Created
November 11, 2014 10:18
-
-
Save caugner/6afb109d1c118b0ba10a to your computer and use it in GitHub Desktop.
Simple Lexer for arithmetic expressions
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
DIGIT = /[0-9]/ | |
LETTER = /[a-z]/i | |
class Lexer | |
def self.lex(input) | |
output = [] | |
it = CharIterator.new(input) | |
peek = it.next | |
while peek | |
case peek | |
when DIGIT | |
val = 0 | |
while peek and DIGIT =~ peek | |
val = 10 * val + Integer(peek) | |
peek = it.next | |
end | |
output << Token.new(:int, val) | |
when LETTER | |
var = "" | |
while peek and LETTER =~ peek | |
var << peek | |
peek = it.next | |
end | |
output << Token.new(:id, var) | |
when '+' | |
output << Token.new(:add) | |
peek = it.next | |
when '-' | |
output << Token.new(:sub) | |
peek = it.next | |
when '*' | |
output << Token.new(:mul) | |
peek = it.next | |
when '/' | |
output << Token.new(:div) | |
peek = it.next | |
else | |
peek = it.next | |
end | |
end | |
return output | |
end | |
end | |
class Token | |
def initialize(name, args=nil) | |
@name = name | |
@args = args | |
end | |
def to_s | |
if @args | |
"<%s, %s>" % [@name, @args] | |
else | |
"<%s>" % @name | |
end | |
end | |
end | |
class CharIterator | |
def initialize(input) | |
@str = input | |
@pos = -1 | |
end | |
def next | |
@pos += 1 | |
@str[@pos].chr if @str[@pos] | |
end | |
def next? | |
@pos + 1 < @str.length | |
end | |
end | |
# examples: [ "1", "2", "12", "1+2", "2-1", "2/1", "1*2", "10+20", "20-10", "20/10", "10*20", "a+b", "b-a", "b/a", "a*b", "ab-ba", "ab/ba", "ab*ba"] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment