Lucene 分页排序

package org.digdata.swustoj.sort; import org.apache.lucene.search.Sort; import org.apache.lucene.search.SortField; /** * Created by wwhhff11 on 16-8-15. */ public class LuceneSortFactory { /** * 获取排序对象 * 按照某个字段进行排序 * * @param field * @return */ public static Sort getSortByField(String field, Boolean desc) { Sort sort = new Sort(); sort.setSort(new SortField(field, SortField.Type.DOC, desc)); return sort; } } package org.digdata.swustoj.sort; import org.apache.lucene.search.Sort; import org.apache.lucene.search.SortField; /** * Created by wwhhff11 on 16-8-15. */ public class LuceneSortFactory { /** * 获取排序对象 * 按照某个字段进行排序 * * @param field * @return */ public static Sort getSortByField(String field, Boolean desc) { Sort sort = new Sort(); sort.setSort(new SortField(field, SortField.Type.DOC, desc)); return sort; } } package org.digdata.swustoj.lucene; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.IntField; import org.apache.lucene.document.TextField; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.Term; import org.apache.lucene.index.TrackingIndexWriter; import org.apache.lucene.search.*; import org.apache.lucene.store.Directory; import org.apache.lucene.store.SimpleFSDirectory; import org.digdata.swustoj.sort.LuceneSortFactory; import org.digdata.swustoj.util.PropertiesUtil; import javax.validation.constraints.NotNull; import java.io.IOException; import java.nio.file.Paths; import java.util.ArrayList; import java.util.HashMap; import java.util.List; import java.util.Map; /** * Created by hongfei.whf on 2016/8/15. */ public class LuceneTemplate { public static final int DEFAULT_MAXX_ROWS = 2000; public static final int DEFAULT_MAXX_PAGE = 20; public static final int DEFAULT_MAXX_PER_PAGE = 20; // 配置文件名 private final String fileName = "lucene-config.properties"; // 索引目录 private Directory directory = null; // 写索引配置文件 private IndexWriterConfig cfg = null; // 分词器 private Analyzer analyzer = null; // 写索引 private IndexWriter writer = null; private TrackingIndexWriter trackingIndexWriter = null; private ControlledRealTimeReopenThread controlledRealTimeReopenThread = null; private SearcherManager searcherManager = null; /** * 构造函数 */ public LuceneTemplate() { try { String indexPath = PropertiesUtil.getPropertyByName(fileName, "index.path"); directory = new SimpleFSDirectory(Paths.get(indexPath)); analyzer = new SmartChineseAnalyzer(); cfg = new IndexWriterConfig(analyzer); init(); } catch (IOException e) { e.printStackTrace(); } } /** * Getter * * @return */ public IndexWriter getWriter() { return writer; } /** * 初始化 * * @return */ public void init() throws IOException { if (writer == null) { writer = openIndexWriter(); } searcherManager = new SearcherManager(writer, false, new SearcherFactory()); trackingIndexWriter = new TrackingIndexWriter(writer); controlledRealTimeReopenThread = new ControlledRealTimeReopenThread<IndexSearcher>( trackingIndexWriter, searcherManager, 5.0, 0.025); controlledRealTimeReopenThread.setDaemon(true);//设为后台进程 controlledRealTimeReopenThread.start(); } /** * 销毁 */ public void destory() { try { writer.commit(); writer.close(); directory.close(); } catch (IOException e) { e.printStackTrace(); } } /** * 开启写索引 * * @return */ private IndexWriter openIndexWriter() throws IOException { if (writer != null) { return writer; } return writer = new IndexWriter(directory, cfg); } /** * 获得Searcher * * @return */ public IndexSearcher openIndexSearcher() throws Exception { searcherManager.maybeRefresh(); return searcherManager.acquire(); } /** * 释放Searcher * * @param searcher * @return */ public Boolean releaseIndexSearcher(IndexSearcher searcher) throws Exception { try { searcherManager.release(searcher); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 向索引增加文档 * * @param document * @return */ public Boolean addDocumentWithCommit(Document document) { try { writer.addDocument(document); writer.commit(); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 向索引增加文档 * * @param document * @return */ public Boolean addDocumentNotCommit(Document document) { try { writer.addDocument(document); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 向索引增加文档 * * @param documents * @return */ public Boolean addDocumentWithCommit(List<Document> documents) { try { writer.addDocuments(documents); writer.commit(); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 向索引增加文档 * * @param documents * @return */ public Boolean addDocumentNotCommit(List<Document> documents) { try { writer.addDocuments(documents); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 提交变更 * * @return */ public Boolean commit() { try { writer.commit(); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 清空 * * @return */ public Boolean deleteAll() { try { writer.deleteAll(); writer.commit(); } catch (IOException e) { e.printStackTrace(); return false; } return true; } /** * 查询 * * @param searcher * @param params * @param rows * @return * @throws IOException */ public List<Document> query(IndexSearcher searcher, Map<String, Object> params, Integer rows) throws IOException { if (rows == null) { rows = DEFAULT_MAXX_ROWS; } Query query = getMulitConditionQuery(params); TopDocs topDocs = searcher.search(query, rows); ScoreDoc[] hits = topDocs.scoreDocs; List<Document> list = new ArrayList<>(); for (int i = 0; i < hits.length; i++) { ScoreDoc hit = hits[i]; Document hitDoc = searcher.doc(hit.doc); list.add(hitDoc); } return list; } /** * 分页查询 * * @param searcher * @param params * @param sort * @param page * @param rows * @return * @throws Exception */ public List<Document> queryByPage(IndexSearcher searcher, Map<String, Object> params, Sort sort, @NotNull Integer page, @NotNull Integer rows) throws Exception { if (page <= 0) { page = 1; } if (page > DEFAULT_MAXX_PAGE) { page = DEFAULT_MAXX_PAGE; } if (rows > DEFAULT_MAXX_PER_PAGE) { rows = DEFAULT_MAXX_PER_PAGE; } Query query = getMulitConditionQuery(params); TopDocs topDocs = searcher.search(query, DEFAULT_MAXX_ROWS, sort); ScoreDoc[] hits = topDocs.scoreDocs; Integer start = (page - 1) * rows; if (start > topDocs.totalHits) { throw new Exception("totalHits is less than start"); } Integer end = Math.min(start + rows, topDocs.totalHits); List<Document> list = new ArrayList<>(); for (int i = start; i < end; i++) { ScoreDoc hit = hits[i]; Document hitDoc = searcher.doc(hit.doc); list.add(hitDoc); } return list; } /** * 获取多条件查询 * * @param params * @return */ private BooleanQuery getMulitConditionQuery(Map<String, Object> params) { BooleanQuery booleanQuery = new BooleanQuery(); for (Map.Entry<String, Object> entry : params.entrySet()) { Object value = entry.getValue(); Query query = null; if (value.getClass() == String.class) { query = new TermQuery(new Term(entry.getKey(), value.toString())); } else if (value.getClass() == Integer.class) { query = NumericRangeQuery.newIntRange(entry.getKey(), (Integer) value, (Integer) value, true, true); } booleanQuery.add(query, BooleanClause.Occur.MUST); } return booleanQuery; } /** * 测试入口 * * @param args */ public static void main(String[] args) throws Exception { LuceneTemplate template = new LuceneTemplate(); IndexWriter writer = template.getWriter(); template.deleteAll(); for (int i = 0; i < 10; i++) { Document doc = new Document(); doc.add(new IntField("id", i, IntField.TYPE_STORED)); doc.add(new IntField("user_id", 2, IntField.TYPE_NOT_STORED)); doc.add(new IntField("compiler_id", 3, IntField.TYPE_NOT_STORED)); doc.add(new IntField("problem_id", 4, IntField.TYPE_NOT_STORED)); doc.add(new IntField("status", i, IntField.TYPE_NOT_STORED)); doc.add(new IntField("contest_id", 6, IntField.TYPE_NOT_STORED)); doc.add(new TextField("username", "wwhhff11", Field.Store.NO)); template.addDocumentNotCommit(doc); } template.commit(); IndexSearcher searcher = template.openIndexSearcher(); Map<String, Object> params = new HashMap<>(); params.put("problem_id", 4); params.put("username", "wwhhff"); Sort sort = LuceneSortFactory.getSortByField("id", true); List<Document> docs = template.queryByPage(searcher, params, sort, 1, 5); for (Document document : docs) { System.out.println(document.get("id")); } template.releaseIndexSearcher(searcher); template.destory(); } }