예제 #1
0
  public static void main(String[] args) throws Exception {
    // the IndexReader object is the main handle that will give you
    // all the documents, terms and inverted index
    IndexReader r = IndexReader.open(FSDirectory.open(new File("index")));

    // You can figure out the number of documents using the maxDoc() function
    System.out.println("The number of documents in this index is: " + r.maxDoc());

    int i = 0;
    // You can find out all the terms that have been indexed using the terms() function
    TermEnum t = r.terms();
    while (t.next()) {
      // Since there are so many terms, let us try printing only term #100000-#100010
      if (i > 100000) System.out.println("[" + i + "] " + t.term().text());
      if (++i > 100010) break;
    }

    // You can create your own query terms by calling the Term constructor, with the field
    // 'contents'
    // In the following example, the query term is 'brute'
    Term te = new Term("contents", "brute");

    // You can also quickly find out the number of documents that have term t
    System.out.println("Number of documents with the word 'brute' is: " + r.docFreq(te));

    // You can use the inverted index to find out all the documents that contain the term 'brute'
    //  by using the termDocs function
    TermDocs td = r.termDocs(te);
    while (td.next()) {
      System.out.println(
          "Document number ["
              + td.doc()
              + "] contains the term 'brute' "
              + td.freq()
              + " time(s).");
    }

    // You can find the URL of the a specific document number using the document() function
    // For example, the URL for document number 14191 is:
    Document d = r.document(14191);
    String url =
        d.getFieldable("path")
            .stringValue(); // the 'path' field of the Document object holds the URL
    System.out.println(url.replace("%%", "/"));

    // -------- Now let us use all of the functions above to make something useful --------
    // The following bit of code is a worked out example of how to get a bunch of documents
    // in response to a query and show them (without ranking them according to TF/IDF)
    Scanner sc = new Scanner(System.in);
    String str = "";
    System.out.print("query> ");
    while (!(str = sc.nextLine()).equals("quit")) {
      String[] terms = str.split("\\s+");
      for (String word : terms) {
        Term term = new Term("contents", word);
        TermDocs tdocs = r.termDocs(term);
        while (tdocs.next()) {
          String d_url =
              r.document(tdocs.doc()).getFieldable("path").stringValue().replace("%%", "/");
          System.out.println("[" + tdocs.doc() + "] " + d_url);
        }
      }
      System.out.print("query> ");
    }
  }
예제 #2
0
파일: TermDumper.java 프로젝트: rlugojr/tnh
  public static void main(String[] args) throws Exception {
    if (args.length < 2) {
      System.err.println("TermDumper [-c|-v value] field <index...>");
      System.exit(1);
    }

    boolean count = false;
    String value = null;
    boolean all = false;

    int i = 0;
    for (; i < args.length; i++) {
      String arg = args[i];

      if ("-h".equals(arg) || "--help".equals(arg)) {
        System.err.println("TermDumper [-c|-v value] field <index...>");
        System.exit(1);
      } else if ("-c".equals(arg) || "--count".equals(arg)) {
        count = true;
      } else if ("-v".equals(arg) || "--vaue".equals(arg)) {
        value = args[++i];
      } else if ("-a".equals(arg) || "--all".equals(arg)) {
        all = true;
      } else {
        break;
      }
    }

    String field = args[i++];

    java.util.ArrayList<IndexReader> readers =
        new java.util.ArrayList<IndexReader>(args.length - 1);
    for (; i < args.length; i++) {
      String arg = args[i];
      try {
        IndexReader reader = IndexReader.open(new MMapDirectory(new File(arg)), true);

        readers.add(reader);
      } catch (IOException ioe) {
        System.err.println("Error reading: " + arg);
      }
    }

    for (IndexReader reader : readers) {
      TermDocs termDocs = reader.termDocs();
      TermEnum termEnum = reader.terms(new Term(field));

      try {
        do {
          Term term = termEnum.term();

          if (term == null || !field.equals(term.field())) break;

          if (value == null) {
            if (count) {
              termDocs.seek(termEnum);

              int c = 0;
              for (; termDocs.next(); c++) ;

              System.out.print(c + " ");
            }
            System.out.println(term.text());
          } else if (value.equals(term.text())) {
            termDocs.seek(termEnum);

            while (termDocs.next()) {
              if (all) {
                Document d = reader.document(termDocs.doc());
                System.out.println(termDocs.doc());
                for (Object o : d.getFields()) {
                  Field f = (Field) o;
                  System.out.println(f.name() + " " + d.get(f.name()));
                }
              } else {
                System.out.println(
                    termDocs.doc() + " " + reader.document(termDocs.doc()).get("url"));
              }
            }
          }
        } while (termEnum.next());
      } finally {
        termDocs.close();
        termEnum.close();
      }
    }
  }