【发布时间】:2022-01-07 17:35:38
【问题描述】:
问题:我想按日期范围搜索图书,但要对结果进行排序。按日期范围搜索有效,但文档排序不正确(插入顺序,参见 ID?):
========== uploadDate:[-2208988800 TO 1893456000] ==========
FOUND: Book[id=1, fileName=Book1 - The beginning.pdf, uploadDate=2000-01-01T09:00:00Z]
FOUND: Book[id=2, fileName=Start Wars 1.pdf, uploadDate=1977-05-25T09:00:00Z]
FOUND: Book[id=3, fileName=Start Wars 2.pdf, uploadDate=1980-05-21T09:00:00Z]
FOUND: Book[id=4, fileName=Start Wars 3.pdf, uploadDate=1983-05-25T08:00:00Z]
FOUND: Book[id=5, fileName=The bible.pdf, uploadDate=2020-01-01T09:00:00Z]
FOUND: Book[id=6, fileName=TheUltimateDeveloperGuide.pdf, uploadDate=2021-02-16T19:00:00Z]
为了按日期对它们进行排序,我将代码更改为:
添加NumericDocValuesField:
document.add(new StoredField("uploadDate", book.uploadDate().getEpochSecond()));
document.add(new LongPoint("uploadDate", book.uploadDate().getEpochSecond()));
document.add(new NumericDocValuesField("uploadDate", book.uploadDate().getEpochSecond()));
添加Sort:
// Build the sorter to sort the documents by date
Sort sorter = new Sort();
SortField sortField = new SortField("uploadDate", SortField.Type.LONG, true);
sorter.setSort(sortField, SortField.FIELD_SCORE);
Query query = parser.parse(queryText, "");
TopDocs hits = indexSearcher.search(query, 100, sorter);
问题:我做错了什么?我需要更改什么以便文档按降序排序(2021 第一,20202 第二,2000 第三......)。看看以下问题没有帮助:Sorting lucene documents by date
我的代码:
import org.apache.lucene.document.*;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.flexible.standard.StandardQueryParser;
import org.apache.lucene.queryparser.flexible.standard.config.PointsConfig;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import java.text.DecimalFormat;
import java.time.Instant;
import java.time.LocalDateTime;
import java.time.ZoneId;
import java.util.*;
public class LuceneDocumentExample {
public static record Book(
Integer id,
String fileName,
Instant uploadDate
) {
}
private static Directory directory;
private static IndexWriter indexWriter;
public static void main(String[] arguments) throws Exception{
// Create the index
directory = new RAMDirectory();
indexWriter = new IndexWriter(new RAMDirectory(), new IndexWriterConfig(new MultiFieldAnalyzer()));
// Define some sample books
List<Book> books = Arrays.asList(
new Book(1, "Book1 - The beginning.pdf", createInstant(2000, 1, 1, 10, 0)),
new Book(2, "Start Wars 1.pdf", createInstant(1977, 5, 25, 10, 0)),
new Book(3, "Start Wars 2.pdf", createInstant(1980, 5, 21, 10, 0)),
new Book(4, "Start Wars 3.pdf", createInstant(1983, 5, 25, 10, 0)),
new Book(5, "The bible.pdf", createInstant(2020, 1, 1, 10, 0)),
new Book(6, "TheUltimateDeveloperGuide.pdf", createInstant(2021, 2, 16, 20, 0))
);
// Add the books
for (Book book : books) {
Document document = new Document();
document.add(new StringField("id", book.id().toString(), Field.Store.YES));
document.add(new StringField("fileName", book.fileName(), Field.Store.YES));
document.add(new StoredField("uploadDate", book.uploadDate().getEpochSecond()));
document.add(new LongPoint("uploadDate", book.uploadDate().getEpochSecond()));
document.add(new NumericDocValuesField("uploadDate", book.uploadDate().getEpochSecond()));
indexWriter.addDocument(document);
indexWriter.commit();
}
// Run several test queries to check the functionality
checkSearchResult("id:1", Set.of(1));
checkSearchResult("id:6", Set.of(6));
checkSearchResult("id:1 OR id:2", Set.of(1, 2));
checkSearchResult("id:1 AND id:2", Set.of());
checkSearchResult("fileName:TheUltimateDeveloperGuide.pdf", Set.of(6));
checkSearchResult("id:6 fileName:TheUltimateDeveloperGuide.pdf", Set.of(6));
checkSearchResult("uploadDate:[" + createInstant(2000, 1, 1, 8, 0).getEpochSecond() + " TO " + createInstant(2000, 1, 1, 12, 0).getEpochSecond() + "]", Set.of(1));
checkSearchResult("uploadDate:[" + createInstant(1977, 1, 1, 1, 0).getEpochSecond() + " TO " + createInstant(1983, 5, 26, 1, 0).getEpochSecond() + "]", Set.of(2, 3, 4));
checkSearchResult("uploadDate:[" + createInstant(1900, 1, 1, 1, 0).getEpochSecond() + " TO " + createInstant(2030, 1, 1, 1, 0).getEpochSecond() + "]", Set.of(1, 2, 3, 4, 5, 6));
checkSearchResult("id:1 uploadDate:[" + createInstant(2000, 1, 1, 8, 0).getEpochSecond() + " TO " + createInstant(2000, 1, 1, 12, 0).getEpochSecond() + "]", Set.of(1));
// Close the index
indexWriter.close();
directory.close();
}
public static List<Book> searchDocuments(String queryText) {
// Create the reader
try (IndexReader indexReader = DirectoryReader.open(indexWriter)) {
IndexSearcher indexSearcher = new IndexSearcher(indexReader);
StandardQueryParser parser = new StandardQueryParser();
parser.setAnalyzer(indexWriter.getAnalyzer());
Map<String, PointsConfig> pointsConfigMap = new HashMap<>();
pointsConfigMap.put("uploadDate", new PointsConfig(new DecimalFormat(), Long.class));
parser.setPointsConfigMap(pointsConfigMap);
// Build the sorter to sort the documents by date
Sort sorter = new Sort();
SortField sortField = new SortField("uploadDate", SortField.Type.LONG, true);
sorter.setSort(sortField, SortField.FIELD_SCORE);
Query query = parser.parse(queryText, "");
TopDocs hits = indexSearcher.search(query, 100, sorter);
List<Book> books = new ArrayList<>();
for (int i = 0; i < hits.scoreDocs.length; i++) {
int docId = hits.scoreDocs[i].doc;
Document document = indexSearcher.doc(docId);
Integer id = Integer.parseInt(document.get("id"));
String fileName = document.get("fileName");
Instant uploadDate = Instant.ofEpochSecond(Long.parseLong(document.get("uploadDate")));
books.add(new Book(id, fileName, uploadDate));
}
return books;
} catch (Exception exception) {
throw new RuntimeException("Unable to execute query " + queryText + ": " + exception.getMessage(), exception);
}
}
public static void checkSearchResult(String queryText, Set<Integer> expectedIds) {
System.out.println("========== " + queryText + " ==========");
List<Book> books = searchDocuments(queryText);
if (!expectedIds.isEmpty()) {
for (Integer expectedId : expectedIds) {
Optional<Book> optionalBook = books.stream().filter(book -> expectedId.equals(book.id())).findAny();
if (optionalBook.isPresent()) {
System.out.println("FOUND: " + optionalBook.get());
} else {
System.out.println("MISSING: " + expectedId);
}
}
} else {
System.out.println("NONE");
}
}
private static Instant createInstant(Integer year, Integer month, Integer day, Integer hour, Integer minute) {
LocalDateTime dateTime = LocalDateTime.of(year, month, day, hour, minute);
return dateTime.atZone(ZoneId.of("Europe/Zurich")).toInstant();
}
}
【问题讨论】: