Basic Lexical Scanner

LexScan.js

const SEMICOLON = [[59, 59]];
const SPACE = [[32, 32]];
const NUMERIC = [[48, 57]];
const ALPHA = [[65, 90], [97, 122]];
const ALPHA_SPACE = [...SPACE, ...ALPHA];
const ALPHA_NUMERIC = [...NUMERIC, ...ALPHA];
const ALPHA_NUMERIC_SPACE = [...SPACE, ...ALPHA_NUMERIC];
// Returns the first contiguous substring in `string`, starting at `start`, which precedes symbols found in `nt`.
function scanToken(string, start = 0, nt = [" "]) {
	var subString = "";
	var char;
	_scanString: for (var loc = start; char = string[loc], loc < string.length; loc++) {
		_scanNonterminals: for (var ntString of nt) {
			var ntChar;
			_matchNonterminal: for (var mLoc = 0; ntChar = ntString[mLoc], mLoc < ntString.length; mLoc++) {
				if (string[loc + mLoc] !== ntChar) {
					break _matchNonterminal;
				}
				if (mLoc === ntString.length - 1) {
					break _scanString;
				}
			}
		}
		subString += char;
	}
	return subString;
}
// Returns the first contiguous substring in `string`, starting at `start`, which precedes symbols found in `nt`.
function scanRange(string, start = 0, ranges = SPACE) {
	if ((typeof ranges) === "string") {
		ranges = getRanges(ranges);
	}
	var subString = "";
	var char;
	var code;
	_scanString: for (var loc = start; loc < string.length; loc++) {
		char = string[loc];
		code = char.charCodeAt(0);
		_scanRange: for (var range of ranges) {
			if (code >= range[0] && code <= range[1]) {
				break _scanString;
			}
		}
		subString += char;
	}
	return subString;
}
// Returns an ordered array containing the unique alphabet of `string`.
function getAlphabet(string) {
	return Array.from(string)
		.map(symbol => symbol.charCodeAt(0))
		.sort((t1, t2) => t1 > t2)
		.filter((symbol, loc, symbols) => loc === 0 || symbol !== symbols[loc - 1]);
}
function getRanges(string) {
	var symbols = getAlphabet(string);
	var codeRanges = [];
	// Reduce contiguous ranges of codes down to arrays of two.
	symbols.forEach(function (symbol, loc) {
		var symbol = symbols[loc]
		if (loc !== 0 && symbol === symbols[loc - 1] + 1) {
			codeRanges[codeRanges.length - 1].push(symbol);
		} else {
			codeRanges.push([symbol]);
		}
	});
	// Complete the ranges for single codes.
	codeRanges.forEach(function (range) {
		if (range.length === 1) {
			range.push(range[0]);
		}
	});
	return codeRanges;
}
function findClosingPos(string, start = 0, opener = "{", closer = "}") {
	var depth = 1;
	var char;
	_scanString: for (var loc = start; char = string[loc], loc < string.length; loc++) {
		if (char === closer) {
			depth--;
			if (depth === 0) {
				return loc;
			}
		} else if (char === opener) {
			depth++;
		}
	}
	return null;
}