refactor to remove mutation

This commit is contained in:
Kurt Hutten IrevDev
2022-11-12 13:33:35 +11:00
parent 3b095c25d7
commit 8ccb18fd54

View File

@ -7,12 +7,11 @@ const WORD = /^[a-zA-Z_][a-zA-Z0-9_]*/;
const STRING = /^(["'])(?:(?=(\\?))\2.)*?\1/;
// regex for operators
const OPERATOR = /^[>=|<=|+|\-|*|/|>|<|^|%]/;
const BLOCK_START = /^\{/
const BLOCK_END = /^\}/
const BLOCK_START = /^\{/;
const BLOCK_END = /^\}/;
const PARAN_START = /^\(/;
const PARAN_END = /^\)/;
export const isNumber = (character: string) => NUMBER.test(character);
export const isWhitespace = (character: string) => WHITESPACE.test(character);
export const isWord = (character: string) => WORD.test(character);
@ -23,7 +22,6 @@ export const isBlockEnd = (character: string) => BLOCK_END.test(character);
export const isParanStart = (character: string) => PARAN_START.test(character);
export const isParanEnd = (character: string) => PARAN_END.test(character);
function matchFirst(str: string, regex: RegExp) {
const theMatch = str.match(regex);
if (!theMatch) {
@ -32,20 +30,12 @@ function matchFirst(str: string, regex: RegExp) {
return theMatch[0];
}
// type TokenTypes =
interface Token {
type: 'number' | 'word' | 'operator' | 'string' | 'brace'
type: "number" | "word" | "operator" | "string" | "brace";
value: string;
}
export const lexer = (str: string): Token[] => {
const tokens: Token[] = [];
let currentIndex = 0;
const returnTokenAtIndex = (
str: string,
startIndex: number
): Token | null => {
const returnTokenAtIndex = (str: string, startIndex: number): Token | null => {
const strFromIndex = str.slice(startIndex);
if (isOperator(strFromIndex)) {
return {
@ -59,25 +49,25 @@ export const lexer = (str: string): Token[] => {
value: matchFirst(strFromIndex, STRING),
};
}
if(isParanEnd(strFromIndex)){
if (isParanEnd(strFromIndex)) {
return {
type: "brace",
value: matchFirst(strFromIndex, PARAN_END),
};
}
if(isParanStart(strFromIndex)){
if (isParanStart(strFromIndex)) {
return {
type: "brace",
value: matchFirst(strFromIndex, PARAN_START),
};
}
if(isBlockStart(strFromIndex)){
if (isBlockStart(strFromIndex)) {
return {
type: "brace",
value: matchFirst(strFromIndex, BLOCK_START),
};
}
if(isBlockEnd(strFromIndex)){
if (isBlockEnd(strFromIndex)) {
return {
type: "brace",
value: matchFirst(strFromIndex, BLOCK_END),
@ -89,31 +79,32 @@ export const lexer = (str: string): Token[] => {
value: matchFirst(strFromIndex, NUMBER),
};
}
if(isWord(strFromIndex)) {
if (isWord(strFromIndex)) {
return {
type: "word",
value: matchFirst(strFromIndex, WORD),
};
}
return null;
};
while (currentIndex < str.length) {
const token = returnTokenAtIndex(str, currentIndex);
if (token) {
tokens.push(token);
currentIndex += token.value.length;
} else {
currentIndex++;
}
}
return tokens
};
async function main() {
const example1 = await fsp.readFile("./examples/addition.cado", "ascii");
const parsed = lexer(example1);
console.log(parsed);
}
export const lexer = (str: string): Token[] => {
const recursivelyTokenise = (
str: string,
currentIndex: number = 0,
previousTokens: Token[] = []
): Token[] => {
if (currentIndex >= str.length) {
return previousTokens;
}
const token = returnTokenAtIndex(str, currentIndex);
if (!token) {
return recursivelyTokenise(str, currentIndex + 1, previousTokens);
}
const nextIndex = currentIndex + token.value.length;
return recursivelyTokenise(str, nextIndex, [...previousTokens, token]);
};
return recursivelyTokenise(str);
};
// main()
// const example1 = await fsp.readFile("./examples/addition.cado", "ascii");