123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632 |
- /*!
- * Autolinker.js
- * v4.0.0
- *
- * Copyright(c) 2022 Gregory Jacobs <greg@greg-jacobs.com>
- * MIT License
- *
- * https://github.com/gregjacobs/Autolinker.js
- */
- (function (global, factory) {
- typeof exports === 'object' && typeof module !== 'undefined' ? module.exports = factory() :
- typeof define === 'function' && define.amd ? define(factory) :
- (global = typeof globalThis !== 'undefined' ? globalThis : global || self, global.Autolinker = factory());
- })(this, (function () { 'use strict';
- // Important: this file is generated from the 'build' script and should not be
- // edited directly
- var version = '4.0.0';
- /**
- * Simpler helper method to check for undefined simply for the benefit of
- * gaining better compression when minified by not needing to have multiple
- * comparisons to the `undefined` keyword in the codebase.
- */
- function isUndefined(value) {
- return value === undefined;
- }
- /**
- * Simpler helper method to check for a boolean type simply for the benefit of
- * gaining better compression when minified by not needing to have multiple
- * `typeof` comparisons in the codebase.
- */
- function isBoolean(value) {
- return typeof value === 'boolean';
- }
- /**
- * Assigns (shallow copies) the properties of `src` onto `dest`, if the
- * corresponding property on `dest` === `undefined`.
- *
- * @param {Object} dest The destination object.
- * @param {Object} src The source object.
- * @return {Object} The destination object (`dest`)
- */
- function defaults(dest, src) {
- for (var prop in src) {
- if (src.hasOwnProperty(prop) && isUndefined(dest[prop])) {
- dest[prop] = src[prop];
- }
- }
- return dest;
- }
- /**
- * Truncates the `str` at `len - ellipsisChars.length`, and adds the `ellipsisChars` to the
- * end of the string (by default, two periods: '..'). If the `str` length does not exceed
- * `len`, the string will be returned unchanged.
- *
- * @param {String} str The string to truncate and add an ellipsis to.
- * @param {Number} truncateLen The length to truncate the string at.
- * @param {String} [ellipsisChars=...] The ellipsis character(s) to add to the end of `str`
- * when truncated. Defaults to '...'
- */
- function ellipsis(str, truncateLen, ellipsisChars) {
- var ellipsisLength;
- if (str.length > truncateLen) {
- if (ellipsisChars == null) {
- ellipsisChars = '…';
- ellipsisLength = 3;
- }
- else {
- ellipsisLength = ellipsisChars.length;
- }
- str = str.substring(0, truncateLen - ellipsisLength) + ellipsisChars;
- }
- return str;
- }
- /**
- * Removes array elements by value. Mutates the input array.
- *
- * Using this instead of the ES5 Array.prototype.filter() function to prevent
- * creating many new arrays in memory for removing an element.
- *
- * @param arr The array to remove elements from. This array is mutated.
- * @param fn The element to remove.
- */
- function remove(arr, item) {
- for (var i = arr.length - 1; i >= 0; i--) {
- if (arr[i] === item) {
- arr.splice(i, 1);
- }
- }
- }
- /**
- * Removes array elements based on a filtering function. Mutates the input
- * array.
- *
- * Using this instead of the ES5 Array.prototype.filter() function to prevent
- * creating many new arrays in memory for filtering.
- *
- * @param arr The array to remove elements from. This array is mutated.
- * @param fn The predicate function which should return `true` to remove an
- * element.
- */
- function removeWithPredicate(arr, fn) {
- for (var i = arr.length - 1; i >= 0; i--) {
- if (fn(arr[i]) === true) {
- arr.splice(i, 1);
- }
- }
- }
- /**
- * Function that should never be called but is used to check that every
- * enum value is handled using TypeScript's 'never' type.
- */
- function assertNever(theValue) {
- throw new Error("Unhandled case for value: '".concat(theValue, "'"));
- }
- /*
- * This file builds and stores a library of the common regular expressions used
- * by the Autolinker utility.
- *
- * Other regular expressions may exist ad-hoc, but these are generally the
- * regular expressions that are shared between source files.
