449 lines
15 KiB
JavaScript
449 lines
15 KiB
JavaScript
|
/*---------------------------------------------------------------------------------------------
|
||
|
* Copyright (c) Microsoft Corporation. All rights reserved.
|
||
|
* Licensed under the MIT License. See License.txt in the project root for license information.
|
||
|
*--------------------------------------------------------------------------------------------*/
|
||
|
/**
|
||
|
* The empty string.
|
||
|
*/
|
||
|
export var empty = '';
|
||
|
export function isFalsyOrWhitespace(str) {
|
||
|
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, l, char) {
|
||
|
if (char === void 0) { char = '0'; }
|
||
|
var str = '' + n;
|
||
|
var r = [str];
|
||
|
for (var i = str.length; i < l; i++) {
|
||
|
r.push(char);
|
||
|
}
|
||
|
return r.reverse().join('');
|
||
|
}
|
||
|
var _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) {
|
||
|
var args = [];
|
||
|
for (var _i = 1; _i < arguments.length; _i++) {
|
||
|
args[_i - 1] = arguments[_i];
|
||
|
}
|
||
|
if (args.length === 0) {
|
||
|
return value;
|
||
|
}
|
||
|
return value.replace(_formatRegexp, function (match, group) {
|
||
|
var 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) {
|
||
|
return html.replace(/[<>&]/g, function (match) {
|
||
|
switch (match) {
|
||
|
case '<': return '<';
|
||
|
case '>': return '>';
|
||
|
case '&': return '&';
|
||
|
default: return match;
|
||
|
}
|
||
|
});
|
||
|
}
|
||
|
/**
|
||
|
* Escapes regular expression characters in a given string
|
||
|
*/
|
||
|
export function escapeRegExpCharacters(value) {
|
||
|
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, needle) {
|
||
|
if (needle === void 0) { needle = ' '; }
|
||
|
var 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, needle) {
|
||
|
if (!haystack || !needle) {
|
||
|
return haystack;
|
||
|
}
|
||
|
var needleLen = needle.length;
|
||
|
if (needleLen === 0 || haystack.length === 0) {
|
||
|
return haystack;
|
||
|
}
|
||
|
var 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, needle) {
|
||
|
if (!haystack || !needle) {
|
||
|
return haystack;
|
||
|
}
|
||
|
var needleLen = needle.length, haystackLen = haystack.length;
|
||
|
if (needleLen === 0 || haystackLen === 0) {
|
||
|
return haystack;
|
||
|
}
|
||
|
var 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) {
|
||
|
return pattern.replace(/[\-\\\{\}\+\?\|\^\$\.\,\[\]\(\)\#\s]/g, '\\$&').replace(/[\*]/g, '.*');
|
||
|
}
|
||
|
/**
|
||
|
* Determines if haystack starts with needle.
|
||
|
*/
|
||
|
export function startsWith(haystack, needle) {
|
||
|
if (haystack.length < needle.length) {
|
||
|
return false;
|
||
|
}
|
||
|
if (haystack === needle) {
|
||
|
return true;
|
||
|
}
|
||
|
for (var 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, needle) {
|
||
|
var 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 function createRegExp(searchString, isRegex, options) {
|
||
|
if (options === void 0) { options = {}; }
|
||
|
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';
|
||
|
}
|
||
|
}
|
||
|
var 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) {
|
||
|
// 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.
