今天按照师兄的安排,开始看lucene,首先看的就是官网的demo教程,但是这里给出的是一个用命令行直接使用的jar包,没有源码,而且demo教程功能比较多,所以我找到了源码,并把它简化了一下,改成了用main函数直接可以运行的,记录如下。

1.IndexFiles.java

首先是索引的建立过程,我在简化官方给的IndexFiles.java文件时,多删除了第121行,导致IndexWriter没有关闭,所以在后面检索的时候就遇到了no segments* file found的错误,正确的最终简化版如下所示:

这里需要注意版本的问题,因为我使用的是最新版(4.10.1)所以里面的Version后面的数字与官网的是不同的,而且一些构造方法的传参也不一样了。

package lucene;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.*;
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;

import java.io.*;
import java.nio.charset.StandardCharsets;

/**
 * Created by shellbye on 10/23/14.
 */
public class LuTestIndex {
    public static void main(String[] arg) throws Exception{
        String docsPath = "/home/shellbye/indexFile/";
        String indexPath = "/home/shellbye/result/";
        System.out.println("Indexing to directory '" + indexPath + "'...");

        Directory dir = FSDirectory.open(new File(indexPath));
        final File docDir = new File(docsPath);
        Analyzer analyzer = new StandardAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_4_10_1, analyzer);

        // Create a new index in the directory, removing any
        // previously indexed documents:
        iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE);

        IndexWriter writer = new IndexWriter(dir, iwc);
        indexDocs(writer, docDir);
        writer.close();
    }

    /**
     * Indexes the given file using the given writer, or if a directory is given,
     * recurses over files and directories found under the given directory.
     * <p/>
     * NOTE: This method indexes one document per input file.  This is slow.  For good
     * throughput, put multiple documents into your input file(s).  An example of this is
     * in the benchmark module, which can create "line doc" files, one document per line,
     * using the
     * <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html"
     * >WriteLineDocTask</a>.
     *
     * @param writer Writer to the index where the given file/dir info will be stored
     * @param file   The file to index, or the directory to recurse into to find files to index
     * @throws java.io.IOException If there is a low-level I/O error
     */
    static void indexDocs(IndexWriter writer, File file)
            throws IOException {
        // do not try to index files that cannot be read
        if (file.canRead()) {
            if (file.isDirectory()) {
                String[] files = file.list();
                // an IO error could occur
                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) {
                    // at least on windows, some temporary files raise this exception with an "access denied" message
                    // checking if the file can be read doesn't help
                    return;
                }

                try {

                    // make a new, empty document
                    Document doc = new Document();

                    // Add the path of the file as a field named "path".  Use a
                    // field that is indexed (i.e. searchable), but don't tokenize
                    // the field into separate words and don't index term frequency
                    // or positional information:
                    Field pathField = new StringField("path", file.getPath(), Field.Store.YES);
                    doc.add(pathField);

                    // Add the last modified date of the file a field named "modified".
                    // Use a LongField that is indexed (i.e. efficiently filterable with
                    // NumericRangeFilter).  This indexes to milli-second resolution, which
                    // is often too fine.  You could instead create a number based on
                    // year/month/day/hour/minutes/seconds, down the resolution you require.
                    // For example the long value 2011021714 would mean
                    // February 17, 2011, 2-3 PM.
                    doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));

                    // Add the contents of the file to a field named "contents".  Specify a Reader,
                    // so that the text of the file is tokenized and indexed, but not stored.
                    // Note that FileReader expects the file to be in UTF-8 encoding.
                    // If that's not the case searching for special characters will fail.
                    doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(fis, StandardCharsets.UTF_8))));

                    if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) {
                        // New index, so we just add the document (no old document can be there):
                        System.out.println("adding " + file);
                        writer.addDocument(doc);
                    } else {
                        // Existing index (an old copy of this document may have been indexed) so
                        // we use updateDocument instead to replace the old one matching the exact
                        // path, if present:
                        System.out.println("updating " + file);
                        writer.updateDocument(new Term("path", file.getPath()), doc);
                    }

                } finally {
                    fis.close();
                }
            }
        }
    }
}


2.SearchFiles.java

官方所给的版本功能比较全面,也比较复杂,所以我做了一点简化,最终结果如下:


package lucene;

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;

import java.io.*;
import java.nio.charset.StandardCharsets;
import java.util.Date;

/**
 * Created by shellbye on 10/23/14.
 */
public class LuTestSearch {
    public static void main(String[] arg) throws Exception{
        //使用LuTestIndex.java建立索引之后索引所在的目录(indexPath)
        String index = "/home/shellbye/result/";
        //这里的field的值取决于LuTestIndex#100中doc.add时的值
        String field = "contents";

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

        BufferedReader in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));

        QueryParser parser = new QueryParser(field, analyzer);
        while (true) {
            System.out.println("Enter query: ");     // prompt the user
            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));
            // 每页显示的数量
            Integer hitsPerPage = 5;
            doPagingSearch(in, searcher, query, hitsPerPage);
        }
        reader.close();
    }

    /**
     * This demonstrates a typical paging search scenario, where the search engine presents
     * pages of size n to the user. The user can then go to the next page if interested in
     * the next hits.
     */
    public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query,
                                      int hitsPerPage) throws IOException {

        // 至多搜索5页的结果
        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;

        while (true) {
            int end = Math.min(hits.length, start + hitsPerPage);

            // 遍历每一页
            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);
                    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");
                }
                System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
            }


            if (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);
            }
        }
    }
}

参考文档:

0.http://stackoverflow.com/questions/3802021/no-segments-file-found



blog comments powered by Disqus

Published

23 October 2014

Category

tech_world

Tags