- */
- /**
- * Regular expression to match upper and lowercase ASCII letters
- */
- var letterRe = /[A-Za-z]/;
- /**
- * Regular expression to match ASCII digits
- */
- var digitRe = /[\d]/;
- /**
- * Regular expression to match whitespace
- */
- var whitespaceRe = /\s/;
- /**
- * Regular expression to match quote characters
- */
- var quoteRe = /['"]/;
- /**
- * Regular expression to match the range of ASCII control characters (0-31), and
- * the backspace char (127)
- */
- var controlCharsRe = /[\x00-\x1F\x7F]/;
- /**
- * The string form of a regular expression that would match all of the
- * alphabetic ("letter") chars in the unicode character set when placed in a
- * RegExp character class (`[]`). This includes all international alphabetic
- * characters.
- *
- * These would be the characters matched by unicode regex engines `\p{L}`
- * escape ("all letters").
- *
- * Taken from the XRegExp library: http://xregexp.com/ (thanks @https://github.com/slevithan)
- * Specifically: http://xregexp.com/v/3.2.0/xregexp-all.js, the 'Letter'
- * regex's bmp
- *
- * VERY IMPORTANT: This set of characters is defined inside of a Regular
- * Expression literal rather than a string literal to prevent UglifyJS from
- * compressing the unicode escape sequences into their actual unicode
- * characters. If Uglify compresses these into the unicode characters
- * themselves, this results in the error "Range out of order in character
- * class" when these characters are used inside of a Regular Expression
- * character class (`[]`). See usages of this const. Alternatively, we can set
- * the UglifyJS option `ascii_only` to true for the build, but that doesn't
- * help others who are pulling in Autolinker into their own build and running
- * UglifyJS themselves.
- */
- // prettier-ignore
- 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/
- .source; // see note in above variable description
- /**
- * The string form of a regular expression that would match all emoji characters
- * Based on the emoji regex defined in this article: https://thekevinscott.com/emojis-in-javascript/
- */
- 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/
- .source;
- /**
- * The string form of a regular expression that would match all of the
- * combining mark characters in the unicode character set when placed in a
- * RegExp character class (`[]`).
- *
- * These would be the characters matched by unicode regex engines `\p{M}`
- * escape ("all marks").
- *
- * Taken from the XRegExp library: http://xregexp.com/ (thanks @https://github.com/slevithan)
- * Specifically: http://xregexp.com/v/3.2.0/xregexp-all.js, the 'Mark'
- * regex's bmp
- *
- * VERY IMPORTANT: This set of characters is defined inside of a Regular
- * Expression literal rather than a string literal to prevent UglifyJS from
- * compressing the unicode escape sequences into their actual unicode
- * characters. If Uglify compresses these into the unicode characters
- * themselves, this results in the error "Range out of order in character
- * class" when these characters are used inside of a Regular Expression
- * character class (`[]`). See usages of this const. Alternatively, we can set
- * the UglifyJS option `ascii_only` to true for the build, but that doesn't
- * help others who are pulling in Autolinker into their own build and running
- * UglifyJS themselves.
- */
- // prettier-ignore
- 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/
- .source; // see note in above variable description
- /**
- * The string form of a regular expression that would match all of the
- * alphabetic ("letter") chars, emoji, and combining marks in the unicode character set
- * when placed in a RegExp character class (`[]`). This includes all
- * international alphabetic characters.
- *
- * These would be the characters matched by unicode regex engines `\p{L}\p{M}`
- * escapes and emoji characters.
- */
- var alphaCharsAndMarksStr = alphaCharsStr + emojiStr + marksStr;
- /**
- * The string form of a regular expression that would match all of the
- * decimal number chars in the unicode character set when placed in a RegExp
- * character class (`[]`).
