-
-
Save oeN/cf4c6a06c1a099be1eb9 to your computer and use it in GitHub Desktop.
basic tokenizer and parser with an approach of Polish notation for calcs
This file contains hidden or 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
require 'tokenizer' | |
class Parser | |
attr_reader :tokens, :prioritize | |
GRAMMAR = { | |
number: "insert_operand", | |
operator: "insert_operator", | |
open_bracket: "open_bracket", | |
close_bracket: "close_bracket" | |
} | |
def parse expression | |
tokenizer = Tokenizer.new expression | |
@tokens = [] | |
@prioritize = false | |
while tokenizer.look_next_token | |
tokenizer.next_token | |
GRAMMAR.each do |t, action| | |
send( action, tokenizer.current_token ) if t == tokenizer.current_token.type | |
end | |
end | |
end | |
def get_result | |
operate | |
@tokens.first.value | |
end | |
def insert_operand token | |
@tokens << token | |
end | |
def insert_operator token | |
if prioritize | |
@tokens.insert @tokens.size - 1, token | |
else | |
@tokens.insert 0, token | |
end | |
end | |
def open_bracket token | |
@prioritize = true | |
end | |
def close_bracket token | |
@prioritize = false | |
end | |
def operate | |
number_stack = [] | |
while @tokens.size != 1 || @tokens.first.type != :number | |
current_token = @tokens.pop | |
number_stack << current_token.value if current_token.type == :number | |
if current_token.type == :operator | |
first_value = number_stack.pop | |
second_value = number_stack.pop | |
if first_value && second_value | |
@tokens << Token.new( :number, first_value.send( current_token.value, second_value ) ) | |
end | |
end | |
end | |
end | |
end |
This file contains hidden or 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 hidden or 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
require 'token' | |
class Tokenizer | |
OPERATORS = ['+', '-', '*', '/'] | |
NUMBER_REGEXP = /^\d*(\.\d+)?$/ | |
OPEN_BRACKETS = ['('] | |
CLOSE_BRACKETS = [')'] | |
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 | |
elsif OPEN_BRACKETS.include? next_char | |
read_next_open_bracket_token expression_to_parse | |
elsif CLOSE_BRACKETS.include? next_char | |
read_next_close_bracket_token expression_to_parse | |
else | |
raise "Unknown token starting with '#{next_char}'" | |
end | |
end | |
def read_next_open_bracket_token expression_to_parse | |
Token.new :open_bracket, expression_to_parse.slice!(0) | |
end | |
def read_next_close_bracket_token expression_to_parse | |
Token.new :close_bracket, expression_to_parse.slice!(0) | |
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