Class: Aspen::CustomGrammar::Lexer
- Inherits:
-
Object
- Object
- Aspen::CustomGrammar::Lexer
- Defined in:
- lib/aspen/custom_grammar/lexer.rb
Class Method Summary collapse
Instance Method Summary collapse
- #no_match(scanner, state) ⇒ Object
- #pop_state ⇒ Object
- #push_state(state) ⇒ Object
- #stack ⇒ Object
- #state ⇒ Object
- #tokenize(code, env = {}) ⇒ Object
Class Method Details
.tokenize(code, env = {}) ⇒ Object
6 7 8 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 6 def self.tokenize(code, env={}) new.tokenize(code, env) end |
Instance Method Details
#no_match(scanner, state) ⇒ Object
69 70 71 72 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 69 def no_match(scanner, state) raise Aspen::LexError, Aspen::Errors.(:unexpected_token, scanner, state) end |
#pop_state ⇒ Object
65 66 67 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 65 def pop_state stack.pop end |
#push_state(state) ⇒ Object
61 62 63 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 61 def push_state(state) stack.push(state) end |
#stack ⇒ Object
53 54 55 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 53 def stack @stack ||= [] end |
#state ⇒ Object
57 58 59 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 57 def state stack.last || :default end |
#tokenize(code, env = {}) ⇒ Object
10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
# File 'lib/aspen/custom_grammar/lexer.rb', line 10 def tokenize(code, env={}) scanner = StringScanner.new(code) tokens = [] # puts "tokens: #{tokens} | state: #{state} | stack: #{stack}" until scanner.eos? case state when :default then if scanner.scan(/\(/) tokens << [:OPEN_PARENS] push_state :capture_segment elsif scanner.scan(/[[[:alnum:]][[:blank:]]\!"\#$%&'*+,\-.\/:;<=>?@\[\\\]^_‘\{\|\}~]+/) tokens << [:BARE, scanner.matched] else no_match(scanner, state) end when :capture_segment if scanner.scan(/\s+/) # NO OP elsif scanner.scan(/^(numeric|integer|float|string)/) tokens << [:TYPE, scanner.matched] elsif scanner.scan(Aspen::Lexer::PASCAL_CASE) tokens << [:TYPE, ["node", scanner.matched]] # TODO: This should only accept legal variable names, like `hello_01` elsif scanner.scan(/^\w+/) tokens << [:VAR_NAME, scanner.matched] elsif scanner.scan(/\)/) tokens << [:CLOSE_PARENS] pop_state else no_match(scanner, state) end else raise Aspen::LexError, "There is no matcher for state #{state.inspect}." end end tokens end |