strings.ts

/*---------------------------------------------------------------------------------------------
 *  Copyright (c) Microsoft Corporation. All rights reserved.
 *  Licensed under the MIT License. See License.txt in the project root for license information.
 *--------------------------------------------------------------------------------------------*/

import { CharCode } from 'vs/base/common/charCode';

/**
 * The empty string.
 */
export const empty = '';

export function isFalsyOrWhitespace(str: string | undefined): boolean {
	if (!str || typeof str !== 'string') {
		return true;
	}
	return str.trim().length === 0;
}

/**
 * @returns the provided number with the given number of preceding zeros.
 */
export function pad(n: number, l: number, char: string = '0'): string {
	const str = '' + n;
	const r = [str];

	for (let i = str.length; i < l; i++) {
		r.push(char);
	}

	return r.reverse().join('');
}

const _formatRegexp = /{(\d+)}/g;

/**
 * Helper to produce a string with a variable number of arguments. Insert variable segments
 * into the string using the {n} notation where N is the index of the argument following the string.
 * @param value string to which formatting is applied
 * @param args replacements for {n}-entries
 */
export function format(value: string, ...args: any[]): string {
	if (args.length === 0) {
		return value;
	}
	return value.replace(_formatRegexp, function (match, group) {
		const idx = parseInt(group, 10);
		return isNaN(idx) || idx < 0 || idx >= args.length ?
			match :
			args[idx];
	});
}

/**
 * Converts HTML characters inside the string to use entities instead. Makes the string safe from
 * being used e.g. in HTMLElement.innerHTML.
 */
export function escape(html: string): string {
	return html.replace(/[<>&]/g, function (match) {
		switch (match) {
			case '<': return '&lt;';
			case '>': return '&gt;';
			case '&': return '&amp;';
			default: return match;
		}
	});
}

/**
 * Escapes regular expression characters in a given string
 */
export function escapeRegExpCharacters(value: string): string {
	return value.replace(/[\\\{\}\*\+\?\|\^\$\.\[\]\(\)\#]/g, '\\$&');
}

/**
 * Removes all occurrences of needle from the beginning and end of haystack.
 * @param haystack string to trim
 * @param needle the thing to trim (default is a blank)
 */
export function trim(haystack: string, needle: string = ' '): string {
	const trimmed = ltrim(haystack, needle);
	return rtrim(trimmed, needle);
}

/**
 * Removes all occurrences of needle from the beginning of haystack.
 * @param haystack string to trim
 * @param needle the thing to trim
 */
export function ltrim(haystack: string, needle: string): string {
	if (!haystack || !needle) {
		return haystack;
	}

	const needleLen = needle.length;
	if (needleLen === 0 || haystack.length === 0) {
		return haystack;
	}

	let offset = 0;

	while (haystack.indexOf(needle, offset) === offset) {
		offset = offset + needleLen;
	}
	return haystack.substring(offset);
}

/**
 * Removes all occurrences of needle from the end of haystack.
 * @param haystack string to trim
 * @param needle the thing to trim
 */
export function rtrim(haystack: string, needle: string): string {
	if (!haystack || !needle) {
		return haystack;
	}

	const needleLen = needle.length,
		haystackLen = haystack.length;

	if (needleLen === 0 || haystackLen === 0) {
		return haystack;
	}

	let offset = haystackLen,
		idx = -1;

	while (true) {
		idx = haystack.lastIndexOf(needle, offset - 1);
		if (idx === -1 || idx + needleLen !== offset) {
			break;
		}
		if (idx === 0) {
			return '';
		}
		offset = idx;
	}

	return haystack.substring(0, offset);
}

export function convertSimple2RegExpPattern(pattern: string): string {
	return pattern.replace(/[\-\\\{\}\+\?\|\^\$\.\,\[\]\(\)\#\s]/g, '\\$&').replace(/[\*]/g, '.*');
}

export function stripWildcards(pattern: string): string {
	return pattern.replace(/\*/g, '');
}

