1 | /*!
|
---|
2 | * Autolinker.js
|
---|
3 | * v3.16.2
|
---|
4 | *
|
---|
5 | * Copyright(c) 2022 Gregory Jacobs <greg@greg-jacobs.com>
|
---|
6 | * MIT License
|
---|
7 | *
|
---|
8 | * https://github.com/gregjacobs/Autolinker.js
|
---|
9 | */
|
---|
10 | (function (global, factory) {
|
---|
11 | typeof exports === 'object' && typeof module !== 'undefined' ? module.exports = factory() :
|
---|
12 | typeof define === 'function' && define.amd ? define(factory) :
|
---|
13 | (global = typeof globalThis !== 'undefined' ? globalThis : global || self, global.Autolinker = factory());
|
---|
14 | })(this, (function () { 'use strict';
|
---|
15 |
|
---|
16 | // Important: this file is generated from the 'build' script and should not be
|
---|
17 | // edited directly
|
---|
18 | var version = '3.16.2';
|
---|
19 |
|
---|
20 | /**
|
---|
21 | * Assigns (shallow copies) the properties of `src` onto `dest`, if the
|
---|
22 | * corresponding property on `dest` === `undefined`.
|
---|
23 | *
|
---|
24 | * @param {Object} dest The destination object.
|
---|
25 | * @param {Object} src The source object.
|
---|
26 | * @return {Object} The destination object (`dest`)
|
---|
27 | */
|
---|
28 | function defaults(dest, src) {
|
---|
29 | for (var prop in src) {
|
---|
30 | if (src.hasOwnProperty(prop) && dest[prop] === undefined) {
|
---|
31 | dest[prop] = src[prop];
|
---|
32 | }
|
---|
33 | }
|
---|
34 | return dest;
|
---|
35 | }
|
---|
36 | /**
|
---|
37 | * Truncates the `str` at `len - ellipsisChars.length`, and adds the `ellipsisChars` to the
|
---|
38 | * end of the string (by default, two periods: '..'). If the `str` length does not exceed
|
---|
39 | * `len`, the string will be returned unchanged.
|
---|
40 | *
|
---|
41 | * @param {String} str The string to truncate and add an ellipsis to.
|
---|
42 | * @param {Number} truncateLen The length to truncate the string at.
|
---|
43 | * @param {String} [ellipsisChars=...] The ellipsis character(s) to add to the end of `str`
|
---|
44 | * when truncated. Defaults to '...'
|
---|
45 | */
|
---|
46 | function ellipsis(str, truncateLen, ellipsisChars) {
|
---|
47 | var ellipsisLength;
|
---|
48 | if (str.length > truncateLen) {
|
---|
49 | if (ellipsisChars == null) {
|
---|
50 | ellipsisChars = '…';
|
---|
51 | ellipsisLength = 3;
|
---|
52 | }
|
---|
53 | else {
|
---|
54 | ellipsisLength = ellipsisChars.length;
|
---|
55 | }
|
---|
56 | str = str.substring(0, truncateLen - ellipsisLength) + ellipsisChars;
|
---|
57 | }
|
---|
58 | return str;
|
---|
59 | }
|
---|
60 | /**
|
---|
61 | * Supports `Array.prototype.indexOf()` functionality for old IE (IE8 and below).
|
---|
62 | *
|
---|
63 | * @param {Array} arr The array to find an element of.
|
---|
64 | * @param {*} element The element to find in the array, and return the index of.
|
---|
65 | * @return {Number} The index of the `element`, or -1 if it was not found.
|
---|
66 | */
|
---|
67 | function indexOf(arr, element) {
|
---|
68 | // @ts-ignore - As far as TypeScript is concerned, this method will always
|
---|
69 | // exist (lowest "lib" in TS is "ES5"). Hence we need to ignore this error
|
---|
70 | // to support IE8 which only implements ES3 and doesn't have this method
|
---|
71 | if (Array.prototype.indexOf) {
|
---|
72 | return arr.indexOf(element);
|
---|
73 | }
|
---|
74 | else {
|
---|
75 | for (var i = 0, len = arr.length; i < len; i++) {
|
---|
76 | if (arr[i] === element)
|
---|
77 | return i;
|
---|
78 | }
|
---|
79 | return -1;
|
---|
80 | }
|
---|
81 | }
|
---|
82 | /**
|
---|
83 | * Removes array elements based on a filtering function. Mutates the input
|
---|
84 | * array.
|
---|
85 | *
|
---|
86 | * Using this instead of the ES5 Array.prototype.filter() function, to allow
|
---|
87 | * Autolinker compatibility with IE8, and also to prevent creating many new
|
---|
88 | * arrays in memory for filtering.
|
---|
89 | *
|
---|
90 | * @param {Array} arr The array to remove elements from. This array is
|
---|
91 | * mutated.
|
---|
92 | * @param {Function} fn A function which should return `true` to
|
---|
93 | * remove an element.
|
---|
94 | * @return {Array} The mutated input `arr`.
|
---|
95 | */
|
---|
96 | function remove(arr, fn) {
|
---|
97 | for (var i = arr.length - 1; i >= 0; i--) {
|
---|
98 | if (fn(arr[i]) === true) {
|
---|
99 | arr.splice(i, 1);
|
---|
100 | }
|
---|
101 | }
|
---|
102 | }
|
---|
103 | /**
|
---|
104 | * Performs the functionality of what modern browsers do when `String.prototype.split()` is called
|
---|
105 | * with a regular expression that contains capturing parenthesis.
|
---|
106 | *
|
---|
107 | * For example:
|
---|
108 | *
|
---|
109 | * // Modern browsers:
|
---|
110 | * "a,b,c".split( /(,)/ ); // --> [ 'a', ',', 'b', ',', 'c' ]
|
---|
111 | *
|
---|
112 | * // Old IE (including IE8):
|
---|
113 | * "a,b,c".split( /(,)/ ); // --> [ 'a', 'b', 'c' ]
|
---|
114 | *
|
---|
115 | * This method emulates the functionality of modern browsers for the old IE case.
|
---|
116 | *
|
---|
117 | * @param {String} str The string to split.
|
---|
118 | * @param {RegExp} splitRegex The regular expression to split the input `str` on. The splitting
|
---|
119 | * character(s) will be spliced into the array, as in the "modern browsers" example in the
|
---|
120 | * description of this method.
|
---|
121 | * Note #1: the supplied regular expression **must** have the 'g' flag specified.
|
---|
122 | * Note #2: for simplicity's sake, the regular expression does not need
|
---|
123 | * to contain capturing parenthesis - it will be assumed that any match has them.
|
---|
124 | * @return {String[]} The split array of strings, with the splitting character(s) included.
|
---|
125 | */
|
---|
126 | function splitAndCapture(str, splitRegex) {
|
---|
127 | if (!splitRegex.global)
|
---|
128 | throw new Error("`splitRegex` must have the 'g' flag set");
|
---|
129 | var result = [], lastIdx = 0, match;
|
---|
130 | while ((match = splitRegex.exec(str))) {
|
---|
131 | result.push(str.substring(lastIdx, match.index));
|
---|
132 | result.push(match[0]); // push the splitting char(s)
|
---|
133 | lastIdx = match.index + match[0].length;
|
---|
134 | }
|
---|
135 | result.push(str.substring(lastIdx));
|
---|
136 | return result;
|
---|
137 | }
|
---|
138 | /**
|
---|
139 | * Function that should never be called but is used to check that every
|
---|
140 | * enum value is handled using TypeScript's 'never' type.
|
---|
141 | */
|
---|
142 | function throwUnhandledCaseError(theValue) {
|
---|
143 | throw new Error("Unhandled case for value: '".concat(theValue, "'"));
|
---|
144 | }
|
---|
145 |
|
---|
146 | /**
|
---|
147 | * @class Autolinker.HtmlTag
|
---|
148 | * @extends Object
|
---|
149 | *
|
---|
150 | * Represents an HTML tag, which can be used to easily build/modify HTML tags programmatically.
|
---|
151 | *
|
---|
152 | * Autolinker uses this abstraction to create HTML tags, and then write them out as strings. You may also use
|
---|
153 | * this class in your code, especially within a {@link Autolinker#replaceFn replaceFn}.
|
---|
154 | *
|
---|
155 | * ## Examples
|
---|
156 | *
|
---|
157 | * Example instantiation:
|
---|
158 | *
|
---|
159 | * var tag = new Autolinker.HtmlTag( {
|
---|
160 | * tagName : 'a',
|
---|
161 | * attrs : { 'href': 'http://google.com', 'class': 'external-link' },
|
---|
162 | * innerHtml : 'Google'
|
---|
163 | * } );
|
---|
164 | *
|
---|
165 | * tag.toAnchorString(); // <a href="http://google.com" class="external-link">Google</a>
|
---|
166 | *
|
---|
167 | * // Individual accessor methods
|
---|
168 | * tag.getTagName(); // 'a'
|
---|
169 | * tag.getAttr( 'href' ); // 'http://google.com'
|
---|
170 | * tag.hasClass( 'external-link' ); // true
|
---|
171 | *
|
---|
172 | *
|
---|
173 | * Using mutator methods (which may be used in combination with instantiation config properties):
|
---|
174 | *
|
---|
175 | * var tag = new Autolinker.HtmlTag();
|
---|
176 | * tag.setTagName( 'a' );
|
---|
177 | * tag.setAttr( 'href', 'http://google.com' );
|
---|
178 | * tag.addClass( 'external-link' );
|
---|
179 | * tag.setInnerHtml( 'Google' );
|
---|
180 | *
|
---|
181 | * tag.getTagName(); // 'a'
|
---|
182 | * tag.getAttr( 'href' ); // 'http://google.com'
|
---|
183 | * tag.hasClass( 'external-link' ); // true
|
---|
184 | *
|
---|
185 | * tag.toAnchorString(); // <a href="http://google.com" class="external-link">Google</a>
|
---|
186 | *
|
---|
187 | *
|
---|
188 | * ## Example use within a {@link Autolinker#replaceFn replaceFn}
|
---|
189 | *
|
---|
190 | * var html = Autolinker.link( "Test google.com", {
|
---|
191 | * replaceFn : function( match ) {
|
---|
192 | * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance, configured with the Match's href and anchor text
|
---|
193 | * tag.setAttr( 'rel', 'nofollow' );
|
---|
194 | *
|
---|
195 | * return tag;
|
---|
196 | * }
|
---|
197 | * } );
|
---|
198 | *
|
---|
199 | * // generated html:
|
---|
200 | * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a>
|
---|
201 | *
|
---|
202 | *
|
---|
203 | * ## Example use with a new tag for the replacement
|
---|
204 | *
|
---|
205 | * var html = Autolinker.link( "Test google.com", {
|
---|
206 | * replaceFn : function( match ) {
|
---|
207 | * var tag = new Autolinker.HtmlTag( {
|
---|
208 | * tagName : 'button',
|
---|
209 | * attrs : { 'title': 'Load URL: ' + match.getAnchorHref() },
|
---|
210 | * innerHtml : 'Load URL: ' + match.getAnchorText()
|
---|
211 | * } );
|
---|
212 | *
|
---|
213 | * return tag;
|
---|
214 | * }
|
---|
215 | * } );
|
---|
216 | *
|
---|
217 | * // generated html:
|
---|
218 | * // Test <button title="Load URL: http://google.com">Load URL: google.com</button>
|
---|
219 | */
|
---|
220 | var HtmlTag = /** @class */ (function () {
|
---|
221 | /**
|
---|
222 | * @method constructor
|
---|
223 | * @param {Object} [cfg] The configuration properties for this class, in an Object (map)
|
---|
224 | */
|
---|
225 | function HtmlTag(cfg) {
|
---|
226 | if (cfg === void 0) { cfg = {}; }
|
---|
227 | /**
|
---|
228 | * @cfg {String} tagName
|
---|
229 | *
|
---|
230 | * The tag name. Ex: 'a', 'button', etc.
|
---|
231 | *
|
---|
232 | * Not required at instantiation time, but should be set using {@link #setTagName} before {@link #toAnchorString}
|
---|
233 | * is executed.
|
---|
234 | */
|
---|
235 | this.tagName = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
236 | /**
|
---|
237 | * @cfg {Object.<String, String>} attrs
|
---|
238 | *
|
---|
239 | * An key/value Object (map) of attributes to create the tag with. The keys are the attribute names, and the
|
---|
240 | * values are the attribute values.
|
---|
241 | */
|
---|
242 | this.attrs = {}; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
243 | /**
|
---|
244 | * @cfg {String} innerHTML
|
---|
245 | *
|
---|
246 | * The inner HTML for the tag.
|
---|
247 | */
|
---|
248 | this.innerHTML = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
249 | /**
|
---|
250 | * @protected
|
---|
251 | * @property {RegExp} whitespaceRegex
|
---|
252 | *
|
---|
253 | * Regular expression used to match whitespace in a string of CSS classes.
|
---|
254 | */
|
---|
255 | this.whitespaceRegex = /\s+/; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
256 | this.tagName = cfg.tagName || '';
|
---|
257 | this.attrs = cfg.attrs || {};
|
---|
258 | this.innerHTML = cfg.innerHtml || cfg.innerHTML || ''; // accept either the camelCased form or the fully capitalized acronym as in the DOM
|
---|
259 | }
|
---|
260 | /**
|
---|
261 | * Sets the tag name that will be used to generate the tag with.
|
---|
262 | *
|
---|
263 | * @param {String} tagName
|
---|
264 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
265 | */
|
---|
266 | HtmlTag.prototype.setTagName = function (tagName) {
|
---|
267 | this.tagName = tagName;
|
---|
268 | return this;
|
---|
269 | };
|
---|
270 | /**
|
---|
271 | * Retrieves the tag name.
|
---|
272 | *
|
---|
273 | * @return {String}
|
---|
274 | */
|
---|
275 | HtmlTag.prototype.getTagName = function () {
|
---|
276 | return this.tagName || '';
|
---|
277 | };
|
---|
278 | /**
|
---|
279 | * Sets an attribute on the HtmlTag.
|
---|
280 | *
|
---|
281 | * @param {String} attrName The attribute name to set.
|
---|
282 | * @param {String} attrValue The attribute value to set.
|
---|
283 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
284 | */
|
---|
285 | HtmlTag.prototype.setAttr = function (attrName, attrValue) {
|
---|
286 | var tagAttrs = this.getAttrs();
|
---|
287 | tagAttrs[attrName] = attrValue;
|
---|
288 | return this;
|
---|
289 | };
|
---|
290 | /**
|
---|
291 | * Retrieves an attribute from the HtmlTag. If the attribute does not exist, returns `undefined`.
|
---|
292 | *
|
---|
293 | * @param {String} attrName The attribute name to retrieve.
|
---|
294 | * @return {String} The attribute's value, or `undefined` if it does not exist on the HtmlTag.
|
---|
295 | */
|
---|
296 | HtmlTag.prototype.getAttr = function (attrName) {
|
---|
297 | return this.getAttrs()[attrName];
|
---|
298 | };
|
---|
299 | /**
|
---|
300 | * Sets one or more attributes on the HtmlTag.
|
---|
301 | *
|
---|
302 | * @param {Object.<String, String>} attrs A key/value Object (map) of the attributes to set.
|
---|
303 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
304 | */
|
---|
305 | HtmlTag.prototype.setAttrs = function (attrs) {
|
---|
306 | Object.assign(this.getAttrs(), attrs);
|
---|
307 | return this;
|
---|
308 | };
|
---|
309 | /**
|
---|
310 | * Retrieves the attributes Object (map) for the HtmlTag.
|
---|
311 | *
|
---|
312 | * @return {Object.<String, String>} A key/value object of the attributes for the HtmlTag.
|
---|
313 | */
|
---|
314 | HtmlTag.prototype.getAttrs = function () {
|
---|
315 | return this.attrs || (this.attrs = {});
|
---|
316 | };
|
---|
317 | /**
|
---|
318 | * Sets the provided `cssClass`, overwriting any current CSS classes on the HtmlTag.
|
---|
319 | *
|
---|
320 | * @param {String} cssClass One or more space-separated CSS classes to set (overwrite).
|
---|
321 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
322 | */
|
---|
323 | HtmlTag.prototype.setClass = function (cssClass) {
|
---|
324 | return this.setAttr('class', cssClass);
|
---|
325 | };
|
---|
326 | /**
|
---|
327 | * Convenience method to add one or more CSS classes to the HtmlTag. Will not add duplicate CSS classes.
|
---|
328 | *
|
---|
329 | * @param {String} cssClass One or more space-separated CSS classes to add.
|
---|
330 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
331 | */
|
---|
332 | HtmlTag.prototype.addClass = function (cssClass) {
|
---|
333 | var classAttr = this.getClass(), whitespaceRegex = this.whitespaceRegex, classes = !classAttr ? [] : classAttr.split(whitespaceRegex), newClasses = cssClass.split(whitespaceRegex), newClass;
|
---|
334 | while ((newClass = newClasses.shift())) {
|
---|
335 | if (indexOf(classes, newClass) === -1) {
|
---|
336 | classes.push(newClass);
|
---|
337 | }
|
---|
338 | }
|
---|
339 | this.getAttrs()['class'] = classes.join(' ');
|
---|
340 | return this;
|
---|
341 | };
|
---|
342 | /**
|
---|
343 | * Convenience method to remove one or more CSS classes from the HtmlTag.
|
---|
344 | *
|
---|
345 | * @param {String} cssClass One or more space-separated CSS classes to remove.
|
---|
346 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
347 | */
|
---|
348 | HtmlTag.prototype.removeClass = function (cssClass) {
|
---|
349 | var classAttr = this.getClass(), whitespaceRegex = this.whitespaceRegex, classes = !classAttr ? [] : classAttr.split(whitespaceRegex), removeClasses = cssClass.split(whitespaceRegex), removeClass;
|
---|
350 | while (classes.length && (removeClass = removeClasses.shift())) {
|
---|
351 | var idx = indexOf(classes, removeClass);
|
---|
352 | if (idx !== -1) {
|
---|
353 | classes.splice(idx, 1);
|
---|
354 | }
|
---|
355 | }
|
---|
356 | this.getAttrs()['class'] = classes.join(' ');
|
---|
357 | return this;
|
---|
358 | };
|
---|
359 | /**
|
---|
360 | * Convenience method to retrieve the CSS class(es) for the HtmlTag, which will each be separated by spaces when
|
---|
361 | * there are multiple.
|
---|
362 | *
|
---|
363 | * @return {String}
|
---|
364 | */
|
---|
365 | HtmlTag.prototype.getClass = function () {
|
---|
366 | return this.getAttrs()['class'] || '';
|
---|
367 | };
|
---|
368 | /**
|
---|
369 | * Convenience method to check if the tag has a CSS class or not.
|
---|
370 | *
|
---|
371 | * @param {String} cssClass The CSS class to check for.
|
---|
372 | * @return {Boolean} `true` if the HtmlTag has the CSS class, `false` otherwise.
|
---|
373 | */
|
---|
374 | HtmlTag.prototype.hasClass = function (cssClass) {
|
---|
375 | return (' ' + this.getClass() + ' ').indexOf(' ' + cssClass + ' ') !== -1;
|
---|
376 | };
|
---|
377 | /**
|
---|
378 | * Sets the inner HTML for the tag.
|
---|
379 | *
|
---|
380 | * @param {String} html The inner HTML to set.
|
---|
381 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
382 | */
|
---|
383 | HtmlTag.prototype.setInnerHTML = function (html) {
|
---|
384 | this.innerHTML = html;
|
---|
385 | return this;
|
---|
386 | };
|
---|
387 | /**
|
---|
388 | * Backwards compatibility method name.
|
---|
389 | *
|
---|
390 | * @param {String} html The inner HTML to set.
|
---|
391 | * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
|
---|
392 | */
|
---|
393 | HtmlTag.prototype.setInnerHtml = function (html) {
|
---|
394 | return this.setInnerHTML(html);
|
---|
395 | };
|
---|
396 | /**
|
---|
397 | * Retrieves the inner HTML for the tag.
|
---|
398 | *
|
---|
399 | * @return {String}
|
---|
400 | */
|
---|
401 | HtmlTag.prototype.getInnerHTML = function () {
|
---|
402 | return this.innerHTML || '';
|
---|
403 | };
|
---|
404 | /**
|
---|
405 | * Backward compatibility method name.
|
---|
406 | *
|
---|
407 | * @return {String}
|
---|
408 | */
|
---|
409 | HtmlTag.prototype.getInnerHtml = function () {
|
---|
410 | return this.getInnerHTML();
|
---|
411 | };
|
---|
412 | /**
|
---|
413 | * Override of superclass method used to generate the HTML string for the tag.
|
---|
414 | *
|
---|
415 | * @return {String}
|
---|
416 | */
|
---|
417 | HtmlTag.prototype.toAnchorString = function () {
|
---|
418 | var tagName = this.getTagName(), attrsStr = this.buildAttrsStr();
|
---|
419 | attrsStr = attrsStr ? ' ' + attrsStr : ''; // prepend a space if there are actually attributes
|
---|
420 | return ['<', tagName, attrsStr, '>', this.getInnerHtml(), '</', tagName, '>'].join('');
|
---|
421 | };
|
---|
422 | /**
|
---|
423 | * Support method for {@link #toAnchorString}, returns the string space-separated key="value" pairs, used to populate
|
---|
424 | * the stringified HtmlTag.
|
---|
425 | *
|
---|
426 | * @protected
|
---|
427 | * @return {String} Example return: `attr1="value1" attr2="value2"`
|
---|
428 | */
|
---|
429 | HtmlTag.prototype.buildAttrsStr = function () {
|
---|
430 | if (!this.attrs)
|
---|
431 | return ''; // no `attrs` Object (map) has been set, return empty string
|
---|
432 | var attrs = this.getAttrs(), attrsArr = [];
|
---|
433 | for (var prop in attrs) {
|
---|
434 | if (attrs.hasOwnProperty(prop)) {
|
---|
435 | attrsArr.push(prop + '="' + attrs[prop] + '"');
|
---|
436 | }
|
---|
437 | }
|
---|
438 | return attrsArr.join(' ');
|
---|
439 | };
|
---|
440 | return HtmlTag;
|
---|
441 | }());
|
---|
442 |
|
---|
443 | /**
|
---|
444 | * Date: 2015-10-05
|
---|
445 | * Author: Kasper Søfren <soefritz@gmail.com> (https://github.com/kafoso)
|
---|
446 | *
|
---|
447 | * A truncation feature, where the ellipsis will be placed at a section within
|
---|
448 | * the URL making it still somewhat human readable.
|
---|
449 | *
|
---|
450 | * @param {String} url A URL.
|
---|
451 | * @param {Number} truncateLen The maximum length of the truncated output URL string.
|
---|
452 | * @param {String} ellipsisChars The characters to place within the url, e.g. "...".
|
---|
453 | * @return {String} The truncated URL.
|
---|
454 | */
|
---|
455 | function truncateSmart(url, truncateLen, ellipsisChars) {
|
---|
456 | var ellipsisLengthBeforeParsing;
|
---|
457 | var ellipsisLength;
|
---|
458 | if (ellipsisChars == null) {
|
---|
459 | ellipsisChars = '…';
|
---|
460 | ellipsisLength = 3;
|
---|
461 | ellipsisLengthBeforeParsing = 8;
|
---|
462 | }
|
---|
463 | else {
|
---|
464 | ellipsisLength = ellipsisChars.length;
|
---|
465 | ellipsisLengthBeforeParsing = ellipsisChars.length;
|
---|
466 | }
|
---|
467 | var parse_url = function (url) {
|
---|
468 | // Functionality inspired by PHP function of same name
|
---|
469 | var urlObj = {};
|
---|
470 | var urlSub = url;
|
---|
471 | var match = urlSub.match(/^([a-z]+):\/\//i);
|
---|
472 | if (match) {
|
---|
473 | urlObj.scheme = match[1];
|
---|
474 | urlSub = urlSub.substr(match[0].length);
|
---|
475 | }
|
---|
476 | match = urlSub.match(/^(.*?)(?=(\?|#|\/|$))/i);
|
---|
477 | if (match) {
|
---|
478 | urlObj.host = match[1];
|
---|
479 | urlSub = urlSub.substr(match[0].length);
|
---|
480 | }
|
---|
481 | match = urlSub.match(/^\/(.*?)(?=(\?|#|$))/i);
|
---|
482 | if (match) {
|
---|
483 | urlObj.path = match[1];
|
---|
484 | urlSub = urlSub.substr(match[0].length);
|
---|
485 | }
|
---|
486 | match = urlSub.match(/^\?(.*?)(?=(#|$))/i);
|
---|
487 | if (match) {
|
---|
488 | urlObj.query = match[1];
|
---|
489 | urlSub = urlSub.substr(match[0].length);
|
---|
490 | }
|
---|
491 | match = urlSub.match(/^#(.*?)$/i);
|
---|
492 | if (match) {
|
---|
493 | urlObj.fragment = match[1];
|
---|
494 | //urlSub = urlSub.substr(match[0].length); -- not used. Uncomment if adding another block.
|
---|
495 | }
|
---|
496 | return urlObj;
|
---|
497 | };
|
---|
498 | var buildUrl = function (urlObj) {
|
---|
499 | var url = '';
|
---|
500 | if (urlObj.scheme && urlObj.host) {
|
---|
501 | url += urlObj.scheme + '://';
|
---|
502 | }
|
---|
503 | if (urlObj.host) {
|
---|
504 | url += urlObj.host;
|
---|
505 | }
|
---|
506 | if (urlObj.path) {
|
---|
507 | url += '/' + urlObj.path;
|
---|
508 | }
|
---|
509 | if (urlObj.query) {
|
---|
510 | url += '?' + urlObj.query;
|
---|
511 | }
|
---|
512 | if (urlObj.fragment) {
|
---|
513 | url += '#' + urlObj.fragment;
|
---|
514 | }
|
---|
515 | return url;
|
---|
516 | };
|
---|
517 | var buildSegment = function (segment, remainingAvailableLength) {
|
---|
518 | var remainingAvailableLengthHalf = remainingAvailableLength / 2, startOffset = Math.ceil(remainingAvailableLengthHalf), endOffset = -1 * Math.floor(remainingAvailableLengthHalf), end = '';
|
---|
519 | if (endOffset < 0) {
|
---|
520 | end = segment.substr(endOffset);
|
---|
521 | }
|
---|
522 | return segment.substr(0, startOffset) + ellipsisChars + end;
|
---|
523 | };
|
---|
524 | if (url.length <= truncateLen) {
|
---|
525 | return url;
|
---|
526 | }
|
---|
527 | var availableLength = truncateLen - ellipsisLength;
|
---|
528 | var urlObj = parse_url(url);
|
---|
529 | // Clean up the URL
|
---|
530 | if (urlObj.query) {
|
---|
531 | var matchQuery = urlObj.query.match(/^(.*?)(?=(\?|\#))(.*?)$/i);
|
---|
532 | if (matchQuery) {
|
---|
533 | // Malformed URL; two or more "?". Removed any content behind the 2nd.
|
---|
534 | urlObj.query = urlObj.query.substr(0, matchQuery[1].length);
|
---|
535 | url = buildUrl(urlObj);
|
---|
536 | }
|
---|
537 | }
|
---|
538 | if (url.length <= truncateLen) {
|
---|
539 | return url;
|
---|
540 | }
|
---|
541 | if (urlObj.host) {
|
---|
542 | urlObj.host = urlObj.host.replace(/^www\./, '');
|
---|
543 | url = buildUrl(urlObj);
|
---|
544 | }
|
---|
545 | if (url.length <= truncateLen) {
|
---|
546 | return url;
|
---|
547 | }
|
---|
548 | // Process and build the URL
|
---|
549 | var str = '';
|
---|
550 | if (urlObj.host) {
|
---|
551 | str += urlObj.host;
|
---|
552 | }
|
---|
553 | if (str.length >= availableLength) {
|
---|
554 | if (urlObj.host.length == truncateLen) {
|
---|
555 | return (urlObj.host.substr(0, truncateLen - ellipsisLength) + ellipsisChars).substr(0, availableLength + ellipsisLengthBeforeParsing);
|
---|
556 | }
|
---|
557 | return buildSegment(str, availableLength).substr(0, availableLength + ellipsisLengthBeforeParsing);
|
---|
558 | }
|
---|
559 | var pathAndQuery = '';
|
---|
560 | if (urlObj.path) {
|
---|
561 | pathAndQuery += '/' + urlObj.path;
|
---|
562 | }
|
---|
563 | if (urlObj.query) {
|
---|
564 | pathAndQuery += '?' + urlObj.query;
|
---|
565 | }
|
---|
566 | if (pathAndQuery) {
|
---|
567 | if ((str + pathAndQuery).length >= availableLength) {
|
---|
568 | if ((str + pathAndQuery).length == truncateLen) {
|
---|
569 | return (str + pathAndQuery).substr(0, truncateLen);
|
---|
570 | }
|
---|
571 | var remainingAvailableLength = availableLength - str.length;
|
---|
572 | return (str + buildSegment(pathAndQuery, remainingAvailableLength)).substr(0, availableLength + ellipsisLengthBeforeParsing);
|
---|
573 | }
|
---|
574 | else {
|
---|
575 | str += pathAndQuery;
|
---|
576 | }
|
---|
577 | }
|
---|
578 | if (urlObj.fragment) {
|
---|
579 | var fragment = '#' + urlObj.fragment;
|
---|
580 | if ((str + fragment).length >= availableLength) {
|
---|
581 | if ((str + fragment).length == truncateLen) {
|
---|
582 | return (str + fragment).substr(0, truncateLen);
|
---|
583 | }
|
---|
584 | var remainingAvailableLength2 = availableLength - str.length;
|
---|
585 | return (str + buildSegment(fragment, remainingAvailableLength2)).substr(0, availableLength + ellipsisLengthBeforeParsing);
|
---|
586 | }
|
---|
587 | else {
|
---|
588 | str += fragment;
|
---|
589 | }
|
---|
590 | }
|
---|
591 | if (urlObj.scheme && urlObj.host) {
|
---|
592 | var scheme = urlObj.scheme + '://';
|
---|
593 | if ((str + scheme).length < availableLength) {
|
---|
594 | return (scheme + str).substr(0, truncateLen);
|
---|
595 | }
|
---|
596 | }
|
---|
597 | if (str.length <= truncateLen) {
|
---|
598 | return str;
|
---|
599 | }
|
---|
600 | var end = '';
|
---|
601 | if (availableLength > 0) {
|
---|
602 | end = str.substr(-1 * Math.floor(availableLength / 2));
|
---|
603 | }
|
---|
604 | return (str.substr(0, Math.ceil(availableLength / 2)) + ellipsisChars + end).substr(0, availableLength + ellipsisLengthBeforeParsing);
|
---|
605 | }
|
---|
606 |
|
---|
607 | /**
|
---|
608 | * Date: 2015-10-05
|
---|
609 | * Author: Kasper Søfren <soefritz@gmail.com> (https://github.com/kafoso)
|
---|
610 | *
|
---|
611 | * A truncation feature, where the ellipsis will be placed in the dead-center of the URL.
|
---|
612 | *
|
---|
613 | * @param {String} url A URL.
|
---|
614 | * @param {Number} truncateLen The maximum length of the truncated output URL string.
|
---|
615 | * @param {String} ellipsisChars The characters to place within the url, e.g. "..".
|
---|
616 | * @return {String} The truncated URL.
|
---|
617 | */
|
---|
618 | function truncateMiddle(url, truncateLen, ellipsisChars) {
|
---|
619 | if (url.length <= truncateLen) {
|
---|
620 | return url;
|
---|
621 | }
|
---|
622 | var ellipsisLengthBeforeParsing;
|
---|
623 | var ellipsisLength;
|
---|
624 | if (ellipsisChars == null) {
|
---|
625 | ellipsisChars = '…';
|
---|
626 | ellipsisLengthBeforeParsing = 8;
|
---|
627 | ellipsisLength = 3;
|
---|
628 | }
|
---|
629 | else {
|
---|
630 | ellipsisLengthBeforeParsing = ellipsisChars.length;
|
---|
631 | ellipsisLength = ellipsisChars.length;
|
---|
632 | }
|
---|
633 | var availableLength = truncateLen - ellipsisLength;
|
---|
634 | var end = '';
|
---|
635 | if (availableLength > 0) {
|
---|
636 | end = url.substr(-1 * Math.floor(availableLength / 2));
|
---|
637 | }
|
---|
638 | return (url.substr(0, Math.ceil(availableLength / 2)) + ellipsisChars + end).substr(0, availableLength + ellipsisLengthBeforeParsing);
|
---|
639 | }
|
---|
640 |
|
---|
641 | /**
|
---|
642 | * A truncation feature where the ellipsis will be placed at the end of the URL.
|
---|
643 | *
|
---|
644 | * @param {String} anchorText
|
---|
645 | * @param {Number} truncateLen The maximum length of the truncated output URL string.
|
---|
646 | * @param {String} ellipsisChars The characters to place within the url, e.g. "..".
|
---|
647 | * @return {String} The truncated URL.
