Example #1
0
  /**
   * Scans a reference. [67]
   *
   * @param f dissolve entities
   * @return entity
   * @throws IOException I/O exception
   */
  private byte[] ref(final boolean f) throws IOException {
    // scans numeric entities
    if (consume('#')) { // [66]
      final TokenBuilder ent = new TokenBuilder();
      int b = 10;
      int ch = nextChar();
      ent.add(ch);
      if (ch == 'x') {
        b = 16;
        ent.add(ch = nextChar());
      }
      int n = 0;
      do {
        final boolean m = ch >= '0' && ch <= '9';
        final boolean h = b == 16 && (ch >= 'a' && ch <= 'f' || ch >= 'A' && ch <= 'F');
        if (!m && !h) {
          completeRef(ent);
          return QUESTION;
        }
        n *= b;
        n += ch & 15;
        if (!m) n += 9;
        ent.add(ch = nextChar());
      } while (ch != ';');

      if (!valid(n)) return QUESTION;
      ent.reset();
      ent.add(n);
      return ent.finish();
    }

    // scans predefined entities [68]
    final byte[] name = name(false);
    if (!consume(';')) return QUESTION;

    if (!f) return concat(AMPER, name, SEMI);

    byte[] en = ents.get(name);
    if (en == null) {
      // unknown entity: try HTML entities (lazy initialization)
      if (HTMLENTS.size() == 0) {
        for (int s = 0; s < HTMLENTITIES.length; s += 2) {
          HTMLENTS.add(token(HTMLENTITIES[s]), token(HTMLENTITIES[s + 1]));
        }
      }
      en = HTMLENTS.get(name);
    }
    return en == null ? QUESTION : en;
  }
 /**
  * Converts the path to a string array, containing the single segments.
  *
  * @param path path, or {@code null}
  * @return path depth
  */
 public static String[] toSegments(final String path) {
   final StringList sl = new StringList();
   if (path != null) {
     final TokenBuilder tb = new TokenBuilder();
     for (int s = 0; s < path.length(); s++) {
       final char ch = path.charAt(s);
       if (ch == '/') {
         if (tb.isEmpty()) continue;
         sl.add(tb.toString());
         tb.reset();
       } else {
         tb.add(ch);
       }
     }
     if (!tb.isEmpty()) sl.add(tb.toString());
   }
   return sl.toArray();
 }
Example #3
0
  /**
   * Splits a token around matches of the given separator.
   *
   * @param token token to be split
   * @param sep separation character
   * @return array
   */
  public static byte[][] split(final byte[] token, final int sep) {
    final int l = token.length;
    final byte[][] split = new byte[l][];

    int s = 0;
    final TokenBuilder tb = new TokenBuilder();
    for (int i = 0; i < l; i += cl(token, i)) {
      final int c = cp(token, i);
      if (c == sep) {
        if (!tb.isEmpty()) {
          split[s++] = tb.finish();
          tb.reset();
        }
      } else {
        tb.add(c);
      }
    }
    if (!tb.isEmpty()) split[s++] = tb.finish();
    return Array.copyOf(split, s);
  }
Example #4
0
  /**
   * Reads and interprets the next token from the input stream.
   *
   * @return true if the document scanning has been completed
   * @throws IOException I/O exception
   */
  boolean more() throws IOException {
    // gets next character from the input stream
    token.reset();
    final int ch = consume();
    if (ch == 0) {
      type = Type.EOF;
      return false;
    }

    // checks the scanner state
    switch (state) {
      case CONTENT:
        scanCONTENT(ch);
        break;
      case TAG:
      case ATT:
        scanTAG(ch);
        break;
      case QUOTE:
        scanATTVALUE(ch);
    }
    return true;
  }
Example #5
0
 /**
  * Adds the error message to the message buffer {@link #info}.
  *
  * @param msg error message
  * @param ext error extension
  * @return {@code false}
  */
 protected final boolean error(final String msg, final Object... ext) {
   info.reset();
   info.addExt(msg == null ? "" : msg, ext);
   return false;
 }