- *
- * These would be the characters matched by unicode regex engines `\p{Nd}`
- * escape ("all decimal numbers")
- *
- * Taken from the XRegExp library: http://xregexp.com/ (thanks @https://github.com/slevithan)
- * Specifically: http://xregexp.com/v/3.2.0/xregexp-all.js, the 'Decimal_Number'
- * regex's bmp
- *
- * VERY IMPORTANT: This set of characters is defined inside of a Regular
- * Expression literal rather than a string literal to prevent UglifyJS from
- * compressing the unicode escape sequences into their actual unicode
- * characters. If Uglify compresses these into the unicode characters
- * themselves, this results in the error "Range out of order in character
- * class" when these characters are used inside of a Regular Expression
- * character class (`[]`). See usages of this const. Alternatively, we can set
- * the UglifyJS option `ascii_only` to true for the build, but that doesn't
- * help others who are pulling in Autolinker into their own build and running
- * UglifyJS themselves.
- */
- // prettier-ignore
- 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/
- .source; // see note in above variable description
- /**
- * The string form of a regular expression that would match all of the
- * letters, combining marks, and decimal number chars in the unicode character
- * set when placed in a RegExp character class (`[]`).
- *
- * These would be the characters matched by unicode regex engines
- * `[\p{L}\p{M}\p{Nd}]` escape ("all letters, combining marks, and decimal
- * numbers")
- */
- var alphaNumericAndMarksCharsStr = alphaCharsAndMarksStr + decimalNumbersStr;
- /**
- * The regular expression that will match a single letter of the
- * {@link #alphaNumericAndMarksCharsStr}.
- */
- var alphaNumericAndMarksRe = new RegExp("[".concat(alphaNumericAndMarksCharsStr, "]"));
- /**
- * @class Autolinker.HtmlTag
- * @extends Object
- *
- * Represents an HTML tag, which can be used to easily build/modify HTML tags programmatically.
- *
- * Autolinker uses this abstraction to create HTML tags, and then write them out as strings. You may also use
- * this class in your code, especially within a {@link Autolinker#replaceFn replaceFn}.
- *
- * ## Examples
- *
- * Example instantiation:
- *
- * var tag = new Autolinker.HtmlTag( {
- * tagName : 'a',
- * attrs : { 'href': 'http://google.com', 'class': 'external-link' },
- * innerHtml : 'Google'
- * } );
- *
- * tag.toAnchorString(); // <a href="http://google.com" class="external-link">Google</a>
- *
- * // Individual accessor methods
- * tag.getTagName(); // 'a'
- * tag.getAttr( 'href' ); // 'http://google.com'
- * tag.hasClass( 'external-link' ); // true
- *
- *
- * Using mutator methods (which may be used in combination with instantiation config properties):
- *
- * var tag = new Autolinker.HtmlTag();
- * tag.setTagName( 'a' );
- * tag.setAttr( 'href', 'http://google.com' );
- * tag.addClass( 'external-link' );
- * tag.setInnerHtml( 'Google' );
- *
- * tag.getTagName(); // 'a'
- * tag.getAttr( 'href' ); // 'http://google.com'
- * tag.hasClass( 'external-link' ); // true
- *
- * tag.toAnchorString(); // <a href="http://google.com" class="external-link">Google</a>
- *
- *
- * ## Example use within a {@link Autolinker#replaceFn replaceFn}
- *
- * var html = Autolinker.link( "Test google.com", {
- * replaceFn : function( match ) {
- * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance, configured with the Match's href and anchor text
- * tag.setAttr( 'rel', 'nofollow' );
- *
- * return tag;
- * }
- * } );
- *
- * // generated html:
- * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a>
- *
- *
- * ## Example use with a new tag for the replacement
- *
- * var html = Autolinker.link( "Test google.com", {
- * replaceFn : function( match ) {
- * var tag = new Autolinker.HtmlTag( {
- * tagName : 'button',
- * attrs : { 'title': 'Load URL: ' + match.getAnchorHref() },
- * innerHtml : 'Load URL: ' + match.getAnchorText()
- * } );
- *
- * return tag;
- * }
- * } );
- *
- * // generated html:
- * // Test <button title="Load URL: http://google.com">Load URL: google.com</button>
- */
- var HtmlTag = /** @class */ (function () {
- /**
- * @method constructor
- * @param {Object} [cfg] The configuration properties for this class, in an Object (map)
- */
- function HtmlTag(cfg) {
- if (cfg === void 0) { cfg = {}; }
- /**
- * @cfg {String} tagName
- *
- * The tag name. Ex: 'a', 'button', etc.