|
---|
648 | */
|
---|
649 | function truncateEnd(anchorText, truncateLen, ellipsisChars) {
|
---|
650 | return ellipsis(anchorText, truncateLen, ellipsisChars);
|
---|
651 | }
|
---|
652 |
|
---|
653 | /**
|
---|
654 | * @protected
|
---|
655 | * @class Autolinker.AnchorTagBuilder
|
---|
656 | * @extends Object
|
---|
657 | *
|
---|
658 | * Builds anchor (<a>) tags for the Autolinker utility when a match is
|
---|
659 | * found.
|
---|
660 | *
|
---|
661 | * Normally this class is instantiated, configured, and used internally by an
|
---|
662 | * {@link Autolinker} instance, but may actually be used indirectly in a
|
---|
663 | * {@link Autolinker#replaceFn replaceFn} to create {@link Autolinker.HtmlTag HtmlTag}
|
---|
664 | * instances which may be modified before returning from the
|
---|
665 | * {@link Autolinker#replaceFn replaceFn}. For example:
|
---|
666 | *
|
---|
667 | * var html = Autolinker.link( "Test google.com", {
|
---|
668 | * replaceFn : function( match ) {
|
---|
669 | * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance
|
---|
670 | * tag.setAttr( 'rel', 'nofollow' );
|
---|
671 | *
|
---|
672 | * return tag;
|
---|
673 | * }
|
---|
674 | * } );
|
---|
675 | *
|
---|
676 | * // generated html:
|
---|
677 | * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a>
|
---|
678 | */
|
---|
679 | var AnchorTagBuilder = /** @class */ (function () {
|
---|
680 | /**
|
---|
681 | * @method constructor
|
---|
682 | * @param {Object} [cfg] The configuration options for the AnchorTagBuilder instance, specified in an Object (map).
|
---|
683 | */
|
---|
684 | function AnchorTagBuilder(cfg) {
|
---|
685 | if (cfg === void 0) { cfg = {}; }
|
---|
686 | /**
|
---|
687 | * @cfg {Boolean} newWindow
|
---|
688 | * @inheritdoc Autolinker#newWindow
|
---|
689 | */
|
---|
690 | this.newWindow = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
691 | /**
|
---|
692 | * @cfg {Object} truncate
|
---|
693 | * @inheritdoc Autolinker#truncate
|
---|
694 | */
|
---|
695 | this.truncate = {}; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
696 | /**
|
---|
697 | * @cfg {String} className
|
---|
698 | * @inheritdoc Autolinker#className
|
---|
699 | */
|
---|
700 | this.className = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
701 | this.newWindow = cfg.newWindow || false;
|
---|
702 | this.truncate = cfg.truncate || {};
|
---|
703 | this.className = cfg.className || '';
|
---|
704 | }
|
---|
705 | /**
|
---|
706 | * Generates the actual anchor (<a>) tag to use in place of the
|
---|
707 | * matched text, via its `match` object.
|
---|
708 | *
|
---|
709 | * @param {Autolinker.match.Match} match The Match instance to generate an
|
---|
710 | * anchor tag from.
|
---|
711 | * @return {Autolinker.HtmlTag} The HtmlTag instance for the anchor tag.
|
---|
712 | */
|
---|
713 | AnchorTagBuilder.prototype.build = function (match) {
|
---|
714 | return new HtmlTag({
|
---|
715 | tagName: 'a',
|
---|
716 | attrs: this.createAttrs(match),
|
---|
717 | innerHtml: this.processAnchorText(match.getAnchorText()),
|
---|
718 | });
|
---|
719 | };
|
---|
720 | /**
|
---|
721 | * Creates the Object (map) of the HTML attributes for the anchor (<a>)
|
---|
722 | * tag being generated.
|
---|
723 | *
|
---|
724 | * @protected
|
---|
725 | * @param {Autolinker.match.Match} match The Match instance to generate an
|
---|
726 | * anchor tag from.
|
---|
727 | * @return {Object} A key/value Object (map) of the anchor tag's attributes.
|
---|
728 | */
|
---|
729 | AnchorTagBuilder.prototype.createAttrs = function (match) {
|
---|
730 | var attrs = {
|
---|
731 | href: match.getAnchorHref(), // we'll always have the `href` attribute
|
---|
732 | };
|
---|
733 | var cssClass = this.createCssClass(match);
|
---|
734 | if (cssClass) {
|
---|
735 | attrs['class'] = cssClass;
|
---|
736 | }
|
---|
737 | if (this.newWindow) {
|
---|
738 | attrs['target'] = '_blank';
|
---|
739 | attrs['rel'] = 'noopener noreferrer'; // Issue #149. See https://mathiasbynens.github.io/rel-noopener/
|
---|
740 | }
|
---|
741 | if (this.truncate) {
|
---|
742 | if (this.truncate.length && this.truncate.length < match.getAnchorText().length) {
|
---|
743 | attrs['title'] = match.getAnchorHref();
|
---|
744 | }
|
---|
745 | }
|
---|
746 | return attrs;
|
---|
747 | };
|
---|
748 | /**
|
---|
749 | * Creates the CSS class that will be used for a given anchor tag, based on
|
---|
750 | * the `matchType` and the {@link #className} config.
|
---|
751 | *
|
---|
752 | * Example returns:
|
---|
753 | *
|
---|
754 | * - "" // no {@link #className}
|
---|
755 | * - "myLink myLink-url" // url match
|
---|
756 | * - "myLink myLink-email" // email match
|
---|
757 | * - "myLink myLink-phone" // phone match
|
---|
758 | * - "myLink myLink-hashtag" // hashtag match
|
---|
759 | * - "myLink myLink-mention myLink-twitter" // mention match with Twitter service
|
---|
760 | *
|
---|
761 | * @protected
|
---|
762 | * @param {Autolinker.match.Match} match The Match instance to generate an
|
---|
763 | * anchor tag from.
|
---|
764 | * @return {String} The CSS class string for the link. Example return:
|
---|
765 | * "myLink myLink-url". If no {@link #className} was configured, returns
|
---|
766 | * an empty string.
|
---|
767 | */
|
---|
768 | AnchorTagBuilder.prototype.createCssClass = function (match) {
|
---|
769 | var className = this.className;
|
---|
770 | if (!className) {
|
---|
771 | return '';
|
---|
772 | }
|
---|
773 | else {
|
---|
774 | var returnClasses = [className], cssClassSuffixes = match.getCssClassSuffixes();
|
---|
775 | for (var i = 0, len = cssClassSuffixes.length; i < len; i++) {
|
---|
776 | returnClasses.push(className + '-' + cssClassSuffixes[i]);
|
---|
777 | }
|
---|
778 | return returnClasses.join(' ');
|
---|
779 | }
|
---|
780 | };
|
---|
781 | /**
|
---|
782 | * Processes the `anchorText` by truncating the text according to the
|
---|
783 | * {@link #truncate} config.
|
---|
784 | *
|
---|
785 | * @private
|
---|
786 | * @param {String} anchorText The anchor tag's text (i.e. what will be
|
---|
787 | * displayed).
|
---|
788 | * @return {String} The processed `anchorText`.
|
---|
789 | */
|
---|
790 | AnchorTagBuilder.prototype.processAnchorText = function (anchorText) {
|
---|
791 | anchorText = this.doTruncate(anchorText);
|
---|
792 | return anchorText;
|
---|
793 | };
|
---|
794 | /**
|
---|
795 | * Performs the truncation of the `anchorText` based on the {@link #truncate}
|
---|
796 | * option. If the `anchorText` is longer than the length specified by the
|
---|
797 | * {@link #truncate} option, the truncation is performed based on the
|
---|
798 | * `location` property. See {@link #truncate} for details.
|
---|
799 | *
|
---|
800 | * @private
|
---|
801 | * @param {String} anchorText The anchor tag's text (i.e. what will be
|
---|
802 | * displayed).
|
---|
803 | * @return {String} The truncated anchor text.
|
---|
804 | */
|
---|
805 | AnchorTagBuilder.prototype.doTruncate = function (anchorText) {
|
---|
806 | var truncate = this.truncate;
|
---|
807 | if (!truncate || !truncate.length)
|
---|
808 | return anchorText;
|
---|
809 | var truncateLength = truncate.length, truncateLocation = truncate.location;
|
---|
810 | if (truncateLocation === 'smart') {
|
---|
811 | return truncateSmart(anchorText, truncateLength);
|
---|
812 | }
|
---|
813 | else if (truncateLocation === 'middle') {
|
---|
814 | return truncateMiddle(anchorText, truncateLength);
|
---|
815 | }
|
---|
816 | else {
|
---|
817 | return truncateEnd(anchorText, truncateLength);
|
---|
818 | }
|
---|
819 | };
|
---|
820 | return AnchorTagBuilder;
|
---|
821 | }());
|
---|
822 |
|
---|
823 | /**
|
---|
824 | * @abstract
|
---|
825 | * @class Autolinker.match.Match
|
---|
826 | *
|
---|
827 | * Represents a match found in an input string which should be Autolinked. A Match object is what is provided in a
|
---|
828 | * {@link Autolinker#replaceFn replaceFn}, and may be used to query for details about the match.
|
---|
829 | *
|
---|
830 | * For example:
|
---|
831 | *
|
---|
832 | * var input = "..."; // string with URLs, Email Addresses, and Mentions (Twitter, Instagram, Soundcloud)
|
---|
833 | *
|
---|
834 | * var linkedText = Autolinker.link( input, {
|
---|
835 | * replaceFn : function( match ) {
|
---|
836 | * console.log( "href = ", match.getAnchorHref() );
|
---|
837 | * console.log( "text = ", match.getAnchorText() );
|
---|
838 | *
|
---|
839 | * switch( match.getType() ) {
|
---|
840 | * case 'url' :
|
---|
841 | * console.log( "url: ", match.getUrl() );
|
---|
842 | *
|
---|
843 | * case 'email' :
|
---|
844 | * console.log( "email: ", match.getEmail() );
|
---|
845 | *
|
---|
846 | * case 'mention' :
|
---|
847 | * console.log( "mention: ", match.getMention() );
|
---|
848 | * }
|
---|
849 | * }
|
---|
850 | * } );
|
---|
851 | *
|
---|
852 | * See the {@link Autolinker} class for more details on using the {@link Autolinker#replaceFn replaceFn}.
|
---|
853 | */
|
---|
854 | var Match = /** @class */ (function () {
|
---|
855 | /**
|
---|
856 | * @member Autolinker.match.Match
|
---|
857 | * @method constructor
|
---|
858 | * @param {Object} cfg The configuration properties for the Match
|
---|
859 | * instance, specified in an Object (map).
|
---|
860 | */
|
---|
861 | function Match(cfg) {
|
---|
862 | /**
|
---|
863 | * @cfg {Autolinker.AnchorTagBuilder} tagBuilder (required)
|
---|
864 | *
|
---|
865 | * Reference to the AnchorTagBuilder instance to use to generate an anchor
|
---|
866 | * tag for the Match.
|
---|
867 | */
|
---|
868 | // @ts-ignore
|
---|
869 | this.__jsduckDummyDocProp = null; // property used just to get the above doc comment into the ES5 output and documentation generator
|
---|
870 | /**
|
---|
871 | * @cfg {String} matchedText (required)
|
---|
872 | *
|
---|
873 | * The original text that was matched by the {@link Autolinker.matcher.Matcher}.
|
---|
874 | */
|
---|
875 | this.matchedText = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
876 | /**
|
---|
877 | * @cfg {Number} offset (required)
|
---|
878 | *
|
---|
879 | * The offset of where the match was made in the input string.
|
---|
880 | */
|
---|
881 | this.offset = 0; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
882 | this.tagBuilder = cfg.tagBuilder;
|
---|
883 | this.matchedText = cfg.matchedText;
|
---|
884 | this.offset = cfg.offset;
|
---|
885 | }
|
---|
886 | /**
|
---|
887 | * Returns the original text that was matched.
|
---|
888 | *
|
---|
889 | * @return {String}
|
---|
890 | */
|
---|
891 | Match.prototype.getMatchedText = function () {
|
---|
892 | return this.matchedText;
|
---|
893 | };
|
---|
894 | /**
|
---|
895 | * Sets the {@link #offset} of where the match was made in the input string.
|
---|
896 | *
|
---|
897 | * A {@link Autolinker.matcher.Matcher} will be fed only HTML text nodes,
|
---|
898 | * and will therefore set an original offset that is relative to the HTML
|
---|
899 | * text node itself. However, we want this offset to be relative to the full
|
---|
900 | * HTML input string, and thus if using {@link Autolinker#parse} (rather
|
---|
901 | * than calling a {@link Autolinker.matcher.Matcher} directly), then this
|
---|
902 | * offset is corrected after the Matcher itself has done its job.
|
---|
903 | *
|
---|
904 | * @param {Number} offset
|
---|
905 | */
|
---|
906 | Match.prototype.setOffset = function (offset) {
|
---|
907 | this.offset = offset;
|
---|
908 | };
|
---|
909 | /**
|
---|
910 | * Returns the offset of where the match was made in the input string. This
|
---|
911 | * is the 0-based index of the match.
|
---|
912 | *
|
---|
913 | * @return {Number}
|
---|
914 | */
|
---|
915 | Match.prototype.getOffset = function () {
|
---|
916 | return this.offset;
|
---|
917 | };
|
---|
918 | /**
|
---|
919 | * Returns the CSS class suffix(es) for this match.
|
---|
920 | *
|
---|
921 | * A CSS class suffix is appended to the {@link Autolinker#className} in
|
---|
922 | * the {@link Autolinker.AnchorTagBuilder} when a match is translated into
|
---|
923 | * an anchor tag.
|
---|
924 | *
|
---|
925 | * For example, if {@link Autolinker#className} was configured as 'myLink',
|
---|
926 | * and this method returns `[ 'url' ]`, the final class name of the element
|
---|
927 | * will become: 'myLink myLink-url'.
|
---|
928 | *
|
---|
929 | * The match may provide multiple CSS class suffixes to be appended to the
|
---|
930 | * {@link Autolinker#className} in order to facilitate better styling
|
---|
931 | * options for different match criteria. See {@link Autolinker.match.Mention}
|
---|
932 | * for an example.
|
---|
933 | *
|
---|
934 | * By default, this method returns a single array with the match's
|
---|
935 | * {@link #getType type} name, but may be overridden by subclasses.
|
---|
936 | *
|
---|
937 | * @return {String[]}
|
---|
938 | */
|
---|
939 | Match.prototype.getCssClassSuffixes = function () {
|
---|
940 | return [this.getType()];
|
---|
941 | };
|
---|
942 | /**
|
---|
943 | * Builds and returns an {@link Autolinker.HtmlTag} instance based on the
|
---|
944 | * Match.
|
---|
945 | *
|
---|
946 | * This can be used to easily generate anchor tags from matches, and either
|
---|
947 | * return their HTML string, or modify them before doing so.
|
---|
948 | *
|
---|
949 | * Example Usage:
|
---|
950 | *
|
---|
951 | * var tag = match.buildTag();
|
---|
952 | * tag.addClass( 'cordova-link' );
|
---|
953 | * tag.setAttr( 'target', '_system' );
|
---|
954 | *
|
---|
955 | * tag.toAnchorString(); // <a href="http://google.com" class="cordova-link" target="_system">Google</a>
|
---|
956 | *
|
---|
957 | * Example Usage in {@link Autolinker#replaceFn}:
|
---|
958 | *
|
---|
959 | * var html = Autolinker.link( "Test google.com", {
|
---|
960 | * replaceFn : function( match ) {
|
---|
961 | * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance
|
---|
962 | * tag.setAttr( 'rel', 'nofollow' );
|
---|
963 | *
|
---|
964 | * return tag;
|
---|
965 | * }
|
---|
966 | * } );
|
---|
967 | *
|
---|
968 | * // generated html:
|
---|
969 | * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a>
|
---|
970 | */
|
---|
971 | Match.prototype.buildTag = function () {
|
---|
972 | return this.tagBuilder.build(this);
|
---|
973 | };
|
---|
974 | return Match;
|
---|
975 | }());
|
---|
976 |
|
---|
977 | /*! *****************************************************************************
|
---|
978 | Copyright (c) Microsoft Corporation.
|
---|
979 |
|
---|
980 | Permission to use, copy, modify, and/or distribute this software for any
|
---|
981 | purpose with or without fee is hereby granted.
|
---|
982 |
|
---|
983 | THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
|
---|
984 | REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
|
---|
985 | AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
|
---|
986 | INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
|
---|
987 | LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
|
---|
988 | OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
|
---|
989 | PERFORMANCE OF THIS SOFTWARE.
|
---|
990 | ***************************************************************************** */
|
---|
991 | /* global Reflect, Promise */
|
---|
992 |
|
---|
993 | var extendStatics = function(d, b) {
|
---|
994 | extendStatics = Object.setPrototypeOf ||
|
---|
995 | ({ __proto__: [] } instanceof Array && function (d, b) { d.__proto__ = b; }) ||
|
---|
996 | function (d, b) { for (var p in b) if (Object.prototype.hasOwnProperty.call(b, p)) d[p] = b[p]; };
|
---|
997 | return extendStatics(d, b);
|
---|
998 | };
|
---|
999 |
|
---|
1000 | function __extends(d, b) {
|
---|
1001 | if (typeof b !== "function" && b !== null)
|
---|
1002 | throw new TypeError("Class extends value " + String(b) + " is not a constructor or null");
|
---|
1003 | extendStatics(d, b);
|
---|
1004 | function __() { this.constructor = d; }
|
---|
1005 | d.prototype = b === null ? Object.create(b) : (__.prototype = b.prototype, new __());
|
---|
1006 | }
|
---|
1007 |
|
---|
1008 | var __assign = function() {
|
---|
1009 | __assign = Object.assign || function __assign(t) {
|
---|
1010 | for (var s, i = 1, n = arguments.length; i < n; i++) {
|
---|
1011 | s = arguments[i];
|
---|
1012 | for (var p in s) if (Object.prototype.hasOwnProperty.call(s, p)) t[p] = s[p];
|
---|
1013 | }
|
---|
1014 | return t;
|
---|
1015 | };
|
---|
1016 | return __assign.apply(this, arguments);
|
---|
1017 | };
|
---|
1018 |
|
---|
1019 | /**
|
---|
1020 | * @class Autolinker.match.Email
|
---|
1021 | * @extends Autolinker.match.Match
|
---|
1022 | *
|
---|
1023 | * Represents a Email match found in an input string which should be Autolinked.
|
---|
1024 | *
|
---|
1025 | * See this class's superclass ({@link Autolinker.match.Match}) for more details.
|
---|
1026 | */
|
---|
1027 | var EmailMatch = /** @class */ (function (_super) {
|
---|
1028 | __extends(EmailMatch, _super);
|
---|
1029 | /**
|
---|
1030 | * @method constructor
|
---|
1031 | * @param {Object} cfg The configuration properties for the Match
|
---|
1032 | * instance, specified in an Object (map).
|
---|
1033 | */
|
---|
1034 | function EmailMatch(cfg) {
|
---|
1035 | var _this = _super.call(this, cfg) || this;
|
---|
1036 | /**
|
---|
1037 | * @cfg {String} email (required)
|
---|
1038 | *
|
---|
1039 | * The email address that was matched.
|
---|
1040 | */
|
---|
1041 | _this.email = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1042 | _this.email = cfg.email;
|
---|
1043 | return _this;
|
---|
1044 | }
|
---|
1045 | /**
|
---|
1046 | * Returns a string name for the type of match that this class represents.
|
---|
1047 | * For the case of EmailMatch, returns 'email'.
|
---|
1048 | *
|
---|
1049 | * @return {String}
|
---|
1050 | */
|
---|
1051 | EmailMatch.prototype.getType = function () {
|
---|
1052 | return 'email';
|
---|
1053 | };
|
---|
1054 | /**
|
---|
1055 | * Returns the email address that was matched.
|
---|
1056 | *
|
---|
1057 | * @return {String}
|
---|
1058 | */
|
---|
1059 | EmailMatch.prototype.getEmail = function () {
|
---|
1060 | return this.email;
|
---|
1061 | };
|
---|
1062 | /**
|
---|
1063 | * Returns the anchor href that should be generated for the match.
|
---|
1064 | *
|
---|
1065 | * @return {String}
|
---|
1066 | */
|
---|
1067 | EmailMatch.prototype.getAnchorHref = function () {
|
---|
1068 | return 'mailto:' + this.email;
|
---|
1069 | };
|
---|
1070 | /**
|
---|
1071 | * Returns the anchor text that should be generated for the match.
|
---|
1072 | *
|
---|
1073 | * @return {String}
|
---|
1074 | */
|
---|
1075 | EmailMatch.prototype.getAnchorText = function () {
|
---|
1076 | return this.email;
|
---|
1077 | };
|
---|
1078 | return EmailMatch;
|
---|
1079 | }(Match));
|
---|
1080 |
|
---|
1081 | /**
|
---|
1082 | * @class Autolinker.match.Hashtag
|
---|
1083 | * @extends Autolinker.match.Match
|
---|
1084 | *
|
---|
1085 | * Represents a Hashtag match found in an input string which should be
|
---|
1086 | * Autolinked.
|
---|
1087 | *
|
---|
1088 | * See this class's superclass ({@link Autolinker.match.Match}) for more
|
---|
1089 | * details.
|
---|
1090 | */
|
---|
1091 | var HashtagMatch = /** @class */ (function (_super) {
|
---|
1092 | __extends(HashtagMatch, _super);
|
---|
1093 | /**
|
---|
1094 | * @method constructor
|
---|
1095 | * @param {Object} cfg The configuration properties for the Match
|
---|
1096 | * instance, specified in an Object (map).
|
---|
1097 | */
|
---|
1098 | function HashtagMatch(cfg) {
|
---|
1099 | var _this = _super.call(this, cfg) || this;
|
---|
1100 | /**
|
---|
1101 | * @cfg {String} serviceName
|
---|
1102 | *
|
---|
1103 | * The service to point hashtag matches to. See {@link Autolinker#hashtag}
|
---|
1104 | * for available values.
|
---|
1105 | */
|
---|
1106 | _this.serviceName = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1107 | /**
|
---|
1108 | * @cfg {String} hashtag (required)
|
---|
1109 | *
|
---|
1110 | * The HashtagMatch that was matched, without the '#'.
|
---|
1111 | */
|
---|
1112 | _this.hashtag = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1113 | _this.serviceName = cfg.serviceName;
|
---|
1114 | _this.hashtag = cfg.hashtag;
|
---|
1115 | return _this;
|
---|
1116 | }
|
---|
1117 | /**
|
---|
1118 | * Returns a string name for the type of match that this class represents.
|
---|
1119 | * For the case of HashtagMatch, returns 'hashtag'.
|
---|
1120 | *
|
---|
1121 | * @return {String}
|
---|
1122 | */
|
---|
1123 | HashtagMatch.prototype.getType = function () {
|
---|
1124 | return 'hashtag';
|
---|
1125 | };
|
---|
1126 | /**
|
---|
1127 | * Returns the configured {@link #serviceName} to point the HashtagMatch to.
|
---|
1128 | * Ex: 'facebook', 'twitter'.
|
---|
1129 | *
|
---|
1130 | * @return {String}
|
---|
1131 | */
|
---|
1132 | HashtagMatch.prototype.getServiceName = function () {
|
---|
1133 | return this.serviceName;
|
---|
1134 | };
|
---|
1135 | /**
|
---|
1136 | * Returns the matched hashtag, without the '#' character.
|
---|
1137 | *
|
---|
1138 | * @return {String}
|
---|
1139 | */
|
---|
1140 | HashtagMatch.prototype.getHashtag = function () {
|
---|
1141 | return this.hashtag;
|
---|
1142 | };
|
---|
1143 | /**
|
---|
1144 | * Returns the anchor href that should be generated for the match.
|
---|
1145 | *
|
---|
1146 | * @return {String}
|
---|
1147 | */
|
---|
1148 | HashtagMatch.prototype.getAnchorHref = function () {
|
---|
1149 | var serviceName = this.serviceName, hashtag = this.hashtag;
|
---|
1150 | switch (serviceName) {
|
---|
1151 | case 'twitter':
|
---|
1152 | return 'https://twitter.com/hashtag/' + hashtag;
|
---|
1153 | case 'facebook':
|
---|
1154 | return 'https://www.facebook.com/hashtag/' + hashtag;
|
---|
1155 | case 'instagram':
|
---|
1156 | return 'https://instagram.com/explore/tags/' + hashtag;
|
---|
1157 | case 'tiktok':
|
---|
1158 | return 'https://www.tiktok.com/tag/' + hashtag;
|
---|
1159 | default:
|
---|
1160 | // Shouldn't happen because Autolinker's constructor should block any invalid values, but just in case.
|
---|
1161 | throw new Error('Unknown service name to point hashtag to: ' + serviceName);
|
---|
1162 | }
|
---|
1163 | };
|
---|
1164 | /**
|
---|
1165 | * Returns the anchor text that should be generated for the match.
|
---|
1166 | *
|
---|
1167 | * @return {String}
|
---|
1168 | */
|
---|
1169 | HashtagMatch.prototype.getAnchorText = function () {
|
---|
1170 | return '#' + this.hashtag;
|
---|
1171 | };
|
---|
1172 | return HashtagMatch;
|
---|
1173 | }(Match));
|
---|
1174 |
|
---|
1175 | /**
|
---|
1176 | * @class Autolinker.match.Mention
|
---|
1177 | * @extends Autolinker.match.Match
|
---|
1178 | *
|
---|
1179 | * Represents a Mention match found in an input string which should be Autolinked.
|
---|
1180 | *
|
---|
1181 | * See this class's superclass ({@link Autolinker.match.Match}) for more details.
|
---|
1182 | */
|
---|
1183 | var MentionMatch = /** @class */ (function (_super) {
|
---|
1184 | __extends(MentionMatch, _super);
|
---|
1185 | /**
|
---|
1186 | * @method constructor
|
---|
1187 | * @param {Object} cfg The configuration properties for the Match
|
---|
1188 | * instance, specified in an Object (map).
|
---|
1189 | */
|
---|
1190 | function MentionMatch(cfg) {
|
---|
1191 | var _this = _super.call(this, cfg) || this;
|
---|
1192 | /**
|
---|
1193 | * @cfg {String} serviceName
|
---|
1194 | *
|
---|
1195 | * The service to point mention matches to. See {@link Autolinker#mention}
|
---|
1196 | * for available values.
|
---|
1197 | */
|
---|
1198 | _this.serviceName = 'twitter'; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1199 | /**
|
---|
1200 | * @cfg {String} mention (required)
|
---|
1201 | *
|
---|
1202 | * The Mention that was matched, without the '@' character.
|
---|
1203 | */
|
---|
1204 | _this.mention = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1205 | _this.mention = cfg.mention;
|
---|
1206 | _this.serviceName = cfg.serviceName;
|
---|
1207 | return _this;
|
---|
1208 | }
|
---|
1209 | /**
|
---|
1210 | * Returns a string name for the type of match that this class represents.
|
---|
1211 | * For the case of MentionMatch, returns 'mention'.
|
---|
1212 | *
|
---|
1213 | * @return {String}
|
---|
1214 | */
|
---|
1215 | MentionMatch.prototype.getType = function () {
|
---|
1216 | return 'mention';
|
---|
1217 | };
|
---|
1218 | /**
|
---|
1219 | * Returns the mention, without the '@' character.
|
---|
1220 | *
|
---|
1221 | * @return {String}
|
---|
1222 | */
|
---|
1223 | MentionMatch.prototype.getMention = function () {
|
---|
1224 | return this.mention;
|
---|
1225 | };
|
---|
1226 | /**
|
---|
1227 | * Returns the configured {@link #serviceName} to point the mention to.
|
---|
1228 | * Ex: 'instagram', 'twitter', 'soundcloud'.
|
---|
1229 | *
|
---|
1230 | * @return {String}
|
---|
1231 | */
|
---|
1232 | MentionMatch.prototype.getServiceName = function () {
|
---|
1233 | return this.serviceName;
|
---|
1234 | };
|
---|
1235 | /**
|
---|
1236 | * Returns the anchor href that should be generated for the match.
|
---|
1237 | *
|
---|
1238 | * @return {String}
|
---|
1239 | */
|
---|
1240 | MentionMatch.prototype.getAnchorHref = function () {
|
---|
1241 | switch (this.serviceName) {
|
---|
1242 | case 'twitter':
|
---|
1243 | return 'https://twitter.com/' + this.mention;
|
---|
1244 | case 'instagram':
|
---|
1245 | return 'https://instagram.com/' + this.mention;
|
---|
1246 | case 'soundcloud':
|
---|
1247 | return 'https://soundcloud.com/' + this.mention;
|
---|
1248 | case 'tiktok':
|
---|
1249 | return 'https://www.tiktok.com/@' + this.mention;
|
---|
1250 | default:
|
---|
1251 | // Shouldn't happen because Autolinker's constructor should block any invalid values, but just in case.
|
---|
1252 | throw new Error('Unknown service name to point mention to: ' + this.serviceName);
|
---|
1253 | }
|
---|
1254 | };
|
---|
1255 | /**
|
---|
1256 | * Returns the anchor text that should be generated for the match.
|
---|
1257 | *
|
---|
1258 | * @return {String}
|
---|
1259 | */
|
---|
1260 | MentionMatch.prototype.getAnchorText = function () {
|
---|
1261 | return '@' + this.mention;
|
---|
1262 | };
|
---|
1263 | /**
|
---|
1264 | * Returns the CSS class suffixes that should be used on a tag built with
|
---|
1265 | * the match. See {@link Autolinker.match.Match#getCssClassSuffixes} for
|
---|
1266 | * details.
|
---|
1267 | *
|
---|
1268 | * @return {String[]}
|
---|
1269 | */
|
---|
1270 | MentionMatch.prototype.getCssClassSuffixes = function () {
|
---|
1271 | var cssClassSuffixes = _super.prototype.getCssClassSuffixes.call(this), serviceName = this.getServiceName();
|
---|
1272 | if (serviceName) {
|
---|
1273 | cssClassSuffixes.push(serviceName);
|
---|
1274 | }
|
---|
1275 | return cssClassSuffixes;
|
---|
1276 | };
|
---|
1277 | return MentionMatch;
|
---|
1278 | }(Match));
|
---|
1279 |
|
---|
1280 | /**
|
---|
1281 | * @class Autolinker.match.Phone
|
---|
1282 | * @extends Autolinker.match.Match
|
---|
1283 | *
|
---|
1284 | * Represents a Phone number match found in an input string which should be
|
---|
1285 | * Autolinked.
|
---|
1286 | *
|
---|
1287 | * See this class's superclass ({@link Autolinker.match.Match}) for more
|
---|
1288 | * details.
|
---|
1289 | */
|
---|
1290 | var PhoneMatch = /** @class */ (function (_super) {
|
---|
1291 | __extends(PhoneMatch, _super);
|
---|
1292 | /**
|
---|
1293 | * @method constructor
|
---|
1294 | * @param {Object} cfg The configuration properties for the Match
|
---|
1295 | * instance, specified in an Object (map).
|
---|
1296 | */
|
---|
1297 | function PhoneMatch(cfg) {
|
---|
1298 | var _this = _super.call(this, cfg) || this;
|
---|
1299 | /**
|
---|
1300 | * @protected
|
---|
1301 | * @property {String} number (required)
|
---|
1302 | *
|
---|
1303 | * The phone number that was matched, without any delimiter characters.
|
---|
1304 | *
|
---|
1305 | * Note: This is a string to allow for prefixed 0's.
|
---|
1306 | */
|
---|
1307 | _this.number = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1308 | /**
|
---|
1309 | * @protected
|
---|
1310 | * @property {Boolean} plusSign (required)
|
---|
1311 | *
|
---|
1312 | * `true` if the matched phone number started with a '+' sign. We'll include
|
---|
1313 | * it in the `tel:` URL if so, as this is needed for international numbers.
|
---|
1314 | *
|
---|
1315 | * Ex: '+1 (123) 456 7879'
|
---|
1316 | */
|
---|
1317 | _this.plusSign = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1318 | _this.number = cfg.number;
|
---|
1319 | _this.plusSign = cfg.plusSign;
|
---|
1320 | return _this;
|
---|
1321 | }
|
---|
1322 | /**
|
---|
1323 | * Returns a string name for the type of match that this class represents.
|
---|
1324 | * For the case of PhoneMatch, returns 'phone'.
|
---|
1325 | *
|
---|
1326 | * @return {String}
|
---|
1327 | */
|
---|
1328 | PhoneMatch.prototype.getType = function () {
|
---|
1329 | return 'phone';
|
---|
1330 | };
|
---|
1331 | /**
|
---|
1332 | * Returns the phone number that was matched as a string, without any
|
---|
1333 | * delimiter characters.
|
---|
1334 | *
|
---|
1335 | * Note: This is a string to allow for prefixed 0's.
|
---|
1336 | *
|
---|
1337 | * @return {String}
|
---|
1338 | */
|
---|
1339 | PhoneMatch.prototype.getPhoneNumber = function () {
|
---|
1340 | return this.number;
|
---|
1341 | };
|
---|
1342 | /**
|
---|
1343 | * Alias of {@link #getPhoneNumber}, returns the phone number that was
|
---|
1344 | * matched as a string, without any delimiter characters.
