Lucene3.6 之 Filter

1、TermRangeFilter

A Filter that restricts search results to a range of term values in a given field. 

This filter matches the documents looking for terms that fall into the supplied range according to Byte.compareTo(Byte), It is not intended for numerical ranges; use NumericRangeFilter instead. 

If you construct a large number of range filters with different ranges but on the same field, FieldCacheRangeFilter may have significantly better performance. 

示例代码

[java]   view plain copy

1. @Test  
2.     public void testTermRangeFilter(){  
3.         try {  
4.             String path = "D:\\LuceneEx\\day01";  
5.             String keyword = "android";  
6.             File file = new File(path);  
7.             Directory mdDirectory = FSDirectory.open(file);  
8.             // 使用 商业分词器  
9.             Analyzer mAnalyzer = new IKAnalyzer();  
10.   
11.             IndexReader reader = IndexReader.open(mdDirectory);  
12.   
13.             IndexSearcher searcher = new IndexSearcher(reader);  
14.   
15.             String[] fields = { "title", "category" }; // (在多个Filed中搜索)  
16.             QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_36,  
17.                     fields, mAnalyzer);  
18.             Query query = parser.parse(keyword);  
19.               
20.             //查询publishTime范围在2011-09 - 2012-06之间的记录  
21.             Filter filter = new TermRangeFilter("publishTime", "2011-09", "2012-06", true, true);  
22.               
23.             TopDocs tops = searcher.search(query, filter, 100);  
24.   
25.             int count = tops.totalHits;  
26.   
27.             System.out.println("totalHits=" + count);  
28.   
29.             ScoreDoc[] docs = tops.scoreDocs;  
30.   
31.             for (int i = 0; i < docs.length; i++) {  
32.                   
33.                 Document doc = searcher.doc(docs[i].doc);  
34.   
35.                 float score = docs[i].score;  
36.                   
37.                 int id = Integer.parseInt(doc.get("id"));  
38.                 String title = doc.get("title");  
39.                 String author = doc.get("author");  
40.                 String publishTime = doc.get("publishTime");  
41.                 String source = doc.get("source");  
42.                 String category = doc.get("category");  
43.                 float reputation = Float.parseFloat(doc.get("reputation"));  
44.   
45.                 System.out.println(id + "\t" + title + "\t" + author + "\t"  
46.                         + publishTime + "\t" + source + "\t" + category + "\t"  
47.                         + reputation+"\t"+score);  
48.             }  
49.   
50.             reader.close();  
51.             searcher.close();  
52.   
53.         } catch (CorruptIndexException e) {  
54.             e.printStackTrace();  
55.         } catch (IOException e) {  
56.             e.printStackTrace();  
57.         } catch (ParseException e) {  
58.             e.printStackTrace();  
59.         }  
60.     }  

2、NumericRangeFilter

A Filter that only accepts numeric values within a specified range. To use this, you must first index the numeric values using IntField, FloatField, LongField or DoubleField (expert: NumericTokenStream). 

示例代码

1. @Test  
2.     public void testNumericRangeFilter(){  
3.         try {  
4.             String path = "D:\\LuceneEx\\day02";  
5.             String keyword = "android";  
6.             File file = new File(path);  
7.             Directory mdDirectory = FSDirectory.open(file);  
8.             // 使用 商业分词器  
9.             Analyzer mAnalyzer = new IKAnalyzer();  
10.   
11.             IndexReader reader = IndexReader.open(mdDirectory);  
12.   
13.             IndexSearcher searcher = new IndexSearcher(reader);  
14.   
15.             String[] fields = { "title", "category" }; // (在多个Filed中搜索)  
16.             QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_36,  
17.                     fields, mAnalyzer);  
18.             Query query = parser.parse(keyword);  
19.               
20.             //过滤 reputation 在9.0f到 9.8 分之间 的记录  
21.             Filter filter = NumericRangeFilter.newFloatRange("reputation", 9.0f, 9.8f, true, true);  
22.               
23.             TopDocs tops = searcher.search(query, filter, 100);  
24.   
25.             int count = tops.totalHits;  
26.   
27.             System.out.println("totalHits=" + count);  
28.   
29.             ScoreDoc[] docs = tops.scoreDocs;  
30.   
31.             for (int i = 0; i < docs.length; i++) {  
32.                   
33.                 Document doc = searcher.doc(docs[i].doc);  
34.   
35.                 float score = docs[i].score;  
36.                   
37.                 int id = Integer.parseInt(doc.get("id"));  
38.                 String title = doc.get("title");  
39.                 String author = doc.get("author");  
40.                 String publishTime = doc.get("publishTime");  
41.                 String source = doc.get("source");  
42.                 String category = doc.get("category");  
43.                 float reputation = Float.parseFloat(doc.get("reputation"));  
44.   
45.                 System.out.println(id + "\t" + title + "\t" + author + "\t"  
46.                         + publishTime + "\t" + source + "\t" + category + "\t"  
47.                         + reputation+"\t"+score);  
48.             }  
49.   
50.             reader.close();  
51.             searcher.close();  
52.   
53.         } catch (CorruptIndexException e) {  
54.             e.printStackTrace();  
55.         } catch (IOException e) {  
56.             e.printStackTrace();  
57.         } catch (ParseException e) {  
58.             e.printStackTrace();  
59.         }  
60.     }