Created
April 17, 2022 19:00
-
-
Save hovsater/12151f7850305e8a0e0760d7a7e1ad5c to your computer and use it in GitHub Desktop.
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
type TokenType = 'ASSIGN' | 'NAME' | 'NUM' | 'OP'; | |
type TokenLiteral = string; | |
type Token = [TokenType, TokenLiteral]; | |
type Tokens = ReadonlyArray<Token>; | |
function assert<T extends Tokens>(actual: T, expected: T): void | never { | |
const stringActual = JSON.stringify(actual); | |
const stringExpected = JSON.stringify(expected); | |
if (stringActual !== stringExpected) { | |
throw new Error(`Expected ${stringActual} to equal ${stringExpected}`); | |
} | |
} | |
function isIdentifier(char: string): boolean { | |
return char >= 'a' && char <= 'z'; | |
} | |
function isNumber(char: string): boolean { | |
return char >= '0' && char <= '9'; | |
} | |
function tokenize(text: string): Tokens { | |
const tokens: Array<Token> = []; | |
let start = 0; | |
let pos = 0; | |
while (pos++ < text.length) { | |
const c = text[start]; | |
switch (text[start]) { | |
case '+': | |
tokens.push(['OP', c]) | |
break; | |
case '=': | |
tokens.push(['ASSIGN', c]); | |
break; | |
case '*': | |
tokens.push(['OP', c]); | |
break; | |
default: | |
if (isIdentifier(c)) { | |
while (isIdentifier(text[pos++])) {} | |
tokens.push(['NAME', text.substring(start, pos - 1)]); | |
} else if (isNumber(c)) { | |
while (isNumber(text[pos++])) {} | |
tokens.push(['NUM', text.substring(start, pos - 1)]); | |
} | |
} | |
start = pos | |
} | |
return tokens; | |
} | |
assert(tokenize("spam = x + 34 * 567"), [['NAME', 'spam'], ['ASSIGN', '='], ['NAME', 'x'], | |
['OP', '+'], ['NUM', '34'], ['OP', '*'], ['NUM', '567']]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment