创建索引：
import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.IOException; import java.io.InputStreamReader; import java.nio.charset.StandardCharsets; import java.util.Date; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.LongField; import org.apache.lucene.document.StringField; import org.apache.lucene.document.TextField; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.Term; import org.apache.lucene.index.IndexWriterConfig.OpenMode; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; public class CreateLuceneIndex { public static void main(String[] args) { if (args == null || args.length <= 0) { args = new String[] { "-index", "E:\00.学习\03.软件\JAVA\lu01\index", "-docs", "E:\00.学习\03.软件\JAVA\lu01\doc" }; } String indexPath = ""; String docsPath = null; boolean create = true; for (int i = 0; i < args.length; i++) { if ("-index".equals(args[i])) { indexPath = args[i + 1]; i++; } else if ("-docs".equals(args[i])) { docsPath = args[i + 1]; i++; } else if ("-update".equals(args[i])) { create = false; } } if (docsPath == null) { System.err.println("资源文件所在目录为空，请指定资源文件所在目录！！！"); System.exit(1); } final File docDir = new File(docsPath); if (!docDir.exists() || !docDir.canRead()) { System.out.println("资源文件目录 '" + docDir.getAbsolutePath() + "' 不存在或不可读，请检查！"); System.exit(1); } Date start = new Date(); try { System.out.println("建立索引文件到该目录 '" + indexPath + "'..."); Directory dir = FSDirectory.open(new File(indexPath)); Analyzer analyzer = new StandardAnalyzer(); IndexWriterConfig iwc = new IndexWriterConfig( Version.LUCENE_4_10_2, analyzer); if (create) { iwc.setOpenMode(OpenMode.CREATE); } else { iwc.setOpenMode(OpenMode.CREATE_OR_APPEND); } IndexWriter writer = new IndexWriter(dir, iwc); indexDocs(writer, docDir); writer.close(); Date end = new Date(); System.out.println(end.getTime() - start.getTime() + " total milliseconds"); } catch (IOException e) { System.out.println(" caught a " + e.getClass() + " with message: " + e.getMessage()); } } /** * 将资源文件索引到指定目录下，生成磁盘的索引文件 * * @param writer * 索引文件 * @param file * 资源文件 */ static void indexDocs(IndexWriter writer, File file) throws IOException { if (!file.canRead()) { return; } if (file.isDirectory()) { String[] files = file.list(); if (files != null) { for (int i = 0; i < files.length; i++) { indexDocs(writer, new File(file, files[i])); } } } else { FileInputStream fis; try { fis = new FileInputStream(file); } catch (FileNotFoundException fnfe) { return; } try { Document doc = new Document(); Field pathField = new StringField("path", file.getPath(), Field.Store.YES); doc.add(pathField); doc.add(new LongField("modified", file.lastModified(), Field.Store.NO)); doc.add(new TextField("contents", new BufferedReader( new InputStreamReader(fis, StandardCharsets.UTF_8)))); if (writer.getConfig().getOpenMode() == OpenMode.CREATE) { System.out.println("adding " + file); writer.addDocument(doc); } else { System.out.println("updating " + file); writer.updateDocument(new Term("path", file.getPath()), doc); } } finally { fis.close(); } } } }
全文检索：
import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.IOException; import java.io.InputStreamReader; import java.nio.charset.StandardCharsets; import java.util.Date; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.index.DirectoryReader; import org.apache.lucene.index.IndexReader; import org.apache.lucene.queryparser.classic.QueryParser; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TopDocs; import org.apache.lucene.store.FSDirectory; public class SearchFiles { public static void main(String[] args) throws Exception { args = new String[] { "-index", "E:\00.学习\03.软件\JAVA\lu01\index" }; if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) { System.exit(0); } String index = "index"; String field = "contents"; String queries = null; int repeat = 0; boolean raw = false; String queryString = null; int hitsPerPage = 10; for (int i = 0; i < args.length; i++) { if ("-index".equals(args[i])) { index = args[i + 1]; i++; } else if ("-field".equals(args[i])) { field = args[i + 1]; i++; } else if ("-queries".equals(args[i])) { queries = args[i + 1]; i++; } else if ("-query".equals(args[i])) { queryString = args[i + 1]; i++; } else if ("-repeat".equals(args[i])) { repeat = Integer.parseInt(args[i + 1]); i++; } else if ("-raw".equals(args[i])) { raw = true; } else if ("-paging".equals(args[i])) { hitsPerPage = Integer.parseInt(args[i + 1]); if (hitsPerPage <= 0) { System.err.println("最少每页有1条数据"); System.exit(1); } i++; } } IndexReader reader = DirectoryReader.open(FSDirectory.open(new File( index))); IndexSearcher searcher = new IndexSearcher(reader); // :Post-Release-Update-Version.LUCENE_XY: Analyzer analyzer = new StandardAnalyzer(); BufferedReader in = null; if (queries != null) { in = new BufferedReader(new InputStreamReader(new FileInputStream( queries), StandardCharsets.UTF_8)); } else { in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8)); } // :Post-Release-Update-Version.LUCENE_XY: QueryParser parser = new QueryParser(field, analyzer); while (true) { if (queries == null && queryString == null) { // prompt the user System.out.println("输入查询关键字: "); } String line = queryString != null ? queryString : 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)); if (repeat > 0) { // repeat & time as benchmark Date start = new Date(); for (int i = 0; i < repeat; i++) { searcher.search(query, null, 100); } Date end = new Date(); System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms"); } doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null); if (queryString != null) { break; } } reader.close(); } public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage, boolean raw, boolean interactive) throws IOException { // Collect enough docs to show 5 pages TopDocs results = searcher.search(query, 5 * hitsPerPage); ScoreDoc[] hits = results.scoreDocs; int numTotalHits = results.totalHits; System.out.println(numTotalHits + " total matching documents"); int start = 0; int end = Math.min(numTotalHits, hitsPerPage); while (true) { if (end > hits.length) { System.out .println("Only results 1 - " + hits.length + " of " + numTotalHits + " total matching documents collected."); System.out.println("Collect more (y/n) ?"); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'n') { break; } hits = searcher.search(query, numTotalHits).scoreDocs; } end = Math.min(hits.length, start + hitsPerPage); for (int i = start; i < end; i++) { if (raw) { // output raw format System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score); continue; } Document doc = searcher.doc(hits[i].doc); String path = doc.get("path"); if (path != null) { System.out.println((i + 1) + ". " + path); String title = doc.get("title"); if (title != null) { System.out.println(" Title: " + doc.get("title")); } } else { System.out.println((i + 1) + ". " + "No path for this document"); } } if (!interactive || end == 0) { break; } if (numTotalHits >= end) { boolean quit = false; while (true) { System.out.print("Press "); if (start - hitsPerPage >= 0) { System.out.print("(p)revious page, "); } if (start + hitsPerPage < numTotalHits) { System.out.print("(n)ext page, "); } System.out .println("(q)uit or enter number to jump to a page."); String line = in.readLine(); if (line.length() == 0 || line.charAt(0) == 'q') { quit = true; break; } if (line.charAt(0) == 'p') { start = Math.max(0, start - hitsPerPage); break; } else if (line.charAt(0) == 'n') { if (start + hitsPerPage < numTotalHits) { start += hitsPerPage; } break; } else { int page = Integer.parseInt(line); if ((page - 1) * hitsPerPage < numTotalHits) { start = (page - 1) * hitsPerPage; break; } else { System.out.println("No such page"); } } } if (quit) break; end = Math.min(numTotalHits, start + hitsPerPage); } } } }
//************************************************************************************************************************
新增部分基础概念的梳理：参考lucene 实战
1、基本概念
lucence 可以认为分为两大组件：
1）索引组件
a、内容获取：即将原始的内容材料，可以是数据库、网站（爬虫）、文本转换为lucence的Docment
Docment 为若干个带值得域
b、文档分析：利用分词器对文档进行分析；
c、建立索引：根据文档分析的结构建立索引文件；
2）搜索组件
a、建立查询：即将用户请求转换为搜索引擎支持的查询对象格式；
b、执行搜索查询；并反馈Document结果集；
2、官方样例代码分析
**索引组件部分工作
1、创建一个包含某个分词器的IndexWriter
private IndexWriter writer;
writer = new IndexWriter(IndexDir, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.UNLIMITED);
2、遍历被索引的文件（即原始内容）将其转换为Document
Docment doc = new Docment();
doc.add(new Field("contents", new FileReader(f));
doc.add(new Field("filename"), f.getName(), Field.Store.Yes, Field.Index.NOT_ANALYZED);
3、针对该Docment创建索引
writer.addDocment(doc);
**搜索组件部分工作
1、打开索引文件
IndexSearcher is = new IndexSearcher(IndexDir);
2、创建一个查询对象
QueryParser parser = new QueryParser(Version.LUCENE_30, "contents", new StandardAnalyzer());
Query query = parser("要找的查询关键字");
3、执行查询并返回结果
TopDocs hits = is.search(query, 10);