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

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485
  1. /*
  2. * Copyright (c) 2006-2017 DMDirc Developers
  3. *
  4. * Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated
  5. * documentation files (the "Software"), to deal in the Software without restriction, including without limitation the
  6. * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to
  7. * permit persons to whom the Software is furnished to do so, subject to the following conditions:
  8. *
  9. * The above copyright notice and this permission notice shall be included in all copies or substantial portions of the
  10. * Software.
  11. *
  12. * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
  13. * WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS
  14. * OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
  15. * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  16. */
  17. package com.dmdirc.addons.calc;
  18. import java.text.ParseException;
  19. import java.util.ArrayList;
  20. import java.util.Arrays;
  21. import java.util.List;
  22. /**
  23. * The lexer takes a String input and produces an ordered list of {@link Token}s corresponding to
  24. * the input.
  25. */
  26. public class Lexer {
  27. /** The input string. */
  28. private final String input;
  29. /**
  30. * Creates a new lexer for the specified input string.
  31. *
  32. * @param input The string to be tokenised
  33. */
  34. public Lexer(final String input) {
  35. this.input = input.replaceAll("\\s+", "");
  36. }
  37. /**
  38. * Tokenises the input string into an ordered list of tokens.
  39. *
  40. * @return A list of tokens corresponding to the input string
  41. *
  42. * @throws ParseException If an expected token is not found
  43. */
  44. public List<Token> tokenise() throws ParseException {
  45. final List<Token> res = new ArrayList<>();
  46. List<TokenType> possibles = Arrays.asList(TokenType.values());
  47. boolean cont = true;
  48. int i = 0;
  49. do {
  50. boolean found = false;
  51. for (TokenType type : possibles) {
  52. final int match = type.match(input, i);
  53. if (match > -1) {
  54. res.add(new Token(type, input.substring(i, match)));
  55. possibles = type.getFollowers();
  56. i = match;
  57. found = true;
  58. cont = type != TokenType.END;
  59. break;
  60. }
  61. }
  62. if (!found) {
  63. throw new ParseException("No legal token found at offset "
  64. + i + ". Expecting one of: "
  65. + Arrays.toString(possibles.toArray()), i);
  66. }
  67. } while (cont);
  68. return res;
  69. }
  70. }