|
---|
1345 | *
|
---|
1346 | * Note: This is a string to allow for prefixed 0's.
|
---|
1347 | *
|
---|
1348 | * @return {String}
|
---|
1349 | */
|
---|
1350 | PhoneMatch.prototype.getNumber = function () {
|
---|
1351 | return this.getPhoneNumber();
|
---|
1352 | };
|
---|
1353 | /**
|
---|
1354 | * Returns the anchor href that should be generated for the match.
|
---|
1355 | *
|
---|
1356 | * @return {String}
|
---|
1357 | */
|
---|
1358 | PhoneMatch.prototype.getAnchorHref = function () {
|
---|
1359 | return 'tel:' + (this.plusSign ? '+' : '') + this.number;
|
---|
1360 | };
|
---|
1361 | /**
|
---|
1362 | * Returns the anchor text that should be generated for the match.
|
---|
1363 | *
|
---|
1364 | * @return {String}
|
---|
1365 | */
|
---|
1366 | PhoneMatch.prototype.getAnchorText = function () {
|
---|
1367 | return this.matchedText;
|
---|
1368 | };
|
---|
1369 | return PhoneMatch;
|
---|
1370 | }(Match));
|
---|
1371 |
|
---|
1372 | /**
|
---|
1373 | * @class Autolinker.match.Url
|
---|
1374 | * @extends Autolinker.match.Match
|
---|
1375 | *
|
---|
1376 | * Represents a Url match found in an input string which should be Autolinked.
|
---|
1377 | *
|
---|
1378 | * See this class's superclass ({@link Autolinker.match.Match}) for more details.
|
---|
1379 | */
|
---|
1380 | var UrlMatch = /** @class */ (function (_super) {
|
---|
1381 | __extends(UrlMatch, _super);
|
---|
1382 | /**
|
---|
1383 | * @method constructor
|
---|
1384 | * @param {Object} cfg The configuration properties for the Match
|
---|
1385 | * instance, specified in an Object (map).
|
---|
1386 | */
|
---|
1387 | function UrlMatch(cfg) {
|
---|
1388 | var _this = _super.call(this, cfg) || this;
|
---|
1389 | /**
|
---|
1390 | * @cfg {String} url (required)
|
---|
1391 | *
|
---|
1392 | * The url that was matched.
|
---|
1393 | */
|
---|
1394 | _this.url = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1395 | /**
|
---|
1396 | * @cfg {"scheme"/"www"/"tld"} urlMatchType (required)
|
---|
1397 | *
|
---|
1398 | * The type of URL match that this class represents. This helps to determine
|
---|
1399 | * if the match was made in the original text with a prefixed scheme (ex:
|
---|
1400 | * 'http://www.google.com'), a prefixed 'www' (ex: 'www.google.com'), or
|
---|
1401 | * was matched by a known top-level domain (ex: 'google.com').
|
---|
1402 | */
|
---|
1403 | _this.urlMatchType = 'scheme'; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1404 | /**
|
---|
1405 | * @cfg {Boolean} protocolUrlMatch (required)
|
---|
1406 | *
|
---|
1407 | * `true` if the URL is a match which already has a protocol (i.e.
|
---|
1408 | * 'http://'), `false` if the match was from a 'www' or known TLD match.
|
---|
1409 | */
|
---|
1410 | _this.protocolUrlMatch = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1411 | /**
|
---|
1412 | * @cfg {Boolean} protocolRelativeMatch (required)
|
---|
1413 | *
|
---|
1414 | * `true` if the URL is a protocol-relative match. A protocol-relative match
|
---|
1415 | * is a URL that starts with '//', and will be either http:// or https://
|
---|
1416 | * based on the protocol that the site is loaded under.
|
---|
1417 | */
|
---|
1418 | _this.protocolRelativeMatch = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1419 | /**
|
---|
1420 | * @cfg {Object} stripPrefix (required)
|
---|
1421 | *
|
---|
1422 | * The Object form of {@link Autolinker#cfg-stripPrefix}.
|
---|
1423 | */
|
---|
1424 | _this.stripPrefix = {
|
---|
1425 | scheme: true,
|
---|
1426 | www: true,
|
---|
1427 | }; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1428 | /**
|
---|
1429 | * @cfg {Boolean} stripTrailingSlash (required)
|
---|
1430 | * @inheritdoc Autolinker#cfg-stripTrailingSlash
|
---|
1431 | */
|
---|
1432 | _this.stripTrailingSlash = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1433 | /**
|
---|
1434 | * @cfg {Boolean} decodePercentEncoding (required)
|
---|
1435 | * @inheritdoc Autolinker#cfg-decodePercentEncoding
|
---|
1436 | */
|
---|
1437 | _this.decodePercentEncoding = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
1438 | /**
|
---|
1439 | * @private
|
---|
1440 | * @property {RegExp} schemePrefixRegex
|
---|
1441 | *
|
---|
1442 | * A regular expression used to remove the 'http://' or 'https://' from
|
---|
1443 | * URLs.
|
---|
1444 | */
|
---|
1445 | _this.schemePrefixRegex = /^(https?:\/\/)?/i;
|
---|
1446 | /**
|
---|
1447 | * @private
|
---|
1448 | * @property {RegExp} wwwPrefixRegex
|
---|
1449 | *
|
---|
1450 | * A regular expression used to remove the 'www.' from URLs.
|
---|
1451 | */
|
---|
1452 | _this.wwwPrefixRegex = /^(https?:\/\/)?(www\.)?/i;
|
---|
1453 | /**
|
---|
1454 | * @private
|
---|
1455 | * @property {RegExp} protocolRelativeRegex
|
---|
1456 | *
|
---|
1457 | * The regular expression used to remove the protocol-relative '//' from the {@link #url} string, for purposes
|
---|
1458 | * of {@link #getAnchorText}. A protocol-relative URL is, for example, "//yahoo.com"
|
---|
1459 | */
|
---|
1460 | _this.protocolRelativeRegex = /^\/\//;
|
---|
1461 | /**
|
---|
1462 | * @private
|
---|
1463 | * @property {Boolean} protocolPrepended
|
---|
1464 | *
|
---|
1465 | * Will be set to `true` if the 'http://' protocol has been prepended to the {@link #url} (because the
|
---|
1466 | * {@link #url} did not have a protocol)
|
---|
1467 | */
|
---|
1468 | _this.protocolPrepended = false;
|
---|
1469 | _this.urlMatchType = cfg.urlMatchType;
|
---|
1470 | _this.url = cfg.url;
|
---|
1471 | _this.protocolUrlMatch = cfg.protocolUrlMatch;
|
---|
1472 | _this.protocolRelativeMatch = cfg.protocolRelativeMatch;
|
---|
1473 | _this.stripPrefix = cfg.stripPrefix;
|
---|
1474 | _this.stripTrailingSlash = cfg.stripTrailingSlash;
|
---|
1475 | _this.decodePercentEncoding = cfg.decodePercentEncoding;
|
---|
1476 | return _this;
|
---|
1477 | }
|
---|
1478 | /**
|
---|
1479 | * Returns a string name for the type of match that this class represents.
|
---|
1480 | * For the case of UrlMatch, returns 'url'.
|
---|
1481 | *
|
---|
1482 | * @return {String}
|
---|
1483 | */
|
---|
1484 | UrlMatch.prototype.getType = function () {
|
---|
1485 | return 'url';
|
---|
1486 | };
|
---|
1487 | /**
|
---|
1488 | * Returns a string name for the type of URL match that this class
|
---|
1489 | * represents.
|
---|
1490 | *
|
---|
1491 | * This helps to determine if the match was made in the original text with a
|
---|
1492 | * prefixed scheme (ex: 'http://www.google.com'), a prefixed 'www' (ex:
|
---|
1493 | * 'www.google.com'), or was matched by a known top-level domain (ex:
|
---|
1494 | * 'google.com').
|
---|
1495 | *
|
---|
1496 | * @return {"scheme"/"www"/"tld"}
|
---|
1497 | */
|
---|
1498 | UrlMatch.prototype.getUrlMatchType = function () {
|
---|
1499 | return this.urlMatchType;
|
---|
1500 | };
|
---|
1501 | /**
|
---|
1502 | * Returns the url that was matched, assuming the protocol to be 'http://' if the original
|
---|
1503 | * match was missing a protocol.
|
---|
1504 | *
|
---|
1505 | * @return {String}
|
---|
1506 | */
|
---|
1507 | UrlMatch.prototype.getUrl = function () {
|
---|
1508 | var url = this.url;
|
---|
1509 | // if the url string doesn't begin with a protocol, assume 'http://'
|
---|
1510 | if (!this.protocolRelativeMatch && !this.protocolUrlMatch && !this.protocolPrepended) {
|
---|
1511 | url = this.url = 'http://' + url;
|
---|
1512 | this.protocolPrepended = true;
|
---|
1513 | }
|
---|
1514 | return url;
|
---|
1515 | };
|
---|
1516 | /**
|
---|
1517 | * Returns the anchor href that should be generated for the match.
|
---|
1518 | *
|
---|
1519 | * @return {String}
|
---|
1520 | */
|
---|
1521 | UrlMatch.prototype.getAnchorHref = function () {
|
---|
1522 | var url = this.getUrl();
|
---|
1523 | return url.replace(/&/g, '&'); // any &'s in the URL should be converted back to '&' if they were displayed as & in the source html
|
---|
1524 | };
|
---|
1525 | /**
|
---|
1526 | * Returns the anchor text that should be generated for the match.
|
---|
1527 | *
|
---|
1528 | * @return {String}
|
---|
1529 | */
|
---|
1530 | UrlMatch.prototype.getAnchorText = function () {
|
---|
1531 | var anchorText = this.getMatchedText();
|
---|
1532 | if (this.protocolRelativeMatch) {
|
---|
1533 | // Strip off any protocol-relative '//' from the anchor text
|
---|
1534 | anchorText = this.stripProtocolRelativePrefix(anchorText);
|
---|
1535 | }
|
---|
1536 | if (this.stripPrefix.scheme) {
|
---|
1537 | anchorText = this.stripSchemePrefix(anchorText);
|
---|
1538 | }
|
---|
1539 | if (this.stripPrefix.www) {
|
---|
1540 | anchorText = this.stripWwwPrefix(anchorText);
|
---|
1541 | }
|
---|
1542 | if (this.stripTrailingSlash) {
|
---|
1543 | anchorText = this.removeTrailingSlash(anchorText); // remove trailing slash, if there is one
|
---|
1544 | }
|
---|
1545 | if (this.decodePercentEncoding) {
|
---|
1546 | anchorText = this.removePercentEncoding(anchorText);
|
---|
1547 | }
|
---|
1548 | return anchorText;
|
---|
1549 | };
|
---|
1550 | // ---------------------------------------
|
---|
1551 | // Utility Functionality
|
---|
1552 | /**
|
---|
1553 | * Strips the scheme prefix (such as "http://" or "https://") from the given
|
---|
1554 | * `url`.
|
---|
1555 | *
|
---|
1556 | * @private
|
---|
1557 | * @param {String} url The text of the anchor that is being generated, for
|
---|
1558 | * which to strip off the url scheme.
|
---|
1559 | * @return {String} The `url`, with the scheme stripped.
|
---|
1560 | */
|
---|
1561 | UrlMatch.prototype.stripSchemePrefix = function (url) {
|
---|
1562 | return url.replace(this.schemePrefixRegex, '');
|
---|
1563 | };
|
---|
1564 | /**
|
---|
1565 | * Strips the 'www' prefix from the given `url`.
|
---|
1566 | *
|
---|
1567 | * @private
|
---|
1568 | * @param {String} url The text of the anchor that is being generated, for
|
---|
1569 | * which to strip off the 'www' if it exists.
|
---|
1570 | * @return {String} The `url`, with the 'www' stripped.
|
---|
1571 | */
|
---|
1572 | UrlMatch.prototype.stripWwwPrefix = function (url) {
|
---|
1573 | return url.replace(this.wwwPrefixRegex, '$1'); // leave any scheme ($1), it one exists
|
---|
1574 | };
|
---|
1575 | /**
|
---|
1576 | * Strips any protocol-relative '//' from the anchor text.
|
---|
1577 | *
|
---|
1578 | * @private
|
---|
1579 | * @param {String} text The text of the anchor that is being generated, for which to strip off the
|
---|
1580 | * protocol-relative prefix (such as stripping off "//")
|
---|
1581 | * @return {String} The `anchorText`, with the protocol-relative prefix stripped.
|
---|
1582 | */
|
---|
1583 | UrlMatch.prototype.stripProtocolRelativePrefix = function (text) {
|
---|
1584 | return text.replace(this.protocolRelativeRegex, '');
|
---|
1585 | };
|
---|
1586 | /**
|
---|
1587 | * Removes any trailing slash from the given `anchorText`, in preparation for the text to be displayed.
|
---|
1588 | *
|
---|
1589 | * @private
|
---|
1590 | * @param {String} anchorText The text of the anchor that is being generated, for which to remove any trailing
|
---|
1591 | * slash ('/') that may exist.
|
---|
1592 | * @return {String} The `anchorText`, with the trailing slash removed.
|
---|
1593 | */
|
---|
1594 | UrlMatch.prototype.removeTrailingSlash = function (anchorText) {
|
---|
1595 | if (anchorText.charAt(anchorText.length - 1) === '/') {
|
---|
1596 | anchorText = anchorText.slice(0, -1);
|
---|
1597 | }
|
---|
1598 | return anchorText;
|
---|
1599 | };
|
---|
1600 | /**
|
---|
1601 | * Decodes percent-encoded characters from the given `anchorText`, in
|
---|
1602 | * preparation for the text to be displayed.
|
---|
1603 | *
|
---|
1604 | * @private
|
---|
1605 | * @param {String} anchorText The text of the anchor that is being
|
---|
1606 | * generated, for which to decode any percent-encoded characters.
|
---|
1607 | * @return {String} The `anchorText`, with the percent-encoded characters
|
---|
1608 | * decoded.
|
---|
1609 | */
|
---|
1610 | UrlMatch.prototype.removePercentEncoding = function (anchorText) {
|
---|
1611 | // First, convert a few of the known % encodings to the corresponding
|
---|
1612 | // HTML entities that could accidentally be interpretted as special
|
---|
1613 | // HTML characters
|
---|
1614 | var preProcessedEntityAnchorText = anchorText
|
---|
1615 | .replace(/%22/gi, '"') // " char
|
---|
1616 | .replace(/%26/gi, '&') // & char
|
---|
1617 | .replace(/%27/gi, ''') // ' char
|
---|
1618 | .replace(/%3C/gi, '<') // < char
|
---|
1619 | .replace(/%3E/gi, '>'); // > char
|
---|
1620 | try {
|
---|
1621 | // Now attempt to decode the rest of the anchor text
|
---|
1622 | return decodeURIComponent(preProcessedEntityAnchorText);
|
---|
1623 | }
|
---|
1624 | catch (e) {
|
---|
1625 | // Invalid % escape sequence in the anchor text
|
---|
1626 | return preProcessedEntityAnchorText;
|
---|
1627 | }
|
---|
1628 | };
|
---|
1629 | return UrlMatch;
|
---|
1630 | }(Match));
|
---|
1631 |
|
---|
1632 | /**
|
---|
1633 | * @abstract
|
---|
1634 | * @class Autolinker.matcher.Matcher
|
---|
1635 | *
|
---|
1636 | * An abstract class and interface for individual matchers to find matches in
|
---|
1637 | * an input string with linkified versions of them.
|
---|
1638 | *
|
---|
1639 | * Note that Matchers do not take HTML into account - they must be fed the text
|
---|
1640 | * nodes of any HTML string, which is handled by {@link Autolinker#parse}.
|
---|
1641 | */
|
---|
1642 | var Matcher = /** @class */ (function () {
|
---|
1643 | /**
|
---|
1644 | * @method constructor
|
---|
1645 | * @param {Object} cfg The configuration properties for the Matcher
|
---|
1646 | * instance, specified in an Object (map).
|
---|
1647 | */
|
---|
1648 | function Matcher(cfg) {
|
---|
1649 | /**
|
---|
1650 | * @cfg {Autolinker.AnchorTagBuilder} tagBuilder (required)
|
---|
1651 | *
|
---|
1652 | * Reference to the AnchorTagBuilder instance to use to generate HTML tags
|
---|
1653 | * for {@link Autolinker.match.Match Matches}.
|
---|
1654 | */
|
---|
1655 | // @ts-ignore
|
---|
1656 | this.__jsduckDummyDocProp = null; // property used just to get the above doc comment into the ES5 output and documentation generator
|
---|
1657 | this.tagBuilder = cfg.tagBuilder;
|
---|
1658 | }
|
---|
1659 | return Matcher;
|
---|
1660 | }());
|
---|
1661 |
|
---|
1662 | /*
|
---|
1663 | * This file builds and stores a library of the common regular expressions used
|
---|
1664 | * by the Autolinker utility.
|
---|
1665 | *
|
---|
1666 | * Other regular expressions may exist ad-hoc, but these are generally the
|
---|
1667 | * regular expressions that are shared between source files.
|
---|
1668 | */
|
---|
1669 | /**
|
---|
1670 | * Regular expression to match upper and lowercase ASCII letters
|
---|
1671 | */
|
---|
1672 | var letterRe = /[A-Za-z]/;
|
---|
1673 | /**
|
---|
1674 | * Regular expression to match ASCII digits
|
---|
1675 | */
|
---|
1676 | var digitRe = /[\d]/;
|
---|
1677 | /**
|
---|
1678 | * Regular expression to match everything *except* ASCII digits
|
---|
1679 | */
|
---|
1680 | var nonDigitRe = /[\D]/;
|
---|
1681 | /**
|
---|
1682 | * Regular expression to match whitespace
|
---|
1683 | */
|
---|
1684 | var whitespaceRe = /\s/;
|
---|
1685 | /**
|
---|
1686 | * Regular expression to match quote characters
|
---|
1687 | */
|
---|
1688 | var quoteRe = /['"]/;
|
---|
1689 | /**
|
---|
1690 | * Regular expression to match the range of ASCII control characters (0-31), and
|
---|
1691 | * the backspace char (127)
|
---|
1692 | */
|
---|
1693 | var controlCharsRe = /[\x00-\x1F\x7F]/;
|
---|
1694 | /**
|
---|
1695 | * The string form of a regular expression that would match all of the
|
---|
1696 | * alphabetic ("letter") chars in the unicode character set when placed in a
|
---|
1697 | * RegExp character class (`[]`). This includes all international alphabetic
|
---|
1698 | * characters.
|
---|
1699 | *
|
---|
1700 | * These would be the characters matched by unicode regex engines `\p{L}`
|
---|
1701 | * escape ("all letters").
|
---|
1702 | *
|
---|
1703 | * Taken from the XRegExp library: http://xregexp.com/ (thanks @https://github.com/slevithan)
|
---|
1704 | * Specifically: http://xregexp.com/v/3.2.0/xregexp-all.js, the 'Letter'
|
---|
1705 | * regex's bmp
|
---|
1706 | *
|
---|
1707 | * VERY IMPORTANT: This set of characters is defined inside of a Regular
|
---|
1708 | * Expression literal rather than a string literal to prevent UglifyJS from
|
---|
1709 | * compressing the unicode escape sequences into their actual unicode
|
---|
1710 | * characters. If Uglify compresses these into the unicode characters
|
---|
1711 | * themselves, this results in the error "Range out of order in character
|
---|
1712 | * class" when these characters are used inside of a Regular Expression
|
---|
1713 | * character class (`[]`). See usages of this const. Alternatively, we can set
|
---|
1714 | * the UglifyJS option `ascii_only` to true for the build, but that doesn't
|
---|
1715 | * help others who are pulling in Autolinker into their own build and running
|
---|
1716 | * UglifyJS themselves.
|
---|
1717 | */
|
---|
1718 | // prettier-ignore
|
---|
1719 | var alphaCharsStr = /A-Za-z\xAA\xB5\xBA\xC0-\xD6\xD8-\xF6\xF8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u037F\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u052F\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0-\u08B4\u08B6-\u08BD\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0980\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0AF9\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C39\u0C3D\u0C58-\u0C5A\u0C60\u0C61\u0C80\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D54-\u0D56\u0D5F-\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F5\u13F8-\u13FD\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16F1-\u16F8\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u1884\u1887-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191E\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19B0-\u19C9\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1C80-\u1C88\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FD5\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA69D\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA7AE\uA7B0-\uA7B7\uA7F7-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA8FD\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uA9E0-\uA9E4\uA9E6-\uA9EF\uA9FA-\uA9FE\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA7E-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uAB30-\uAB5A\uAB5C-\uAB65\uAB70-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC/
|
---|
1720 | .source; // see note in above variable description
|
---|
1721 | /**
|
---|
1722 | * The string form of a regular expression that would match all emoji characters
|
---|
1723 | * Based on the emoji regex defined in this article: https://thekevinscott.com/emojis-in-javascript/
|
---|
1724 | */
|
---|
1725 | var emojiStr = /\u2700-\u27bf\udde6-\uddff\ud800-\udbff\udc00-\udfff\ufe0e\ufe0f\u0300-\u036f\ufe20-\ufe23\u20d0-\u20f0\ud83c\udffb-\udfff\u200d\u3299\u3297\u303d\u3030\u24c2\ud83c\udd70-\udd71\udd7e-\udd7f\udd8e\udd91-\udd9a\udde6-\uddff\ude01-\ude02\ude1a\ude2f\ude32-\ude3a\ude50-\ude51\u203c\u2049\u25aa-\u25ab\u25b6\u25c0\u25fb-\u25fe\u00a9\u00ae\u2122\u2139\udc04\u2600-\u26FF\u2b05\u2b06\u2b07\u2b1b\u2b1c\u2b50\u2b55\u231a\u231b\u2328\u23cf\u23e9-\u23f3\u23f8-\u23fa\udccf\u2935\u2934\u2190-\u21ff/
|
---|
1726 | .source;
|
---|
1727 | /**
|
---|
1728 | * The string form of a regular expression that would match all of the
|
---|
1729 | * combining mark characters in the unicode character set when placed in a
|
---|
1730 | * RegExp character class (`[]`).
|
---|
1731 | *
|
---|
1732 | * These would be the characters matched by unicode regex engines `\p{M}`
|
---|
1733 | * escape ("all marks").
|
---|
1734 | *
|
---|
1735 | * Taken from the XRegExp library: http://xregexp.com/ (thanks @https://github.com/slevithan)
|
---|
1736 | * Specifically: http://xregexp.com/v/3.2.0/xregexp-all.js, the 'Mark'
|
---|
1737 | * regex's bmp
|
---|
1738 | *
|
---|
1739 | * VERY IMPORTANT: This set of characters is defined inside of a Regular
|
---|
1740 | * Expression literal rather than a string literal to prevent UglifyJS from
|
---|
1741 | * compressing the unicode escape sequences into their actual unicode
|
---|
1742 | * characters. If Uglify compresses these into the unicode characters
|
---|
1743 | * themselves, this results in the error "Range out of order in character
|
---|
1744 | * class" when these characters are used inside of a Regular Expression
|
---|
1745 | * character class (`[]`). See usages of this const. Alternatively, we can set
|
---|
1746 | * the UglifyJS option `ascii_only` to true for the build, but that doesn't
|
---|
1747 | * help others who are pulling in Autolinker into their own build and running
|
---|
1748 | * UglifyJS themselves.
|
---|
1749 | */
|
---|
1750 | // prettier-ignore
|
---|
1751 | var marksStr = /\u0300-\u036F\u0483-\u0489\u0591-\u05BD\u05BF\u05C1\u05C2\u05C4\u05C5\u05C7\u0610-\u061A\u064B-\u065F\u0670\u06D6-\u06DC\u06DF-\u06E4\u06E7\u06E8\u06EA-\u06ED\u0711\u0730-\u074A\u07A6-\u07B0\u07EB-\u07F3\u0816-\u0819\u081B-\u0823\u0825-\u0827\u0829-\u082D\u0859-\u085B\u08D4-\u08E1\u08E3-\u0903\u093A-\u093C\u093E-\u094F\u0951-\u0957\u0962\u0963\u0981-\u0983\u09BC\u09BE-\u09C4\u09C7\u09C8\u09CB-\u09CD\u09D7\u09E2\u09E3\u0A01-\u0A03\u0A3C\u0A3E-\u0A42\u0A47\u0A48\u0A4B-\u0A4D\u0A51\u0A70\u0A71\u0A75\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AE2\u0AE3\u0B01-\u0B03\u0B3C\u0B3E-\u0B44\u0B47\u0B48\u0B4B-\u0B4D\u0B56\u0B57\u0B62\u0B63\u0B82\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C00-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55\u0C56\u0C62\u0C63\u0C81-\u0C83\u0CBC\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5\u0CD6\u0CE2\u0CE3\u0D01-\u0D03\u0D3E-\u0D44\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D62\u0D63\u0D82\u0D83\u0DCA\u0DCF-\u0DD4\u0DD6\u0DD8-\u0DDF\u0DF2\u0DF3\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB\u0EBC\u0EC8-\u0ECD\u0F18\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86\u0F87\u0F8D-\u0F97\u0F99-\u0FBC\u0FC6\u102B-\u103E\u1056-\u1059\u105E-\u1060\u1062-\u1064\u1067-\u106D\u1071-\u1074\u1082-\u108D\u108F\u109A-\u109D\u135D-\u135F\u1712-\u1714\u1732-\u1734\u1752\u1753\u1772\u1773\u17B4-\u17D3\u17DD\u180B-\u180D\u1885\u1886\u18A9\u1920-\u192B\u1930-\u193B\u1A17-\u1A1B\u1A55-\u1A5E\u1A60-\u1A7C\u1A7F\u1AB0-\u1ABE\u1B00-\u1B04\u1B34-\u1B44\u1B6B-\u1B73\u1B80-\u1B82\u1BA1-\u1BAD\u1BE6-\u1BF3\u1C24-\u1C37\u1CD0-\u1CD2\u1CD4-\u1CE8\u1CED\u1CF2-\u1CF4\u1CF8\u1CF9\u1DC0-\u1DF5\u1DFB-\u1DFF\u20D0-\u20F0\u2CEF-\u2CF1\u2D7F\u2DE0-\u2DFF\u302A-\u302F\u3099\u309A\uA66F-\uA672\uA674-\uA67D\uA69E\uA69F\uA6F0\uA6F1\uA802\uA806\uA80B\uA823-\uA827\uA880\uA881\uA8B4-\uA8C5\uA8E0-\uA8F1\uA926-\uA92D\uA947-\uA953\uA980-\uA983\uA9B3-\uA9C0\uA9E5\uAA29-\uAA36\uAA43\uAA4C\uAA4D\uAA7B-\uAA7D\uAAB0\uAAB2-\uAAB4\uAAB7\uAAB8\uAABE\uAABF\uAAC1\uAAEB-\uAAEF\uAAF5\uAAF6\uABE3-\uABEA\uABEC\uABED\uFB1E\uFE00-\uFE0F\uFE20-\uFE2F/
|
---|
1752 | .source; // see note in above variable description
|
---|
1753 | /**
|
---|
1754 | * The string form of a regular expression that would match all of the
|
---|
1755 | * alphabetic ("letter") chars, emoji, and combining marks in the unicode character set
|
---|
1756 | * when placed in a RegExp character class (`[]`). This includes all
|
---|
1757 | * international alphabetic characters.
|
---|
1758 | *
|
---|
1759 | * These would be the characters matched by unicode regex engines `\p{L}\p{M}`
|
---|
1760 | * escapes and emoji characters.
|
---|
1761 | */
|
---|
1762 | var alphaCharsAndMarksStr = alphaCharsStr + emojiStr + marksStr;
|
---|
1763 | /**
|
---|
1764 | * The string form of a regular expression that would match all of the
|
---|
1765 | * decimal number chars in the unicode character set when placed in a RegExp
|
---|
1766 | * character class (`[]`).
|
---|
1767 | *
|
---|
1768 | * These would be the characters matched by unicode regex engines `\p{Nd}`
|
---|
1769 | * escape ("all decimal numbers")
|
---|
1770 | *
|
---|
1771 | * Taken from the XRegExp library: http://xregexp.com/ (thanks @https://github.com/slevithan)
|
---|
1772 | * Specifically: http://xregexp.com/v/3.2.0/xregexp-all.js, the 'Decimal_Number'
|
---|
1773 | * regex's bmp
|
---|
1774 | *
|
---|
1775 | * VERY IMPORTANT: This set of characters is defined inside of a Regular
|
---|
1776 | * Expression literal rather than a string literal to prevent UglifyJS from
|
---|
1777 | * compressing the unicode escape sequences into their actual unicode
|
---|
1778 | * characters. If Uglify compresses these into the unicode characters
|
---|
1779 | * themselves, this results in the error "Range out of order in character
|
---|
1780 | * class" when these characters are used inside of a Regular Expression
|
---|
1781 | * character class (`[]`). See usages of this const. Alternatively, we can set
|
---|
1782 | * the UglifyJS option `ascii_only` to true for the build, but that doesn't
|
---|
1783 | * help others who are pulling in Autolinker into their own build and running
|
---|
1784 | * UglifyJS themselves.
|
---|
1785 | */
|
---|
1786 | // prettier-ignore
|
---|
1787 | var decimalNumbersStr = /0-9\u0660-\u0669\u06F0-\u06F9\u07C0-\u07C9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE6-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0DE6-\u0DEF\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u1040-\u1049\u1090-\u1099\u17E0-\u17E9\u1810-\u1819\u1946-\u194F\u19D0-\u19D9\u1A80-\u1A89\u1A90-\u1A99\u1B50-\u1B59\u1BB0-\u1BB9\u1C40-\u1C49\u1C50-\u1C59\uA620-\uA629\uA8D0-\uA8D9\uA900-\uA909\uA9D0-\uA9D9\uA9F0-\uA9F9\uAA50-\uAA59\uABF0-\uABF9\uFF10-\uFF19/
|
---|
1788 | .source; // see note in above variable description
|
---|
1789 | /**
|
---|
1790 | * The string form of a regular expression that would match all of the
|
---|
1791 | * letters and decimal number chars in the unicode character set when placed in
|
---|
1792 | * a RegExp character class (`[]`).
|
---|
1793 | *
|
---|
1794 | * These would be the characters matched by unicode regex engines
|
---|
1795 | * `[\p{L}\p{Nd}]` escape ("all letters and decimal numbers")
|
---|
1796 | */
|
---|
1797 | var alphaNumericCharsStr = alphaCharsAndMarksStr + decimalNumbersStr;
|
---|
1798 | /**
|
---|
1799 | * The string form of a regular expression that would match all of the
|
---|
1800 | * letters, combining marks, and decimal number chars in the unicode character
|
---|
1801 | * set when placed in a RegExp character class (`[]`).
|
---|
1802 | *
|
---|
1803 | * These would be the characters matched by unicode regex engines
|
---|
1804 | * `[\p{L}\p{M}\p{Nd}]` escape ("all letters, combining marks, and decimal
|
---|
1805 | * numbers")
|
---|
1806 | */
|
---|
1807 | var alphaNumericAndMarksCharsStr = alphaCharsAndMarksStr + decimalNumbersStr;
|
---|
1808 | /**
|
---|
1809 | * The regular expression that will match a single letter of the
|
---|
1810 | * {@link #alphaNumericAndMarksCharsStr}.
|
---|
1811 | */
|
---|
1812 | var alphaNumericAndMarksCharRe = new RegExp("[".concat(alphaNumericAndMarksCharsStr, "]"));
|
---|
1813 | // Simplified IP regular expression
|
---|
1814 | var ipStr = '(?:[' + decimalNumbersStr + ']{1,3}\\.){3}[' + decimalNumbersStr + ']{1,3}';
|
---|
1815 | // Protected domain label which do not allow "-" or "_" character on the beginning and the end of a single label
|
---|
1816 | // prettier-ignore
|
---|
1817 | var domainLabelStr = '[' + alphaNumericAndMarksCharsStr + '](?:[' + alphaNumericAndMarksCharsStr + '\\-_]{0,61}[' + alphaNumericAndMarksCharsStr + '])?';
|
---|
1818 | var getDomainLabelStr = function (group) {
|
---|
1819 | return '(?=(' + domainLabelStr + '))\\' + group;
|
---|
1820 | };
|
---|
1821 | /**
|
---|
1822 | * A function to match domain names of a URL or email address.
|
---|
1823 | * Ex: 'google', 'yahoo', 'some-other-company', etc.
|
---|
1824 | */
|
---|
1825 | // prettier-ignore
|
---|
1826 | var getDomainNameStr = function (group) {
|
---|
1827 | return '(?:' + getDomainLabelStr(group) + '(?:\\.' + getDomainLabelStr(group + 1) + '){0,126}|' + ipStr + ')';
|
---|
1828 | };
|
---|
1829 | /**
|
---|
1830 | * A regular expression that is simply the character class of the characters
|
---|
1831 | * that may be used in a domain name, minus the '-' or '.'
