Lucene自带示例精简,只留下了主要代码。以备查看
对文件夹生成索引
对索引进行查询
对文件夹生成索引
package zhch.illq.lucene;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class LuceneIndex {
static final File INDEX_DIR = new File("d:\\temp\\index");
// 主要代码 索引docDir文件夹下文档,索引文件在INDEX_DIR文件夹中
public static void main(String[] args) {
File docDir = new File("d:\\temp\\neirong");
try {
IndexWriter standardWriter = new IndexWriter(FSDirectory.open(INDEX_DIR), new StandardAnalyzer(
Version.LUCENE_CURRENT), true, IndexWriter.MaxFieldLength.LIMITED);
// 如果是索引中文内容,可以使用Paoding中文分词器
IndexWriter writer = new IndexWriter(FSDirectory.open(INDEX_DIR), new PaodingAnalyzer(), true,
IndexWriter.MaxFieldLength.LIMITED);
String[] files = docDir.list();
for (String fileStr : files) {
File file = new File(docDir, fileStr);
if (!file.isDirectory()) {
writer.addDocument(document(file));
}
}
writer.optimize();
writer.close();
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
}
}
public static Document document(File f) throws java.io.FileNotFoundException {
Document doc = new Document();
// 添加path,索引(可查询)但不切词
doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
// 添加最后修改日期
doc.add(new Field("modified", DateTools.timeToString(f.lastModified(), DateTools.Resolution.MINUTE),
Field.Store.YES, Field.Index.NOT_ANALYZED));
// 添加内容,指定一个Reader,文件内容解析但不存储,这里的Reader使用系统默认的编码读入
doc.add(new Field("contents", new FileReader(f)));
return doc;
}
}
对索引进行查询
package zhch.illq.lucene;
import java.io.BufferedReader;
import java.io.File;
import java.io.IOException;
import java.io.InputStreamReader;
import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class LuceneSearch {
/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
String index = "d:\\temp\\index";
String field = "contents";
String queries = null;
boolean raw = false;
// 要显示条数
int hitsPerPage = 10;
// searching, so read-only=true
IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)), true); // only
Searcher searcher = new IndexSearcher(reader);
Analyzer standardAnalyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
// 如果是索引中文内容,可以使用Paoding中文分词器
Analyzer analyzer = new PaodingAnalyzer();
BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
QueryParser parser = new QueryParser(field, analyzer);
while (true) {
if (queries == null) // prompt the user
System.out.println("Enter query: ");
String line = in.readLine();
if (line == null || line.length() == -1)
break;
line = line.trim();
if (line.length() == 0)
break;
Query query = parser.parse(line);
System.out.println("Searching for: " + query.toString(field));
doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null);
}
reader.close();
}
public static void doPagingSearch(BufferedReader in, Searcher searcher, Query query, int hitsPerPage, boolean raw,
boolean interactive) throws IOException {
TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, false);
searcher.search(query, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
int end, numTotalHits = collector.getTotalHits();
System.out.println(numTotalHits + " total matching documents");
int start = 0;
end = Math.min(hits.length, start + hitsPerPage);
for (int i = start; i < end; i++) {
Document doc = searcher.doc(hits[i].doc);
String path = doc.get("path");
if (path != null) {
System.out.println((i + 1) + ". " + path);
System.out.println(" modified: " + doc.get("modified"));
} else {
System.out.println((i + 1) + ". " + "No path for this document");
}
}
}
}