- *
- * Not required at instantiation time, but should be set using {@link #setTagName} before {@link #toAnchorString}
- * is executed.
- */
- this.tagName = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Object.<String, String>} attrs
- *
- * An key/value Object (map) of attributes to create the tag with. The keys are the attribute names, and the
- * values are the attribute values.
- */
- this.attrs = {}; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {String} innerHTML
- *
- * The inner HTML for the tag.
- */
- this.innerHTML = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- this.tagName = cfg.tagName || '';
- this.attrs = cfg.attrs || {};
- this.innerHTML = cfg.innerHtml || cfg.innerHTML || ''; // accept either the camelCased form or the fully capitalized acronym as in the DOM
- }
- /**
- * Sets the tag name that will be used to generate the tag with.
- *
- * @param {String} tagName
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.setTagName = function (tagName) {
- this.tagName = tagName;
- return this;
- };
- /**
- * Retrieves the tag name.
- *
- * @return {String}
- */
- HtmlTag.prototype.getTagName = function () {
- return this.tagName || '';
- };
- /**
- * Sets an attribute on the HtmlTag.
- *
- * @param {String} attrName The attribute name to set.
- * @param {String} attrValue The attribute value to set.
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.setAttr = function (attrName, attrValue) {
- var tagAttrs = this.getAttrs();
- tagAttrs[attrName] = attrValue;
- return this;
- };
- /**
- * Retrieves an attribute from the HtmlTag. If the attribute does not exist, returns `undefined`.
- *
- * @param {String} attrName The attribute name to retrieve.
- * @return {String} The attribute's value, or `undefined` if it does not exist on the HtmlTag.
- */
- HtmlTag.prototype.getAttr = function (attrName) {
- return this.getAttrs()[attrName];
- };
- /**
- * Sets one or more attributes on the HtmlTag.
- *
- * @param {Object.<String, String>} attrs A key/value Object (map) of the attributes to set.
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.setAttrs = function (attrs) {
- Object.assign(this.getAttrs(), attrs);
- return this;
- };
- /**
- * Retrieves the attributes Object (map) for the HtmlTag.
- *
- * @return {Object.<String, String>} A key/value object of the attributes for the HtmlTag.
- */
- HtmlTag.prototype.getAttrs = function () {
- return this.attrs || (this.attrs = {});
- };
- /**
- * Sets the provided `cssClass`, overwriting any current CSS classes on the HtmlTag.
- *
- * @param {String} cssClass One or more space-separated CSS classes to set (overwrite).
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.setClass = function (cssClass) {
- return this.setAttr('class', cssClass);
- };
- /**
- * Convenience method to add one or more CSS classes to the HtmlTag. Will not add duplicate CSS classes.
- *
- * @param {String} cssClass One or more space-separated CSS classes to add.
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.addClass = function (cssClass) {
- var classAttr = this.getClass(), classes = !classAttr ? [] : classAttr.split(whitespaceRe), newClasses = cssClass.split(whitespaceRe), newClass;
- while ((newClass = newClasses.shift())) {
- if (classes.indexOf(newClass) === -1) {
- classes.push(newClass);
- }
- }
- this.getAttrs()['class'] = classes.join(' ');
- return this;
- };
- /**
- * Convenience method to remove one or more CSS classes from the HtmlTag.
- *
- * @param {String} cssClass One or more space-separated CSS classes to remove.
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.removeClass = function (cssClass) {
- var classAttr = this.getClass(), classes = !classAttr ? [] : classAttr.split(whitespaceRe), removeClasses = cssClass.split(whitespaceRe), removeClass;
- while (classes.length && (removeClass = removeClasses.shift())) {
- var idx = classes.indexOf(removeClass);
- if (idx !== -1) {
- classes.splice(idx, 1);
- }
- }
- this.getAttrs()['class'] = classes.join(' ');
- return this;
- };
- /**
- * Convenience method to retrieve the CSS class(es) for the HtmlTag, which will each be separated by spaces when
- * there are multiple.
- *
- * @return {String}
- */
- HtmlTag.prototype.getClass = function () {
- return this.getAttrs()['class'] || '';
- };
- /**
- * Convenience method to check if the tag has a CSS class or not.
