Question

我正在尝试在我的应用程序中实现luecene搜索引擎。

我正在使用lucene 5.4.1

我已经成功实现了lucene的wildequeries和普通查询。

但我主要关注的是使用正则表达式模式搜索文本文件中的特定文本。

Index Writer代码：

public IndexWriter generateIndex(String docsPath) throws IOException {

      String indexPath = System.getProperty("java.io.tmpdir") +File.separator+"indexDirectory";
        if (indexPath == null) {
          throw new IOException("System property 'java.io.tmpdir' does not specify a tmp dir");
        }
        File tmpDir = new File(indexPath);
        if (!tmpDir.exists()) {
          boolean created = tmpDir.mkdirs();
          if (!created) {
            throw new IOException("Unable to create tmp dir " + tmpDir);
          }
        }

    boolean create = true;
    final Path docDir = Paths.get(docsPath);
    if (!Files.isReadable(docDir)) {
        System.out.println("Document directory '" + docDir.toAbsolutePath()
                + "' does not exist or is not readable, please check the path");
        System.exit(1);
    }

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

        Directory dir = FSDirectory.open(Paths.get(indexPath));
        Analyzer analyzer = new StandardAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);

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

        IndexWriter writer = new IndexWriter(dir, iwc);
        indexDocs(writer, docDir);
        setIndexWriter(writer);

        Date end = new Date();
        System.out.println(end.getTime() - start.getTime() + " total milliseconds");
        writer.close();
    } catch (IOException e) {
        System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
    }

    return getIndexWriter();
}

static void indexDocs(final IndexWriter writer, Path path) throws IOException {
    if (Files.isDirectory(path)) {
        Files.walkFileTree(path, new SimpleFileVisitor<Path>() {
            @Override
            public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
                try {
                    indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
                } catch (IOException ignore) {
                    // don't index files that can't be read.
                }
                return FileVisitResult.CONTINUE;
            }
        });
    } else {
        indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
    }
}

static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    try (InputStream stream = Files.newInputStream(file)) {
        Document doc = new Document();
        Field pathField = new StringField("path", file.toString(), Field.Store.NO);
        doc.add(pathField);

        doc.add(new LongField("modified", lastModified, Field.Store.NO));
        doc.add(new TextField("contents",
                new BufferedReader(new InputStreamReader(stream, 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.toString()), doc);
        }
    }
}

索引搜索代码：

public IndexReader searchExecutor(String index, String queryString, RegexCapabilities capability) throws Exception {

    String field = "contents";
    String queries = null;
    boolean raw = false;
    int hitsPerPage = Integer.MAX_VALUE;
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    Query q = new RegexpQuery(new Term("text", queryString));
    q = q.rewrite(reader);

    RegexQuery query = new RegexQuery(new Term("\\s*(FIND|find)"));

     if (capability != null)
          query.setRegexImplementation(capability);

    System.out.println("Searching for: " + query.toString(field));
    searcher.search(query, null, 1000);
    doSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);
    //reader.close();
    return reader;

}

public static void doSearch(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;
    //generateIndex.deleteDocuments(query);
    //generateIndex.getDirectory();
    // TermsEnum.totalTermFreq();
    int numTotalHits = results.totalHits;
    System.out.println(numTotalHits + " total matching documents");
    int start = 0;
    int end = Math.min(numTotalHits, hitsPerPage);

    for (int i = start; i < end; i++) {
        Document doc = searcher.doc(hits[i].doc);
        String path = doc.get("path");
        File file = new File(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");
        }

    }
}

请帮忙。

Answer 1

您的问题是关于在lucene中使用正则表达式进行搜索。

您使用的是不推荐使用的RegexQuery，请尝试使用RegexpQuery
您的注册表示例以\s*开头，但您不使用KeywordTokenizer。大多数其他标记器将删除（又名＆＃34;拆分为＆＃34;）空白
您的regEx示例并非纯粹的小写。但标准分析仪包含LowerCaseFilter。请注意：您的regEx将直接针对您的索引的令牌（而不是原始文本）

- ＆GT;阅读Supported RegExp syntax和syntax in ES以及TestRegexpRandom (test class)并在您的索引上使用https://github.com/DmitryKey/luke。

正则表达式查询如何在lucene上运行？

1 个答案: