操作lucene索引的工具類

jopen 10年前發布 | 20K 次閱讀 Lucene 搜索引擎
public class OperatorIndex {
public static final String INDEX_PATH = "D:/indexDir";
// 創建分詞器
private Analyzer analyzer = null;
// 索引保存目錄
private File indexFile = null;
// 目錄對象
private Directory directory = null;
// 創建indexWriterConfig 只能實例化一次用一次
private IndexWriterConfig indexWriterConfig = null;
SimpleDateFormat simpleDateFormat;
private IndexSearcher indexSearcher;
public void init() throws IOException {
analyzer = new IKAnalyzer();
indexFile = new File(INDEX_PATH);
directory = FSDirectory.open(indexFile);
simpleDateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
System.out.println("##初始化完成##");
}
// 數據庫中需要建立索引的比表封裝成Document對象
public Document createDocument(Article article) {
Document document = new Document();
document.add(new TextField("id", article.getId() + "", Field.Store.YES));
document.add(new TextField("title", article.getTitle(), Field.Store.YES));
document.add(new TextField("content", article.getContent(),
Field.Store.YES));
return document;
}
// 獲得日期
public String getDate() {
return simpleDateFormat.format(new Date());
}
// 查詢所有索引
public void openIndexFile() throws IOException {
System.out.println("讀取索引開始...");
IndexReader indexReader = IndexReader.open(directory);
// 獲取索引個數
int maxDoc = indexReader.maxDoc();
System.out.println("maxDoc:" + maxDoc);
Article article = null;
for (int i = 0; i < maxDoc; i++) {
Document document = indexReader.document(i);
article = new Article();
if (document.get("id") == null) {
System.out.println("id 為空");
}
article.setId(Integer.parseInt(document.get("id")));
article.setTitle(document.get("title"));
article.setContent(document.get("content"));
System.out.println(article);
}
indexReader.close();
System.out.println("讀取索引結束");
}
// 創建索引
public void createIndex(Article article) throws IOException {
indexWriterConfig = new IndexWriterConfig(Version.LATEST, analyzer);
IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig);
// 創建索引前刪除以前的索引
// indexWriter.deleteAll();
Document createDocument = createDocument(article);
indexWriter.addDocument(createDocument);
// indexWriter.commit();
indexWriter.close();
System.out.println("[" + getDate() + "]" + "lucene寫入索引到" + "["

indexFile.getAbsolutePath() + "]" + "成功");
}

// 批量創建索引
public void createIndexes(List<Article> articles) throws IOException {
// indexWriterConfig = new IndexWriterConfig(Version.LATEST, analyzer);
// IndexWriter indexWriter = new IndexWriter(directory,
// indexWriterConfig);
// indexWriter.deleteAll();
for (Article article : articles) {
createIndex(article);
}
}
// 刪除索引
public void deleteIndex(int id) throws IOException {
if (indexFile.exists()) {
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(
Version.LATEST, analyzer);
IndexWriter indexWriter = new IndexWriter(directory,
indexWriterConfig);
indexWriter.deleteDocuments(new Term("id", String.valueOf(id)));
System.out.println("[" + getDate() + "]" + "lucene刪除索引成功");
indexWriter.close();
} else {
System.out.println("刪除索引失敗");
}
}
// 批量刪除索引
public void deleteIndexes(List<Article> articles) {
if (articles == null || articles.size() == 0) {
return;
}
for (Article article : articles) {
try {
deleteIndex(article.getId());
} catch (IOException e) {
// TODO Auto-generated catch block
System.out.println("刪除索引失敗");
e.printStackTrace();
}
}
}
// 更新索引 先刪除索引在添加索引
public void updateIndex(Article article) throws IOException {
deleteIndex(article.getId());
createIndex(article);
}
//查詢索引
public void searchIndex(String keyword) {
IndexReader indexReader = null;
try {
indexReader = IndexReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);
QueryParser queryParser = new QueryParser(Version.LATEST, "title",
new IKAnalyzer(false));
Query query = queryParser.parse(keyword.trim());
TopDocs topDocs = indexSearcher.search(query, 100);
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
if (scoreDocs == null || scoreDocs.length == 0) {
System.out.println("很遺憾！沒有找到！");
}
for (ScoreDoc scoreDoc : scoreDocs) {
Document document = indexSearcher.doc(scoreDoc.doc);
System.out.println(document.toString());
System.out.println("[title:" + document.get("title")

",content:" + document.get("content") + "]");

