I.Sorting search results
在Lucene中有两种特别的类型是用来排序的:Score和Index order
要排序结果 可以使用IndexSearcher的重载serach函数,提供一个Sort参数.看个例子.SortingExample.java
01 package lia.advsearching;
02
03 import org.apache.commons.lang.StringUtils;
04 import org.apache.lucene.document.Document;
05 import org.apache.lucene.index.Term;
06 import org.apache.lucene.search.Hits;
07 import org.apache.lucene.search.IndexSearcher;
08 import org.apache.lucene.search.Query;
09 import org.apache.lucene.search.RangeQuery;
10 import org.apache.lucene.search.Sort;
11 import org.apache.lucene.search.SortField;
12 import org.apache.lucene.store.Directory;
13 import org.apache.lucene.store.FSDirectory;
14
15 import java.io.IOException;
16 import java.text.DecimalFormat;
17
18 public class SortingExample {
19 private Directory directory;
20
21 public SortingExample(Directory directory) {
22 this.directory = directory;
23 }
24 // 显示搜索结果
25 public void displayHits(Query query, Sort sort)
26 throws IOException {
27 IndexSearcher searcher = new IndexSearcher(directory);
28
29 Hits hits = searcher.search(query, sort); // 安sort 来排序搜索结果
30
31 System.out.println("\nResults for: " +
32 query.toString() + " sorted by " + sort); // 打印query 和sort
33
34 System.out.println(StringUtils.rightPad("Title", 30) + // 使用StringUtils(来自Apache commons)打印结果
35 StringUtils.rightPad("pubmonth", 10) +
36 StringUtils.center("id", 4) +
37 StringUtils.center("score", 15));
38
39 DecimalFormat scoreFormatter = new DecimalFormat("0.######");
40 for (int i = 0; i < hits.length(); i++) { // 打印结果
41 Document doc = hits.doc(i);
42 System.out.println(
43 StringUtils.rightPad(
44 StringUtils.abbreviate(doc.get("title"), 29), 30) +
45 StringUtils.rightPad(doc.get("pubmonth"), 10) +
46 StringUtils.center("" + hits.id(i), 4) +
47 StringUtils.leftPad(
48 scoreFormatter.format(hits.score(i)), 12));
49 System.out.println(" " + doc.get("category"));
50 // System.out.println(searcher.explain(query, hits.id(i)));
51 }
52
53 searcher.close();
54 }
55
56 public static void main(String[] args) throws Exception {
57 Term earliest = new Term("pubmonth", "190001");
58 Term latest = new Term("pubmonth", "201012");
59 RangeQuery allBooks = new RangeQuery(earliest, latest, true); // query
60
61 String indexDir = System.getProperty("index.dir"); // index的目录
62
63 FSDirectory directory =
64 FSDirectory.getDirectory(indexDir, false);
65 SortingExample example = new SortingExample(directory);
66
67 example.displayHits(allBooks, Sort.RELEVANCE); // 使用Lucene默认的排序
68
69 example.displayHits(allBooks, Sort.INDEXORDER); // 根据IndexOrder排序
70
71 example.displayHits(allBooks, new Sort("category")); // 根据category 排序
72
73 example.displayHits(allBooks, new Sort("pubmonth", true)); // 根据pubmonth 排序
74
75 example.displayHits(allBooks,
76 new Sort(new SortField[]{
77 new SortField("category"),
78 SortField.FIELD_SCORE,
79 new SortField("pubmonth", SortField.INT, true)
80 })); ///
81
82
83 example.displayHits(allBooks, new Sort(new SortField[] {SortField.FIELD_SCORE, new SortField("category")}));
84 }
85 }
当sort 参数是null ,new Sort(),和Sort.RELEVANCE 时,使用的是Lucene的默认排序(按照Relevance的递减排序), 默认搜索的结果如下:
先按照Score递减排序 如果Score相同则按照Docnum 递增排序.
If the order documents were indexed is relevant, you can use Sort.INDEXORDER.
下面是其输出结果:(安装ID来排序)
要利用Field排序,该field要满足第二章排序(参考我的Blog上的内容)的要求. 下面是使用category field的输出.
默认的field排序是按照自然排序,利用Sort的重载函数,提供一个reverse参数可以改变顺序.结果如下:
example.displayHits(allBooks, new Sort("pubmonth", true)); 提供了true参数.
还可以根据多个Field排序. 用法如下:
example.displayHits(allBooks,
new Sort(new SortField[]{
new SortField("category"),
SortField.FIELD_SCORE,
new SortField("pubmonth", SortField.INT, true)
}));
margin: 5pt 6