|
---|
1832 | */
|
---|
1833 | var domainNameCharRegex = alphaNumericAndMarksCharRe;
|
---|
1834 |
|
---|
1835 | // NOTE: THIS IS A GENERATED FILE
|
---|
1836 | // To update with the latest TLD list, run `npm run update-tld-regex`
|
---|
1837 | var tldRegex = /(?:xn--vermgensberatung-pwb|xn--vermgensberater-ctb|xn--clchc0ea0b2g2a9gcd|xn--w4r85el8fhu5dnra|northwesternmutual|travelersinsurance|vermögensberatung|xn--5su34j936bgsg|xn--bck1b9a5dre4c|xn--mgbah1a3hjkrd|xn--mgbai9azgqp6j|xn--mgberp4a5d4ar|xn--xkc2dl3a5ee0h|vermögensberater|xn--fzys8d69uvgm|xn--mgba7c0bbn0a|xn--mgbcpq6gpa1a|xn--xkc2al3hye2a|americanexpress|kerryproperties|sandvikcoromant|xn--i1b6b1a6a2e|xn--kcrx77d1x4a|xn--lgbbat1ad8j|xn--mgba3a4f16a|xn--mgbaakc7dvf|xn--mgbc0a9azcg|xn--nqv7fs00ema|americanfamily|bananarepublic|cancerresearch|cookingchannel|kerrylogistics|weatherchannel|xn--54b7fta0cc|xn--6qq986b3xl|xn--80aqecdr1a|xn--b4w605ferd|xn--fiq228c5hs|xn--h2breg3eve|xn--jlq480n2rg|xn--jlq61u9w7b|xn--mgba3a3ejt|xn--mgbaam7a8h|xn--mgbayh7gpa|xn--mgbbh1a71e|xn--mgbca7dzdo|xn--mgbi4ecexp|xn--mgbx4cd0ab|xn--rvc1e0am3e|international|lifeinsurance|travelchannel|wolterskluwer|xn--cckwcxetd|xn--eckvdtc9d|xn--fpcrj9c3d|xn--fzc2c9e2c|xn--h2brj9c8c|xn--tiq49xqyj|xn--yfro4i67o|xn--ygbi2ammx|construction|lplfinancial|scholarships|versicherung|xn--3e0b707e|xn--45br5cyl|xn--4dbrk0ce|xn--80adxhks|xn--80asehdb|xn--8y0a063a|xn--gckr3f0f|xn--mgb9awbf|xn--mgbab2bd|xn--mgbgu82a|xn--mgbpl2fh|xn--mgbt3dhd|xn--mk1bu44c|xn--ngbc5azd|xn--ngbe9e0a|xn--ogbpf8fl|xn--qcka1pmc|accountants|barclaycard|blackfriday|blockbuster|bridgestone|calvinklein|contractors|creditunion|engineering|enterprises|foodnetwork|investments|kerryhotels|lamborghini|motorcycles|olayangroup|photography|playstation|productions|progressive|redumbrella|williamhill|xn--11b4c3d|xn--1ck2e1b|xn--1qqw23a|xn--2scrj9c|xn--3bst00m|xn--3ds443g|xn--3hcrj9c|xn--42c2d9a|xn--45brj9c|xn--55qw42g|xn--6frz82g|xn--80ao21a|xn--9krt00a|xn--cck2b3b|xn--czr694b|xn--d1acj3b|xn--efvy88h|xn--fct429k|xn--fjq720a|xn--flw351e|xn--g2xx48c|xn--gecrj9c|xn--gk3at1e|xn--h2brj9c|xn--hxt814e|xn--imr513n|xn--j6w193g|xn--jvr189m|xn--kprw13d|xn--kpry57d|xn--mgbbh1a|xn--mgbtx2b|xn--mix891f|xn--nyqy26a|xn--otu796d|xn--pgbs0dh|xn--q9jyb4c|xn--rhqv96g|xn--rovu88b|xn--s9brj9c|xn--ses554g|xn--t60b56a|xn--vuq861b|xn--w4rs40l|xn--xhq521b|xn--zfr164b|சிங்கப்பூர்|accountant|apartments|associates|basketball|bnpparibas|boehringer|capitalone|consulting|creditcard|cuisinella|eurovision|extraspace|foundation|healthcare|immobilien|industries|management|mitsubishi|nextdirect|properties|protection|prudential|realestate|republican|restaurant|schaeffler|tatamotors|technology|university|vlaanderen|volkswagen|xn--30rr7y|xn--3pxu8k|xn--45q11c|xn--4gbrim|xn--55qx5d|xn--5tzm5g|xn--80aswg|xn--90a3ac|xn--9dbq2a|xn--9et52u|xn--c2br7g|xn--cg4bki|xn--czrs0t|xn--czru2d|xn--fiq64b|xn--fiqs8s|xn--fiqz9s|xn--io0a7i|xn--kput3i|xn--mxtq1m|xn--o3cw4h|xn--pssy2u|xn--q7ce6a|xn--unup4y|xn--wgbh1c|xn--wgbl6a|xn--y9a3aq|accenture|alfaromeo|allfinanz|amsterdam|analytics|aquarelle|barcelona|bloomberg|christmas|community|directory|education|equipment|fairwinds|financial|firestone|fresenius|frontdoor|furniture|goldpoint|hisamitsu|homedepot|homegoods|homesense|institute|insurance|kuokgroup|lancaster|landrover|lifestyle|marketing|marshalls|melbourne|microsoft|panasonic|passagens|pramerica|richardli|shangrila|solutions|statebank|statefarm|stockholm|travelers|vacations|xn--90ais|xn--c1avg|xn--d1alf|xn--e1a4c|xn--fhbei|xn--j1aef|xn--j1amh|xn--l1acc|xn--ngbrx|xn--nqv7f|xn--p1acf|xn--qxa6a|xn--tckwe|xn--vhquv|yodobashi|موريتانيا|abudhabi|airforce|allstate|attorney|barclays|barefoot|bargains|baseball|boutique|bradesco|broadway|brussels|builders|business|capetown|catering|catholic|cipriani|cityeats|cleaning|clinique|clothing|commbank|computer|delivery|deloitte|democrat|diamonds|discount|discover|download|engineer|ericsson|etisalat|exchange|feedback|fidelity|firmdale|football|frontier|goodyear|grainger|graphics|guardian|hdfcbank|helsinki|holdings|hospital|infiniti|ipiranga|istanbul|jpmorgan|lighting|lundbeck|marriott|maserati|mckinsey|memorial|merckmsd|mortgage|observer|partners|pharmacy|pictures|plumbing|property|redstone|reliance|saarland|samsclub|security|services|shopping|showtime|softbank|software|stcgroup|supplies|training|vanguard|ventures|verisign|woodside|xn--90ae|xn--node|xn--p1ai|xn--qxam|yokohama|السعودية|abogado|academy|agakhan|alibaba|android|athleta|auction|audible|auspost|avianca|banamex|bauhaus|bentley|bestbuy|booking|brother|bugatti|capital|caravan|careers|channel|charity|chintai|citadel|clubmed|college|cologne|comcast|company|compare|contact|cooking|corsica|country|coupons|courses|cricket|cruises|dentist|digital|domains|exposed|express|farmers|fashion|ferrari|ferrero|finance|fishing|fitness|flights|florist|flowers|forsale|frogans|fujitsu|gallery|genting|godaddy|grocery|guitars|hamburg|hangout|hitachi|holiday|hosting|hoteles|hotmail|hyundai|ismaili|jewelry|juniper|kitchen|komatsu|lacaixa|lanxess|lasalle|latrobe|leclerc|limited|lincoln|markets|monster|netbank|netflix|network|neustar|okinawa|oldnavy|organic|origins|philips|pioneer|politie|realtor|recipes|rentals|reviews|rexroth|samsung|sandvik|schmidt|schwarz|science|shiksha|singles|staples|storage|support|surgery|systems|temasek|theater|theatre|tickets|tiffany|toshiba|trading|walmart|wanggou|watches|weather|website|wedding|whoswho|windows|winners|xfinity|yamaxun|youtube|zuerich|католик|اتصالات|البحرين|الجزائر|العليان|پاکستان|كاثوليك|இந்தியா|abarth|abbott|abbvie|africa|agency|airbus|airtel|alipay|alsace|alstom|amazon|anquan|aramco|author|bayern|beauty|berlin|bharti|bostik|boston|broker|camera|career|casino|center|chanel|chrome|church|circle|claims|clinic|coffee|comsec|condos|coupon|credit|cruise|dating|datsun|dealer|degree|dental|design|direct|doctor|dunlop|dupont|durban|emerck|energy|estate|events|expert|family|flickr|futbol|gallup|garden|george|giving|global|google|gratis|health|hermes|hiphop|hockey|hotels|hughes|imamat|insure|intuit|jaguar|joburg|juegos|kaufen|kinder|kindle|kosher|lancia|latino|lawyer|lefrak|living|locker|london|luxury|madrid|maison|makeup|market|mattel|mobile|monash|mormon|moscow|museum|mutual|nagoya|natura|nissan|nissay|norton|nowruz|office|olayan|online|oracle|orange|otsuka|pfizer|photos|physio|pictet|quebec|racing|realty|reisen|repair|report|review|rocher|rogers|ryukyu|safety|sakura|sanofi|school|schule|search|secure|select|shouji|soccer|social|stream|studio|supply|suzuki|swatch|sydney|taipei|taobao|target|tattoo|tennis|tienda|tjmaxx|tkmaxx|toyota|travel|unicom|viajes|viking|villas|virgin|vision|voting|voyage|vuelos|walter|webcam|xihuan|yachts|yandex|zappos|москва|онлайн|ابوظبي|ارامكو|الاردن|المغرب|امارات|فلسطين|مليسيا|भारतम्|இலங்கை|ファッション|actor|adult|aetna|amfam|amica|apple|archi|audio|autos|azure|baidu|beats|bible|bingo|black|boats|bosch|build|canon|cards|chase|cheap|cisco|citic|click|cloud|coach|codes|crown|cymru|dabur|dance|deals|delta|drive|dubai|earth|edeka|email|epson|faith|fedex|final|forex|forum|gallo|games|gifts|gives|glass|globo|gmail|green|gripe|group|gucci|guide|homes|honda|horse|house|hyatt|ikano|irish|jetzt|koeln|kyoto|lamer|lease|legal|lexus|lilly|linde|lipsy|loans|locus|lotte|lotto|macys|mango|media|miami|money|movie|music|nexus|nikon|ninja|nokia|nowtv|omega|osaka|paris|parts|party|phone|photo|pizza|place|poker|praxi|press|prime|promo|quest|radio|rehab|reise|ricoh|rocks|rodeo|rugby|salon|sener|seven|sharp|shell|shoes|skype|sling|smart|smile|solar|space|sport|stada|store|study|style|sucks|swiss|tatar|tires|tirol|tmall|today|tokyo|tools|toray|total|tours|trade|trust|tunes|tushu|ubank|vegas|video|vodka|volvo|wales|watch|weber|weibo|works|world|xerox|yahoo|ישראל|ایران|بازار|بھارت|سودان|سورية|همراه|भारोत|संगठन|বাংলা|భారత్|ഭാരതം|嘉里大酒店|aarp|able|adac|aero|akdn|ally|amex|arab|army|arpa|arte|asda|asia|audi|auto|baby|band|bank|bbva|beer|best|bike|bing|blog|blue|bofa|bond|book|buzz|cafe|call|camp|care|cars|casa|case|cash|cbre|cern|chat|citi|city|club|cool|coop|cyou|data|date|dclk|deal|dell|desi|diet|dish|docs|dvag|erni|fage|fail|fans|farm|fast|fiat|fido|film|fire|fish|flir|food|ford|free|fund|game|gbiz|gent|ggee|gift|gmbh|gold|golf|goog|guge|guru|hair|haus|hdfc|help|here|hgtv|host|hsbc|icbc|ieee|imdb|immo|info|itau|java|jeep|jobs|jprs|kddi|kids|kiwi|kpmg|kred|land|lego|lgbt|lidl|life|like|limo|link|live|loan|loft|love|ltda|luxe|maif|meet|meme|menu|mini|mint|mobi|moda|moto|name|navy|news|next|nico|nike|ollo|open|page|pars|pccw|pics|ping|pink|play|plus|pohl|porn|post|prod|prof|qpon|read|reit|rent|rest|rich|room|rsvp|ruhr|safe|sale|sarl|save|saxo|scot|seat|seek|sexy|shaw|shia|shop|show|silk|sina|site|skin|sncf|sohu|song|sony|spot|star|surf|talk|taxi|team|tech|teva|tiaa|tips|town|toys|tube|vana|visa|viva|vivo|vote|voto|wang|weir|wien|wiki|wine|work|xbox|yoga|zara|zero|zone|дети|сайт|بارت|بيتك|ڀارت|تونس|شبكة|عراق|عمان|موقع|भारत|ভারত|ভাৰত|ਭਾਰਤ|ભારત|ଭାରତ|ಭಾರತ|ලංකා|アマゾン|グーグル|クラウド|ポイント|组织机构|電訊盈科|香格里拉|aaa|abb|abc|aco|ads|aeg|afl|aig|anz|aol|app|art|aws|axa|bar|bbc|bbt|bcg|bcn|bet|bid|bio|biz|bms|bmw|bom|boo|bot|box|buy|bzh|cab|cal|cam|car|cat|cba|cbn|cbs|ceo|cfa|cfd|com|cpa|crs|dad|day|dds|dev|dhl|diy|dnp|dog|dot|dtv|dvr|eat|eco|edu|esq|eus|fan|fit|fly|foo|fox|frl|ftr|fun|fyi|gal|gap|gay|gdn|gea|gle|gmo|gmx|goo|gop|got|gov|hbo|hiv|hkt|hot|how|ibm|ice|icu|ifm|inc|ing|ink|int|ist|itv|jcb|jio|jll|jmp|jnj|jot|joy|kfh|kia|kim|kpn|krd|lat|law|lds|llc|llp|lol|lpl|ltd|man|map|mba|med|men|mil|mit|mlb|mls|mma|moe|moi|mom|mov|msd|mtn|mtr|nab|nba|nec|net|new|nfl|ngo|nhk|now|nra|nrw|ntt|nyc|obi|one|ong|onl|ooo|org|ott|ovh|pay|pet|phd|pid|pin|pnc|pro|pru|pub|pwc|red|ren|ril|rio|rip|run|rwe|sap|sas|sbi|sbs|sca|scb|ses|sew|sex|sfr|ski|sky|soy|spa|srl|stc|tab|tax|tci|tdk|tel|thd|tjx|top|trv|tui|tvs|ubs|uno|uol|ups|vet|vig|vin|vip|wed|win|wme|wow|wtc|wtf|xin|xxx|xyz|you|yun|zip|бел|ком|қаз|мкд|мон|орг|рус|срб|укр|հայ|קום|عرب|قطر|كوم|مصر|कॉम|नेट|คอม|ไทย|ລາວ|ストア|セール|みんな|中文网|亚马逊|天主教|我爱你|新加坡|淡马锡|诺基亚|飞利浦|ac|ad|ae|af|ag|ai|al|am|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw|ελ|ευ|бг|ею|рф|გე|닷넷|닷컴|삼성|한국|コム|世界|中信|中国|中國|企业|佛山|信息|健康|八卦|公司|公益|台湾|台灣|商城|商店|商标|嘉里|在线|大拿|娱乐|家電|广东|微博|慈善|手机|招聘|政务|政府|新闻|时尚|書籍|机构|游戏|澳門|点看|移动|网址|网店|网站|网络|联通|谷歌|购物|通販|集团|食品|餐厅|香港)/;
|
---|
1838 |
|
---|
1839 | // For debugging: search for other "For debugging" lines
|
---|
1840 | // import CliTable from 'cli-table';
|
---|
1841 | // RegExp objects which are shared by all instances of EmailMatcher. These are
|
---|
1842 | // here to avoid re-instantiating the RegExp objects if `Autolinker.link()` is
|
---|
1843 | // called multiple times, thus instantiating EmailMatcher and its RegExp
|
---|
1844 | // objects each time (which is very expensive - see https://github.com/gregjacobs/Autolinker.js/issues/314).
|
---|
1845 | // See descriptions of the properties where they are used for details about them
|
---|
1846 | var localPartCharRegex = new RegExp("[".concat(alphaNumericAndMarksCharsStr, "!#$%&'*+/=?^_`{|}~-]"));
|
---|
1847 | var strictTldRegex = new RegExp("^".concat(tldRegex.source, "$"));
|
---|
1848 | /**
|
---|
1849 | * @class Autolinker.matcher.Email
|
---|
1850 | * @extends Autolinker.matcher.Matcher
|
---|
1851 | *
|
---|
1852 | * Matcher to find email matches in an input string.
|
---|
1853 | *
|
---|
1854 | * See this class's superclass ({@link Autolinker.matcher.Matcher}) for more details.
|
---|
1855 | */
|
---|
1856 | var EmailMatcher = /** @class */ (function (_super) {
|
---|
1857 | __extends(EmailMatcher, _super);
|
---|
1858 | function EmailMatcher() {
|
---|
1859 | var _this = _super !== null && _super.apply(this, arguments) || this;
|
---|
1860 | /**
|
---|
1861 | * Valid characters that can be used in the "local" part of an email address,
|
---|
1862 | * i.e. the "name" part of "name@site.com"
|
---|
1863 | */
|
---|
1864 | _this.localPartCharRegex = localPartCharRegex;
|
---|
1865 | /**
|
---|
1866 | * Stricter TLD regex which adds a beginning and end check to ensure
|
---|
1867 | * the string is a valid TLD
|
---|
1868 | */
|
---|
1869 | _this.strictTldRegex = strictTldRegex;
|
---|
1870 | return _this;
|
---|
1871 | }
|
---|
1872 | /**
|
---|
1873 | * @inheritdoc
|
---|
1874 | */
|
---|
1875 | EmailMatcher.prototype.parseMatches = function (text) {
|
---|
1876 | var tagBuilder = this.tagBuilder, localPartCharRegex = this.localPartCharRegex, strictTldRegex = this.strictTldRegex, matches = [], len = text.length, noCurrentEmailMatch = new CurrentEmailMatch();
|
---|
1877 | // for matching a 'mailto:' prefix
|
---|
1878 | var mailtoTransitions = {
|
---|
1879 | m: 'a',
|
---|
1880 | a: 'i',
|
---|
1881 | i: 'l',
|
---|
1882 | l: 't',
|
---|
1883 | t: 'o',
|
---|
1884 | o: ':',
|
---|
1885 | };
|
---|
1886 | var charIdx = 0, state = 0 /* NonEmailMatch */, currentEmailMatch = noCurrentEmailMatch;
|
---|
1887 | // For debugging: search for other "For debugging" lines
|
---|
1888 | // const table = new CliTable( {
|
---|
1889 | // head: [ 'charIdx', 'char', 'state', 'charIdx', 'currentEmailAddress.idx', 'hasDomainDot' ]
|
---|
1890 | // } );
|
---|
1891 | while (charIdx < len) {
|
---|
1892 | var char = text.charAt(charIdx);
|
---|
1893 | // For debugging: search for other "For debugging" lines
|
---|
1894 | // table.push(
|
---|
1895 | // [ charIdx, char, State[ state ], charIdx, currentEmailAddress.idx, currentEmailAddress.hasDomainDot ]
|
---|
1896 | // );
|
---|
1897 | switch (state) {
|
---|
1898 | case 0 /* NonEmailMatch */:
|
---|
1899 | stateNonEmailAddress(char);
|
---|
1900 | break;
|
---|
1901 | case 1 /* Mailto */:
|
---|
1902 | stateMailTo(text.charAt(charIdx - 1), char);
|
---|
1903 | break;
|
---|
1904 | case 2 /* LocalPart */:
|
---|
1905 | stateLocalPart(char);
|
---|
1906 | break;
|
---|
1907 | case 3 /* LocalPartDot */:
|
---|
1908 | stateLocalPartDot(char);
|
---|
1909 | break;
|
---|
1910 | case 4 /* AtSign */:
|
---|
1911 | stateAtSign(char);
|
---|
1912 | break;
|
---|
1913 | case 5 /* DomainChar */:
|
---|
1914 | stateDomainChar(char);
|
---|
1915 | break;
|
---|
1916 | case 6 /* DomainHyphen */:
|
---|
1917 | stateDomainHyphen(char);
|
---|
1918 | break;
|
---|
1919 | case 7 /* DomainDot */:
|
---|
1920 | stateDomainDot(char);
|
---|
1921 | break;
|
---|
1922 | default:
|
---|
1923 | throwUnhandledCaseError(state);
|
---|
1924 | }
|
---|
1925 | // For debugging: search for other "For debugging" lines
|
---|
1926 | // table.push(
|
---|
1927 | // [ charIdx, char, State[ state ], charIdx, currentEmailAddress.idx, currentEmailAddress.hasDomainDot ]
|
---|
1928 | // );
|
---|
1929 | charIdx++;
|
---|
1930 | }
|
---|
1931 | // Capture any valid match at the end of the string
|
---|
1932 | captureMatchIfValidAndReset();
|
---|
1933 | // For debugging: search for other "For debugging" lines
|
---|
1934 | //console.log( '\n' + table.toString() );
|
---|
1935 | return matches;
|
---|
1936 | // Handles the state when we're not in an email address
|
---|
1937 | function stateNonEmailAddress(char) {
|
---|
1938 | if (char === 'm') {
|
---|
1939 | beginEmailMatch(1 /* Mailto */);
|
---|
1940 | }
|
---|
1941 | else if (localPartCharRegex.test(char)) {
|
---|
1942 | beginEmailMatch();
|
---|
1943 | }
|
---|
1944 | else ;
|
---|
1945 | }
|
---|
1946 | // Handles if we're reading a 'mailto:' prefix on the string
|
---|
1947 | function stateMailTo(prevChar, char) {
|
---|
1948 | if (prevChar === ':') {
|
---|
1949 | // We've reached the end of the 'mailto:' prefix
|
---|
1950 | if (localPartCharRegex.test(char)) {
|
---|
1951 | state = 2 /* LocalPart */;
|
---|
1952 | currentEmailMatch = new CurrentEmailMatch(__assign(__assign({}, currentEmailMatch), { hasMailtoPrefix: true }));
|
---|
1953 | }
|
---|
1954 | else {
|
---|
1955 | // we've matched 'mailto:' but didn't get anything meaningful
|
---|
1956 | // immediately afterwards (for example, we encountered a
|
---|
1957 | // space character, or an '@' character which formed 'mailto:@'
|
---|
1958 | resetToNonEmailMatchState();
|
---|
1959 | }
|
---|
1960 | }
|
---|
1961 | else if (mailtoTransitions[prevChar] === char) ;
|
---|
1962 | else if (localPartCharRegex.test(char)) {
|
---|
1963 | // We we're reading a prefix of 'mailto:', but encountered a
|
---|
1964 | // different character that didn't continue the prefix
|
---|
1965 | state = 2 /* LocalPart */;
|
---|
1966 | }
|
---|
1967 | else if (char === '.') {
|
---|
1968 | // We we're reading a prefix of 'mailto:', but encountered a
|
---|
1969 | // dot character
|
---|
1970 | state = 3 /* LocalPartDot */;
|
---|
1971 | }
|
---|
1972 | else if (char === '@') {
|
---|
1973 | // We we're reading a prefix of 'mailto:', but encountered a
|
---|
1974 | // an @ character
|
---|
1975 | state = 4 /* AtSign */;
|
---|
1976 | }
|
---|
1977 | else {
|
---|
1978 | // not an email address character, return to "NonEmailAddress" state
|
---|
1979 | resetToNonEmailMatchState();
|
---|
1980 | }
|
---|
1981 | }
|
---|
1982 | // Handles the state when we're currently in the "local part" of an
|
---|
1983 | // email address (as opposed to the "domain part")
|
---|
1984 | function stateLocalPart(char) {
|
---|
1985 | if (char === '.') {
|
---|
1986 | state = 3 /* LocalPartDot */;
|
---|
1987 | }
|
---|
1988 | else if (char === '@') {
|
---|
1989 | state = 4 /* AtSign */;
|
---|
1990 | }
|
---|
1991 | else if (localPartCharRegex.test(char)) ;
|
---|
1992 | else {
|
---|
1993 | // not an email address character, return to "NonEmailAddress" state
|
---|
1994 | resetToNonEmailMatchState();
|
---|
1995 | }
|
---|
1996 | }
|
---|
1997 | // Handles the state where we've read
|
---|
1998 | function stateLocalPartDot(char) {
|
---|
1999 | if (char === '.') {
|
---|
2000 | // We read a second '.' in a row, not a valid email address
|
---|
2001 | // local part
|
---|
2002 | resetToNonEmailMatchState();
|
---|
2003 | }
|
---|
2004 | else if (char === '@') {
|
---|
2005 | // We read the '@' character immediately after a dot ('.'), not
|
---|
2006 | // an email address
|
---|
2007 | resetToNonEmailMatchState();
|
---|
2008 | }
|
---|
2009 | else if (localPartCharRegex.test(char)) {
|
---|
2010 | state = 2 /* LocalPart */;
|
---|
2011 | }
|
---|
2012 | else {
|
---|
2013 | // Anything else, not an email address
|
---|
2014 | resetToNonEmailMatchState();
|
---|
2015 | }
|
---|
2016 | }
|
---|
2017 | function stateAtSign(char) {
|
---|
2018 | if (domainNameCharRegex.test(char)) {
|
---|
2019 | state = 5 /* DomainChar */;
|
---|
2020 | }
|
---|
2021 | else {
|
---|
2022 | // Anything else, not an email address
|
---|
2023 | resetToNonEmailMatchState();
|
---|
2024 | }
|
---|
2025 | }
|
---|
2026 | function stateDomainChar(char) {
|
---|
2027 | if (char === '.') {
|
---|
2028 | state = 7 /* DomainDot */;
|
---|
2029 | }
|
---|
2030 | else if (char === '-') {
|
---|
2031 | state = 6 /* DomainHyphen */;
|
---|
2032 | }
|
---|
2033 | else if (domainNameCharRegex.test(char)) ;
|
---|
2034 | else {
|
---|
2035 | // Anything else, we potentially matched if the criteria has
|
---|
2036 | // been met
|
---|
2037 | captureMatchIfValidAndReset();
|
---|
2038 | }
|
---|
2039 | }
|
---|
2040 | function stateDomainHyphen(char) {
|
---|
2041 | if (char === '-' || char === '.') {
|
---|
2042 | // Not valid to have two hyphens ("--") or hypen+dot ("-.")
|
---|
2043 | captureMatchIfValidAndReset();
|
---|
2044 | }
|
---|
2045 | else if (domainNameCharRegex.test(char)) {
|
---|
2046 | state = 5 /* DomainChar */;
|
---|
2047 | }
|
---|
2048 | else {
|
---|
2049 | // Anything else
|
---|
2050 | captureMatchIfValidAndReset();
|
---|
2051 | }
|
---|
2052 | }
|
---|
2053 | function stateDomainDot(char) {
|
---|
2054 | if (char === '.' || char === '-') {
|
---|
2055 | // not valid to have two dots ("..") or dot+hypen (".-")
|
---|
2056 | captureMatchIfValidAndReset();
|
---|
2057 | }
|
---|
2058 | else if (domainNameCharRegex.test(char)) {
|
---|
2059 | state = 5 /* DomainChar */;
|
---|
2060 | // After having read a '.' and then a valid domain character,
|
---|
2061 | // we now know that the domain part of the email is valid, and
|
---|
2062 | // we have found at least a partial EmailMatch (however, the
|
---|
2063 | // email address may have additional characters from this point)
|
---|
2064 | currentEmailMatch = new CurrentEmailMatch(__assign(__assign({}, currentEmailMatch), { hasDomainDot: true }));
|
---|
2065 | }
|
---|
2066 | else {
|
---|
2067 | // Anything else
|
---|
2068 | captureMatchIfValidAndReset();
|
---|
2069 | }
|
---|
2070 | }
|
---|
2071 | function beginEmailMatch(newState) {
|
---|
2072 | if (newState === void 0) { newState = 2 /* LocalPart */; }
|
---|
2073 | state = newState;
|
---|
2074 | currentEmailMatch = new CurrentEmailMatch({ idx: charIdx });
|
---|
2075 | }
|
---|
2076 | function resetToNonEmailMatchState() {
|
---|
2077 | state = 0 /* NonEmailMatch */;
|
---|
2078 | currentEmailMatch = noCurrentEmailMatch;
|
---|
2079 | }
|
---|
2080 | /*
|
---|
2081 | * Captures the current email address as an EmailMatch if it's valid,
|
---|
2082 | * and resets the state to read another email address.
|
---|
2083 | */
|
---|
2084 | function captureMatchIfValidAndReset() {
|
---|
2085 | if (currentEmailMatch.hasDomainDot) {
|
---|
2086 | // we need at least one dot in the domain to be considered a valid email address
|
---|
2087 | var matchedText = text.slice(currentEmailMatch.idx, charIdx);
|
---|
2088 | // If we read a '.' or '-' char that ended the email address
|
---|
2089 | // (valid domain name characters, but only valid email address
|
---|
2090 | // characters if they are followed by something else), strip
|
---|
2091 | // it off now
|
---|
2092 | if (/[-.]$/.test(matchedText)) {
|
---|
2093 | matchedText = matchedText.slice(0, -1);
|
---|
2094 | }
|
---|
2095 | var emailAddress = currentEmailMatch.hasMailtoPrefix
|
---|
2096 | ? matchedText.slice('mailto:'.length)
|
---|
2097 | : matchedText;
|
---|
2098 | // if the email address has a valid TLD, add it to the list of matches
|
---|
2099 | if (doesEmailHaveValidTld(emailAddress)) {
|
---|
2100 | matches.push(new EmailMatch({
|
---|
2101 | tagBuilder: tagBuilder,
|
---|
2102 | matchedText: matchedText,
|
---|
2103 | offset: currentEmailMatch.idx,
|
---|
2104 | email: emailAddress,
|
---|
2105 | }));
|
---|
2106 | }
|
---|
2107 | }
|
---|
2108 | resetToNonEmailMatchState();
|
---|
2109 | /**
|
---|
2110 | * Determines if the given email address has a valid TLD or not
|
---|
2111 | * @param {string} emailAddress - email address
|
---|
2112 | * @return {Boolean} - true is email have valid TLD, false otherwise
|
---|
2113 | */
|
---|
2114 | function doesEmailHaveValidTld(emailAddress) {
|
---|
2115 | var emailAddressTld = emailAddress.split('.').pop() || '';
|
---|
2116 | var emailAddressNormalized = emailAddressTld.toLowerCase();
|
---|
2117 | var isValidTld = strictTldRegex.test(emailAddressNormalized);
|
---|
2118 | return isValidTld;
|
---|
2119 | }
|
---|
2120 | }
|
---|
2121 | };
|
---|
2122 | return EmailMatcher;
|
---|
2123 | }(Matcher));
|
---|
2124 | var CurrentEmailMatch = /** @class */ (function () {
|
---|
2125 | function CurrentEmailMatch(cfg) {
|
---|
2126 | if (cfg === void 0) { cfg = {}; }
|
---|
2127 | this.idx = cfg.idx !== undefined ? cfg.idx : -1;
|
---|
2128 | this.hasMailtoPrefix = !!cfg.hasMailtoPrefix;
|
---|
2129 | this.hasDomainDot = !!cfg.hasDomainDot;
|
---|
2130 | }
|
---|
2131 | return CurrentEmailMatch;
|
---|
2132 | }());
|
---|
2133 |
|
---|
2134 | /**
|
---|
2135 | * @private
|
---|
2136 | * @class Autolinker.matcher.UrlMatchValidator
|
---|
2137 | * @singleton
|
---|
2138 | *
|
---|
2139 | * Used by Autolinker to filter out false URL positives from the
|
---|
2140 | * {@link Autolinker.matcher.Url UrlMatcher}.
|
---|
2141 | *
|
---|
2142 | * Due to the limitations of regular expressions (including the missing feature
|
---|
2143 | * of look-behinds in JS regular expressions), we cannot always determine the
|
---|
2144 | * validity of a given match. This class applies a bit of additional logic to
|
---|
2145 | * filter out any false positives that have been matched by the
|
---|
2146 | * {@link Autolinker.matcher.Url UrlMatcher}.
|
---|
2147 | */
|
---|
2148 | var UrlMatchValidator = /** @class */ (function () {
|
---|
2149 | function UrlMatchValidator() {
|
---|
2150 | }
|
---|
2151 | /**
|
---|
2152 | * Determines if a given URL match found by the {@link Autolinker.matcher.Url UrlMatcher}
|
---|
2153 | * is valid. Will return `false` for:
|
---|
2154 | *
|
---|
2155 | * 1) URL matches which do not have at least have one period ('.') in the
|
---|
2156 | * domain name (effectively skipping over matches like "abc:def").
|
---|
2157 | * However, URL matches with a protocol will be allowed (ex: 'http://localhost')
|
---|
2158 | * 2) URL matches which do not have at least one word character in the
|
---|
2159 | * domain name (effectively skipping over matches like "git:1.0").