}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
if (indexReader != null) {
try {
indexReader.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
//分頁查詢
public void paginationQuery(String keyword, int pageSize, int currentPage) {
String[] fields = { "title", "content" };
IndexReader indexReader = null;
try {
MultiFieldQueryParser multiFieldQueryParser = new MultiFieldQueryParser(
Version.LATEST, fields, new IKAnalyzer(false));
Query query = multiFieldQueryParser.parse(keyword.trim());
indexReader = IndexReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);
// 搜索返回的結果并取前100的結果
TopDocs topDocs = indexSearcher.search(query, 100);
TopDocs allDocs = indexSearcher
.search(new MatchAllDocsQuery(), 100);
int totalHits = topDocs.totalHits;
System.out.println("總數：" + totalHits);
// 搜索返回的結果集合
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
int begin = (currentPage - 1) * pageSize;
int end = Math.min(begin + pageSize, scoreDocs.length);
for (int i = begin; i < end; i++) {
Document document = indexSearcher.doc(scoreDocs[i].doc);
System.out.println("[title：" + document.get("title") + "]");
}
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
if (indexReader != null) {
try {
indexReader.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
//查詢高亮顯示
public void highlighterSearch() {
IndexReader indexReader = null;
try {
indexReader = IndexReader.open(directory);
IndexSearcher indexSearcher = new IndexSearcher(indexReader);
Term term = new Term("content", "中國");
TermQuery termQuery = new TermQuery(term);
TopDocs topDocs = indexSearcher
.search(termQuery, Integer.MAX_VALUE);
System.out.println("查詢結果數：" + topDocs.totalHits);
System.out.println("最大的評分" + topDocs.getMaxScore());
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (ScoreDoc scoreDoc : scoreDocs) {
Document document = indexSearcher.doc(scoreDoc.doc);
System.out.println("檢索條件:" + term.toString());
String content = document.get("content");
System.out.println("content:" + document.get("content"));
// 高亮展示
SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(
"【", "】");
Highlighter highlighter = new Highlighter(simpleHTMLFormatter,
new QueryScorer(termQuery));
highlighter.setTextFragmenter(new SimpleFragmenter(content
.length()));
if (!"".equals(content)) {
TokenStream tokenStream = new IKAnalyzer().tokenStream(
content, new StringReader(content));
String bestFragment = highlighter.getBestFragment(
tokenStream, content);
System.out.println("高亮顯示：" + "檢索結果如下所示:");
System.out.println(bestFragment);
// 結束關鍵字高亮
System.out.println("文件內容:" + content);
// 匹配相關度
System.out.println(scoreDoc.score);
}
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (InvalidTokenOffsetsException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
if (indexReader != null) {
try {
indexReader.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
// 釋放資源
public void destory() throws IOException {
analyzer.close();
directory.close();
System.out.println("銷毀成功");
}
public static void main(String[] args) throws IOException {
OperatorIndex index = new OperatorIndex();
index.init();
// Article article = new Article();
// article.setId(1);
// article.setTitle("hello");
// article.setContent("hello world!");
//
// index.createIndex(article);
// index.openIndexFile();
// index.deleteIndex(1);
// index.openIndexFile();
// article.setContent("hello");
// index.updateIndex(article);
// index.openIndexFile();
List<Article> articles = new ArrayList<Article>();
Article article = new Article(1, "中國", "11111gdfjs中國");
Article article1 = new Article(2, "我愛你中國", "11111gdfjs我愛你中國");
Article article2 = new Article(3, "國中之國", "fdsab;1gdfjs國中之國");
Article article3 = new Article(4, "44", "111gdsa11gdfjs中國將成為世界上最強大的國家");
Article article4 = new Article(5, "55", "111gdas11gdfjs");
articles.add(article);
articles.add(article1);
articles.add(article2);
articles.add(article3);
articles.add(article4);
index.deleteIndexes(articles);
index.createIndexes(articles);
index.openIndexFile();
index.searchIndex("中國");
index.paginationQuery("中國", 1, 1);
index.highlighterSearch();
// index.destory();
}
}
Article.java實體
public class Article {
private int id;
private String title;
private String content;
public int getId() {
return id;
}
public void setId(int id) {
this.id = id;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public String getContent() {
return content;
}
public void setContent(String content) {
this.content = content;
}
public Article(int id, String title, String content) {
super();
this.id = id;
this.title = title;
this.content = content;
}
public Article() {
// TODO Auto-generated constructor stub
}
@Override
public String toString() {
// TODO Auto-generated method stub
return "article[id:" + id + ",title:" + title + ",content:" + content

"]";
}

}</pre>
本文由用戶 jopen 自行上傳分享，僅供網友學習交流。所有權歸原作者，若您的權利被侵害，請聯系管理員。
轉載本站原創文章，請注明出處，并保留原始鏈接、圖片水印。
本站是一個以用戶分享為主的開源技術平臺，歡迎各類分享！
本文地址：http://www.baiduhome.net/lib/view/open1419163122698.html
Lucene 搜索引擎
操作lucene索引的工具類

相關經驗

相關資訊

相關文檔

目錄