/**
 * Determines if haystack starts with needle.
 */
export function startsWith(haystack: string, needle: string): boolean {
	if (haystack.length < needle.length) {
		return false;
	}

	if (haystack === needle) {
		return true;
	}

	for (let i = 0; i < needle.length; i++) {
		if (haystack[i] !== needle[i]) {
			return false;
		}
	}

	return true;
}

/**
 * Determines if haystack ends with needle.
 */
export function endsWith(haystack: string, needle: string): boolean {
	const diff = haystack.length - needle.length;
	if (diff > 0) {
		return haystack.indexOf(needle, diff) === diff;
	} else if (diff === 0) {
		return haystack === needle;
	} else {
		return false;
	}
}

export interface RegExpOptions {
	matchCase?: boolean;
	wholeWord?: boolean;
	multiline?: boolean;
	global?: boolean;
	unicode?: boolean;
}

export function createRegExp(searchString: string, isRegex: boolean, options: RegExpOptions = {}): RegExp {
	if (!searchString) {
		throw new Error('Cannot create regex from empty string');
	}
	if (!isRegex) {
		searchString = escapeRegExpCharacters(searchString);
	}
	if (options.wholeWord) {
		if (!/\B/.test(searchString.charAt(0))) {
			searchString = '\\b' + searchString;
		}
		if (!/\B/.test(searchString.charAt(searchString.length - 1))) {
			searchString = searchString + '\\b';
		}
	}
	let modifiers = '';
	if (options.global) {
		modifiers += 'g';
	}
	if (!options.matchCase) {
		modifiers += 'i';
	}
	if (options.multiline) {
		modifiers += 'm';
	}
	if (options.unicode) {
		modifiers += 'u';
	}

	return new RegExp(searchString, modifiers);
}

export function regExpLeadsToEndlessLoop(regexp: RegExp): boolean {
	// Exit early if it's one of these special cases which are meant to match
	// against an empty string
	if (regexp.source === '^' || regexp.source === '^$' || regexp.source === '$' || regexp.source === '^\\s*$') {
		return false;
	}

	// We check against an empty string. If the regular expression doesn't advance
	// (e.g. ends in an endless loop) it will match an empty string.
	const match = regexp.exec('');
	return !!(match && regexp.lastIndex === 0);
}

export function regExpContainsBackreference(regexpValue: string): boolean {
	return !!regexpValue.match(/([^\\]|^)(\\\\)*\\\d+/);
}

export function regExpFlags(regexp: RegExp): string {
	return (regexp.global ? 'g' : '')
		+ (regexp.ignoreCase ? 'i' : '')
		+ (regexp.multiline ? 'm' : '')
		+ ((regexp as any).unicode ? 'u' : '');
}

/**
 * Returns first index of the string that is not whitespace.
 * If string is empty or contains only whitespaces, returns -1
 */
export function firstNonWhitespaceIndex(str: string): number {
	for (let i = 0, len = str.length; i < len; i++) {
		const chCode = str.charCodeAt(i);
		if (chCode !== CharCode.Space && chCode !== CharCode.Tab) {
			return i;
		}
	}
	return -1;
}

/**
 * Returns the leading whitespace of the string.
 * If the string contains only whitespaces, returns entire string
 */
export function getLeadingWhitespace(str: string, start: number = 0, end: number = str.length): string {
	for (let i = start; i < end; i++) {
		const chCode = str.charCodeAt(i);
		if (chCode !== CharCode.Space && chCode !== CharCode.Tab) {
			return str.substring(start, i);
		}
	}
	return str.substring(start, end);
}

