You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Lexer.java 2.9KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990
  1. /*
  2. * Copyright (c) 2006-2014 DMDirc Developers
  3. *
  4. * Permission is hereby granted, free of charge, to any person obtaining a copy
  5. * of this software and associated documentation files (the "Software"), to deal
  6. * in the Software without restriction, including without limitation the rights
  7. * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  8. * copies of the Software, and to permit persons to whom the Software is
  9. * furnished to do so, subject to the following conditions:
  10. *
  11. * The above copyright notice and this permission notice shall be included in
  12. * all copies or substantial portions of the Software.
  13. *
  14. * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  15. * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  16. * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  17. * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  18. * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  19. * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  20. * SOFTWARE.
  21. */
  22. package com.dmdirc.addons.calc;
  23. import java.text.ParseException;
  24. import java.util.ArrayList;
  25. import java.util.Arrays;
  26. import java.util.List;
  27. /**
  28. * The lexer takes a String input and produces an ordered list of {@link Token}s corresponding to
  29. * the input.
  30. */
  31. public class Lexer {
  32. /** The input string. */
  33. private final String input;
  34. /**
  35. * Creates a new lexer for the specified input string.
  36. *
  37. * @param input The string to be tokenised
  38. */
  39. public Lexer(final String input) {
  40. this.input = input.replaceAll("\\s+", "");
  41. }
  42. /**
  43. * Tokenises the input string into an ordered list of tokens.
  44. *
  45. * @return A list of tokens corresponding to the input string
  46. *
  47. * @throws ParseException If an expected token is not found
  48. */
  49. public List<Token> tokenise() throws ParseException {
  50. final List<Token> res = new ArrayList<>();
  51. List<TokenType> possibles = Arrays.asList(TokenType.values());
  52. boolean cont = true;
  53. int i = 0;
  54. do {
  55. boolean found = false;
  56. for (TokenType type : possibles) {
  57. final int match = type.match(input, i);
  58. if (match > -1) {
  59. res.add(new Token(type, input.substring(i, match)));
  60. possibles = type.getFollowers();
  61. i = match;
  62. found = true;
  63. cont = type != TokenType.END;
  64. break;
  65. }
  66. }
  67. if (!found) {
  68. throw new ParseException("No legal token found at offset "
  69. + i + ". Expecting one of: "
  70. + Arrays.toString(possibles.toArray()), i);
  71. }
  72. } while (cont);
  73. return res;
  74. }
  75. }