|
---|
2160 | * However, URL matches with a protocol will be allowed (ex: 'intra-net://271219.76')
|
---|
2161 | * 3) A protocol-relative url match (a URL beginning with '//') whose
|
---|
2162 | * previous character is a word character (effectively skipping over
|
---|
2163 | * strings like "abc//google.com")
|
---|
2164 | *
|
---|
2165 | * Otherwise, returns `true`.
|
---|
2166 | *
|
---|
2167 | * @param {String} urlMatch The matched URL, if there was one. Will be an
|
---|
2168 | * empty string if the match is not a URL match.
|
---|
2169 | * @param {String} protocolUrlMatch The match URL string for a protocol
|
---|
2170 | * match. Ex: 'http://yahoo.com'. This is used to match something like
|
---|
2171 | * 'http://localhost', where we won't double check that the domain name
|
---|
2172 | * has at least one '.' in it.
|
---|
2173 | * @return {Boolean} `true` if the match given is valid and should be
|
---|
2174 | * processed, or `false` if the match is invalid and/or should just not be
|
---|
2175 | * processed.
|
---|
2176 | */
|
---|
2177 | UrlMatchValidator.isValid = function (urlMatch, protocolUrlMatch) {
|
---|
2178 | if ((protocolUrlMatch && !this.isValidUriScheme(protocolUrlMatch)) ||
|
---|
2179 | this.urlMatchDoesNotHaveProtocolOrDot(urlMatch, protocolUrlMatch) || // At least one period ('.') must exist in the URL match for us to consider it an actual URL, *unless* it was a full protocol match (like 'http://localhost')
|
---|
2180 | (this.urlMatchDoesNotHaveAtLeastOneWordChar(urlMatch, protocolUrlMatch) && // At least one letter character must exist in the domain name after a protocol match. Ex: skip over something like "git:1.0"
|
---|
2181 | !this.isValidIpAddress(urlMatch)) || // Except if it's an IP address
|
---|
2182 | this.containsMultipleDots(urlMatch)) {
|
---|
2183 | return false;
|
---|
2184 | }
|
---|
2185 | return true;
|
---|
2186 | };
|
---|
2187 | UrlMatchValidator.isValidIpAddress = function (uriSchemeMatch) {
|
---|
2188 | var newRegex = new RegExp(this.hasFullProtocolRegex.source + this.ipRegex.source);
|
---|
2189 | var uriScheme = uriSchemeMatch.match(newRegex);
|
---|
2190 | return uriScheme !== null;
|
---|
2191 | };
|
---|
2192 | UrlMatchValidator.containsMultipleDots = function (urlMatch) {
|
---|
2193 | var stringBeforeSlash = urlMatch;
|
---|
2194 | if (this.hasFullProtocolRegex.test(urlMatch)) {
|
---|
2195 | stringBeforeSlash = urlMatch.split('://')[1];
|
---|
2196 | }
|
---|
2197 | return stringBeforeSlash.split('/')[0].indexOf('..') > -1;
|
---|
2198 | };
|
---|
2199 | /**
|
---|
2200 | * Determines if the URI scheme is a valid scheme to be autolinked. Returns
|
---|
2201 | * `false` if the scheme is 'javascript:' or 'vbscript:'
|
---|
2202 | *
|
---|
2203 | * @private
|
---|
2204 | * @param {String} uriSchemeMatch The match URL string for a full URI scheme
|
---|
2205 | * match. Ex: 'http://yahoo.com' or 'mailto:a@a.com'.
|
---|
2206 | * @return {Boolean} `true` if the scheme is a valid one, `false` otherwise.
|
---|
2207 | */
|
---|
2208 | UrlMatchValidator.isValidUriScheme = function (uriSchemeMatch) {
|
---|
2209 | var uriSchemeMatchArr = uriSchemeMatch.match(this.uriSchemeRegex), uriScheme = uriSchemeMatchArr && uriSchemeMatchArr[0].toLowerCase();
|
---|
2210 | return uriScheme !== 'javascript:' && uriScheme !== 'vbscript:';
|
---|
2211 | };
|
---|
2212 | /**
|
---|
2213 | * Determines if a URL match does not have either:
|
---|
2214 | *
|
---|
2215 | * a) a full protocol (i.e. 'http://'), or
|
---|
2216 | * b) at least one dot ('.') in the domain name (for a non-full-protocol
|
---|
2217 | * match).
|
---|
2218 | *
|
---|
2219 | * Either situation is considered an invalid URL (ex: 'git:d' does not have
|
---|
2220 | * either the '://' part, or at least one dot in the domain name. If the
|
---|
2221 | * match was 'git:abc.com', we would consider this valid.)
|
---|
2222 | *
|
---|
2223 | * @private
|
---|
2224 | * @param {String} urlMatch The matched URL, if there was one. Will be an
|
---|
2225 | * empty string if the match is not a URL match.
|
---|
2226 | * @param {String} protocolUrlMatch The match URL string for a protocol
|
---|
2227 | * match. Ex: 'http://yahoo.com'. This is used to match something like
|
---|
2228 | * 'http://localhost', where we won't double check that the domain name
|
---|
2229 | * has at least one '.' in it.
|
---|
2230 | * @return {Boolean} `true` if the URL match does not have a full protocol,
|
---|
2231 | * or at least one dot ('.') in a non-full-protocol match.
|
---|
2232 | */
|
---|
2233 | UrlMatchValidator.urlMatchDoesNotHaveProtocolOrDot = function (urlMatch, protocolUrlMatch) {
|
---|
2234 | return (!!urlMatch &&
|
---|
2235 | (!protocolUrlMatch || !this.hasFullProtocolRegex.test(protocolUrlMatch)) &&
|
---|
2236 | urlMatch.indexOf('.') === -1);
|
---|
2237 | };
|
---|
2238 | /**
|
---|
2239 | * Determines if a URL match does not have either:
|
---|
2240 | *
|
---|
2241 | * a) a full protocol (i.e. 'http://'), or
|
---|
2242 | * b) at least one word character after the protocol (i.e. in the domain name)
|
---|
2243 | *
|
---|
2244 | * At least one letter character must exist in the domain name after a
|
---|
2245 | * protocol match. Ex: skip over something like "git:1.0"
|
---|
2246 | *
|
---|
2247 | * @private
|
---|
2248 | * @param {String} urlMatch The matched URL, if there was one. Will be an
|
---|
2249 | * empty string if the match is not a URL match.
|
---|
2250 | * @param {String} protocolUrlMatch The match URL string for a protocol
|
---|
2251 | * match. Ex: 'http://yahoo.com'. This is used to know whether or not we
|
---|
2252 | * have a protocol in the URL string, in order to check for a word
|
---|
2253 | * character after the protocol separator (':').
|
---|
2254 | * @return {Boolean} `true` if the URL match does not have a full protocol, or
|
---|
2255 | * at least one word character in it, `false` otherwise.
|
---|
2256 | */
|
---|
2257 | UrlMatchValidator.urlMatchDoesNotHaveAtLeastOneWordChar = function (urlMatch, protocolUrlMatch) {
|
---|
2258 | if (urlMatch && protocolUrlMatch) {
|
---|
2259 | return (!this.hasFullProtocolRegex.test(protocolUrlMatch) &&
|
---|
2260 | !this.hasWordCharAfterProtocolRegex.test(urlMatch));
|
---|
2261 | }
|
---|
2262 | else {
|
---|
2263 | return false;
|
---|
2264 | }
|
---|
2265 | };
|
---|
2266 | /**
|
---|
2267 | * Regex to test for a full protocol, with the two trailing slashes. Ex: 'http://'
|
---|
2268 | *
|
---|
2269 | * @private
|
---|
2270 | * @property {RegExp} hasFullProtocolRegex
|
---|
2271 | */
|
---|
2272 | UrlMatchValidator.hasFullProtocolRegex = /^[A-Za-z][-.+A-Za-z0-9]*:\/\//;
|
---|
2273 | /**
|
---|
2274 | * Regex to find the URI scheme, such as 'mailto:'.
|
---|
2275 | *
|
---|
2276 | * This is used to filter out 'javascript:' and 'vbscript:' schemes.
|
---|
2277 | *
|
---|
2278 | * @private
|
---|
2279 | * @property {RegExp} uriSchemeRegex
|
---|
2280 | */
|
---|
2281 | UrlMatchValidator.uriSchemeRegex = /^[A-Za-z][-.+A-Za-z0-9]*:/;
|
---|
2282 | /**
|
---|
2283 | * Regex to determine if at least one word char exists after the protocol (i.e. after the ':')
|
---|
2284 | *
|
---|
2285 | * @private
|
---|
2286 | * @property {RegExp} hasWordCharAfterProtocolRegex
|
---|
2287 | */
|
---|
2288 | UrlMatchValidator.hasWordCharAfterProtocolRegex = new RegExp(':[^\\s]*?[' + alphaCharsStr + ']');
|
---|
2289 | /**
|
---|
2290 | * Regex to determine if the string is a valid IP address
|
---|
2291 | *
|
---|
2292 | * @private
|
---|
2293 | * @property {RegExp} ipRegex
|
---|
2294 | */
|
---|
2295 | UrlMatchValidator.ipRegex = /[0-9][0-9]?[0-9]?\.[0-9][0-9]?[0-9]?\.[0-9][0-9]?[0-9]?\.[0-9][0-9]?[0-9]?(:[0-9]*)?\/?$/;
|
---|
2296 | return UrlMatchValidator;
|
---|
2297 | }());
|
---|
2298 |
|
---|
2299 | // RegExp objects which are shared by all instances of UrlMatcher. These are
|
---|
2300 | // here to avoid re-instantiating the RegExp objects if `Autolinker.link()` is
|
---|
2301 | // called multiple times, thus instantiating UrlMatcher and its RegExp
|
---|
2302 | // objects each time (which is very expensive - see https://github.com/gregjacobs/Autolinker.js/issues/314).
|
---|
2303 | // See descriptions of the properties where they are used for details about them
|
---|
2304 | // prettier-ignore
|
---|
2305 | var matcherRegex = (function () {
|
---|
2306 | var schemeRegex = /(?:[A-Za-z][-.+A-Za-z0-9]{0,63}:(?![A-Za-z][-.+A-Za-z0-9]{0,63}:\/\/)(?!\d+\/?)(?:\/\/)?)/, // match protocol, allow in format "http://" or "mailto:". However, do not match the first part of something like 'link:http://www.google.com' (i.e. don't match "link:"). Also, make sure we don't interpret 'google.com:8000' as if 'google.com' was a protocol here (i.e. ignore a trailing port number in this regex)
|
---|
2307 | wwwRegex = /(?:www\.)/, // starting with 'www.'
|
---|
2308 | // Allow optional path, query string, and hash anchor, not ending in the following characters: "?!:,.;"
|
---|
2309 | // http://blog.codinghorror.com/the-problem-with-urls/
|
---|
2310 | urlSuffixRegex = new RegExp('[/?#](?:[' + alphaNumericAndMarksCharsStr + '\\-+&@#/%=~_()|\'$*\\[\\]{}?!:,.;^\u2713]*[' + alphaNumericAndMarksCharsStr + '\\-+&@#/%=~_()|\'$*\\[\\]{}\u2713])?');
|
---|
2311 | return new RegExp([
|
---|
2312 | '(?:',
|
---|
2313 | '(',
|
---|
2314 | schemeRegex.source,
|
---|
2315 | getDomainNameStr(2),
|
---|
2316 | ')',
|
---|
2317 | '|',
|
---|
2318 | '(',
|
---|
2319 | '(//)?',
|
---|
2320 | wwwRegex.source,
|
---|
2321 | getDomainNameStr(6),
|
---|
2322 | ')',
|
---|
2323 | '|',
|
---|
2324 | '(',
|
---|
2325 | '(//)?',
|
---|
2326 | getDomainNameStr(10) + '\\.',
|
---|
2327 | tldRegex.source,
|
---|
2328 | '(?![-' + alphaNumericCharsStr + '])',
|
---|
2329 | ')',
|
---|
2330 | ')',
|
---|
2331 | '(?::[0-9]+)?',
|
---|
2332 | '(?:' + urlSuffixRegex.source + ')?' // match for path, query string, and/or hash anchor - optional
|
---|
2333 | ].join(""), 'gi');
|
---|
2334 | })();
|
---|
2335 | var wordCharRegExp = new RegExp('[' + alphaNumericAndMarksCharsStr + ']');
|
---|
2336 | /**
|
---|
2337 | * @class Autolinker.matcher.Url
|
---|
2338 | * @extends Autolinker.matcher.Matcher
|
---|
2339 | *
|
---|
2340 | * Matcher to find URL matches in an input string.
|
---|
2341 | *
|
---|
2342 | * See this class's superclass ({@link Autolinker.matcher.Matcher}) for more details.
|
---|
2343 | */
|
---|
2344 | var UrlMatcher = /** @class */ (function (_super) {
|
---|
2345 | __extends(UrlMatcher, _super);
|
---|
2346 | /**
|
---|
2347 | * @method constructor
|
---|
2348 | * @param {Object} cfg The configuration properties for the Match instance,
|
---|
2349 | * specified in an Object (map).
|
---|
2350 | */
|
---|
2351 | function UrlMatcher(cfg) {
|
---|
2352 | var _this = _super.call(this, cfg) || this;
|
---|
2353 | /**
|
---|
2354 | * @cfg {Object} stripPrefix (required)
|
---|
2355 | *
|
---|
2356 | * The Object form of {@link Autolinker#cfg-stripPrefix}.
|
---|
2357 | */
|
---|
2358 | _this.stripPrefix = {
|
---|
2359 | scheme: true,
|
---|
2360 | www: true,
|
---|
2361 | }; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
2362 | /**
|
---|
2363 | * @cfg {Boolean} stripTrailingSlash (required)
|
---|
2364 | * @inheritdoc Autolinker#stripTrailingSlash
|
---|
2365 | */
|
---|
2366 | _this.stripTrailingSlash = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
2367 | /**
|
---|
2368 | * @cfg {Boolean} decodePercentEncoding (required)
|
---|
2369 | * @inheritdoc Autolinker#decodePercentEncoding
|
---|
2370 | */
|
---|
2371 | _this.decodePercentEncoding = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
2372 | /**
|
---|
2373 | * @protected
|
---|
2374 | * @property {RegExp} matcherRegex
|
---|
2375 | *
|
---|
2376 | * The regular expression to match URLs with an optional scheme, port
|
---|
2377 | * number, path, query string, and hash anchor.
|
---|
2378 | *
|
---|
2379 | * Example matches:
|
---|
2380 | *
|
---|
2381 | * http://google.com
|
---|
2382 | * www.google.com
|
---|
2383 | * google.com/path/to/file?q1=1&q2=2#myAnchor
|
---|
2384 | *
|
---|
2385 | *
|
---|
2386 | * This regular expression will have the following capturing groups:
|
---|
2387 | *
|
---|
2388 | * 1. Group that matches a scheme-prefixed URL (i.e. 'http://google.com').
|
---|
2389 | * This is used to match scheme URLs with just a single word, such as
|
---|
2390 | * 'http://localhost', where we won't double check that the domain name
|
---|
2391 | * has at least one dot ('.') in it.
|
---|
2392 | * 2. Group that matches a 'www.' prefixed URL. This is only matched if the
|
---|
2393 | * 'www.' text was not prefixed by a scheme (i.e.: not prefixed by
|
---|
2394 | * 'http://', 'ftp:', etc.)
|
---|
2395 | * 3. A protocol-relative ('//') match for the case of a 'www.' prefixed
|
---|
2396 | * URL. Will be an empty string if it is not a protocol-relative match.
|
---|
2397 | * We need to know the character before the '//' in order to determine
|
---|
2398 | * if it is a valid match or the // was in a string we don't want to
|
---|
2399 | * auto-link.
|
---|
2400 | * 4. Group that matches a known TLD (top level domain), when a scheme
|
---|
2401 | * or 'www.'-prefixed domain is not matched.
|
---|
2402 | * 5. A protocol-relative ('//') match for the case of a known TLD prefixed
|
---|
2403 | * URL. Will be an empty string if it is not a protocol-relative match.
|
---|
2404 | * See #3 for more info.
|
---|
2405 | */
|
---|
2406 | _this.matcherRegex = matcherRegex;
|
---|
2407 | /**
|
---|
2408 | * A regular expression to use to check the character before a protocol-relative
|
---|
2409 | * URL match. We don't want to match a protocol-relative URL if it is part
|
---|
2410 | * of another word.
|
---|
2411 | *
|
---|
2412 | * For example, we want to match something like "Go to: //google.com",
|
---|
2413 | * but we don't want to match something like "abc//google.com"
|
---|
2414 | *
|
---|
2415 | * This regular expression is used to test the character before the '//'.
|
---|
2416 | *
|
---|
2417 | * @protected
|
---|
2418 | * @type {RegExp} wordCharRegExp
|
---|
2419 | */
|
---|
2420 | _this.wordCharRegExp = wordCharRegExp;
|
---|
2421 | _this.stripPrefix = cfg.stripPrefix;
|
---|
2422 | _this.stripTrailingSlash = cfg.stripTrailingSlash;
|
---|
2423 | _this.decodePercentEncoding = cfg.decodePercentEncoding;
|
---|
2424 | return _this;
|
---|
2425 | }
|
---|
2426 | /**
|
---|
2427 | * @inheritdoc
|
---|
2428 | */
|
---|
2429 | UrlMatcher.prototype.parseMatches = function (text) {
|
---|
2430 | var matcherRegex = this.matcherRegex, stripPrefix = this.stripPrefix, stripTrailingSlash = this.stripTrailingSlash, decodePercentEncoding = this.decodePercentEncoding, tagBuilder = this.tagBuilder, matches = [], match;
|
---|
2431 | var _loop_1 = function () {
|
---|
2432 | var matchStr = match[0], schemeUrlMatch = match[1], wwwUrlMatch = match[4], wwwProtocolRelativeMatch = match[5],
|
---|
2433 | //tldUrlMatch = match[ 8 ], -- not needed at the moment
|
---|
2434 | tldProtocolRelativeMatch = match[9], offset = match.index, protocolRelativeMatch = wwwProtocolRelativeMatch || tldProtocolRelativeMatch, prevChar = text.charAt(offset - 1);
|
---|
2435 | if (!UrlMatchValidator.isValid(matchStr, schemeUrlMatch)) {
|
---|
2436 | return "continue";
|
---|
2437 | }
|
---|
2438 | // If the match is preceded by an '@' character, then it is either
|
---|
2439 | // an email address or a username. Skip these types of matches.
|
---|
2440 | if (offset > 0 && prevChar === '@') {
|
---|
2441 | return "continue";
|
---|
2442 | }
|
---|
2443 | // If it's a protocol-relative '//' match, but the character before the '//'
|
---|
2444 | // was a word character (i.e. a letter/number), then we found the '//' in the
|
---|
2445 | // middle of another word (such as "asdf//asdf.com"). In this case, skip the
|
---|
2446 | // match.
|
---|
2447 | if (offset > 0 && protocolRelativeMatch && this_1.wordCharRegExp.test(prevChar)) {
|
---|
2448 | return "continue";
|
---|
2449 | }
|
---|
2450 | // If the URL ends with a question mark, don't include the question
|
---|
2451 | // mark as part of the URL. We'll assume the question mark was the
|
---|
2452 | // end of a sentence, such as: "Going to google.com?"
|
---|
2453 | if (/\?$/.test(matchStr)) {
|
---|
2454 | matchStr = matchStr.substr(0, matchStr.length - 1);
|
---|
2455 | }
|
---|
2456 | // Handle a closing parenthesis or square bracket at the end of the
|
---|
2457 | // match, and exclude it if there is not a matching open parenthesis
|
---|
2458 | // or square bracket in the match itself.
|
---|
2459 | if (this_1.matchHasUnbalancedClosingParen(matchStr)) {
|
---|
2460 | matchStr = matchStr.substr(0, matchStr.length - 1); // remove the trailing ")"
|
---|
2461 | }
|
---|
2462 | else {
|
---|
2463 | // Handle an invalid character after the TLD
|
---|
2464 | var pos = this_1.matchHasInvalidCharAfterTld(matchStr, schemeUrlMatch);
|
---|
2465 | if (pos > -1) {
|
---|
2466 | matchStr = matchStr.substr(0, pos); // remove the trailing invalid chars
|
---|
2467 | }
|
---|
2468 | }
|
---|
2469 | // The autolinker accepts many characters in a url's scheme (like `fake://test.com`).
|
---|
2470 | // However, in cases where a URL is missing whitespace before an obvious link,
|
---|
2471 | // (for example: `nowhitespacehttp://www.test.com`), we only want the match to start
|
---|
2472 | // at the http:// part. We will check if the match contains a common scheme and then
|
---|
2473 | // shift the match to start from there.
|
---|
2474 | var foundCommonScheme = ['http://', 'https://'].find(function (commonScheme) { return !!schemeUrlMatch && schemeUrlMatch.indexOf(commonScheme) !== -1; });
|
---|
2475 | if (foundCommonScheme) {
|
---|
2476 | // If we found an overmatched URL, we want to find the index
|
---|
2477 | // of where the match should start and shift the match to
|
---|
2478 | // start from the beginning of the common scheme
|
---|
2479 | var indexOfSchemeStart = matchStr.indexOf(foundCommonScheme);
|
---|
2480 | matchStr = matchStr.substr(indexOfSchemeStart);
|
---|
2481 | schemeUrlMatch = schemeUrlMatch.substr(indexOfSchemeStart);
|
---|
2482 | offset = offset + indexOfSchemeStart;
|
---|
2483 | }
|
---|
2484 | var urlMatchType = schemeUrlMatch
|
---|
2485 | ? 'scheme'
|
---|
2486 | : wwwUrlMatch
|
---|
2487 | ? 'www'
|
---|
2488 | : 'tld', protocolUrlMatch = !!schemeUrlMatch;
|
---|
2489 | matches.push(new UrlMatch({
|
---|
2490 | tagBuilder: tagBuilder,
|
---|
2491 | matchedText: matchStr,
|
---|
2492 | offset: offset,
|
---|
2493 | urlMatchType: urlMatchType,
|
---|
2494 | url: matchStr,
|
---|
2495 | protocolUrlMatch: protocolUrlMatch,
|
---|
2496 | protocolRelativeMatch: !!protocolRelativeMatch,
|
---|
2497 | stripPrefix: stripPrefix,
|
---|
2498 | stripTrailingSlash: stripTrailingSlash,
|
---|
2499 | decodePercentEncoding: decodePercentEncoding,
|
---|
2500 | }));
|
---|
2501 | };
|
---|
2502 | var this_1 = this;
|
---|
2503 | while ((match = matcherRegex.exec(text)) !== null) {
|
---|
2504 | _loop_1();
|
---|
2505 | }
|
---|
2506 | return matches;
|
---|
2507 | };
|
---|
2508 | /**
|
---|
2509 | * Determines if a match found has an unmatched closing parenthesis,
|
---|
2510 | * square bracket or curly bracket. If so, the symbol will be removed
|
---|
2511 | * from the match itself, and appended after the generated anchor tag.
|
---|
2512 | *
|
---|
2513 | * A match may have an extra closing parenthesis at the end of the match
|
---|
2514 | * because the regular expression must include parenthesis for URLs such as
|
---|
2515 | * "wikipedia.com/something_(disambiguation)", which should be auto-linked.
|
---|
2516 | *
|
---|
2517 | * However, an extra parenthesis *will* be included when the URL itself is
|
---|
2518 | * wrapped in parenthesis, such as in the case of:
|
---|
2519 | * "(wikipedia.com/something_(disambiguation))"
|
---|
2520 | * In this case, the last closing parenthesis should *not* be part of the
|
---|
2521 | * URL itself, and this method will return `true`.
|
---|
2522 | *
|
---|
2523 | * For square brackets in URLs such as in PHP arrays, the same behavior as
|
---|
2524 | * parenthesis discussed above should happen:
|
---|
2525 | * "[http://www.example.com/foo.php?bar[]=1&bar[]=2&bar[]=3]"
|
---|
2526 | * The closing square bracket should not be part of the URL itself, and this
|
---|
2527 | * method will return `true`.
|
---|
2528 | *
|
---|
2529 | * @protected
|
---|
2530 | * @param {String} matchStr The full match string from the {@link #matcherRegex}.
|
---|
2531 | * @return {Boolean} `true` if there is an unbalanced closing parenthesis or
|
---|
2532 | * square bracket at the end of the `matchStr`, `false` otherwise.
|
---|
2533 | */
|
---|
2534 | UrlMatcher.prototype.matchHasUnbalancedClosingParen = function (matchStr) {
|
---|
2535 | var endChar = matchStr.charAt(matchStr.length - 1);
|
---|
2536 | var startChar;
|
---|
2537 | if (endChar === ')') {
|
---|
2538 | startChar = '(';
|
---|
2539 | }
|
---|
2540 | else if (endChar === ']') {
|
---|
2541 | startChar = '[';
|
---|
2542 | }
|
---|
2543 | else if (endChar === '}') {
|
---|
2544 | startChar = '{';
|
---|
2545 | }
|
---|
2546 | else {
|
---|
2547 | return false; // not a close parenthesis or square bracket
|
---|
2548 | }
|
---|
2549 | // Find if there are the same number of open braces as close braces in
|
---|
2550 | // the URL string, minus the last character (which we have already
|
---|
2551 | // determined to be either ')', ']' or '}'
|
---|
2552 | var numOpenBraces = 0;
|
---|
2553 | for (var i = 0, len = matchStr.length - 1; i < len; i++) {
|
---|
2554 | var char = matchStr.charAt(i);
|
---|
2555 | if (char === startChar) {
|
---|
2556 | numOpenBraces++;
|
---|
2557 | }
|
---|
2558 | else if (char === endChar) {
|
---|
2559 | numOpenBraces = Math.max(numOpenBraces - 1, 0);
|
---|
2560 | }
|
---|
2561 | }
|
---|
2562 | // If the number of open braces matches the number of close braces in
|
---|
2563 | // the URL minus the last character, then the match has *unbalanced*
|
---|
2564 | // braces because of the last character. Example of unbalanced braces
|
---|
2565 | // from the regex match:
|
---|
2566 | // "http://example.com?a[]=1]"
|
---|
2567 | if (numOpenBraces === 0) {
|
---|
2568 | return true;
|
---|
2569 | }
|
---|
2570 | return false;
|
---|
2571 | };
|
---|
2572 | /**
|
---|
2573 | * Determine if there's an invalid character after the TLD in a URL. Valid
|
---|
2574 | * characters after TLD are ':/?#'. Exclude scheme matched URLs from this
|
---|
2575 | * check.
|
---|
2576 | *
|
---|
2577 | * @protected
|
---|
2578 | * @param {String} urlMatch The matched URL, if there was one. Will be an
|
---|
2579 | * empty string if the match is not a URL match.
|
---|
2580 | * @param {String} schemeUrlMatch The match URL string for a scheme
|
---|
2581 | * match. Ex: 'http://yahoo.com'. This is used to match something like
|
---|
2582 | * 'http://localhost', where we won't double check that the domain name
|
---|
2583 | * has at least one '.' in it.
|
---|
2584 | * @return {Number} the position where the invalid character was found. If
|
---|
2585 | * no such character was found, returns -1
|
---|
2586 | */
|
---|
2587 | UrlMatcher.prototype.matchHasInvalidCharAfterTld = function (urlMatch, schemeUrlMatch) {
|
---|
2588 | if (!urlMatch) {
|
---|
2589 | return -1;
|
---|
2590 | }
|
---|
2591 | var offset = 0;
|
---|
2592 | if (schemeUrlMatch) {
|
---|
2593 | offset = urlMatch.indexOf(':');
|
---|
2594 | urlMatch = urlMatch.slice(offset);
|
---|
2595 | }
|
---|
2596 | // prettier-ignore
|
---|
2597 | var re = new RegExp("^((.?\/\/)?[-." + alphaNumericAndMarksCharsStr + "]*[-" + alphaNumericAndMarksCharsStr + "]\\.[-" + alphaNumericAndMarksCharsStr + "]+)");
|
---|
2598 | var res = re.exec(urlMatch);
|
---|
2599 | if (res === null) {
|
---|
2600 | return -1;
|
---|
2601 | }
|
---|
2602 | offset += res[1].length;
|
---|
2603 | urlMatch = urlMatch.slice(res[1].length);
|
---|
2604 | if (/^[^-.A-Za-z0-9:\/?#]/.test(urlMatch)) {
|
---|
2605 | return offset;
|
---|
2606 | }
|
---|
2607 | return -1;
|
---|
2608 | };
|
---|
2609 | return UrlMatcher;
|
---|
2610 | }(Matcher));
|
---|
2611 |
|
---|
2612 | // For debugging: search for other "For debugging" lines
|
---|
2613 | // import CliTable from 'cli-table';
|
---|
2614 | var hashtagTextCharRe = new RegExp("[_".concat(alphaNumericAndMarksCharsStr, "]"));
|
---|
2615 | /**
|
---|
2616 | * @class Autolinker.matcher.Hashtag
|
---|
2617 | * @extends Autolinker.matcher.Matcher
|
---|
2618 | *
|
---|
2619 | * Matcher to find HashtagMatch matches in an input string.
|
---|
2620 | */
|
---|
2621 | var HashtagMatcher = /** @class */ (function (_super) {
|
---|
2622 | __extends(HashtagMatcher, _super);
|
---|
2623 | /**
|
---|
2624 | * @method constructor
|
---|
2625 | * @param {Object} cfg The configuration properties for the Match instance,
|
---|
2626 | * specified in an Object (map).
|
---|
2627 | */
|
---|
2628 | function HashtagMatcher(cfg) {
|
---|
2629 | var _this = _super.call(this, cfg) || this;
|
---|
2630 | /**
|
---|
2631 | * @cfg {String} service
|
---|
2632 | *
|
---|
2633 | * A string for the service name to have hashtags (ex: "#myHashtag")
|
---|
2634 | * auto-linked to. The currently-supported values are:
|
---|
2635 | *
|
---|
2636 | * - 'twitter'
|
---|
2637 | * - 'facebook'
|
---|
2638 | * - 'instagram'
|
---|
2639 | * - 'tiktok'
|
---|
2640 | */
|
---|
2641 | _this.serviceName = 'twitter'; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
2642 | _this.serviceName = cfg.serviceName;
|
---|
2643 | return _this;
|
---|
2644 | }
|
---|
2645 | /**
|
---|
2646 | * @inheritdoc
|
---|
2647 | */
|
---|
2648 | HashtagMatcher.prototype.parseMatches = function (text) {
|
---|
2649 | var tagBuilder = this.tagBuilder;
|
---|
2650 | var serviceName = this.serviceName;
|
---|
2651 | var matches = [];
|
---|
2652 | var len = text.length;
|
---|
2653 | var charIdx = 0, hashCharIdx = -1, state = 0 /* None */;
|
---|
2654 | // For debugging: search for other "For debugging" lines
|
---|
2655 | // const table = new CliTable( {
|
---|
2656 | // head: [ 'charIdx', 'char', 'state', 'charIdx', 'currentEmailAddress.idx', 'hasDomainDot' ]
|
---|
2657 | // } );
|
---|
2658 | while (charIdx < len) {
|
---|
2659 | var char = text.charAt(charIdx);
|
---|
2660 | // For debugging: search for other "For debugging" lines
|
---|
2661 | // table.push(
|
---|
2662 | // [ charIdx, char, State[ state ], charIdx, currentEmailAddress.idx, currentEmailAddress.hasDomainDot ]
|
---|
2663 | // );
|
---|
2664 | switch (state) {
|
---|
2665 | case 0 /* None */:
|
---|
2666 | stateNone(char);
|
---|
2667 | break;
|
---|
2668 | case 1 /* NonHashtagWordChar */:
|
---|
2669 | stateNonHashtagWordChar(char);
|
---|
2670 | break;
|
---|
2671 | case 2 /* HashtagHashChar */:
|
---|
2672 | stateHashtagHashChar(char);
|
---|
2673 | break;
|
---|
2674 | case 3 /* HashtagTextChar */:
|
---|
2675 | stateHashtagTextChar(char);
|
---|
2676 | break;
|
---|
2677 | default:
|
---|
2678 | throwUnhandledCaseError(state);
|
---|
2679 | }
|
---|
2680 | // For debugging: search for other "For debugging" lines
|
---|
2681 | // table.push(
|
---|
2682 | // [ charIdx, char, State[ state ], charIdx, currentEmailAddress.idx, currentEmailAddress.hasDomainDot ]
|
---|
2683 | // );
|
---|
2684 | charIdx++;
|
---|
2685 | }
|
---|
2686 | // Capture any valid match at the end of the string
|
---|
2687 | captureMatchIfValid();
|
---|
2688 | // For debugging: search for other "For debugging" lines
|
---|
2689 | //console.log( '\n' + table.toString() );
|
---|
2690 | return matches;
|
---|
2691 | // Handles the state when we're not in a hashtag or any word
|
---|
2692 | function stateNone(char) {
|
---|
2693 | if (char === '#') {
|
---|
2694 | state = 2 /* HashtagHashChar */;
|
---|
2695 | hashCharIdx = charIdx;
|
---|
2696 | }
|
---|
2697 | else if (alphaNumericAndMarksCharRe.test(char)) {
|
---|
2698 | state = 1 /* NonHashtagWordChar */;
|
---|
2699 | }
|
---|
2700 | else ;
|
---|
2701 | }
|
---|
2702 | // Handles the state when we've encountered a word character but are not
|
---|
2703 | // in a hashtag. This is used to distinguish between a standalone
|
---|
2704 | // hashtag such as '#Stuff' vs a hash char that is part of a word like
|
---|
2705 | // 'asdf#stuff' (the latter of which would not be a match)
|
---|
2706 | function stateNonHashtagWordChar(char) {
|
---|
2707 | if (alphaNumericAndMarksCharRe.test(char)) ;
|
---|
2708 | else {
|
---|
2709 | state = 0 /* None */;
|
---|
2710 | }
|
---|
2711 | }
|
---|
2712 | // Handles the state when we've just encountered a '#' character
|
---|
2713 | function stateHashtagHashChar(char) {
|
---|
2714 | if (hashtagTextCharRe.test(char)) {
|
---|
2715 | // '#' char with valid hash text char following
|
---|
2716 | state = 3 /* HashtagTextChar */;
|
---|
2717 | }
|
---|
2718 | else if (alphaNumericAndMarksCharRe.test(char)) {
|
---|
2719 | state = 1 /* NonHashtagWordChar */;
|
---|
2720 | }
|
---|
2721 | else {
|
---|
2722 | state = 0 /* None */;
|
---|
2723 | }
|
---|
2724 | }
|
---|
2725 | // Handles the state when we're currently in the hash tag's text chars
|
---|
2726 | function stateHashtagTextChar(char) {
|
---|
2727 | if (hashtagTextCharRe.test(char)) ;
|
---|
2728 | else {
|
---|
2729 | captureMatchIfValid();
|
---|
2730 | hashCharIdx = -1;
|
---|
2731 | if (alphaNumericAndMarksCharRe.test(char)) {
|
---|
2732 | state = 1 /* NonHashtagWordChar */;
|
---|
2733 | }
|
---|
2734 | else {
|
---|
2735 | state = 0 /* None */;
|
---|
2736 | }
|
---|
2737 | }
|
---|
2738 | }
|
---|
2739 | /*
|
---|
2740 | * Captures the current hashtag as a HashtagMatch if it's valid.