/**
 * Returns last index of the string that is not whitespace.
 * If string is empty or contains only whitespaces, returns -1
 */
export function lastNonWhitespaceIndex(str: string, startIndex: number = str.length - 1): number {
	for (let i = startIndex; i >= 0; i--) {
		const chCode = str.charCodeAt(i);
		if (chCode !== CharCode.Space && chCode !== CharCode.Tab) {
			return i;
		}
	}
	return -1;
}

export function compare(a: string, b: string): number {
	if (a < b) {
		return -1;
	} else if (a > b) {
		return 1;
	} else {
		return 0;
	}
}

export function compareIgnoreCase(a: string, b: string): number {
	const len = Math.min(a.length, b.length);
	for (let i = 0; i < len; i++) {
		let codeA = a.charCodeAt(i);
		let codeB = b.charCodeAt(i);

		if (codeA === codeB) {
			// equal
			continue;
		}

		if (isUpperAsciiLetter(codeA)) {
			codeA += 32;
		}

		if (isUpperAsciiLetter(codeB)) {
			codeB += 32;
		}

		const diff = codeA - codeB;

		if (diff === 0) {
			// equal -> ignoreCase
			continue;

		} else if (isLowerAsciiLetter(codeA) && isLowerAsciiLetter(codeB)) {
			//
			return diff;

		} else {
			return compare(a.toLowerCase(), b.toLowerCase());
		}
	}

	if (a.length < b.length) {
		return -1;
	} else if (a.length > b.length) {
		return 1;
	} else {
		return 0;
	}
}

export function isLowerAsciiLetter(code: number): boolean {
	return code >= CharCode.a && code <= CharCode.z;
}

export function isUpperAsciiLetter(code: number): boolean {
	return code >= CharCode.A && code <= CharCode.Z;
}

function isAsciiLetter(code: number): boolean {
	return isLowerAsciiLetter(code) || isUpperAsciiLetter(code);
}

export function equalsIgnoreCase(a: string, b: string): boolean {
	const len1 = a ? a.length : 0;
	const len2 = b ? b.length : 0;

	if (len1 !== len2) {
		return false;
	}

	return doEqualsIgnoreCase(a, b);
}

function doEqualsIgnoreCase(a: string, b: string, stopAt = a.length): boolean {
	if (typeof a !== 'string' || typeof b !== 'string') {
		return false;
	}

	for (let i = 0; i < stopAt; i++) {
		const codeA = a.charCodeAt(i);
		const codeB = b.charCodeAt(i);

		if (codeA === codeB) {
			continue;
		}

		// a-z A-Z
		if (isAsciiLetter(codeA) && isAsciiLetter(codeB)) {
			const diff = Math.abs(codeA - codeB);
			if (diff !== 0 && diff !== 32) {
				return false;
			}
		}

		// Any other charcode
		else {
			if (String.fromCharCode(codeA).toLowerCase() !== String.fromCharCode(codeB).toLowerCase()) {
				return false;
			}
		}
	}

	return true;
}

export function startsWithIgnoreCase(str: string, candidate: string): boolean {
	const candidateLength = candidate.length;
	if (candidate.length > str.length) {
		return false;
	}

	return doEqualsIgnoreCase(str, candidate, candidateLength);
}

/**
 * @returns the length of the common prefix of the two strings.
 */
export function commonPrefixLength(a: string, b: string): number {

	let i: number,
		len = Math.min(a.length, b.length);

	for (i = 0; i < len; i++) {
		if (a.charCodeAt(i) !== b.charCodeAt(i)) {
			return i;
		}
	}

	return len;
}

/**
 * @returns the length of the common suffix of the two strings.
 */
export function commonSuffixLength(a: string, b: string): number {

	let i: number,
		len = Math.min(a.length, b.length);

	const aLastIndex = a.length - 1;
	const bLastIndex = b.length - 1;

	for (i = 0; i < len; i++) {
		if (a.charCodeAt(aLastIndex - i) !== b.charCodeAt(bLastIndex - i)) {
			return i;
		}
	}

	return len;
}

function substrEquals(a: string, aStart: number, aEnd: number, b: string, bStart: number, bEnd: number): boolean {
	while (aStart < aEnd && bStart < bEnd) {
		if (a[aStart] !== b[bStart]) {
			return false;
		}
		aStart += 1;
		bStart += 1;
	}
	return true;
}