|
||
|
var match = regexp.exec('');
|
||
|
return !!(match && regexp.lastIndex === 0);
|
||
|
}
|
||
|
export function regExpFlags(regexp) {
|
||
|
return (regexp.global ? 'g' : '')
|
||
|
+ (regexp.ignoreCase ? 'i' : '')
|
||
|
+ (regexp.multiline ? 'm' : '')
|
||
|
+ (regexp.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) {
|
||
|
for (var i = 0, len = str.length; i < len; i++) {
|
||
|
var chCode = str.charCodeAt(i);
|
||
|
if (chCode !== 32 /* Space */ && chCode !== 9 /* 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, start, end) {
|
||
|
if (start === void 0) { start = 0; }
|
||
|
if (end === void 0) { end = str.length; }
|
||
|
for (var i = start; i < end; i++) {
|
||
|
var chCode = str.charCodeAt(i);
|
||
|
if (chCode !== 32 /* Space */ && chCode !== 9 /* 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, startIndex) {
|
||
|
if (startIndex === void 0) { startIndex = str.length - 1; }
|
||
|
for (var i = startIndex; i >= 0; i--) {
|
||
|
var chCode = str.charCodeAt(i);
|
||
|
if (chCode !== 32 /* Space */ && chCode !== 9 /* Tab */) {
|
||
|
return i;
|
||
|
}
|
||
|
}
|
||
|
return -1;
|
||
|
}
|
||
|
export function compare(a, b) {
|
||
|
if (a < b) {
|
||
|
return -1;
|
||
|
}
|
||
|
else if (a > b) {
|
||
|
return 1;
|
||
|
}
|
||
|
else {
|
||
|
return 0;
|
||
|
}
|
||
|
}
|
||
|
export function isLowerAsciiLetter(code) {
|
||
|
return code >= 97 /* a */ && code <= 122 /* z */;
|
||
|
}
|
||
|
export function isUpperAsciiLetter(code) {
|
||
|
return code >= 65 /* A */ && code <= 90 /* Z */;
|
||
|
}
|
||
|
function isAsciiLetter(code) {
|
||
|
return isLowerAsciiLetter(code) || isUpperAsciiLetter(code);
|
||
|
}
|
||
|
export function equalsIgnoreCase(a, b) {
|
||
|
var len1 = a ? a.length : 0;
|
||
|
var len2 = b ? b.length : 0;
|
||
|
if (len1 !== len2) {
|
||
|
return false;
|
||
|
}
|
||
|
return doEqualsIgnoreCase(a, b);
|
||
|
}
|
||
|
function doEqualsIgnoreCase(a, b, stopAt) {
|
||
|
if (stopAt === void 0) { stopAt = a.length; }
|
||
|
if (typeof a !== 'string' || typeof b !== 'string') {
|
||
|
return false;
|
||
|
}
|
||
|
for (var i = 0; i < stopAt; i++) {
|
||
|
var codeA = a.charCodeAt(i);
|
||
|
var codeB = b.charCodeAt(i);
|
||
|
if (codeA === codeB) {
|
||
|
continue;
|
||
|
}
|
||
|
// a-z A-Z
|
||
|
if (isAsciiLetter(codeA) && isAsciiLetter(codeB)) {
|
||
|
var 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, candidate) {
|
||
|
var 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, b) {
|
||
|
var i, 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, b) {
|
||
|
var i, len = Math.min(a.length, b.length);
|
||
|
var aLastIndex = a.length - 1;
|
||
|
var bLastIndex = b.length - 1;
|
||
|
for (i = 0; i < len; i++) {
|
||
|
if (a.charCodeAt(aLastIndex - i) !== b.charCodeAt(bLastIndex - i)) {
|
||
|
return i;
|
||
|
}
|
||
|
}
|
||
|
return len;
|
||
|
}
|
||
|
// --- 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) {
|
||
|
return (0xD800 <= charCode && charCode <= 0xDBFF);
|
||
|
}
|
||
|
export function isLowSurrogate(charCode) {
|
||
|
return (0xDC00 <= charCode && charCode <= 0xDFFF);
|
||
|
}
|
||
|
/**
|
||
|
* Generated using https://github.com/alexandrudima/unicode-utils/blob/master/generate-rtl-test.js
|
||
|
*/
|
||
|
var 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) {
|
||
|
return CONTAINS_RTL.test(str);
|
||
|
}
|
||
|
/**
|
||
|
* Generated using https://github.com/alexandrudima/unicode-utils/blob/master/generate-emoji-test.js
|
||
|
*/
|
||
|
var 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) {
|
||
|
return CONTAINS_EMOJI.test(str);
|
||
|
}
|
||
|
var 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) {
|
||
|
return IS_BASIC_ASCII.test(str);
|
||
|
}
|
||
|
export function containsFullWidthCharacter(str) {
|
||
|
for (var i = 0, len = str.length; i < len; i++) {
|
||
|
if (isFullWidthCharacter(str.charCodeAt(i))) {
|
||
|
return true;
|
||
|
}
|
||
|
}
|
||
|
return false;
|
||
|
}
|
||
|
export function isFullWidthCharacter(charCode) {
|
||
|
// 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));
|
||
|
}
|
||
|
// -- UTF-8 BOM
|
||
|
export var UTF8_BOM_CHARACTER = String.fromCharCode(65279 /* UTF8_BOM */);
|
||
|
export function startsWithUTF8BOM(str) {
|
||
|
return !!(str && str.length > 0 && str.charCodeAt(0) === 65279 /* UTF8_BOM */);
|
||
|
}
|
||
|
export function safeBtoa(str) {
|
||
|
return btoa(encodeURIComponent(str)); // we use encodeURIComponent because btoa fails for non Latin 1 values
|
||
|
}
|
||
|
export function repeat(s, count) {
|
||
|
var result = '';
|
||
|
for (var i = 0; i < count; i++) {
|
||
|
result += s;
|
||
|
}
|
||
|
return result;
|
||
|
}
|