Module: Dhaka::LexerSupport

Defined in:

lib/dhaka/lexer/regex_grammar.rb,
lib/dhaka/lexer/dfa.rb,
lib/dhaka/lexer/state.rb,
lib/dhaka/lexer/alphabet.rb,
lib/dhaka/lexer/state_machine.rb,
lib/dhaka/lexer/accept_actions.rb,
lib/dhaka/lexer/regex_tokenizer.rb

Overview

:nodoc:all

Defined Under Namespace

Classes: ASTNode, AcceptAction, AcceptingNode, BinaryNode, CatNode, CheckpointAction, CheckpointNode, DFA, DFARun, InvalidRegexException, LeafNode, LookaheadAcceptAction, LookaheadAcceptingNode, LookaheadNode, OneOrMoreNode, OrNode, RegexGrammar, RegexParser, RegexTokenizer, RootNode, State, StateMachine, UnaryNode, ZeroOrMoreNode, ZeroOrOneNode

Constant Summary

DIGITS =

('0'..'9').to_a

LOWERCASE_LETTERS =

('a'..'z').to_a

UPPERCASE_LETTERS =

('A'..'Z').to_a

LETTERS =

LOWERCASE_LETTERS + UPPERCASE_LETTERS

WHITESPACE =

[" ", "\r", "\n", "\t"]

SYMBOLS =

%w| ~ ` ! @ # % & _ = : ; " ' < , > - |

CLASSES =

{'d' => DIGITS, 'w' => LETTERS, 's' => WHITESPACE}

OPERATOR_CHARACTERS =

{'(' => 'open_parenth', ')' => 'close_parenth', '[' => 'open_square_bracket', 
']' => 'close_square_bracket', '+' => 'plus', '*' => 'asterisk', 
'?' => 'question_mark', '.' => 'period', '\\' => 'back_slash', 
'|' => 'pipe', '{' => 'left_curly_brace', '}' => 'right_curly_brace', 
'/' => 'forward_slash', '^' => 'caret', '$' => 'dollar'}

SET_OPERATOR_CHARACTERS =

%w| - ^ [ ] \\ |

ALL_CHARACTERS =

DIGITS + LETTERS + SYMBOLS + WHITESPACE + OPERATOR_CHARACTERS.keys