Created
April 15, 2015 09:41
-
-
Save nicolaracco/d60efa116c65262b8973 to your computer and use it in GitHub Desktop.
example of a tokenizer and a parser (very basic, even operator precedence is absent)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Parser | |
def parse expression | |
tokenizer = Tokenizer.new expression | |
first_value = read_next_number tokenizer | |
while tokenizer.look_next_token | |
operator = read_next_operator tokenizer | |
second_value = read_next_number tokenizer | |
first_value = operate(first_value, operator, second_value) | |
end | |
first_value | |
end | |
def read_next_number tokenizer | |
token = tokenizer.next_token | |
raise "Unexpected #{token.type} - expected number" if token.type != :number | |
token.value | |
end | |
def read_next_operator tokenizer | |
token = tokenizer.next_token | |
raise "Unexpected #{token.type} - expected operator" if token.type != :operator | |
token.value | |
end | |
def operate first_value, operator, second_value | |
first_value.send operator, second_value | |
end | |
end |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Token | |
attr_reader :type, :value | |
def initialize type, value | |
@type, @value = type, value | |
end | |
end |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class Tokenizer | |
OPERATORS = ['+', '-', '*', '/'] | |
NUMBER_REGEXP = /^\d*(\.\d+)?$/ | |
attr_reader :tokens, :cursor | |
def initialize expression | |
tokenize expression | |
@cursor = -1 | |
end | |
def current_token | |
return nil if @cursor == -1 | |
@tokens[cursor] | |
end | |
def next_token | |
@cursor += 1 | |
current_token | |
end | |
def look_next_token | |
@tokens[cursor + 1] | |
end | |
private | |
def tokenize expression | |
@tokens = [] | |
expression_to_parse = expression.strip | |
while expression_to_parse.size > 0 | |
@tokens << read_next_token(expression_to_parse) | |
end | |
end | |
def read_next_token expression_to_parse | |
expression_to_parse.strip! | |
next_char = expression_to_parse.slice 0 | |
if OPERATORS.include? next_char | |
read_next_operator_token expression_to_parse | |
elsif next_char =~ NUMBER_REGEXP | |
read_next_numeric_token expression_to_parse | |
else | |
raise "Unknown token starting with '#{next_char}'" | |
end | |
end | |
def read_next_operator_token expression_to_parse | |
Token.new :operator, expression_to_parse.slice!(0) | |
end | |
def read_next_numeric_token expression_to_parse | |
numeric_value = expression_to_parse.slice! 0 | |
next_char = expression_to_parse.slice 0 | |
while next_char && "#{numeric_value}#{next_char}" =~ NUMBER_REGEXP | |
numeric_value << expression_to_parse.slice!(0) | |
end | |
Token.new :number, numeric_value.to_f | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment