searchAfter(lastSd,q, pageSize);
for(ScoreDoc sd:tds.scoreDocs) {
Document doc = searcher.doc(sd.doc);
System.out.println(sd.doc+":"+doc.get("path")+"-->"+doc.get("filename"));
}
searcher.close();
} catch (org.apache.lucene.queryParser.ParseException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
@Test
public void testSearchPage02() {
for(int i=1;i<7;i++){
su.searchPageByAfter("java", i,10);
System.out.println("==========================================");
}
}