/**
 * Return the overlap between the suffix of `a` and the prefix of `b`.
 * For instance `overlap("foobar", "arr, I'm a pirate") === 2`.
 */
export function overlap(a: string, b: string): number {
	const aEnd = a.length;
	let bEnd = b.length;
	let aStart = aEnd - bEnd;

	if (aStart === 0) {
		return a === b ? aEnd : 0;
	} else if (aStart < 0) {
		bEnd += aStart;
		aStart = 0;
	}

	while (aStart < aEnd && bEnd > 0) {
		if (substrEquals(a, aStart, aEnd, b, 0, bEnd)) {
			return bEnd;
		}
		bEnd -= 1;
		aStart += 1;
	}
	return 0;
}

// --- unicode
// http://en.wikipedia.org/wiki/Surrogate_pair
// Returns the code point starting at a specified index in a string
// Code points U+0000 to U+D7FF and U+E000 to U+FFFF are represented on a single character
// Code points U+10000 to U+10FFFF are represented on two consecutive characters
//export function getUnicodePoint(str:string, index:number, len:number):number {
//	const chrCode = str.charCodeAt(index);
//	if (0xD800 <= chrCode && chrCode <= 0xDBFF && index + 1 < len) {
//		const nextChrCode = str.charCodeAt(index + 1);
//		if (0xDC00 <= nextChrCode && nextChrCode <= 0xDFFF) {
//			return (chrCode - 0xD800) << 10 + (nextChrCode - 0xDC00) + 0x10000;
//		}
//	}
//	return chrCode;
//}
export function isHighSurrogate(charCode: number): boolean {
	return (0xD800 <= charCode && charCode <= 0xDBFF);
}

export function isLowSurrogate(charCode: number): boolean {
	return (0xDC00 <= charCode && charCode <= 0xDFFF);
}

/**
 * Generated using https://github.com/alexandrudima/unicode-utils/blob/master/generate-rtl-test.js
 */
const CONTAINS_RTL = /(?:[\u05BE\u05C0\u05C3\u05C6\u05D0-\u05F4\u0608\u060B\u060D\u061B-\u064A\u066D-\u066F\u0671-\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u0710\u0712-\u072F\u074D-\u07A5\u07B1-\u07EA\u07F4\u07F5\u07FA-\u0815\u081A\u0824\u0828\u0830-\u0858\u085E-\u08BD\u200F\uFB1D\uFB1F-\uFB28\uFB2A-\uFD3D\uFD50-\uFDFC\uFE70-\uFEFC]|\uD802[\uDC00-\uDD1B\uDD20-\uDE00\uDE10-\uDE33\uDE40-\uDEE4\uDEEB-\uDF35\uDF40-\uDFFF]|\uD803[\uDC00-\uDCFF]|\uD83A[\uDC00-\uDCCF\uDD00-\uDD43\uDD50-\uDFFF]|\uD83B[\uDC00-\uDEBB])/;

/**
 * Returns true if `str` contains any Unicode character that is classified as "R" or "AL".
 */
export function containsRTL(str: string): boolean {
	return CONTAINS_RTL.test(str);
}