- *
- * @param {String} cssClass The CSS class to check for.
- * @return {Boolean} `true` if the HtmlTag has the CSS class, `false` otherwise.
- */
- HtmlTag.prototype.hasClass = function (cssClass) {
- return (' ' + this.getClass() + ' ').indexOf(' ' + cssClass + ' ') !== -1;
- };
- /**
- * Sets the inner HTML for the tag.
- *
- * @param {String} html The inner HTML to set.
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.setInnerHTML = function (html) {
- this.innerHTML = html;
- return this;
- };
- /**
- * Backwards compatibility method name.
- *
- * @param {String} html The inner HTML to set.
- * @return {Autolinker.HtmlTag} This HtmlTag instance, so that method calls may be chained.
- */
- HtmlTag.prototype.setInnerHtml = function (html) {
- return this.setInnerHTML(html);
- };
- /**
- * Retrieves the inner HTML for the tag.
- *
- * @return {String}
- */
- HtmlTag.prototype.getInnerHTML = function () {
- return this.innerHTML || '';
- };
- /**
- * Backward compatibility method name.
- *
- * @return {String}
- */
- HtmlTag.prototype.getInnerHtml = function () {
- return this.getInnerHTML();
- };
- /**
- * Generates the HTML string for the tag.
- *
- * @return {String}
- */
- HtmlTag.prototype.toAnchorString = function () {
- var tagName = this.getTagName(), attrsStr = this.buildAttrsStr();
- attrsStr = attrsStr ? ' ' + attrsStr : ''; // prepend a space if there are actually attributes
- return ['<', tagName, attrsStr, '>', this.getInnerHtml(), '</', tagName, '>'].join('');
- };
- /**
- * Support method for {@link #toAnchorString}, returns the string space-separated key="value" pairs, used to populate
- * the stringified HtmlTag.
- *
- * @protected
- * @return {String} Example return: `attr1="value1" attr2="value2"`
- */
- HtmlTag.prototype.buildAttrsStr = function () {
- if (!this.attrs)
- return ''; // no `attrs` Object (map) has been set, return empty string
- var attrs = this.getAttrs(), attrsArr = [];
- for (var prop in attrs) {
- if (attrs.hasOwnProperty(prop)) {
- attrsArr.push(prop + '="' + attrs[prop] + '"');
- }
- }
- return attrsArr.join(' ');
- };
- return HtmlTag;
- }());
- /**
- * Date: 2015-10-05
- * Author: Kasper Søfren <soefritz@gmail.com> (https://github.com/kafoso)
- *
- * A truncation feature, where the ellipsis will be placed at a section within
- * the URL making it still somewhat human readable.
- *
- * @param {String} url A URL.
- * @param {Number} truncateLen The maximum length of the truncated output URL string.
- * @param {String} ellipsisChars The characters to place within the url, e.g. "...".
- * @return {String} The truncated URL.
- */
- function truncateSmart(url, truncateLen, ellipsisChars) {
- var ellipsisLengthBeforeParsing;
- var ellipsisLength;
- if (ellipsisChars == null) {
- ellipsisChars = '…';
- ellipsisLength = 3;
- ellipsisLengthBeforeParsing = 8;
- }
- else {
- ellipsisLength = ellipsisChars.length;
- ellipsisLengthBeforeParsing = ellipsisChars.length;
- }
- var parse_url = function (url) {
- // Functionality inspired by PHP function of same name
- var urlObj = {};
- var urlSub = url;
- var match = urlSub.match(/^([a-z]+):\/\//i);
- if (match) {
- urlObj.scheme = match[1];
- urlSub = urlSub.substr(match[0].length);
- }
- match = urlSub.match(/^(.*?)(?=(\?|#|\/|$))/i);
- if (match) {
- urlObj.host = match[1];
- urlSub = urlSub.substr(match[0].length);
- }
- match = urlSub.match(/^\/(.*?)(?=(\?|#|$))/i);
- if (match) {
- urlObj.path = match[1];
- urlSub = urlSub.substr(match[0].length);
- }
- match = urlSub.match(/^\?(.*?)(?=(#|$))/i);
- if (match) {
- urlObj.query = match[1];
- urlSub = urlSub.substr(match[0].length);
- }
- match = urlSub.match(/^#(.*?)$/i);
- if (match) {
- urlObj.fragment = match[1];
- //urlSub = urlSub.substr(match[0].length); -- not used. Uncomment if adding another block.
- }
- return urlObj;
- };
- var buildUrl = function (urlObj) {
- var url = '';
- if (urlObj.scheme && urlObj.host) {
- url += urlObj.scheme + '://';
- }
- if (urlObj.host) {
- url += urlObj.host;
- }
- if (urlObj.path) {
- url += '/' + urlObj.path;
- }
- if (urlObj.query) {
- url += '?' + urlObj.query;
- }
- if (urlObj.fragment) {
- url += '#' + urlObj.fragment;
- }
- return url;
- };
- var buildSegment = function (segment, remainingAvailableLength) {
- var remainingAvailableLengthHalf = remainingAvailableLength / 2, startOffset = Math.ceil(remainingAvailableLengthHalf), endOffset = -1 * Math.floor(remainingAvailableLengthHalf), end = '';
- if (endOffset < 0) {
- end = segment.substr(endOffset);
- }
- return segment.substr(0, startOffset) + ellipsisChars + end;
- };
- if (url.length <= truncateLen) {
- return url;
- }
- var availableLength = truncateLen - ellipsisLength;
- var urlObj = parse_url(url);
- // Clean up the URL
- if (urlObj.query) {
- var matchQuery = urlObj.query.match(/^(.*?)(?=(\?|\#))(.*?)$/i);
- if (matchQuery) {
- // Malformed URL; two or more "?". Removed any content behind the 2nd.
- urlObj.query = urlObj.query.substr(0, matchQuery[1].length);
- url = buildUrl(urlObj);
- }
- }
- if (url.length <= truncateLen) {
- return url;
- }
- if (urlObj.host) {
- urlObj.host = urlObj.host.replace(/^www\./, '');
- url = buildUrl(urlObj);
- }
- if (url.length <= truncateLen) {
- return url;
- }
- // Process and build the URL
- var str = '';
- if (urlObj.host) {
- str += urlObj.host;
- }
- if (str.length >= availableLength) {
- if (urlObj.host.length == truncateLen) {
- return (urlObj.host.substr(0, truncateLen - ellipsisLength) + ellipsisChars).substr(0, availableLength + ellipsisLengthBeforeParsing);
- }
- return buildSegment(str, availableLength).substr(0, availableLength + ellipsisLengthBeforeParsing);
- }
- var pathAndQuery = '';
- if (urlObj.path) {
- pathAndQuery += '/' + urlObj.path;
- }
- if (urlObj.query) {
- pathAndQuery += '?' + urlObj.query;
- }
- if (pathAndQuery) {
- if ((str + pathAndQuery).length >= availableLength) {
- if ((str + pathAndQuery).length == truncateLen) {
- return (str + pathAndQuery).substr(0, truncateLen);
- }
- var remainingAvailableLength = availableLength - str.length;
- return (str + buildSegment(pathAndQuery, remainingAvailableLength)).substr(0, availableLength + ellipsisLengthBeforeParsing);
- }
- else {
- str += pathAndQuery;
- }
- }
- if (urlObj.fragment) {
- var fragment = '#' + urlObj.fragment;
- if ((str + fragment).length >= availableLength) {
- if ((str + fragment).length == truncateLen) {
- return (str + fragment).substr(0, truncateLen);
- }
- var remainingAvailableLength2 = availableLength - str.length;
- return (str + buildSegment(fragment, remainingAvailableLength2)).substr(0, availableLength + ellipsisLengthBeforeParsing);
- }
- else {
- str += fragment;
- }
- }
- if (urlObj.scheme && urlObj.host) {
- var scheme = urlObj.scheme + '://';
- if ((str + scheme).length < availableLength) {
- return (scheme + str).substr(0, truncateLen);
- }
- }
- if (str.length <= truncateLen) {
- return str;
- }
- var end = '';
- if (availableLength > 0) {
- end = str.substr(-1 * Math.floor(availableLength / 2));
- }
- return (str.substr(0, Math.ceil(availableLength / 2)) + ellipsisChars + end).substr(0, availableLength + ellipsisLengthBeforeParsing);
- }
- /**
- * Date: 2015-10-05
- * Author: Kasper Søfren <soefritz@gmail.com> (https://github.com/kafoso)
- *
- * A truncation feature, where the ellipsis will be placed in the dead-center of the URL.