|
---|
2741 | */
|
---|
2742 | function captureMatchIfValid() {
|
---|
2743 | if (hashCharIdx > -1 && charIdx - hashCharIdx <= 140) {
|
---|
2744 | // Max length of 140 for a hashtag ('#' char + 139 word chars)
|
---|
2745 | var matchedText = text.slice(hashCharIdx, charIdx);
|
---|
2746 | var match = new HashtagMatch({
|
---|
2747 | tagBuilder: tagBuilder,
|
---|
2748 | matchedText: matchedText,
|
---|
2749 | offset: hashCharIdx,
|
---|
2750 | serviceName: serviceName,
|
---|
2751 | hashtag: matchedText.slice(1),
|
---|
2752 | });
|
---|
2753 | matches.push(match);
|
---|
2754 | }
|
---|
2755 | }
|
---|
2756 | };
|
---|
2757 | return HashtagMatcher;
|
---|
2758 | }(Matcher));
|
---|
2759 | var hashtagServices = ['twitter', 'facebook', 'instagram', 'tiktok'];
|
---|
2760 |
|
---|
2761 | // RegExp objects which are shared by all instances of PhoneMatcher. These are
|
---|
2762 | // here to avoid re-instantiating the RegExp objects if `Autolinker.link()` is
|
---|
2763 | // called multiple times, thus instantiating PhoneMatcher and its RegExp
|
---|
2764 | // objects each time (which is very expensive - see https://github.com/gregjacobs/Autolinker.js/issues/314).
|
---|
2765 | // See descriptions of the properties where they are used for details about them
|
---|
2766 | // Over the years, many people have added to this regex, but it should have been
|
---|
2767 | // split up by country. Maybe one day we can break this down.
|
---|
2768 | var mostPhoneNumbers = /(?:(?:(?:(\+)?\d{1,3}[-\040.]?)?\(?\d{3}\)?[-\040.]?\d{3}[-\040.]?\d{4})|(?:(\+)(?:9[976]\d|8[987530]\d|6[987]\d|5[90]\d|42\d|3[875]\d|2[98654321]\d|9[8543210]|8[6421]|6[6543210]|5[87654321]|4[987654310]|3[9643210]|2[70]|7|1)[-\040.]?(?:\d[-\040.]?){6,12}\d+))([,;]+[0-9]+#?)*/;
|
---|
2769 | // Regex for Japanese phone numbers
|
---|
2770 | var japanesePhoneRe = /(0([1-9]{1}-?[1-9]\d{3}|[1-9]{2}-?\d{3}|[1-9]{2}\d{1}-?\d{2}|[1-9]{2}\d{2}-?\d{1})-?\d{4}|0[789]0-?\d{4}-?\d{4}|050-?\d{4}-?\d{4})/;
|
---|
2771 | // Combined regex
|
---|
2772 | var phoneMatcherRegex = new RegExp("".concat(mostPhoneNumbers.source, "|").concat(japanesePhoneRe.source), 'g');
|
---|
2773 | /**
|
---|
2774 | * @class Autolinker.matcher.Phone
|
---|
2775 | * @extends Autolinker.matcher.Matcher
|
---|
2776 | *
|
---|
2777 | * Matcher to find Phone number matches in an input string.
|
---|
2778 | *
|
---|
2779 | * See this class's superclass ({@link Autolinker.matcher.Matcher}) for more
|
---|
2780 | * details.
|
---|
2781 | */
|
---|
2782 | var PhoneMatcher = /** @class */ (function (_super) {
|
---|
2783 | __extends(PhoneMatcher, _super);
|
---|
2784 | function PhoneMatcher() {
|
---|
2785 | var _this = _super !== null && _super.apply(this, arguments) || this;
|
---|
2786 | /**
|
---|
2787 | * The regular expression to match Phone numbers. Example matches:
|
---|
2788 | *
|
---|
2789 | * (123) 456-7890
|
---|
2790 | * 123 456 7890
|
---|
2791 | * 123-456-7890
|
---|
2792 | * +18004441234,,;,10226420346#
|
---|
2793 | * +1 (800) 444 1234
|
---|
2794 | * 10226420346#
|
---|
2795 | * 1-800-444-1234,1022,64,20346#
|
---|
2796 | *
|
---|
2797 | * This regular expression has the following capturing groups:
|
---|
2798 | *
|
---|
2799 | * 1 or 2. The prefixed '+' sign, if there is one.
|
---|
2800 | *
|
---|
2801 | * @protected
|
---|
2802 | * @property {RegExp} matcherRegex
|
---|
2803 | */
|
---|
2804 | _this.matcherRegex = phoneMatcherRegex;
|
---|
2805 | return _this;
|
---|
2806 | }
|
---|
2807 | /**
|
---|
2808 | * @inheritdoc
|
---|
2809 | */
|
---|
2810 | PhoneMatcher.prototype.parseMatches = function (text) {
|
---|
2811 | var matcherRegex = this.matcherRegex, tagBuilder = this.tagBuilder, matches = [], match;
|
---|
2812 | while ((match = matcherRegex.exec(text)) !== null) {
|
---|
2813 | // Remove non-numeric values from phone number string
|
---|
2814 | var matchedText = match[0], cleanNumber = matchedText.replace(/[^0-9,;#]/g, ''), // strip out non-digit characters exclude comma semicolon and #
|
---|
2815 | plusSign = !!(match[1] || match[2]), // match[ 1 ] or match[ 2 ] is the prefixed plus sign, if there is one
|
---|
2816 | before = match.index == 0 ? '' : text.substr(match.index - 1, 1), after = text.substr(match.index + matchedText.length, 1), contextClear = !before.match(/\d/) && !after.match(/\d/);
|
---|
2817 | if (this.testMatch(match[3]) && this.testMatch(matchedText) && contextClear) {
|
---|
2818 | matches.push(new PhoneMatch({
|
---|
2819 | tagBuilder: tagBuilder,
|
---|
2820 | matchedText: matchedText,
|
---|
2821 | offset: match.index,
|
---|
2822 | number: cleanNumber,
|
---|
2823 | plusSign: plusSign,
|
---|
2824 | }));
|
---|
2825 | }
|
---|
2826 | }
|
---|
2827 | return matches;
|
---|
2828 | };
|
---|
2829 | PhoneMatcher.prototype.testMatch = function (text) {
|
---|
2830 | return nonDigitRe.test(text);
|
---|
2831 | };
|
---|
2832 | return PhoneMatcher;
|
---|
2833 | }(Matcher));
|
---|
2834 |
|
---|
2835 | // RegExp objects which are shared by all instances of MentionMatcher. These are
|
---|
2836 | // here to avoid re-instantiating the RegExp objects if `Autolinker.link()` is
|
---|
2837 | // called multiple times, thus instantiating MentionMatcher and its RegExp
|
---|
2838 | // objects each time (which is very expensive - see https://github.com/gregjacobs/Autolinker.js/issues/314).
|
---|
2839 | // See descriptions of the properties where they are used for details about them
|
---|
2840 | var twitterRegex = new RegExp("@[_".concat(alphaNumericAndMarksCharsStr, "]{1,50}(?![_").concat(alphaNumericAndMarksCharsStr, "])"), 'g'); // lookahead used to make sure we don't match something above 50 characters
|
---|
2841 | var instagramRegex = new RegExp("@[_.".concat(alphaNumericAndMarksCharsStr, "]{1,30}(?![_").concat(alphaNumericAndMarksCharsStr, "])"), 'g'); // lookahead used to make sure we don't match something above 30 characters
|
---|
2842 | var soundcloudRegex = new RegExp("@[-_.".concat(alphaNumericAndMarksCharsStr, "]{1,50}(?![-_").concat(alphaNumericAndMarksCharsStr, "])"), 'g'); // lookahead used to make sure we don't match something above 50 characters
|
---|
2843 | // TikTok usernames are 1-24 characters containing letters, numbers, underscores
|
---|
2844 | // and periods, but cannot end in a period: https://support.tiktok.com/en/getting-started/setting-up-your-profile/changing-your-username
|
---|
2845 | var tiktokRegex = new RegExp("@[_.".concat(alphaNumericAndMarksCharsStr, "]{1,23}[_").concat(alphaNumericAndMarksCharsStr, "](?![_").concat(alphaNumericAndMarksCharsStr, "])"), 'g'); // lookahead used to make sure we don't match something above 24 characters
|
---|
2846 | var nonWordCharRegex = new RegExp('[^' + alphaNumericAndMarksCharsStr + ']');
|
---|
2847 | /**
|
---|
2848 | * @class Autolinker.matcher.Mention
|
---|
2849 | * @extends Autolinker.matcher.Matcher
|
---|
2850 | *
|
---|
2851 | * Matcher to find/replace username matches in an input string.
|
---|
2852 | */
|
---|
2853 | var MentionMatcher = /** @class */ (function (_super) {
|
---|
2854 | __extends(MentionMatcher, _super);
|
---|
2855 | /**
|
---|
2856 | * @method constructor
|
---|
2857 | * @param {Object} cfg The configuration properties for the Match instance,
|
---|
2858 | * specified in an Object (map).
|
---|
2859 | */
|
---|
2860 | function MentionMatcher(cfg) {
|
---|
2861 | var _this = _super.call(this, cfg) || this;
|
---|
2862 | /**
|
---|
2863 | * @cfg {'twitter'/'instagram'/'soundcloud'} protected
|
---|
2864 | *
|
---|
2865 | * The name of service to link @mentions to.
|
---|
2866 | *
|
---|
2867 | * Valid values are: 'twitter', 'instagram', 'soundcloud', or 'tiktok'
|
---|
2868 | */
|
---|
2869 | _this.serviceName = 'twitter'; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
2870 | /**
|
---|
2871 | * Hash of regular expression to match username handles. Example match:
|
---|
2872 | *
|
---|
2873 | * @asdf
|
---|
2874 | *
|
---|
2875 | * @private
|
---|
2876 | * @property {Object} matcherRegexes
|
---|
2877 | */
|
---|
2878 | _this.matcherRegexes = {
|
---|
2879 | twitter: twitterRegex,
|
---|
2880 | instagram: instagramRegex,
|
---|
2881 | soundcloud: soundcloudRegex,
|
---|
2882 | tiktok: tiktokRegex,
|
---|
2883 | };
|
---|
2884 | /**
|
---|
2885 | * The regular expression to use to check the character before a username match to
|
---|
2886 | * make sure we didn't accidentally match an email address.
|
---|
2887 | *
|
---|
2888 | * For example, the string "asdf@asdf.com" should not match "@asdf" as a username.
|
---|
2889 | *
|
---|
2890 | * @private
|
---|
2891 | * @property {RegExp} nonWordCharRegex
|
---|
2892 | */
|
---|
2893 | _this.nonWordCharRegex = nonWordCharRegex;
|
---|
2894 | _this.serviceName = cfg.serviceName;
|
---|
2895 | return _this;
|
---|
2896 | }
|
---|
2897 | /**
|
---|
2898 | * @inheritdoc
|
---|
2899 | */
|
---|
2900 | MentionMatcher.prototype.parseMatches = function (text) {
|
---|
2901 | var serviceName = this.serviceName, matcherRegex = this.matcherRegexes[this.serviceName], nonWordCharRegex = this.nonWordCharRegex, tagBuilder = this.tagBuilder, matches = [], match;
|
---|
2902 | if (!matcherRegex) {
|
---|
2903 | return matches;
|
---|
2904 | }
|
---|
2905 | while ((match = matcherRegex.exec(text)) !== null) {
|
---|
2906 | var offset = match.index, prevChar = text.charAt(offset - 1);
|
---|
2907 | // If we found the match at the beginning of the string, or we found the match
|
---|
2908 | // and there is a whitespace char in front of it (meaning it is not an email
|
---|
2909 | // address), then it is a username match.
|
---|
2910 | if (offset === 0 || nonWordCharRegex.test(prevChar)) {
|
---|
2911 | var matchedText = match[0].replace(/\.+$/g, ''), // strip off trailing .
|
---|
2912 | mention = matchedText.slice(1); // strip off the '@' character at the beginning
|
---|
2913 | matches.push(new MentionMatch({
|
---|
2914 | tagBuilder: tagBuilder,
|
---|
2915 | matchedText: matchedText,
|
---|
2916 | offset: offset,
|
---|
2917 | serviceName: serviceName,
|
---|
2918 | mention: mention,
|
---|
2919 | }));
|
---|
2920 | }
|
---|
2921 | }
|
---|
2922 | return matches;
|
---|
2923 | };
|
---|
2924 | return MentionMatcher;
|
---|
2925 | }(Matcher));
|
---|
2926 |
|
---|
2927 | // For debugging: search for other "For debugging" lines
|
---|
2928 | // import CliTable from 'cli-table';
|
---|
2929 | /**
|
---|
2930 | * Parses an HTML string, calling the callbacks to notify of tags and text.
|
---|
2931 | *
|
---|
2932 | * ## History
|
---|
2933 | *
|
---|
2934 | * This file previously used a regular expression to find html tags in the input
|
---|
2935 | * text. Unfortunately, we ran into a bunch of catastrophic backtracking issues
|
---|
2936 | * with certain input text, causing Autolinker to either hang or just take a
|
---|
2937 | * really long time to parse the string.
|
---|
2938 | *
|
---|
2939 | * The current code is intended to be a O(n) algorithm that walks through
|
---|
2940 | * the string in one pass, and tries to be as cheap as possible. We don't need
|
---|
2941 | * to implement the full HTML spec, but rather simply determine where the string
|
---|
2942 | * looks like an HTML tag, and where it looks like text (so that we can autolink
|
---|
2943 | * that).
|
---|
2944 | *
|
---|
2945 | * This state machine parser is intended just to be a simple but performant
|
---|
2946 | * parser of HTML for the subset of requirements we have. We simply need to:
|
---|
2947 | *
|
---|
2948 | * 1. Determine where HTML tags are
|
---|
2949 | * 2. Determine the tag name (Autolinker specifically only cares about <a>,
|
---|
2950 | * <script>, and <style> tags, so as not to link any text within them)
|
---|
2951 | *
|
---|
2952 | * We don't need to:
|
---|
2953 | *
|
---|
2954 | * 1. Create a parse tree
|
---|
2955 | * 2. Auto-close tags with invalid markup
|
---|
2956 | * 3. etc.
|
---|
2957 | *
|
---|
2958 | * The other intention behind this is that we didn't want to add external
|
---|
2959 | * dependencies on the Autolinker utility which would increase its size. For
|
---|
2960 | * instance, adding htmlparser2 adds 125kb to the minified output file,
|
---|
2961 | * increasing its final size from 47kb to 172kb (at the time of writing). It
|
---|
2962 | * also doesn't work exactly correctly, treating the string "<3 blah blah blah"
|
---|
2963 | * as an HTML tag.
|
---|
2964 | *
|
---|
2965 | * Reference for HTML spec:
|
---|
2966 | *
|
---|
2967 | * https://www.w3.org/TR/html51/syntax.html#sec-tokenization
|
---|
2968 | *
|
---|
2969 | * @param {String} html The HTML to parse
|
---|
2970 | * @param {Object} callbacks
|
---|
2971 | * @param {Function} callbacks.onOpenTag Callback function to call when an open
|
---|
2972 | * tag is parsed. Called with the tagName as its argument.
|
---|
2973 | * @param {Function} callbacks.onCloseTag Callback function to call when a close
|
---|
2974 | * tag is parsed. Called with the tagName as its argument. If a self-closing
|
---|
2975 | * tag is found, `onCloseTag` is called immediately after `onOpenTag`.
|
---|
2976 | * @param {Function} callbacks.onText Callback function to call when text (i.e
|
---|
2977 | * not an HTML tag) is parsed. Called with the text (string) as its first
|
---|
2978 | * argument, and offset (number) into the string as its second.
|
---|
2979 | */
|
---|
2980 | function parseHtml(html, _a) {
|
---|
2981 | var onOpenTag = _a.onOpenTag, onCloseTag = _a.onCloseTag, onText = _a.onText, onComment = _a.onComment, onDoctype = _a.onDoctype;
|
---|
2982 | var noCurrentTag = new CurrentTag();
|
---|
2983 | var charIdx = 0, len = html.length, state = 0 /* Data */, currentDataIdx = 0, // where the current data start index is
|
---|
2984 | currentTag = noCurrentTag; // describes the current tag that is being read
|
---|
2985 | // For debugging: search for other "For debugging" lines
|
---|
2986 | // const table = new CliTable( {
|
---|
2987 | // head: [ 'charIdx', 'char', 'state', 'currentDataIdx', 'currentOpenTagIdx', 'tag.type' ]
|
---|
2988 | // } );
|
---|
2989 | while (charIdx < len) {
|
---|
2990 | var char = html.charAt(charIdx);
|
---|
2991 | // For debugging: search for other "For debugging" lines
|
---|
2992 | // ALSO: Temporarily remove the 'const' keyword on the State enum
|
---|
2993 | // table.push(
|
---|
2994 | // [ charIdx, char, State[ state ], currentDataIdx, currentTag.idx, currentTag.idx === -1 ? '' : currentTag.type ]
|
---|
2995 | // );
|
---|
2996 | switch (state) {
|
---|
2997 | case 0 /* Data */:
|
---|
2998 | stateData(char);
|
---|
2999 | break;
|
---|
3000 | case 1 /* TagOpen */:
|
---|
3001 | stateTagOpen(char);
|
---|
3002 | break;
|
---|
3003 | case 2 /* EndTagOpen */:
|
---|
3004 | stateEndTagOpen(char);
|
---|
3005 | break;
|
---|
3006 | case 3 /* TagName */:
|
---|
3007 | stateTagName(char);
|
---|
3008 | break;
|
---|
3009 | case 4 /* BeforeAttributeName */:
|
---|
3010 | stateBeforeAttributeName(char);
|
---|
3011 | break;
|
---|
3012 | case 5 /* AttributeName */:
|
---|
3013 | stateAttributeName(char);
|
---|
3014 | break;
|
---|
3015 | case 6 /* AfterAttributeName */:
|
---|
3016 | stateAfterAttributeName(char);
|
---|
3017 | break;
|
---|
3018 | case 7 /* BeforeAttributeValue */:
|
---|
3019 | stateBeforeAttributeValue(char);
|
---|
3020 | break;
|
---|
3021 | case 8 /* AttributeValueDoubleQuoted */:
|
---|
3022 | stateAttributeValueDoubleQuoted(char);
|
---|
3023 | break;
|
---|
3024 | case 9 /* AttributeValueSingleQuoted */:
|
---|
3025 | stateAttributeValueSingleQuoted(char);
|
---|
3026 | break;
|
---|
3027 | case 10 /* AttributeValueUnquoted */:
|
---|
3028 | stateAttributeValueUnquoted(char);
|
---|
3029 | break;
|
---|
3030 | case 11 /* AfterAttributeValueQuoted */:
|
---|
3031 | stateAfterAttributeValueQuoted(char);
|
---|
3032 | break;
|
---|
3033 | case 12 /* SelfClosingStartTag */:
|
---|
3034 | stateSelfClosingStartTag(char);
|
---|
3035 | break;
|
---|
3036 | case 13 /* MarkupDeclarationOpenState */:
|
---|
3037 | stateMarkupDeclarationOpen();
|
---|
3038 | break;
|
---|
3039 | case 14 /* CommentStart */:
|
---|
3040 | stateCommentStart(char);
|
---|
3041 | break;
|
---|
3042 | case 15 /* CommentStartDash */:
|
---|
3043 | stateCommentStartDash(char);
|
---|
3044 | break;
|
---|
3045 | case 16 /* Comment */:
|
---|
3046 | stateComment(char);
|
---|
3047 | break;
|
---|
3048 | case 17 /* CommentEndDash */:
|
---|
3049 | stateCommentEndDash(char);
|
---|
3050 | break;
|
---|
3051 | case 18 /* CommentEnd */:
|
---|
3052 | stateCommentEnd(char);
|
---|
3053 | break;
|
---|
3054 | case 19 /* CommentEndBang */:
|
---|
3055 | stateCommentEndBang(char);
|
---|
3056 | break;
|
---|
3057 | case 20 /* Doctype */:
|
---|
3058 | stateDoctype(char);
|
---|
3059 | break;
|
---|
3060 | default:
|
---|
3061 | throwUnhandledCaseError(state);
|
---|
3062 | }
|
---|
3063 | // For debugging: search for other "For debugging" lines
|
---|
3064 | // ALSO: Temporarily remove the 'const' keyword on the State enum
|
---|
3065 | // table.push(
|
---|
3066 | // [ charIdx, char, State[ state ], currentDataIdx, currentTag.idx, currentTag.idx === -1 ? '' : currentTag.type ]
|
---|
3067 | // );
|
---|
3068 | charIdx++;
|
---|
3069 | }
|
---|
3070 | if (currentDataIdx < charIdx) {
|
---|
3071 | emitText();
|
---|
3072 | }
|
---|
3073 | // For debugging: search for other "For debugging" lines
|
---|
3074 | // console.log( '\n' + table.toString() );
|
---|
3075 | // Called when non-tags are being read (i.e. the text around HTML †ags)
|
---|
3076 | // https://www.w3.org/TR/html51/syntax.html#data-state
|
---|
3077 | function stateData(char) {
|
---|
3078 | if (char === '<') {
|
---|
3079 | startNewTag();
|
---|
3080 | }
|
---|
3081 | }
|
---|
3082 | // Called after a '<' is read from the Data state
|
---|
3083 | // https://www.w3.org/TR/html51/syntax.html#tag-open-state
|
---|
3084 | function stateTagOpen(char) {
|
---|
3085 | if (char === '!') {
|
---|
3086 | state = 13 /* MarkupDeclarationOpenState */;
|
---|
3087 | }
|
---|
3088 | else if (char === '/') {
|
---|
3089 | state = 2 /* EndTagOpen */;
|
---|
3090 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { isClosing: true }));
|
---|
3091 | }
|
---|
3092 | else if (char === '<') {
|
---|
3093 | // start of another tag (ignore the previous, incomplete one)
|
---|
3094 | startNewTag();
|
---|
3095 | }
|
---|
3096 | else if (letterRe.test(char)) {
|
---|
3097 | // tag name start (and no '/' read)
|
---|
3098 | state = 3 /* TagName */;
|
---|
3099 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { isOpening: true }));
|
---|
3100 | }
|
---|
3101 | else {
|
---|
3102 | // Any other
|
---|
3103 | state = 0 /* Data */;
|
---|
3104 | currentTag = noCurrentTag;
|
---|
3105 | }
|
---|
3106 | }
|
---|
3107 | // After a '<x', '</x' sequence is read (where 'x' is a letter character),
|
---|
3108 | // this is to continue reading the tag name
|
---|
3109 | // https://www.w3.org/TR/html51/syntax.html#tag-name-state
|
---|
3110 | function stateTagName(char) {
|
---|
3111 | if (whitespaceRe.test(char)) {
|
---|
3112 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { name: captureTagName() }));
|
---|
3113 | state = 4 /* BeforeAttributeName */;
|
---|
3114 | }
|
---|
3115 | else if (char === '<') {
|
---|
3116 | // start of another tag (ignore the previous, incomplete one)
|
---|
3117 | startNewTag();
|
---|
3118 | }
|
---|
3119 | else if (char === '/') {
|
---|
3120 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { name: captureTagName() }));
|
---|
3121 | state = 12 /* SelfClosingStartTag */;
|
---|
3122 | }
|
---|
3123 | else if (char === '>') {
|
---|
3124 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { name: captureTagName() }));
|
---|
3125 | emitTagAndPreviousTextNode(); // resets to Data state as well
|
---|
3126 | }
|
---|
3127 | else if (!letterRe.test(char) && !digitRe.test(char) && char !== ':') {
|
---|
3128 | // Anything else that does not form an html tag. Note: the colon
|
---|
3129 | // character is accepted for XML namespaced tags
|
---|
3130 | resetToDataState();
|
---|
3131 | }
|
---|
3132 | else ;
|
---|
3133 | }
|
---|
3134 | // Called after the '/' is read from a '</' sequence
|
---|
3135 | // https://www.w3.org/TR/html51/syntax.html#end-tag-open-state
|
---|
3136 | function stateEndTagOpen(char) {
|
---|
3137 | if (char === '>') {
|
---|
3138 | // parse error. Encountered "</>". Skip it without treating as a tag
|
---|
3139 | resetToDataState();
|
---|
3140 | }
|
---|
3141 | else if (letterRe.test(char)) {
|
---|
3142 | state = 3 /* TagName */;
|
---|
3143 | }
|
---|
3144 | else {
|
---|
3145 | // some other non-tag-like character, don't treat this as a tag
|
---|
3146 | resetToDataState();
|
---|
3147 | }
|
---|
3148 | }
|
---|
3149 | // https://www.w3.org/TR/html51/syntax.html#before-attribute-name-state
|
---|
3150 | function stateBeforeAttributeName(char) {
|
---|
3151 | if (whitespaceRe.test(char)) ;
|
---|
3152 | else if (char === '/') {
|
---|
3153 | state = 12 /* SelfClosingStartTag */;
|
---|
3154 | }
|
---|
3155 | else if (char === '>') {
|
---|
3156 | emitTagAndPreviousTextNode(); // resets to Data state as well
|
---|
3157 | }
|
---|
3158 | else if (char === '<') {
|
---|
3159 | // start of another tag (ignore the previous, incomplete one)
|
---|
3160 | startNewTag();
|
---|
3161 | }
|
---|
3162 | else if (char === "=" || quoteRe.test(char) || controlCharsRe.test(char)) {
|
---|
3163 | // "Parse error" characters that, according to the spec, should be
|
---|
3164 | // appended to the attribute name, but we'll treat these characters
|
---|
3165 | // as not forming a real HTML tag
|
---|
3166 | resetToDataState();
|
---|
3167 | }
|
---|
3168 | else {
|
---|
3169 | // Any other char, start of a new attribute name
|
---|
3170 | state = 5 /* AttributeName */;
|
---|
3171 | }
|
---|
3172 | }
|
---|
3173 | // https://www.w3.org/TR/html51/syntax.html#attribute-name-state
|
---|
3174 | function stateAttributeName(char) {
|
---|
3175 | if (whitespaceRe.test(char)) {
|
---|
3176 | state = 6 /* AfterAttributeName */;
|
---|
3177 | }
|
---|
3178 | else if (char === '/') {
|
---|
3179 | state = 12 /* SelfClosingStartTag */;
|
---|
3180 | }
|
---|
3181 | else if (char === '=') {
|
---|
3182 | state = 7 /* BeforeAttributeValue */;
|
---|
3183 | }
|
---|
3184 | else if (char === '>') {
|
---|
3185 | emitTagAndPreviousTextNode(); // resets to Data state as well
|
---|
3186 | }
|
---|
3187 | else if (char === '<') {
|
---|
3188 | // start of another tag (ignore the previous, incomplete one)
|
---|
3189 | startNewTag();
|
---|
3190 | }
|
---|
3191 | else if (quoteRe.test(char)) {
|
---|
3192 | // "Parse error" characters that, according to the spec, should be
|
---|
3193 | // appended to the attribute name, but we'll treat these characters
|
---|
3194 | // as not forming a real HTML tag
|
---|
3195 | resetToDataState();
|
---|
3196 | }
|
---|
3197 | else ;
|
---|
3198 | }
|
---|
3199 | // https://www.w3.org/TR/html51/syntax.html#after-attribute-name-state
|
---|
3200 | function stateAfterAttributeName(char) {
|
---|
3201 | if (whitespaceRe.test(char)) ;
|
---|
3202 | else if (char === '/') {
|
---|
3203 | state = 12 /* SelfClosingStartTag */;
|
---|
3204 | }
|
---|
3205 | else if (char === '=') {
|
---|
3206 | state = 7 /* BeforeAttributeValue */;
|
---|
3207 | }
|
---|
3208 | else if (char === '>') {
|
---|
3209 | emitTagAndPreviousTextNode();
|
---|
3210 | }
|
---|
3211 | else if (char === '<') {
|
---|
3212 | // start of another tag (ignore the previous, incomplete one)
|
---|
3213 | startNewTag();
|
---|
3214 | }
|
---|
3215 | else if (quoteRe.test(char)) {
|
---|
3216 | // "Parse error" characters that, according to the spec, should be
|
---|
3217 | // appended to the attribute name, but we'll treat these characters
|
---|
3218 | // as not forming a real HTML tag
|
---|
3219 | resetToDataState();
|
---|
3220 | }
|
---|
3221 | else {
|
---|
3222 | // Any other character, start a new attribute in the current tag
|
---|
3223 | state = 5 /* AttributeName */;
|
---|
3224 | }
|
---|
3225 | }
|
---|
3226 | // https://www.w3.org/TR/html51/syntax.html#before-attribute-value-state
|
---|
3227 | function stateBeforeAttributeValue(char) {
|
---|
3228 | if (whitespaceRe.test(char)) ;
|
---|
3229 | else if (char === "\"") {
|
---|
3230 | state = 8 /* AttributeValueDoubleQuoted */;
|
---|
3231 | }
|
---|
3232 | else if (char === "'") {
|
---|
3233 | state = 9 /* AttributeValueSingleQuoted */;
|
---|
3234 | }
|
---|
3235 | else if (/[>=`]/.test(char)) {
|
---|
3236 | // Invalid chars after an '=' for an attribute value, don't count
|
---|
3237 | // the current tag as an HTML tag
|
---|
3238 | resetToDataState();
|
---|
3239 | }
|
---|
3240 | else if (char === '<') {
|
---|
3241 | // start of another tag (ignore the previous, incomplete one)
|
---|
3242 | startNewTag();
|
---|
3243 | }
|
---|
3244 | else {
|
---|
3245 | // Any other character, consider it an unquoted attribute value
|
---|
3246 | state = 10 /* AttributeValueUnquoted */;
|
---|
3247 | }
|
---|
3248 | }
|
---|
3249 | // https://www.w3.org/TR/html51/syntax.html#attribute-value-double-quoted-state
|
---|
3250 | function stateAttributeValueDoubleQuoted(char) {
|
---|
3251 | if (char === "\"") {
|
---|
3252 | // end the current double-quoted attribute
|
---|
3253 | state = 11 /* AfterAttributeValueQuoted */;
|
---|
3254 | }
|
---|
3255 | }
|
---|
3256 | // https://www.w3.org/TR/html51/syntax.html#attribute-value-single-quoted-state
|
---|
3257 | function stateAttributeValueSingleQuoted(char) {
|
---|
3258 | if (char === "'") {
|
---|
3259 | // end the current single-quoted attribute
|
---|
3260 | state = 11 /* AfterAttributeValueQuoted */;
|
---|
3261 | }
|
---|
3262 | }
|
---|
3263 | // https://www.w3.org/TR/html51/syntax.html#attribute-value-unquoted-state
|
---|
3264 | function stateAttributeValueUnquoted(char) {
|
---|
3265 | if (whitespaceRe.test(char)) {
|
---|
3266 | state = 4 /* BeforeAttributeName */;
|
---|
3267 | }
|
---|
3268 | else if (char === '>') {
|
---|
3269 | emitTagAndPreviousTextNode();
|
---|
3270 | }
|
---|
3271 | else if (char === '<') {
|
---|
3272 | // start of another tag (ignore the previous, incomplete one)
|
---|
3273 | startNewTag();
|
---|
3274 | }
|
---|
3275 | else ;
|
---|
3276 | }
|
---|
3277 | // https://www.w3.org/TR/html51/syntax.html#after-attribute-value-quoted-state
|
---|
3278 | function stateAfterAttributeValueQuoted(char) {
|
---|
3279 | if (whitespaceRe.test(char)) {
|
---|
3280 | state = 4 /* BeforeAttributeName */;
|
---|
3281 | }
|
---|
3282 | else if (char === '/') {
|
---|
3283 | state = 12 /* SelfClosingStartTag */;
|
---|
3284 | }
|
---|
3285 | else if (char === '>') {
|
---|
3286 | emitTagAndPreviousTextNode();
|
---|
3287 | }
|
---|
3288 | else if (char === '<') {
|
---|
3289 | // start of another tag (ignore the previous, incomplete one)
|
---|
3290 | startNewTag();
|
---|
3291 | }
|
---|
3292 | else {
|
---|
3293 | // Any other character, "parse error". Spec says to switch to the
|
---|
3294 | // BeforeAttributeState and re-consume the character, as it may be
|
---|
3295 | // the start of a new attribute name
|
---|
3296 | state = 4 /* BeforeAttributeName */;
|
---|
3297 | reconsumeCurrentCharacter();
|
---|
3298 | }
|
---|
3299 | }
|
---|
3300 | // A '/' has just been read in the current tag (presumably for '/>'), and
|
---|
3301 | // this handles the next character
|
---|
3302 | // https://www.w3.org/TR/html51/syntax.html#self-closing-start-tag-state
|
---|
3303 | function stateSelfClosingStartTag(char) {
|
---|
3304 | if (char === '>') {
|
---|
3305 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { isClosing: true }));
|
---|
3306 | emitTagAndPreviousTextNode(); // resets to Data state as well
|
---|
3307 | }
|
---|
3308 | else {
|
---|
3309 | state = 4 /* BeforeAttributeName */;
|
---|
3310 | }
|
---|
3311 | }
|
---|
3312 | // https://www.w3.org/TR/html51/syntax.html#markup-declaration-open-state
|
---|
3313 | // (HTML Comments or !DOCTYPE)
|
---|
3314 | function stateMarkupDeclarationOpen(char) {
|
---|
3315 | if (html.substr(charIdx, 2) === '--') {
|
---|
3316 | // html comment
|
---|
3317 | charIdx += 2; // "consume" characters
|
---|
3318 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { type: 'comment' }));
|
---|
3319 | state = 14 /* CommentStart */;
|
---|
3320 | }
|
---|
3321 | else if (html.substr(charIdx, 7).toUpperCase() === 'DOCTYPE') {
|
---|
3322 | charIdx += 7; // "consume" characters
|
---|
3323 | currentTag = new CurrentTag(__assign(__assign({}, currentTag), { type: 'doctype' }));
|
---|
3324 | state = 20 /* Doctype */;
|
---|
3325 | }
|
---|
3326 | else {
|
---|
3327 | // At this point, the spec specifies that the state machine should
|
---|
3328 | // enter the "bogus comment" state, in which case any character(s)
|
---|
3329 | // after the '<!' that were read should become an HTML comment up
|
---|
3330 | // until the first '>' that is read (or EOF). Instead, we'll assume
|
---|
3331 | // that a user just typed '<!' as part of text data
|
---|
3332 | resetToDataState();
|
---|
3333 | }
|
---|
3334 | }
|
---|
3335 | // Handles after the sequence '<!--' has been read
|
---|
3336 | // https://www.w3.org/TR/html51/syntax.html#comment-start-state
|
---|
3337 | function stateCommentStart(char) {
|
---|
3338 | if (char === '-') {
|
---|
3339 | // We've read the sequence '<!---' at this point (3 dashes)
|
---|
3340 | state = 15 /* CommentStartDash */;
|
---|
3341 | }
|
---|
3342 | else if (char === '>') {
|
---|
3343 | // At this point, we'll assume the comment wasn't a real comment
|
---|
3344 | // so we'll just emit it as data. We basically read the sequence
|
---|
3345 | // '<!-->'
|
---|
3346 | resetToDataState();
|
---|
3347 | }
|
---|
3348 | else {
|
---|
3349 | // Any other char, take it as part of the comment
|
---|
3350 | state = 16 /* Comment */;
|
---|
3351 | }
|
---|
3352 | }
|
---|
3353 | // We've read the sequence '<!---' at this point (3 dashes)
|
---|
3354 | // https://www.w3.org/TR/html51/syntax.html#comment-start-dash-state
|
---|
3355 | function stateCommentStartDash(char) {
|
---|
3356 | if (char === '-') {
|
---|
3357 | // We've read '<!----' (4 dashes) at this point
|
---|
3358 | state = 18 /* CommentEnd */;
|
---|
3359 | }
|
---|
3360 | else if (char === '>') {
|
---|
3361 | // At this point, we'll assume the comment wasn't a real comment
|
---|
3362 | // so we'll just emit it as data. We basically read the sequence
|
---|
3363 | // '<!--->'
|
---|
3364 | resetToDataState();
|
---|
3365 | }
|
---|
3366 | else {
|
---|
3367 | // Anything else, take it as a valid comment
|
---|
3368 | state = 16 /* Comment */;
|
---|
3369 | }
|
---|
3370 | }
|
---|
3371 | // Currently reading the comment's text (data)
|
---|
3372 | // https://www.w3.org/TR/html51/syntax.html#comment-state
|
---|
3373 | function stateComment(char) {
|
---|
3374 | if (char === '-') {
|
---|
3375 | state = 17 /* CommentEndDash */;
|
---|
3376 | }
|
---|
3377 | }
|
---|
3378 | // When we we've read the first dash inside a comment, it may signal the
|
---|
3379 | // end of the comment if we read another dash
|
---|
3380 | // https://www.w3.org/TR/html51/syntax.html#comment-end-dash-state
|
---|
3381 | function stateCommentEndDash(char) {
|
---|
3382 | if (char === '-') {
|
---|
3383 | state = 18 /* CommentEnd */;
|
---|
3384 | }
|
---|
3385 | else {
|
---|
3386 | // Wasn't a dash, must still be part of the comment
|
---|
3387 | state = 16 /* Comment */;
|
---|
3388 | }
|
---|
3389 | }
|
---|
3390 | // After we've read two dashes inside a comment, it may signal the end of
|
---|
3391 | // the comment if we then read a '>' char
|
---|
3392 | // https://www.w3.org/TR/html51/syntax.html#comment-end-state
|
---|
3393 | function stateCommentEnd(char) {
|
---|
3394 | if (char === '>') {
|
---|
3395 | emitTagAndPreviousTextNode();
|
---|
3396 | }
|
---|
3397 | else if (char === '!') {
|
---|
3398 | state = 19 /* CommentEndBang */;
|
---|
3399 | }
|
---|
3400 | else if (char === '-') ;
|
---|
3401 | else {
|
---|
3402 | // Anything else, switch back to the comment state since we didn't
|
---|
3403 | // read the full "end comment" sequence (i.e. '-->')
|
---|
3404 | state = 16 /* Comment */;
|
---|
3405 | }
|
---|
3406 | }
|
---|
3407 | // We've read the sequence '--!' inside of a comment
|
---|
3408 | // https://www.w3.org/TR/html51/syntax.html#comment-end-bang-state
|
---|
3409 | function stateCommentEndBang(char) {
|
---|
3410 | if (char === '-') {
|
---|
3411 | // We read the sequence '--!-' inside of a comment. The last dash
|
---|
3412 | // could signify that the comment is going to close
|
---|
3413 | state = 17 /* CommentEndDash */;
|
---|
3414 | }
|
---|
3415 | else if (char === '>') {
|
---|
3416 | // End of comment with the sequence '--!>'
|
---|
3417 | emitTagAndPreviousTextNode();
|
---|
3418 | }
|
---|
3419 | else {
|
---|
3420 | // The '--!' was not followed by a '>', continue reading the
|
---|
3421 | // comment's text
|
---|
3422 | state = 16 /* Comment */;
|
---|
3423 | }
|
---|
3424 | }
|
---|
3425 | /**
|
---|
3426 | * For DOCTYPES in particular, we don't care about the attributes. Just
|
---|
3427 | * advance to the '>' character and emit the tag, unless we find a '<'
|
---|
3428 | * character in which case we'll start a new tag.