/**
 * Generated using https://github.com/alexandrudima/unicode-utils/blob/master/generate-emoji-test.js
 */
const CONTAINS_EMOJI = /(?:[\u231A\u231B\u23F0\u23F3\u2600-\u27BF\u2B50\u2B55]|\uD83C[\uDDE6-\uDDFF\uDF00-\uDFFF]|\uD83D[\uDC00-\uDE4F\uDE80-\uDEF8]|\uD83E[\uDD00-\uDDE6])/;

export function containsEmoji(str: string): boolean {
	return CONTAINS_EMOJI.test(str);
}

const IS_BASIC_ASCII = /^[\t\n\r\x20-\x7E]*$/;
/**
 * Returns true if `str` contains only basic ASCII characters in the range 32 - 126 (including 32 and 126) or \n, \r, \t
 */
export function isBasicASCII(str: string): boolean {
	return IS_BASIC_ASCII.test(str);
}

export function containsFullWidthCharacter(str: string): boolean {
	for (let i = 0, len = str.length; i < len; i++) {
		if (isFullWidthCharacter(str.charCodeAt(i))) {
			return true;
		}
	}
	return false;
}

export function isFullWidthCharacter(charCode: number): boolean {
	// Do a cheap trick to better support wrapping of wide characters, treat them as 2 columns
	// http://jrgraphix.net/research/unicode_blocks.php
	//          2E80 — 2EFF   CJK Radicals Supplement
	//          2F00 — 2FDF   Kangxi Radicals
	//          2FF0 — 2FFF   Ideographic Description Characters
	//          3000 — 303F   CJK Symbols and Punctuation
	//          3040 — 309F   Hiragana
	//          30A0 — 30FF   Katakana
	//          3100 — 312F   Bopomofo
	//          3130 — 318F   Hangul Compatibility Jamo
	//          3190 — 319F   Kanbun
	//          31A0 — 31BF   Bopomofo Extended
	//          31F0 — 31FF   Katakana Phonetic Extensions
	//          3200 — 32FF   Enclosed CJK Letters and Months
	//          3300 — 33FF   CJK Compatibility
	//          3400 — 4DBF   CJK Unified Ideographs Extension A
	//          4DC0 — 4DFF   Yijing Hexagram Symbols
	//          4E00 — 9FFF   CJK Unified Ideographs
	//          A000 — A48F   Yi Syllables
	//          A490 — A4CF   Yi Radicals
	//          AC00 — D7AF   Hangul Syllables
	// [IGNORE] D800 — DB7F   High Surrogates
	// [IGNORE] DB80 — DBFF   High Private Use Surrogates
	// [IGNORE] DC00 — DFFF   Low Surrogates
	// [IGNORE] E000 — F8FF   Private Use Area
	//          F900 — FAFF   CJK Compatibility Ideographs
	// [IGNORE] FB00 — FB4F   Alphabetic Presentation Forms
	// [IGNORE] FB50 — FDFF   Arabic Presentation Forms-A
	// [IGNORE] FE00 — FE0F   Variation Selectors
	// [IGNORE] FE20 — FE2F   Combining Half Marks
	// [IGNORE] FE30 — FE4F   CJK Compatibility Forms
	// [IGNORE] FE50 — FE6F   Small Form Variants
	// [IGNORE] FE70 — FEFF   Arabic Presentation Forms-B
	//          FF00 — FFEF   Halfwidth and Fullwidth Forms
	//               [https://en.wikipedia.org/wiki/Halfwidth_and_fullwidth_forms]
	//               of which FF01 - FF5E fullwidth ASCII of 21 to 7E
	// [IGNORE]    and FF65 - FFDC halfwidth of Katakana and Hangul
	// [IGNORE] FFF0 — FFFF   Specials
	charCode = +charCode; // @perf
	return (
		(charCode >= 0x2E80 && charCode <= 0xD7AF)
		|| (charCode >= 0xF900 && charCode <= 0xFAFF)
		|| (charCode >= 0xFF01 && charCode <= 0xFF5E)
	);
}

