lucene学习

创建索引

package org.apache.lucene.demo;

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.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.NumericField;
import org.apache.lucene.index.FieldInfo;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class IndexFiles {
	public static void main(String[] args) {

		//索引文件所在的目录
		String indexPath = "c:/index";
		//需要索引的文件目录
		String docsPath = "c:/docs";
		//是否创建
		boolean create = true;

		
		File docDir = new File(docsPath);

		Date start = new Date();
		try {
			System.out.println("Indexing to directory '" + indexPath + "'...");

			
			Directory dir = FSDirectory.open(new File(indexPath));
			Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);
			IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_31, analyzer);

			if (create) {
				iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
			} else {
				iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
			}

			IndexWriter writer = new IndexWriter(dir, iwc);
			//创建索引文件
			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() + "\n with message: " + e.getMessage());
		}
	}

	static void indexDocs(IndexWriter writer, File file) throws IOException {
		if (file.canRead())
			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 代表索引的一条数据
					Document doc = new Document();

					Field pathField = new Field("path", file.getPath(), Field.Store.YES,
							Field.Index.NOT_ANALYZED_NO_NORMS);
					pathField.setIndexOptions(FieldInfo.IndexOptions.DOCS_ONLY);
					doc.add(pathField);

					NumericField modifiedField = new NumericField("modified");
					modifiedField.setLongValue(file.lastModified());
					doc.add(modifiedField);

					doc.add(new Field("contents", new BufferedReader(new InputStreamReader(fis,
							"UTF-8"))));

					if (writer.getConfig().getOpenMode() == IndexWriterConfig.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();
				}
			}
	}
}

 

利用索引查找文件

package org.apache.lucene.demo;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.PrintStream;
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.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.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class SearchFiles {
	public static void main(String[] args) throws Exception {

		String index = "c:/index";
		String field = "contents";
		String queries = null;
		int repeat = 0;
		boolean raw = false;
		String queryString = null;
		int hitsPerPage = 10;


		IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)));
		IndexSearcher searcher = new IndexSearcher(reader);
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);

		BufferedReader in = null;
		if (queries != null)
			in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
		else {
			in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
		}
		QueryParser parser = new QueryParser(Version.LUCENE_31, field, analyzer);
		while (true) {
			if ((queries == null) && (queryString == null)) {
				System.out.println("Enter query: ");
			}

			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) {
				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;
			}
		}
		searcher.close();
		reader.close();
	}

	public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query,
			int hitsPerPage, boolean raw, boolean interactive) throws IOException {
		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) {
					System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
				} else {
					System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);

					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");
						System.out.println(doc.get("contents"));
						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;
					}
					if (line.charAt(0) == 'n') {
						if (start + hitsPerPage >= numTotalHits)
							break;
						start += hitsPerPage;
						break;
					}

					int page = Integer.parseInt(line);
					if ((page - 1) * hitsPerPage < numTotalHits) {
						start = (page - 1) * hitsPerPage;
						break;
					}
					System.out.println("No such page");
				}

				if (quit)
					break;
				end = Math.min(numTotalHits, start + hitsPerPage);
			}
		}
	}
}