lucene4.7 入门例子。中文分词例子。
新建一个maven项目：
在eclipse插件里new一个也可以，不是maven项目也行，最下面是我新建项目的命令。
然后把项目导入到eclipse里
打开pom.xml 添加如下的依赖：
<properties>
<lucene.version>4.7.2</lucene.version>
<mmseg4j.version>1.9.1</mmseg4j.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
<version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-queryparser</artifactId>
<version>${lucene.version}</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers-common</artifactId>
<version>${lucene.version}</version>
</dependency>
然后刷新项目，或者mvn clean install. 然后就有lucene的jar包了。项目如下：
如果不是maven项目，可以去官网上下载lucene,解压后，手动的拷贝相应的jar包，添加到项目里，jar都在文件里不太好找。
然后我去找了最新版本的庖丁解牛分词器，iK analyzer，MMseg4j这几个分词器，几经尝试，都不支持4.7的lucene.实在是很无赖啊。本来是来学习如何分词的，结果非要用过了时的lucene版本。
然后照着官网写了一些lucene的入门例子，了解了一下lucene如何使用
public class Test {
private static final String docLocation = "D:\\lucene\\docs";
private static final String indexLocation = "D:\\lucene\\index";
private static final String docLocation2 = "D:\\lucene\\otherDocs";
private static final String indexLocation2 = "D:\\lucene\\otherIndex";
public static void main(String[] args) {
// 测试中文分词
// testSeg();
// 建立索引
//testIndex();
// 测试搜索
// testSearch();
//testSearchWithParser();
//测试合并
//testMergeIndex();
//测试删除文档
//testDeleteDoc();
}
/**
* 测试中文分词
*/
private static void testSeg() {
Reader reader = null;
try {
Analyzer analyzer = new ChineseAnalyzer();
reader = new FileReader("D:\\lucene\\docs\\海贼王.txt");
TokenStream ts = analyzer.tokenStream("", reader);
ts.reset();
CharTermAttribute term = ts.getAttribute(CharTermAttribute.class);
// 遍历分词数据
while (ts.incrementToken()) {
System.out.print(term.toString() + "|");
// 我|是|要|成|为|海|贼|王|的|男|人|烧|烧|果|实|是|假|的|一|看|就|知|道|了| 这词分的真是一绝
}
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
if (reader != null) {
try {
reader.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
/**
* 测试建立索引
*/
private static void testIndex() {
final File docDir = new File(docLocation2);
if (!docDir.exists() || !docDir.canRead()) {
System.out.println("please check the path");
}
try {
Directory dir = FSDirectory.open(new File(indexLocation2));
Analyzer analyzer = new ChineseAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_47,
analyzer);
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);// 如果已经有索引，就追加
// iwc.setRAMBufferSizeMB(256.0);
IndexWriter writer = new IndexWriter(dir, iwc);
indexDocs(docDir, writer);
// writer.forceMerge(1);//如果文档基本是静态的不怎么变，可以优化一下索引，这个过程比较耗时
writer.close();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 建立索引
*
* @param docDir
* @param writer
* @throws IOException
*/
private static void indexDocs(File docDir, IndexWriter writer)
throws IOException {
if (docDir.isDirectory()) {
File[] files = docDir.listFiles();
for (File file : files) {
indexDocs(file, writer);
}
} else {
FileInputStream fis = null;
try {
fis = new FileInputStream(docDir);
} catch (FileNotFoundException e) {
return;
}
try {
Document doc = new Document();
// 索引但不存，不分词
Field fileName = new StringField("fileName", docDir.getName(),
Field.Store.YES);
doc.add(fileName);
// 索引但不存
doc.add(new LongField("lastModified", docDir.lastModified(),
Field.Store.NO));
doc.add(new TextField("content", new BufferedReader(
new InputStreamReader(fis, "UTF-8"))));
if (OpenMode.CREATE.equals(writer.getConfig().getOpenMode())) {
writer.addDocument(doc);
} else {
writer.updateDocument(
new Term("fileName", docDir.getName()), doc);
}
} finally {
fis.close();
}
}
}
/**
* term查询
*/
private static void testSearch() {
try {
IndexReader reader = DirectoryReader.open(FSDirectory
.open(new File(indexLocation)));
IndexSearcher searcher = new IndexSearcher(reader);
// Term term = new Term("fileName","海贼王.txt");
// Term term = new Term("content","海贼王");//查不出来
Term term = new Term("content", "文");// 有
Query query = new TermQuery(term);
Query query2 = new TermQuery(new Term("content", "火"));
BooleanQuery query3 = new BooleanQuery();
query3.add(query, Occur.SHOULD);
query3.add(query2, Occur.SHOULD);// 0.34144828 混淆.txt0.08536207
// 海贼王.txt0.08536207 火影忍者.txt
TopDocs top5 = searcher.search(query3, 5);
ScoreDoc[] hits = top5.scoreDocs;
for (ScoreDoc doc : hits) {
System.out.println(doc.score + " "
+ searcher.doc(doc.doc).get("fileName"));
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 用解析器查询
*/
private static void testSearchWithParser() {
try {
IndexReader reader = DirectoryReader.open(FSDirectory
.open(new File(indexLocation)));
IndexSearcher searcher = new IndexSearcher(reader);
Analyzer analyzer = new ChineseAnalyzer();
QueryParser parser = new QueryParser(Version.LUCENE_47, "content",
analyzer);
Query query = parser.parse("海贼王 火影忍者");
TopDocs top5 = searcher.search(query, 5);
ScoreDoc[] hits = top5.scoreDocs;
for (ScoreDoc doc : hits) {
System.out.println(doc.score + " "
+ searcher.doc(doc.doc).get("fileName"));
}
} catch (IOException e) {
e.printStackTrace();
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
/**
* 测试合并索引
*/
private static void testMergeIndex() {
try {
Directory dir = FSDirectory.open(new File(indexLocation));
Analyzer analyzer = new ChineseAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_47,analyzer);
IndexWriter writer = new IndexWriter(dir, iwc);
Directory dir2 = FSDirectory.open(new File(indexLocation2));
writer.addIndexes(dir2);
writer.close();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 删除一个索引
*/
private static void testDeleteDoc(){
try {
Directory dir = FSDirectory.open(new File(indexLocation));
Analyzer analyzer = new ChineseAnalyzer();
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_47,analyzer);
IndexWriter writer = new IndexWriter(dir, iwc);
Term term = new Term("fileName","文章.txt");
writer.deleteDocuments(term);
writer.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
。首先在d盘建立了一个专用目录，存了一些简单的txt文件，以文件名为id，建立了索引。还测试了一下如何合并和删除索引。
成功的话，会生成如下的索引目录：
使用旧版本的lunece 和庖丁分词
新建一个项目
public static void main(String[] args) {
try {
Analyzer analyzer = new PaodingAnalyzer();
Reader reader = new BufferedReader(new InputStreamReader(new FileInputStream(new File("D:\\lucene\\docs\\海贼王.txt")),"UTF-8"));
TokenStream stream = analyzer.tokenStream("", reader);
Token token = null;
while((token=stream.next())!=null){
System.out.println(token.termText());
}
} catch (UnsupportedEncodingException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}