/**
 * Given a string and a max length returns a shorted version. Shorting
 * happens at favorable positions - such as whitespace or punctuation characters.
 */
export function lcut(text: string, n: number) {
	if (text.length < n) {
		return text;
	}

	const re = /\b/g;
	let i = 0;
	while (re.test(text)) {
		if (text.length - re.lastIndex < n) {
			break;
		}

		i = re.lastIndex;
		re.lastIndex += 1;
	}

	return text.substring(i).replace(/^\s/, empty);
}

// Escape codes
// http://en.wikipedia.org/wiki/ANSI_escape_code
const EL = /\x1B\x5B[12]?K/g; // Erase in line
const COLOR_START = /\x1b\[\d+m/g; // Color
const COLOR_END = /\x1b\[0?m/g; // Color

export function removeAnsiEscapeCodes(str: string): string {
	if (str) {
		str = str.replace(EL, '');
		str = str.replace(COLOR_START, '');
		str = str.replace(COLOR_END, '');
	}

	return str;
}

export const removeAccents: (str: string) => string = (function () {
	if (typeof (String.prototype as any).normalize !== 'function') {
		// ☹️ no ES6 features...
		return function (str: string) { return str; };
	} else {
		// transform into NFD form and remove accents
		// see: https://stackoverflow.com/questions/990904/remove-accents-diacritics-in-a-string-in-javascript/37511463#37511463
		const regex = /[\u0300-\u036f]/g;
		return function (str: string) {
			return (str as any).normalize('NFD').replace(regex, empty);
		};
	}
})();


// -- UTF-8 BOM

export const UTF8_BOM_CHARACTER = String.fromCharCode(CharCode.UTF8_BOM);

export function startsWithUTF8BOM(str: string): boolean {
	return !!(str && str.length > 0 && str.charCodeAt(0) === CharCode.UTF8_BOM);
}

export function stripUTF8BOM(str: string): string {
	return startsWithUTF8BOM(str) ? str.substr(1) : str;
}

export function safeBtoa(str: string): string {
	return btoa(encodeURIComponent(str)); // we use encodeURIComponent because btoa fails for non Latin 1 values
}

export function repeat(s: string, count: number): string {
	let result = '';
	for (let i = 0; i < count; i++) {
		result += s;
	}
	return result;
}

/**
 * Checks if the characters of the provided query string are included in the
 * target string. The characters do not have to be contiguous within the string.
 */
export function fuzzyContains(target: string, query: string): boolean {
	if (!target || !query) {
		return false; // return early if target or query are undefined
	}

	if (target.length < query.length) {
		return false; // impossible for query to be contained in target
	}

	const queryLen = query.length;
	const targetLower = target.toLowerCase();

	let index = 0;
	let lastIndexOf = -1;
	while (index < queryLen) {
		const indexOf = targetLower.indexOf(query[index], lastIndexOf + 1);
		if (indexOf < 0) {
			return false;
		}

		lastIndexOf = indexOf;

		index++;
	}

	return true;
}

export function containsUppercaseCharacter(target: string, ignoreEscapedChars = false): boolean {
	if (!target) {
		return false;
	}

	if (ignoreEscapedChars) {
		target = target.replace(/\\./g, '');
	}

	return target.toLowerCase() !== target;
}

export function uppercaseFirstLetter(str: string): string {
	return str.charAt(0).toUpperCase() + str.slice(1);
}

export function getNLines(str: string, n = 1): string {
	if (n === 0) {
		return '';
	}

	let idx = -1;
	do {
		idx = str.indexOf('\n', idx + 1);
		n--;
	} while (n > 0 && idx >= 0);

	return idx >= 0 ?
		str.substr(0, idx) :
		str;
}

/**
 * Produces 'a'-'z', followed by 'A'-'Z'... followed by 'a'-'z', etc.
 */
export function singleLetterHash(n: number): string {
	const LETTERS_CNT = (CharCode.Z - CharCode.A + 1);

	n = n % (2 * LETTERS_CNT);

	if (n < LETTERS_CNT) {
		return String.fromCharCode(CharCode.a + n);
	}

	return String.fromCharCode(CharCode.A + n - LETTERS_CNT);
}