|
---|
3429 | *
|
---|
3430 | * Example doctype tag:
|
---|
3431 | * <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
|
---|
3432 | *
|
---|
3433 | * Actual spec: https://www.w3.org/TR/html51/syntax.html#doctype-state
|
---|
3434 | */
|
---|
3435 | function stateDoctype(char) {
|
---|
3436 | if (char === '>') {
|
---|
3437 | emitTagAndPreviousTextNode();
|
---|
3438 | }
|
---|
3439 | else if (char === '<') {
|
---|
3440 | startNewTag();
|
---|
3441 | }
|
---|
3442 | else ;
|
---|
3443 | }
|
---|
3444 | /**
|
---|
3445 | * Resets the state back to the Data state, and removes the current tag.
|
---|
3446 | *
|
---|
3447 | * We'll generally run this function whenever a "parse error" is
|
---|
3448 | * encountered, where the current tag that is being read no longer looks
|
---|
3449 | * like a real HTML tag.
|
---|
3450 | */
|
---|
3451 | function resetToDataState() {
|
---|
3452 | state = 0 /* Data */;
|
---|
3453 | currentTag = noCurrentTag;
|
---|
3454 | }
|
---|
3455 | /**
|
---|
3456 | * Starts a new HTML tag at the current index, ignoring any previous HTML
|
---|
3457 | * tag that was being read.
|
---|
3458 | *
|
---|
3459 | * We'll generally run this function whenever we read a new '<' character,
|
---|
3460 | * including when we read a '<' character inside of an HTML tag that we were
|
---|
3461 | * previously reading.
|
---|
3462 | */
|
---|
3463 | function startNewTag() {
|
---|
3464 | state = 1 /* TagOpen */;
|
---|
3465 | currentTag = new CurrentTag({ idx: charIdx });
|
---|
3466 | }
|
---|
3467 | /**
|
---|
3468 | * Once we've decided to emit an open tag, that means we can also emit the
|
---|
3469 | * text node before it.
|
---|
3470 | */
|
---|
3471 | function emitTagAndPreviousTextNode() {
|
---|
3472 | var textBeforeTag = html.slice(currentDataIdx, currentTag.idx);
|
---|
3473 | if (textBeforeTag) {
|
---|
3474 | // the html tag was the first element in the html string, or two
|
---|
3475 | // tags next to each other, in which case we should not emit a text
|
---|
3476 | // node
|
---|
3477 | onText(textBeforeTag, currentDataIdx);
|
---|
3478 | }
|
---|
3479 | if (currentTag.type === 'comment') {
|
---|
3480 | onComment(currentTag.idx);
|
---|
3481 | }
|
---|
3482 | else if (currentTag.type === 'doctype') {
|
---|
3483 | onDoctype(currentTag.idx);
|
---|
3484 | }
|
---|
3485 | else {
|
---|
3486 | if (currentTag.isOpening) {
|
---|
3487 | onOpenTag(currentTag.name, currentTag.idx);
|
---|
3488 | }
|
---|
3489 | if (currentTag.isClosing) {
|
---|
3490 | // note: self-closing tags will emit both opening and closing
|
---|
3491 | onCloseTag(currentTag.name, currentTag.idx);
|
---|
3492 | }
|
---|
3493 | }
|
---|
3494 | // Since we just emitted a tag, reset to the data state for the next char
|
---|
3495 | resetToDataState();
|
---|
3496 | currentDataIdx = charIdx + 1;
|
---|
3497 | }
|
---|
3498 | function emitText() {
|
---|
3499 | var text = html.slice(currentDataIdx, charIdx);
|
---|
3500 | onText(text, currentDataIdx);
|
---|
3501 | currentDataIdx = charIdx + 1;
|
---|
3502 | }
|
---|
3503 | /**
|
---|
3504 | * Captures the tag name from the start of the tag to the current character
|
---|
3505 | * index, and converts it to lower case
|
---|
3506 | */
|
---|
3507 | function captureTagName() {
|
---|
3508 | var startIdx = currentTag.idx + (currentTag.isClosing ? 2 : 1);
|
---|
3509 | return html.slice(startIdx, charIdx).toLowerCase();
|
---|
3510 | }
|
---|
3511 | /**
|
---|
3512 | * Causes the main loop to re-consume the current character, such as after
|
---|
3513 | * encountering a "parse error" that changed state and needs to reconsume
|
---|
3514 | * the same character in that new state.
|
---|
3515 | */
|
---|
3516 | function reconsumeCurrentCharacter() {
|
---|
3517 | charIdx--;
|
---|
3518 | }
|
---|
3519 | }
|
---|
3520 | var CurrentTag = /** @class */ (function () {
|
---|
3521 | function CurrentTag(cfg) {
|
---|
3522 | if (cfg === void 0) { cfg = {}; }
|
---|
3523 | this.idx = cfg.idx !== undefined ? cfg.idx : -1;
|
---|
3524 | this.type = cfg.type || 'tag';
|
---|
3525 | this.name = cfg.name || '';
|
---|
3526 | this.isOpening = !!cfg.isOpening;
|
---|
3527 | this.isClosing = !!cfg.isClosing;
|
---|
3528 | }
|
---|
3529 | return CurrentTag;
|
---|
3530 | }());
|
---|
3531 |
|
---|
3532 | /**
|
---|
3533 | * @class Autolinker
|
---|
3534 | * @extends Object
|
---|
3535 | *
|
---|
3536 | * Utility class used to process a given string of text, and wrap the matches in
|
---|
3537 | * the appropriate anchor (<a>) tags to turn them into links.
|
---|
3538 | *
|
---|
3539 | * Any of the configuration options may be provided in an Object provided
|
---|
3540 | * to the Autolinker constructor, which will configure how the {@link #link link()}
|
---|
3541 | * method will process the links.
|
---|
3542 | *
|
---|
3543 | * For example:
|
---|
3544 | *
|
---|
3545 | * var autolinker = new Autolinker( {
|
---|
3546 | * newWindow : false,
|
---|
3547 | * truncate : 30
|
---|
3548 | * } );
|
---|
3549 | *
|
---|
3550 | * var html = autolinker.link( "Joe went to www.yahoo.com" );
|
---|
3551 | * // produces: 'Joe went to <a href="http://www.yahoo.com">yahoo.com</a>'
|
---|
3552 | *
|
---|
3553 | *
|
---|
3554 | * The {@link #static-link static link()} method may also be used to inline
|
---|
3555 | * options into a single call, which may be more convenient for one-off uses.
|
---|
3556 | * For example:
|
---|
3557 | *
|
---|
3558 | * var html = Autolinker.link( "Joe went to www.yahoo.com", {
|
---|
3559 | * newWindow : false,
|
---|
3560 | * truncate : 30
|
---|
3561 | * } );
|
---|
3562 | * // produces: 'Joe went to <a href="http://www.yahoo.com">yahoo.com</a>'
|
---|
3563 | *
|
---|
3564 | *
|
---|
3565 | * ## Custom Replacements of Links
|
---|
3566 | *
|
---|
3567 | * If the configuration options do not provide enough flexibility, a {@link #replaceFn}
|
---|
3568 | * may be provided to fully customize the output of Autolinker. This function is
|
---|
3569 | * called once for each URL/Email/Phone#/Hashtag/Mention (Twitter, Instagram, Soundcloud)
|
---|
3570 | * match that is encountered.
|
---|
3571 | *
|
---|
3572 | * For example:
|
---|
3573 | *
|
---|
3574 | * var input = "..."; // string with URLs, Email Addresses, Phone #s, Hashtags, and Mentions (Twitter, Instagram, Soundcloud)
|
---|
3575 | *
|
---|
3576 | * var linkedText = Autolinker.link( input, {
|
---|
3577 | * replaceFn : function( match ) {
|
---|
3578 | * console.log( "href = ", match.getAnchorHref() );
|
---|
3579 | * console.log( "text = ", match.getAnchorText() );
|
---|
3580 | *
|
---|
3581 | * switch( match.getType() ) {
|
---|
3582 | * case 'url' :
|
---|
3583 | * console.log( "url: ", match.getUrl() );
|
---|
3584 | *
|
---|
3585 | * if( match.getUrl().indexOf( 'mysite.com' ) === -1 ) {
|
---|
3586 | * var tag = match.buildTag(); // returns an `Autolinker.HtmlTag` instance, which provides mutator methods for easy changes
|
---|
3587 | * tag.setAttr( 'rel', 'nofollow' );
|
---|
3588 | * tag.addClass( 'external-link' );
|
---|
3589 | *
|
---|
3590 | * return tag;
|
---|
3591 | *
|
---|
3592 | * } else {
|
---|
3593 | * return true; // let Autolinker perform its normal anchor tag replacement
|
---|
3594 | * }
|
---|
3595 | *
|
---|
3596 | * case 'email' :
|
---|
3597 | * var email = match.getEmail();
|
---|
3598 | * console.log( "email: ", email );
|
---|
3599 | *
|
---|
3600 | * if( email === "my@own.address" ) {
|
---|
3601 | * return false; // don't auto-link this particular email address; leave as-is
|
---|
3602 | * } else {
|
---|
3603 | * return; // no return value will have Autolinker perform its normal anchor tag replacement (same as returning `true`)
|
---|
3604 | * }
|
---|
3605 | *
|
---|
3606 | * case 'phone' :
|
---|
3607 | * var phoneNumber = match.getPhoneNumber();
|
---|
3608 | * console.log( phoneNumber );
|
---|
3609 | *
|
---|
3610 | * return '<a href="http://newplace.to.link.phone.numbers.to/">' + phoneNumber + '</a>';
|
---|
3611 | *
|
---|
3612 | * case 'hashtag' :
|
---|
3613 | * var hashtag = match.getHashtag();
|
---|
3614 | * console.log( hashtag );
|
---|
3615 | *
|
---|
3616 | * return '<a href="http://newplace.to.link.hashtag.handles.to/">' + hashtag + '</a>';
|
---|
3617 | *
|
---|
3618 | * case 'mention' :
|
---|
3619 | * var mention = match.getMention();
|
---|
3620 | * console.log( mention );
|
---|
3621 | *
|
---|
3622 | * return '<a href="http://newplace.to.link.mention.to/">' + mention + '</a>';
|
---|
3623 | * }
|
---|
3624 | * }
|
---|
3625 | * } );
|
---|
3626 | *
|
---|
3627 | *
|
---|
3628 | * The function may return the following values:
|
---|
3629 | *
|
---|
3630 | * - `true` (Boolean): Allow Autolinker to replace the match as it normally
|
---|
3631 | * would.
|
---|
3632 | * - `false` (Boolean): Do not replace the current match at all - leave as-is.
|
---|
3633 | * - Any String: If a string is returned from the function, the string will be
|
---|
3634 | * used directly as the replacement HTML for the match.
|
---|
3635 | * - An {@link Autolinker.HtmlTag} instance, which can be used to build/modify
|
---|
3636 | * an HTML tag before writing out its HTML text.
|
---|
3637 | */
|
---|
3638 | var Autolinker = /** @class */ (function () {
|
---|
3639 | /**
|
---|
3640 | * @method constructor
|
---|
3641 | * @param {Object} [cfg] The configuration options for the Autolinker instance,
|
---|
3642 | * specified in an Object (map).
|
---|
3643 | */
|
---|
3644 | function Autolinker(cfg) {
|
---|
3645 | if (cfg === void 0) { cfg = {}; }
|
---|
3646 | /**
|
---|
3647 | * The Autolinker version number exposed on the instance itself.
|
---|
3648 | *
|
---|
3649 | * Ex: 0.25.1
|
---|
3650 | */
|
---|
3651 | this.version = Autolinker.version;
|
---|
3652 | /**
|
---|
3653 | * @cfg {Boolean/Object} [urls]
|
---|
3654 | *
|
---|
3655 | * `true` if URLs should be automatically linked, `false` if they should not
|
---|
3656 | * be. Defaults to `true`.
|
---|
3657 | *
|
---|
3658 | * Examples:
|
---|
3659 | *
|
---|
3660 | * urls: true
|
---|
3661 | *
|
---|
3662 | * // or
|
---|
3663 | *
|
---|
3664 | * urls: {
|
---|
3665 | * schemeMatches : true,
|
---|
3666 | * wwwMatches : true,
|
---|
3667 | * tldMatches : true
|
---|
3668 | * }
|
---|
3669 | *
|
---|
3670 | * As shown above, this option also accepts an Object form with 3 properties
|
---|
3671 | * to allow for more customization of what exactly gets linked. All default
|
---|
3672 | * to `true`:
|
---|
3673 | *
|
---|
3674 | * @cfg {Boolean} [urls.schemeMatches] `true` to match URLs found prefixed
|
---|
3675 | * with a scheme, i.e. `http://google.com`, or `other+scheme://google.com`,
|
---|
3676 | * `false` to prevent these types of matches.
|
---|
3677 | * @cfg {Boolean} [urls.wwwMatches] `true` to match urls found prefixed with
|
---|
3678 | * `'www.'`, i.e. `www.google.com`. `false` to prevent these types of
|
---|
3679 | * matches. Note that if the URL had a prefixed scheme, and
|
---|
3680 | * `schemeMatches` is true, it will still be linked.
|
---|
3681 | * @cfg {Boolean} [urls.tldMatches] `true` to match URLs with known top
|
---|
3682 | * level domains (.com, .net, etc.) that are not prefixed with a scheme or
|
---|
3683 | * `'www.'`. This option attempts to match anything that looks like a URL
|
---|
3684 | * in the given text. Ex: `google.com`, `asdf.org/?page=1`, etc. `false`
|
---|
3685 | * to prevent these types of matches.
|
---|
3686 | */
|
---|
3687 | this.urls = {}; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3688 | /**
|
---|
3689 | * @cfg {Boolean} [email=true]
|
---|
3690 | *
|
---|
3691 | * `true` if email addresses should be automatically linked, `false` if they
|
---|
3692 | * should not be.
|
---|
3693 | */
|
---|
3694 | this.email = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3695 | /**
|
---|
3696 | * @cfg {Boolean} [phone=true]
|
---|
3697 | *
|
---|
3698 | * `true` if Phone numbers ("(555)555-5555") should be automatically linked,
|
---|
3699 | * `false` if they should not be.
|
---|
3700 | */
|
---|
3701 | this.phone = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3702 | /**
|
---|
3703 | * @cfg {Boolean/String} [hashtag=false]
|
---|
3704 | *
|
---|
3705 | * A string for the service name to have hashtags (ex: "#myHashtag")
|
---|
3706 | * auto-linked to. The currently-supported values are:
|
---|
3707 | *
|
---|
3708 | * - 'twitter'
|
---|
3709 | * - 'facebook'
|
---|
3710 | * - 'instagram'
|
---|
3711 | *
|
---|
3712 | * Pass `false` to skip auto-linking of hashtags.
|
---|
3713 | */
|
---|
3714 | this.hashtag = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3715 | /**
|
---|
3716 | * @cfg {String/Boolean} [mention=false]
|
---|
3717 | *
|
---|
3718 | * A string for the service name to have mentions (ex: "@myuser")
|
---|
3719 | * auto-linked to. The currently supported values are:
|
---|
3720 | *
|
---|
3721 | * - 'twitter'
|
---|
3722 | * - 'instagram'
|
---|
3723 | * - 'soundcloud'
|
---|
3724 | *
|
---|
3725 | * Defaults to `false` to skip auto-linking of mentions.
|
---|
3726 | */
|
---|
3727 | this.mention = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3728 | /**
|
---|
3729 | * @cfg {Boolean} [newWindow=true]
|
---|
3730 | *
|
---|
3731 | * `true` if the links should open in a new window, `false` otherwise.
|
---|
3732 | */
|
---|
3733 | this.newWindow = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3734 | /**
|
---|
3735 | * @cfg {Boolean/Object} [stripPrefix=true]
|
---|
3736 | *
|
---|
3737 | * `true` if 'http://' (or 'https://') and/or the 'www.' should be stripped
|
---|
3738 | * from the beginning of URL links' text, `false` otherwise. Defaults to
|
---|
3739 | * `true`.
|
---|
3740 | *
|
---|
3741 | * Examples:
|
---|
3742 | *
|
---|
3743 | * stripPrefix: true
|
---|
3744 | *
|
---|
3745 | * // or
|
---|
3746 | *
|
---|
3747 | * stripPrefix: {
|
---|
3748 | * scheme : true,
|
---|
3749 | * www : true
|
---|
3750 | * }
|
---|
3751 | *
|
---|
3752 | * As shown above, this option also accepts an Object form with 2 properties
|
---|
3753 | * to allow for more customization of what exactly is prevented from being
|
---|
3754 | * displayed. Both default to `true`:
|
---|
3755 | *
|
---|
3756 | * @cfg {Boolean} [stripPrefix.scheme] `true` to prevent the scheme part of
|
---|
3757 | * a URL match from being displayed to the user. Example:
|
---|
3758 | * `'http://google.com'` will be displayed as `'google.com'`. `false` to
|
---|
3759 | * not strip the scheme. NOTE: Only an `'http://'` or `'https://'` scheme
|
---|
3760 | * will be removed, so as not to remove a potentially dangerous scheme
|
---|
3761 | * (such as `'file://'` or `'javascript:'`)
|
---|
3762 | * @cfg {Boolean} [stripPrefix.www] www (Boolean): `true` to prevent the
|
---|
3763 | * `'www.'` part of a URL match from being displayed to the user. Ex:
|
---|
3764 | * `'www.google.com'` will be displayed as `'google.com'`. `false` to not
|
---|
3765 | * strip the `'www'`.
|
---|
3766 | */
|
---|
3767 | this.stripPrefix = {
|
---|
3768 | scheme: true,
|
---|
3769 | www: true,
|
---|
3770 | }; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3771 | /**
|
---|
3772 | * @cfg {Boolean} [stripTrailingSlash=true]
|
---|
3773 | *
|
---|
3774 | * `true` to remove the trailing slash from URL matches, `false` to keep
|
---|
3775 | * the trailing slash.
|
---|
3776 | *
|
---|
3777 | * Example when `true`: `http://google.com/` will be displayed as
|
---|
3778 | * `http://google.com`.
|
---|
3779 | */
|
---|
3780 | this.stripTrailingSlash = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3781 | /**
|
---|
3782 | * @cfg {Boolean} [decodePercentEncoding=true]
|
---|
3783 | *
|
---|
3784 | * `true` to decode percent-encoded characters in URL matches, `false` to keep
|
---|
3785 | * the percent-encoded characters.
|
---|
3786 | *
|
---|
3787 | * Example when `true`: `https://en.wikipedia.org/wiki/San_Jos%C3%A9` will
|
---|
3788 | * be displayed as `https://en.wikipedia.org/wiki/San_José`.
|
---|
3789 | */
|
---|
3790 | this.decodePercentEncoding = true; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3791 | /**
|
---|
3792 | * @cfg {Number/Object} [truncate=0]
|
---|
3793 | *
|
---|
3794 | * ## Number Form
|
---|
3795 | *
|
---|
3796 | * A number for how many characters matched text should be truncated to
|
---|
3797 | * inside the text of a link. If the matched text is over this number of
|
---|
3798 | * characters, it will be truncated to this length by adding a two period
|
---|
3799 | * ellipsis ('..') to the end of the string.
|
---|
3800 | *
|
---|
3801 | * For example: A url like 'http://www.yahoo.com/some/long/path/to/a/file'
|
---|
3802 | * truncated to 25 characters might look something like this:
|
---|
3803 | * 'yahoo.com/some/long/pat..'
|
---|
3804 | *
|
---|
3805 | * Example Usage:
|
---|
3806 | *
|
---|
3807 | * truncate: 25
|
---|
3808 | *
|
---|
3809 | *
|
---|
3810 | * Defaults to `0` for "no truncation."
|
---|
3811 | *
|
---|
3812 | *
|
---|
3813 | * ## Object Form
|
---|
3814 | *
|
---|
3815 | * An Object may also be provided with two properties: `length` (Number) and
|
---|
3816 | * `location` (String). `location` may be one of the following: 'end'
|
---|
3817 | * (default), 'middle', or 'smart'.
|
---|
3818 | *
|
---|
3819 | * Example Usage:
|
---|
3820 | *
|
---|
3821 | * truncate: { length: 25, location: 'middle' }
|
---|
3822 | *
|
---|
3823 | * @cfg {Number} [truncate.length=0] How many characters to allow before
|
---|
3824 | * truncation will occur. Defaults to `0` for "no truncation."
|
---|
3825 | * @cfg {"end"/"middle"/"smart"} [truncate.location="end"]
|
---|
3826 | *
|
---|
3827 | * - 'end' (default): will truncate up to the number of characters, and then
|
---|
3828 | * add an ellipsis at the end. Ex: 'yahoo.com/some/long/pat..'
|
---|
3829 | * - 'middle': will truncate and add the ellipsis in the middle. Ex:
|
---|
3830 | * 'yahoo.com/s..th/to/a/file'
|
---|
3831 | * - 'smart': for URLs where the algorithm attempts to strip out unnecessary
|
---|
3832 | * parts first (such as the 'www.', then URL scheme, hash, etc.),
|
---|
3833 | * attempting to make the URL human-readable before looking for a good
|
---|
3834 | * point to insert the ellipsis if it is still too long. Ex:
|
---|
3835 | * 'yahoo.com/some..to/a/file'. For more details, see
|
---|
3836 | * {@link Autolinker.truncate.TruncateSmart}.
|
---|
3837 | */
|
---|
3838 | this.truncate = {
|
---|
3839 | length: 0,
|
---|
3840 | location: 'end',
|
---|
3841 | }; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3842 | /**
|
---|
3843 | * @cfg {String} className
|
---|
3844 | *
|
---|
3845 | * A CSS class name to add to the generated links. This class will be added
|
---|
3846 | * to all links, as well as this class plus match suffixes for styling
|
---|
3847 | * url/email/phone/hashtag/mention links differently.
|
---|
3848 | *
|
---|
3849 | * For example, if this config is provided as "myLink", then:
|
---|
3850 | *
|
---|
3851 | * - URL links will have the CSS classes: "myLink myLink-url"
|
---|
3852 | * - Email links will have the CSS classes: "myLink myLink-email", and
|
---|
3853 | * - Phone links will have the CSS classes: "myLink myLink-phone"
|
---|
3854 | * - Hashtag links will have the CSS classes: "myLink myLink-hashtag"
|
---|
3855 | * - Mention links will have the CSS classes: "myLink myLink-mention myLink-[type]"
|
---|
3856 | * where [type] is either "instagram", "twitter" or "soundcloud"
|
---|
3857 | */
|
---|
3858 | this.className = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3859 | /**
|
---|
3860 | * @cfg {Function} replaceFn
|
---|
3861 | *
|
---|
3862 | * A function to individually process each match found in the input string.
|
---|
3863 | *
|
---|
3864 | * See the class's description for usage.
|
---|
3865 | *
|
---|
3866 | * The `replaceFn` can be called with a different context object (`this`
|
---|
3867 | * reference) using the {@link #context} cfg.
|
---|
3868 | *
|
---|
3869 | * This function is called with the following parameter:
|
---|
3870 | *
|
---|
3871 | * @cfg {Autolinker.match.Match} replaceFn.match The Match instance which
|
---|
3872 | * can be used to retrieve information about the match that the `replaceFn`
|
---|
3873 | * is currently processing. See {@link Autolinker.match.Match} subclasses
|
---|
3874 | * for details.
|
---|
3875 | */
|
---|
3876 | this.replaceFn = null; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3877 | /**
|
---|
3878 | * @cfg {Object} context
|
---|
3879 | *
|
---|
3880 | * The context object (`this` reference) to call the `replaceFn` with.
|
---|
3881 | *
|
---|
3882 | * Defaults to this Autolinker instance.
|
---|
3883 | */
|
---|
3884 | this.context = undefined; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3885 | /**
|
---|
3886 | * @cfg {Boolean} [sanitizeHtml=false]
|
---|
3887 | *
|
---|
3888 | * `true` to HTML-encode the start and end brackets of existing HTML tags found
|
---|
3889 | * in the input string. This will escape `<` and `>` characters to `<` and
|
---|
3890 | * `>`, respectively.
