序
说lucene是Java界的检索之王,当之无愧。近年来elasticsearch的火爆登场,包括之前的solr及solr cloud,其底层都是lucene。简单了解lucene,对使用elasticsearch还是有点帮助的。本文就简单过一下其简单的api使用。
添加依赖
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
<version>4.6.1</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-common</artifactId>
<version>4.6.1</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-queryparser</artifactId>
<version>4.6.1</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-codecs</artifactId>
<version>4.6.1</version>
</dependency>
索引与检索
创建索引
File indexDir = new File(this.getClass().getClassLoader().getResource("").getFile());
@Test
public void createIndex() throws IOException {
// Directory index = new RAMDirectory();
Directory index = FSDirectory.open(indexDir);
// 0. Specify the analyzer for tokenizing text.
// The same analyzer should be used for indexing and searching
StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);
IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, analyzer);
// 1. create the index
IndexWriter w = new IndexWriter(index, config);
addDoc(w, "Lucene in Action", "193398817");
addDoc(w, "Lucene for Dummies", "55320055Z");
addDoc(w, "Managing Gigabytes", "55063554A");
addDoc(w, "The Art of Computer Science", "9900333X");
w.close();
}
private void addDoc(IndexWriter w, String title, String isbn) throws IOException {
Document doc = new Document();
doc.add(new TextField("title", title, Field.Store.YES));
// use a string field for isbn because we don't want it tokenized
doc.add(new StringField("isbn", isbn, Field.Store.YES));
w.addDocument(doc);
}
检索
@Test
public void search() throws IOException {
// 2. query
String querystr = "lucene";
// the "title" arg specifies the default field to use
// when no field is explicitly specified in the query.
Query q = null;
try {
StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);
q = new QueryParser(Version.LUCENE_46,"title", analyzer).parse(querystr);
} catch (Exception e) {
e.printStackTrace();
}
// 3. search
int hitsPerPage = 10;
Directory index = FSDirectory.open(indexDir);
IndexReader reader = DirectoryReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
searcher.search(q, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
// 4. display results
System.out.println("Found " + hits.length + " hits.");
for (int i = 0; i < hits.length; ++i) {
int docId = hits[i].doc;
Document d = searcher.doc(docId);
System.out.println((i + 1) + ". " + d.get("isbn") + "\t" + d.get("title"));
}
// reader can only be closed when there
// is no need to access the documents any more.
reader.close();
}
分词
对于搜索来说,分词出现在两个地方,一个是对用户输入的关键词进行分词,另一个是在索引文档时对文档内容的分词。两个分词最好一样,这样才可以更好地匹配出来。
@Test
public void cutWords() throws IOException {
// StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);
// CJKAnalyzer analyzer = new CJKAnalyzer(Version.LUCENE_46);
SimpleAnalyzer analyzer = new SimpleAnalyzer();
String text = "Spark是当前最流行的开源大数据内存计算框架,采用Scala语言实现,由UC伯克利大学AMPLab实验室开发并于2010年开源。";
TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(text));
CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
try {
tokenStream.reset();
while (tokenStream.incrementToken()) {
System.out.println(charTermAttribute.toString());
}
tokenStream.end();
} finally {
tokenStream.close();
analyzer.close();
}
}
输出
spark
是
当前
最
流行
的
开源
大数
据
内存
计算
框架
采用
scala
语言
实现
由
uc
伯克利
大学
amplab
实验室
开发
并于
2010
年
开源
本工程github