我是 Lucene 的新手。我有两个文档,我想对名为“关键字”的文档字段进行完全匹配(该字段可能在文档中出现多次)。
第一个文档包含关键字“注释很酷”。第二个文档包含关键字“注释也很酷”。当我搜索“注释很酷”时,如何构建查询以便只找到第一个文档?
我读了一些关于“StringField”的东西,它没有被标记化。如果我在方法“addDoc”中将“关键字”字段从“TextField”更改为“StringField”,则将找不到任何内容。
这是我的代码:
private IndexWriter writer;
public void lucene() throws IOException, ParseException {
// Build the index
StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_42);
Directory index = new RAMDirectory();
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_42,
analyzer);
this.writer = new IndexWriter(index, config);
// Add documents to the index
addDoc("Spring", new String[] { "Java", "JSP",
"Annotation is cool" });
addDoc("Java", new String[] { "Oracle", "Annotation is cool too" });
writer.close();
// Search the index
IndexReader reader = DirectoryReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
BooleanQuery qry = new BooleanQuery();
qry.add(new TermQuery(new Term("keyword", "\"Annotation is cool\"")), BooleanClause.Occur.MUST);
System.out.println(qry.toString());
Query q = new QueryParser(Version.LUCENE_42, "title", analyzer).parse(qry.toString());
int hitsPerPage = 10;
TopScoreDocCollector collector = TopScoreDocCollector.create(
hitsPerPage, true);
searcher.search(q, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
for (int i = 0; i < hits.length; ++i) {
int docId = hits[i].doc;
Document doc = searcher.doc(docId);
System.out.println((i + 1) + ". \t" + doc.get("title"));
}
reader.close();
}
private void addDoc(String title, String[] keywords) throws IOException {
// Create new document
Document doc = new Document();
// Add title
doc.add(new TextField("title", title, Field.Store.YES));
// Add keywords
for (int i = 0; i < keywords.length; i++) {
doc.add(new TextField("keyword", keywords[i], Field.Store.YES));
}
// Add document to index
this.writer.addDocument(doc);
}