|
---|
3891 | *
|
---|
3892 | * Setting this to `true` will prevent XSS (Cross-site Scripting) attacks,
|
---|
3893 | * but will remove the significance of existing HTML tags in the input string. If
|
---|
3894 | * you would like to maintain the significance of existing HTML tags while also
|
---|
3895 | * making the output HTML string safe, leave this option as `false` and use a
|
---|
3896 | * tool like https://github.com/cure53/DOMPurify (or others) on the input string
|
---|
3897 | * before running Autolinker.
|
---|
3898 | */
|
---|
3899 | this.sanitizeHtml = false; // default value just to get the above doc comment in the ES5 output and documentation generator
|
---|
3900 | /**
|
---|
3901 | * @private
|
---|
3902 | * @property {Autolinker.matcher.Matcher[]} matchers
|
---|
3903 | *
|
---|
3904 | * The {@link Autolinker.matcher.Matcher} instances for this Autolinker
|
---|
3905 | * instance.
|
---|
3906 | *
|
---|
3907 | * This is lazily created in {@link #getMatchers}.
|
---|
3908 | */
|
---|
3909 | this.matchers = null;
|
---|
3910 | /**
|
---|
3911 | * @private
|
---|
3912 | * @property {Autolinker.AnchorTagBuilder} tagBuilder
|
---|
3913 | *
|
---|
3914 | * The AnchorTagBuilder instance used to build match replacement anchor tags.
|
---|
3915 | * Note: this is lazily instantiated in the {@link #getTagBuilder} method.
|
---|
3916 | */
|
---|
3917 | this.tagBuilder = null;
|
---|
3918 | // Note: when `this.something` is used in the rhs of these assignments,
|
---|
3919 | // it refers to the default values set above the constructor
|
---|
3920 | this.urls = this.normalizeUrlsCfg(cfg.urls);
|
---|
3921 | this.email = typeof cfg.email === 'boolean' ? cfg.email : this.email;
|
---|
3922 | this.phone = typeof cfg.phone === 'boolean' ? cfg.phone : this.phone;
|
---|
3923 | this.hashtag = cfg.hashtag || this.hashtag;
|
---|
3924 | this.mention = cfg.mention || this.mention;
|
---|
3925 | this.newWindow = typeof cfg.newWindow === 'boolean' ? cfg.newWindow : this.newWindow;
|
---|
3926 | this.stripPrefix = this.normalizeStripPrefixCfg(cfg.stripPrefix);
|
---|
3927 | this.stripTrailingSlash =
|
---|
3928 | typeof cfg.stripTrailingSlash === 'boolean'
|
---|
3929 | ? cfg.stripTrailingSlash
|
---|
3930 | : this.stripTrailingSlash;
|
---|
3931 | this.decodePercentEncoding =
|
---|
3932 | typeof cfg.decodePercentEncoding === 'boolean'
|
---|
3933 | ? cfg.decodePercentEncoding
|
---|
3934 | : this.decodePercentEncoding;
|
---|
3935 | this.sanitizeHtml = cfg.sanitizeHtml || false;
|
---|
3936 | // Validate the value of the `mention` cfg
|
---|
3937 | var mention = this.mention;
|
---|
3938 | if (mention !== false &&
|
---|
3939 | ['twitter', 'instagram', 'soundcloud', 'tiktok'].indexOf(mention) === -1) {
|
---|
3940 | throw new Error("invalid `mention` cfg '".concat(mention, "' - see docs"));
|
---|
3941 | }
|
---|
3942 | // Validate the value of the `hashtag` cfg
|
---|
3943 | var hashtag = this.hashtag;
|
---|
3944 | if (hashtag !== false && hashtagServices.indexOf(hashtag) === -1) {
|
---|
3945 | throw new Error("invalid `hashtag` cfg '".concat(hashtag, "' - see docs"));
|
---|
3946 | }
|
---|
3947 | this.truncate = this.normalizeTruncateCfg(cfg.truncate);
|
---|
3948 | this.className = cfg.className || this.className;
|
---|
3949 | this.replaceFn = cfg.replaceFn || this.replaceFn;
|
---|
3950 | this.context = cfg.context || this;
|
---|
3951 | }
|
---|
3952 | /**
|
---|
3953 | * Automatically links URLs, Email addresses, Phone Numbers, Twitter handles,
|
---|
3954 | * Hashtags, and Mentions found in the given chunk of HTML. Does not link URLs
|
---|
3955 | * found within HTML tags.
|
---|
3956 | *
|
---|
3957 | * For instance, if given the text: `You should go to http://www.yahoo.com`,
|
---|
3958 | * then the result will be `You should go to <a href="http://www.yahoo.com">http://www.yahoo.com</a>`
|
---|
3959 | *
|
---|
3960 | * Example:
|
---|
3961 | *
|
---|
3962 | * var linkedText = Autolinker.link( "Go to google.com", { newWindow: false } );
|
---|
3963 | * // Produces: "Go to <a href="http://google.com">google.com</a>"
|
---|
3964 | *
|
---|
3965 | * @static
|
---|
3966 | * @param {String} textOrHtml The HTML or text to find matches within (depending
|
---|
3967 | * on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #mention},
|
---|
3968 | * {@link #hashtag}, and {@link #mention} options are enabled).
|
---|
3969 | * @param {Object} [options] Any of the configuration options for the Autolinker
|
---|
3970 | * class, specified in an Object (map). See the class description for an
|
---|
3971 | * example call.
|
---|
3972 | * @return {String} The HTML text, with matches automatically linked.
|
---|
3973 | */
|
---|
3974 | Autolinker.link = function (textOrHtml, options) {
|
---|
3975 | var autolinker = new Autolinker(options);
|
---|
3976 | return autolinker.link(textOrHtml);
|
---|
3977 | };
|
---|
3978 | /**
|
---|
3979 | * Parses the input `textOrHtml` looking for URLs, email addresses, phone
|
---|
3980 | * numbers, username handles, and hashtags (depending on the configuration
|
---|
3981 | * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match}
|
---|
3982 | * objects describing those matches (without making any replacements).
|
---|
3983 | *
|
---|
3984 | * Note that if parsing multiple pieces of text, it is slightly more efficient
|
---|
3985 | * to create an Autolinker instance, and use the instance-level {@link #parse}
|
---|
3986 | * method.
|
---|
3987 | *
|
---|
3988 | * Example:
|
---|
3989 | *
|
---|
3990 | * var matches = Autolinker.parse( "Hello google.com, I am asdf@asdf.com", {
|
---|
3991 | * urls: true,
|
---|
3992 | * email: true
|
---|
3993 | * } );
|
---|
3994 | *
|
---|
3995 | * console.log( matches.length ); // 2
|
---|
3996 | * console.log( matches[ 0 ].getType() ); // 'url'
|
---|
3997 | * console.log( matches[ 0 ].getUrl() ); // 'google.com'
|
---|
3998 | * console.log( matches[ 1 ].getType() ); // 'email'
|
---|
3999 | * console.log( matches[ 1 ].getEmail() ); // 'asdf@asdf.com'
|
---|
4000 | *
|
---|
4001 | * @static
|
---|
4002 | * @param {String} textOrHtml The HTML or text to find matches within
|
---|
4003 | * (depending on if the {@link #urls}, {@link #email}, {@link #phone},
|
---|
4004 | * {@link #hashtag}, and {@link #mention} options are enabled).
|
---|
4005 | * @param {Object} [options] Any of the configuration options for the Autolinker
|
---|
4006 | * class, specified in an Object (map). See the class description for an
|
---|
4007 | * example call.
|
---|
4008 | * @return {Autolinker.match.Match[]} The array of Matches found in the
|
---|
4009 | * given input `textOrHtml`.
|
---|
4010 | */
|
---|
4011 | Autolinker.parse = function (textOrHtml, options) {
|
---|
4012 | var autolinker = new Autolinker(options);
|
---|
4013 | return autolinker.parse(textOrHtml);
|
---|
4014 | };
|
---|
4015 | /**
|
---|
4016 | * Normalizes the {@link #urls} config into an Object with 3 properties:
|
---|
4017 | * `schemeMatches`, `wwwMatches`, and `tldMatches`, all Booleans.
|
---|
4018 | *
|
---|
4019 | * See {@link #urls} config for details.
|
---|
4020 | *
|
---|
4021 | * @private
|
---|
4022 | * @param {Boolean/Object} urls
|
---|
4023 | * @return {Object}
|
---|
4024 | */
|
---|
4025 | Autolinker.prototype.normalizeUrlsCfg = function (urls) {
|
---|
4026 | if (urls == null)
|
---|
4027 | urls = true; // default to `true`
|
---|
4028 | if (typeof urls === 'boolean') {
|
---|
4029 | return { schemeMatches: urls, wwwMatches: urls, tldMatches: urls };
|
---|
4030 | }
|
---|
4031 | else {
|
---|
4032 | // object form
|
---|
4033 | return {
|
---|
4034 | schemeMatches: typeof urls.schemeMatches === 'boolean' ? urls.schemeMatches : true,
|
---|
4035 | wwwMatches: typeof urls.wwwMatches === 'boolean' ? urls.wwwMatches : true,
|
---|
4036 | tldMatches: typeof urls.tldMatches === 'boolean' ? urls.tldMatches : true,
|
---|
4037 | };
|
---|
4038 | }
|
---|
4039 | };
|
---|
4040 | /**
|
---|
4041 | * Normalizes the {@link #stripPrefix} config into an Object with 2
|
---|
4042 | * properties: `scheme`, and `www` - both Booleans.
|
---|
4043 | *
|
---|
4044 | * See {@link #stripPrefix} config for details.
|
---|
4045 | *
|
---|
4046 | * @private
|
---|
4047 | * @param {Boolean/Object} stripPrefix
|
---|
4048 | * @return {Object}
|
---|
4049 | */
|
---|
4050 | Autolinker.prototype.normalizeStripPrefixCfg = function (stripPrefix) {
|
---|
4051 | if (stripPrefix == null)
|
---|
4052 | stripPrefix = true; // default to `true`
|
---|
4053 | if (typeof stripPrefix === 'boolean') {
|
---|
4054 | return { scheme: stripPrefix, www: stripPrefix };
|
---|
4055 | }
|
---|
4056 | else {
|
---|
4057 | // object form
|
---|
4058 | return {
|
---|
4059 | scheme: typeof stripPrefix.scheme === 'boolean' ? stripPrefix.scheme : true,
|
---|
4060 | www: typeof stripPrefix.www === 'boolean' ? stripPrefix.www : true,
|
---|
4061 | };
|
---|
4062 | }
|
---|
4063 | };
|
---|
4064 | /**
|
---|
4065 | * Normalizes the {@link #truncate} config into an Object with 2 properties:
|
---|
4066 | * `length` (Number), and `location` (String).
|
---|
4067 | *
|
---|
4068 | * See {@link #truncate} config for details.
|
---|
4069 | *
|
---|
4070 | * @private
|
---|
4071 | * @param {Number/Object} truncate
|
---|
4072 | * @return {Object}
|
---|
4073 | */
|
---|
4074 | Autolinker.prototype.normalizeTruncateCfg = function (truncate) {
|
---|
4075 | if (typeof truncate === 'number') {
|
---|
4076 | return { length: truncate, location: 'end' };
|
---|
4077 | }
|
---|
4078 | else {
|
---|
4079 | // object, or undefined/null
|
---|
4080 | return defaults(truncate || {}, {
|
---|
4081 | length: Number.POSITIVE_INFINITY,
|
---|
4082 | location: 'end',
|
---|
4083 | });
|
---|
4084 | }
|
---|
4085 | };
|
---|
4086 | /**
|
---|
4087 | * Parses the input `textOrHtml` looking for URLs, email addresses, phone
|
---|
4088 | * numbers, username handles, and hashtags (depending on the configuration
|
---|
4089 | * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match}
|
---|
4090 | * objects describing those matches (without making any replacements).
|
---|
4091 | *
|
---|
4092 | * This method is used by the {@link #link} method, but can also be used to
|
---|
4093 | * simply do parsing of the input in order to discover what kinds of links
|
---|
4094 | * there are and how many.
|
---|
4095 | *
|
---|
4096 | * Example usage:
|
---|
4097 | *
|
---|
4098 | * var autolinker = new Autolinker( {
|
---|
4099 | * urls: true,
|
---|
4100 | * email: true
|
---|
4101 | * } );
|
---|
4102 | *
|
---|
4103 | * var matches = autolinker.parse( "Hello google.com, I am asdf@asdf.com" );
|
---|
4104 | *
|
---|
4105 | * console.log( matches.length ); // 2
|
---|
4106 | * console.log( matches[ 0 ].getType() ); // 'url'
|
---|
4107 | * console.log( matches[ 0 ].getUrl() ); // 'google.com'
|
---|
4108 | * console.log( matches[ 1 ].getType() ); // 'email'
|
---|
4109 | * console.log( matches[ 1 ].getEmail() ); // 'asdf@asdf.com'
|
---|
4110 | *
|
---|
4111 | * @param {String} textOrHtml The HTML or text to find matches within
|
---|
4112 | * (depending on if the {@link #urls}, {@link #email}, {@link #phone},
|
---|
4113 | * {@link #hashtag}, and {@link #mention} options are enabled).
|
---|
4114 | * @return {Autolinker.match.Match[]} The array of Matches found in the
|
---|
4115 | * given input `textOrHtml`.
|
---|
4116 | */
|
---|
4117 | Autolinker.prototype.parse = function (textOrHtml) {
|
---|
4118 | var _this = this;
|
---|
4119 | var skipTagNames = ['a', 'style', 'script'], skipTagsStackCount = 0, // used to only Autolink text outside of anchor/script/style tags. We don't want to autolink something that is already linked inside of an <a> tag, for instance
|
---|
4120 | matches = [];
|
---|
4121 | // Find all matches within the `textOrHtml` (but not matches that are
|
---|
4122 | // already nested within <a>, <style> and <script> tags)
|
---|
4123 | parseHtml(textOrHtml, {
|
---|
4124 | onOpenTag: function (tagName) {
|
---|
4125 | if (skipTagNames.indexOf(tagName) >= 0) {
|
---|
4126 | skipTagsStackCount++;
|
---|
4127 | }
|
---|
4128 | },
|
---|
4129 | onText: function (text, offset) {
|
---|
4130 | // Only process text nodes that are not within an <a>, <style> or <script> tag
|
---|
4131 | if (skipTagsStackCount === 0) {
|
---|
4132 | // "Walk around" common HTML entities. An ' ' (for example)
|
---|
4133 | // could be at the end of a URL, but we don't want to
|
---|
4134 | // include the trailing '&' in the URL. See issue #76
|
---|
4135 | // TODO: Handle HTML entities separately in parseHtml() and
|
---|
4136 | // don't emit them as "text" except for & entities
|
---|
4137 | var htmlCharacterEntitiesRegex = /( | |<|<|>|>|"|"|')/gi;
|
---|
4138 | var textSplit = splitAndCapture(text, htmlCharacterEntitiesRegex);
|
---|
4139 | var currentOffset_1 = offset;
|
---|
4140 | textSplit.forEach(function (splitText, i) {
|
---|
4141 | // even number matches are text, odd numbers are html entities
|
---|
4142 | if (i % 2 === 0) {
|
---|
4143 | var textNodeMatches = _this.parseText(splitText, currentOffset_1);
|
---|
4144 | matches.push.apply(matches, textNodeMatches);
|
---|
4145 | }
|
---|
4146 | currentOffset_1 += splitText.length;
|
---|
4147 | });
|
---|
4148 | }
|
---|
4149 | },
|
---|
4150 | onCloseTag: function (tagName) {
|
---|
4151 | if (skipTagNames.indexOf(tagName) >= 0) {
|
---|
4152 | skipTagsStackCount = Math.max(skipTagsStackCount - 1, 0); // attempt to handle extraneous </a> tags by making sure the stack count never goes below 0
|
---|
4153 | }
|
---|
4154 | },
|
---|
4155 | onComment: function (offset) { },
|
---|
4156 | onDoctype: function (offset) { }, // no need to process doctype nodes
|
---|
4157 | });
|
---|
4158 | // After we have found all matches, remove subsequent matches that
|
---|
4159 | // overlap with a previous match. This can happen for instance with URLs,
|
---|
4160 | // where the url 'google.com/#link' would match '#link' as a hashtag.
|
---|
4161 | matches = this.compactMatches(matches);
|
---|
4162 | // And finally, remove matches for match types that have been turned
|
---|
4163 | // off. We needed to have all match types turned on initially so that
|
---|
4164 | // things like hashtags could be filtered out if they were really just
|
---|
4165 | // part of a URL match (for instance, as a named anchor).
|
---|
4166 | matches = this.removeUnwantedMatches(matches);
|
---|
4167 | return matches;
|
---|
4168 | };
|
---|
4169 | /**
|
---|
4170 | * After we have found all matches, we need to remove matches that overlap
|
---|
4171 | * with a previous match. This can happen for instance with URLs, where the
|
---|
4172 | * url 'google.com/#link' would match '#link' as a hashtag. Because the
|
---|
4173 | * '#link' part is contained in a larger match that comes before the HashTag
|
---|
4174 | * match, we'll remove the HashTag match.
|
---|
4175 | *
|
---|
4176 | * @private
|
---|
4177 | * @param {Autolinker.match.Match[]} matches
|
---|
4178 | * @return {Autolinker.match.Match[]}
|
---|
4179 | */
|
---|
4180 | Autolinker.prototype.compactMatches = function (matches) {
|
---|
4181 | // First, the matches need to be sorted in order of offset
|
---|
4182 | matches.sort(function (a, b) {
|
---|
4183 | return a.getOffset() - b.getOffset();
|
---|
4184 | });
|
---|
4185 | var i = 0;
|
---|
4186 | while (i < matches.length - 1) {
|
---|
4187 | var match = matches[i], offset = match.getOffset(), matchedTextLength = match.getMatchedText().length, endIdx = offset + matchedTextLength;
|
---|
4188 | if (i + 1 < matches.length) {
|
---|
4189 | // Remove subsequent matches that equal offset with current match
|
---|
4190 | if (matches[i + 1].getOffset() === offset) {
|
---|
4191 | var removeIdx = matches[i + 1].getMatchedText().length > matchedTextLength ? i : i + 1;
|
---|
4192 | matches.splice(removeIdx, 1);
|
---|
4193 | continue;
|
---|
4194 | }
|
---|
4195 | // Remove subsequent matches that overlap with the current match
|
---|
4196 | if (matches[i + 1].getOffset() < endIdx) {
|
---|
4197 | matches.splice(i + 1, 1);
|
---|
4198 | continue;
|
---|
4199 | }
|
---|
4200 | }
|
---|
4201 | i++;
|
---|
4202 | }
|
---|
4203 | return matches;
|
---|
4204 | };
|
---|
4205 | /**
|
---|
4206 | * Removes matches for matchers that were turned off in the options. For
|
---|
4207 | * example, if {@link #hashtag hashtags} were not to be matched, we'll
|
---|
4208 | * remove them from the `matches` array here.
|
---|
4209 | *
|
---|
4210 | * Note: we *must* use all Matchers on the input string, and then filter
|
---|
4211 | * them out later. For example, if the options were `{ url: false, hashtag: true }`,
|
---|
4212 | * we wouldn't want to match the text '#link' as a HashTag inside of the text
|
---|
4213 | * 'google.com/#link'. The way the algorithm works is that we match the full
|
---|
4214 | * URL first (which prevents the accidental HashTag match), and then we'll
|
---|
4215 | * simply throw away the URL match.
|
---|
4216 | *
|
---|
4217 | * @private
|
---|
4218 | * @param {Autolinker.match.Match[]} matches The array of matches to remove
|
---|
4219 | * the unwanted matches from. Note: this array is mutated for the
|
---|
4220 | * removals.
|
---|
4221 | * @return {Autolinker.match.Match[]} The mutated input `matches` array.
|
---|
4222 | */
|
---|
4223 | Autolinker.prototype.removeUnwantedMatches = function (matches) {
|
---|
4224 | if (!this.hashtag)
|
---|
4225 | remove(matches, function (match) {
|
---|
4226 | return match.getType() === 'hashtag';
|
---|
4227 | });
|
---|
4228 | if (!this.email)
|
---|
4229 | remove(matches, function (match) {
|
---|
4230 | return match.getType() === 'email';
|
---|
4231 | });
|
---|
4232 | if (!this.phone)
|
---|
4233 | remove(matches, function (match) {
|
---|
4234 | return match.getType() === 'phone';
|
---|
4235 | });
|
---|
4236 | if (!this.mention)
|
---|
4237 | remove(matches, function (match) {
|
---|
4238 | return match.getType() === 'mention';
|
---|
4239 | });
|
---|
4240 | if (!this.urls.schemeMatches) {
|
---|
4241 | remove(matches, function (m) {
|
---|
4242 | return m.getType() === 'url' && m.getUrlMatchType() === 'scheme';
|
---|
4243 | });
|
---|
4244 | }
|
---|
4245 | if (!this.urls.wwwMatches) {
|
---|
4246 | remove(matches, function (m) { return m.getType() === 'url' && m.getUrlMatchType() === 'www'; });
|
---|
4247 | }
|
---|
4248 | if (!this.urls.tldMatches) {
|
---|
4249 | remove(matches, function (m) { return m.getType() === 'url' && m.getUrlMatchType() === 'tld'; });
|
---|
4250 | }
|
---|
4251 | return matches;
|
---|
4252 | };
|
---|
4253 | /**
|
---|
4254 | * Parses the input `text` looking for URLs, email addresses, phone
|
---|
4255 | * numbers, username handles, and hashtags (depending on the configuration
|
---|
4256 | * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match}
|
---|
4257 | * objects describing those matches.
|
---|
4258 | *
|
---|
4259 | * This method processes a **non-HTML string**, and is used to parse and
|
---|
4260 | * match within the text nodes of an HTML string. This method is used
|
---|
4261 | * internally by {@link #parse}.
|
---|
4262 | *
|
---|
4263 | * @private
|
---|
4264 | * @param {String} text The text to find matches within (depending on if the
|
---|
4265 | * {@link #urls}, {@link #email}, {@link #phone},
|
---|
4266 | * {@link #hashtag}, and {@link #mention} options are enabled). This must be a non-HTML string.
|
---|
4267 | * @param {Number} [offset=0] The offset of the text node within the
|
---|
4268 | * original string. This is used when parsing with the {@link #parse}
|
---|
4269 | * method to generate correct offsets within the {@link Autolinker.match.Match}
|
---|
4270 | * instances, but may be omitted if calling this method publicly.
|
---|
4271 | * @return {Autolinker.match.Match[]} The array of Matches found in the
|
---|
4272 | * given input `text`.
|
---|
4273 | */
|
---|
4274 | Autolinker.prototype.parseText = function (text, offset) {
|
---|
4275 | if (offset === void 0) { offset = 0; }
|
---|
4276 | offset = offset || 0;
|
---|
4277 | var matchers = this.getMatchers(), matches = [];
|
---|
4278 | for (var i = 0, numMatchers = matchers.length; i < numMatchers; i++) {
|
---|
4279 | var textMatches = matchers[i].parseMatches(text);
|
---|
4280 | // Correct the offset of each of the matches. They are originally
|
---|
4281 | // the offset of the match within the provided text node, but we
|
---|
4282 | // need to correct them to be relative to the original HTML input
|
---|
4283 | // string (i.e. the one provided to #parse).
|
---|
4284 | for (var j = 0, numTextMatches = textMatches.length; j < numTextMatches; j++) {
|
---|
4285 | textMatches[j].setOffset(offset + textMatches[j].getOffset());
|
---|
4286 | }
|
---|
4287 | matches.push.apply(matches, textMatches);
|
---|
4288 | }
|
---|
4289 | return matches;
|
---|
4290 | };
|
---|
4291 | /**
|
---|
4292 | * Automatically links URLs, Email addresses, Phone numbers, Hashtags,
|
---|
4293 | * and Mentions (Twitter, Instagram, Soundcloud) found in the given chunk of HTML. Does not link
|
---|
4294 | * URLs found within HTML tags.
|
---|
4295 | *
|
---|
4296 | * For instance, if given the text: `You should go to http://www.yahoo.com`,
|
---|
4297 | * then the result will be `You should go to
|
---|
4298 | * <a href="http://www.yahoo.com">http://www.yahoo.com</a>`
|
---|
4299 | *
|
---|
4300 | * This method finds the text around any HTML elements in the input
|
---|
4301 | * `textOrHtml`, which will be the text that is processed. Any original HTML
|
---|
4302 | * elements will be left as-is, as well as the text that is already wrapped
|
---|
4303 | * in anchor (<a>) tags.
|
---|
4304 | *
|
---|
4305 | * @param {String} textOrHtml The HTML or text to autolink matches within
|
---|
4306 | * (depending on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #hashtag}, and {@link #mention} options are enabled).
|
---|
4307 | * @return {String} The HTML, with matches automatically linked.
|
---|
4308 | */
|
---|
4309 | Autolinker.prototype.link = function (textOrHtml) {
|
---|
4310 | if (!textOrHtml) {
|
---|
4311 | return '';
|
---|
4312 | } // handle `null` and `undefined` (for JavaScript users that don't have TypeScript support)
|
---|
4313 | /* We would want to sanitize the start and end characters of a tag
|
---|
4314 | * before processing the string in order to avoid an XSS scenario.
|
---|
4315 | * This behaviour can be changed by toggling the sanitizeHtml option.
|
---|
4316 | */
|
---|
4317 | if (this.sanitizeHtml) {
|
---|
4318 | textOrHtml = textOrHtml.replace(/</g, '<').replace(/>/g, '>');
|
---|
4319 | }
|
---|
4320 | var matches = this.parse(textOrHtml), newHtml = [], lastIndex = 0;
|
---|
4321 | for (var i = 0, len = matches.length; i < len; i++) {
|
---|
4322 | var match = matches[i];
|
---|
4323 | newHtml.push(textOrHtml.substring(lastIndex, match.getOffset()));
|
---|
4324 | newHtml.push(this.createMatchReturnVal(match));
|
---|
4325 | lastIndex = match.getOffset() + match.getMatchedText().length;
|
---|
4326 | }
|
---|
4327 | newHtml.push(textOrHtml.substring(lastIndex)); // handle the text after the last match
|
---|
4328 | return newHtml.join('');
|
---|
4329 | };
|
---|
4330 | /**
|
---|
4331 | * Creates the return string value for a given match in the input string.
|
---|
4332 | *
|
---|
4333 | * This method handles the {@link #replaceFn}, if one was provided.
|
---|
4334 | *
|
---|
4335 | * @private
|
---|
4336 | * @param {Autolinker.match.Match} match The Match object that represents
|
---|
4337 | * the match.
|
---|
4338 | * @return {String} The string that the `match` should be replaced with.
|
---|
4339 | * This is usually the anchor tag string, but may be the `matchStr` itself
|
---|
4340 | * if the match is not to be replaced.
|
---|
4341 | */
|
---|
4342 | Autolinker.prototype.createMatchReturnVal = function (match) {
|
---|
4343 | // Handle a custom `replaceFn` being provided
|
---|
4344 | var replaceFnResult;
|
---|
4345 | if (this.replaceFn) {
|
---|
4346 | replaceFnResult = this.replaceFn.call(this.context, match); // Autolinker instance is the context
|
---|
4347 | }
|
---|
4348 | if (typeof replaceFnResult === 'string') {
|
---|
4349 | return replaceFnResult; // `replaceFn` returned a string, use that
|
---|
4350 | }
|
---|
4351 | else if (replaceFnResult === false) {
|
---|
4352 | return match.getMatchedText(); // no replacement for the match
|
---|
4353 | }
|
---|
4354 | else if (replaceFnResult instanceof HtmlTag) {
|
---|
4355 | return replaceFnResult.toAnchorString();
|
---|
4356 | }
|
---|
4357 | else {
|
---|
4358 | // replaceFnResult === true, or no/unknown return value from function
|
---|
4359 | // Perform Autolinker's default anchor tag generation
|
---|
4360 | var anchorTag = match.buildTag(); // returns an Autolinker.HtmlTag instance
|
---|
4361 | return anchorTag.toAnchorString();
|
---|
4362 | }
|
---|
4363 | };
|
---|
4364 | /**
|
---|
4365 | * Lazily instantiates and returns the {@link Autolinker.matcher.Matcher}
|
---|
4366 | * instances for this Autolinker instance.
|
---|
4367 | *
|
---|
4368 | * @private
|
---|
4369 | * @return {Autolinker.matcher.Matcher[]}
|
---|
4370 | */
|
---|
4371 | Autolinker.prototype.getMatchers = function () {
|
---|
4372 | if (!this.matchers) {
|
---|
4373 | var tagBuilder = this.getTagBuilder();
|
---|
4374 | var matchers = [
|
---|
4375 | new HashtagMatcher({
|
---|
4376 | tagBuilder: tagBuilder,
|
---|
4377 | serviceName: this.hashtag,
|
---|
4378 | }),
|
---|
4379 | new EmailMatcher({ tagBuilder: tagBuilder }),
|
---|
4380 | new PhoneMatcher({ tagBuilder: tagBuilder }),
|
---|
4381 | new MentionMatcher({
|
---|
4382 | tagBuilder: tagBuilder,
|
---|
4383 | serviceName: this.mention,
|
---|
4384 | }),
|
---|
4385 | new UrlMatcher({
|
---|
4386 | tagBuilder: tagBuilder,
|
---|
4387 | stripPrefix: this.stripPrefix,
|
---|
4388 | stripTrailingSlash: this.stripTrailingSlash,
|
---|
4389 | decodePercentEncoding: this.decodePercentEncoding,
|
---|
4390 | }),
|
---|
4391 | ];
|
---|
4392 | return (this.matchers = matchers);
|
---|
4393 | }
|
---|
4394 | else {
|
---|
4395 | return this.matchers;
|
---|
4396 | }
|
---|
4397 | };
|
---|
4398 | /**
|
---|
4399 | * Returns the {@link #tagBuilder} instance for this Autolinker instance,
|
---|
4400 | * lazily instantiating it if it does not yet exist.
|
---|
4401 | *
|
---|
4402 | * @private
|
---|
4403 | * @return {Autolinker.AnchorTagBuilder}
|
---|
4404 | */
|
---|
4405 | Autolinker.prototype.getTagBuilder = function () {
|
---|
4406 | var tagBuilder = this.tagBuilder;
|
---|
4407 | if (!tagBuilder) {
|
---|
4408 | tagBuilder = this.tagBuilder = new AnchorTagBuilder({
|
---|
4409 | newWindow: this.newWindow,
|
---|
4410 | truncate: this.truncate,
|
---|
4411 | className: this.className,
|
---|
4412 | });
|
---|
4413 | }
|
---|
4414 | return tagBuilder;
|
---|
4415 | };
|
---|
4416 | // NOTE: must be 'export default' here for UMD module
|
---|
4417 | /**
|
---|
4418 | * @static
|
---|
4419 | * @property {String} version
|
---|
4420 | *
|
---|
4421 | * The Autolinker version number in the form major.minor.patch
|
---|
4422 | *
|
---|
4423 | * Ex: 3.15.0
|
---|
4424 | */
|
---|
4425 | Autolinker.version = version;
|
---|
4426 | /**
|
---|
4427 | * For backwards compatibility with Autolinker 1.x, the AnchorTagBuilder
|
---|
4428 | * class is provided as a static on the Autolinker class.
|
---|
4429 | */
|
---|
4430 | Autolinker.AnchorTagBuilder = AnchorTagBuilder;
|
---|
4431 | /**
|
---|
4432 | * For backwards compatibility with Autolinker 1.x, the HtmlTag class is
|
---|
4433 | * provided as a static on the Autolinker class.
|
---|
4434 | */
|
---|
4435 | Autolinker.HtmlTag = HtmlTag;
|
---|
4436 | /**
|
---|
4437 | * For backwards compatibility with Autolinker 1.x, the Matcher classes are
|
---|
4438 | * provided as statics on the Autolinker class.
|
---|
4439 | */
|
---|
4440 | Autolinker.matcher = {
|
---|
4441 | Email: EmailMatcher,
|
---|
4442 | Hashtag: HashtagMatcher,
|
---|
4443 | Matcher: Matcher,
|
---|
4444 | Mention: MentionMatcher,
|
---|
4445 | Phone: PhoneMatcher,
|
---|
4446 | Url: UrlMatcher,
|
---|
4447 | };
|
---|
4448 | /**
|
---|
4449 | * For backwards compatibility with Autolinker 1.x, the Match classes are
|
---|
4450 | * provided as statics on the Autolinker class.
|
---|
4451 | */
|
---|
4452 | Autolinker.match = {
|
---|
4453 | Email: EmailMatch,
|
---|
4454 | Hashtag: HashtagMatch,
|
---|
4455 | Match: Match,
|
---|
4456 | Mention: MentionMatch,
|
---|
4457 | Phone: PhoneMatch,
|
---|
4458 | Url: UrlMatch,
|
---|
4459 | };
|
---|
4460 | return Autolinker;
|
---|
4461 | }());
|
---|
4462 |
|
---|
4463 | return Autolinker;
|
---|
4464 |
|
---|
4465 | }));
|
---|
4466 | //# sourceMappingURL=autolinker.js.map
|
---|