- *
- * @param {String} url A URL.
- * @param {Number} truncateLen The maximum length of the truncated output URL string.
- * @param {String} ellipsisChars The characters to place within the url, e.g. "..".
- * @return {String} The truncated URL.
- */
- function truncateMiddle(url, truncateLen, ellipsisChars) {
- if (url.length <= truncateLen) {
- return url;
- }
- var ellipsisLengthBeforeParsing;
- var ellipsisLength;
- if (ellipsisChars == null) {
- ellipsisChars = '…';
- ellipsisLengthBeforeParsing = 8;
- ellipsisLength = 3;
- }
- else {
- ellipsisLengthBeforeParsing = ellipsisChars.length;
- ellipsisLength = ellipsisChars.length;
- }
- var availableLength = truncateLen - ellipsisLength;
- var end = '';
- if (availableLength > 0) {
- end = url.substr(-1 * Math.floor(availableLength / 2));
- }
- return (url.substr(0, Math.ceil(availableLength / 2)) + ellipsisChars + end).substr(0, availableLength + ellipsisLengthBeforeParsing);
- }
- /**
- * A truncation feature where the ellipsis will be placed at the end of the URL.
- *
- * @param {String} anchorText
- * @param {Number} truncateLen The maximum length of the truncated output URL string.
- * @param {String} ellipsisChars The characters to place within the url, e.g. "..".
- * @return {String} The truncated URL.
- */
- function truncateEnd(anchorText, truncateLen, ellipsisChars) {
- return ellipsis(anchorText, truncateLen, ellipsisChars);
- }
- /**
- * @protected
- * @class Autolinker.AnchorTagBuilder
- * @extends Object
- *
- * Builds anchor (<a>) tags for the Autolinker utility when a match is
- * found.
- *
- * Normally this class is instantiated, configured, and used internally by an
- * {@link Autolinker} instance, but may actually be used indirectly in a
- * {@link Autolinker#replaceFn replaceFn} to create {@link Autolinker.HtmlTag HtmlTag}
- * instances which may be modified before returning from the
- * {@link Autolinker#replaceFn replaceFn}. For example:
- *
- * var html = Autolinker.link( "Test google.com", {
- * replaceFn : function( match ) {
- * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance
- * tag.setAttr( 'rel', 'nofollow' );
- *
- * return tag;
- * }
- * } );
- *
- * // generated html:
- * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a>
- */
- var AnchorTagBuilder = /** @class */ (function () {
- /**
- * @method constructor
- * @param {Object} [cfg] The configuration options for the AnchorTagBuilder instance, specified in an Object (map).
- */
- function AnchorTagBuilder(cfg) {
- if (cfg === void 0) { cfg = {}; }
- /**
- * @cfg {Boolean} newWindow
- * @inheritdoc Autolinker#newWindow
- */
- this.newWindow = false; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Object} truncate
- * @inheritdoc Autolinker#truncate
- */
- this.truncate = {}; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {String} className
- * @inheritdoc Autolinker#className
- */
- this.className = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- this.newWindow = cfg.newWindow || false;
- this.truncate = cfg.truncate || {};
- this.className = cfg.className || '';
- }
- /**
- * Generates the actual anchor (<a>) tag to use in place of the
- * matched text, via its `match` object.
- *
- * @param match The Match instance to generate an anchor tag from.
- * @return The HtmlTag instance for the anchor tag.
- */
- AnchorTagBuilder.prototype.build = function (match) {
- return new HtmlTag({
- tagName: 'a',
- attrs: this.createAttrs(match),
- innerHtml: this.processAnchorText(match.getAnchorText()),
- });
- };
- /**
- * Creates the Object (map) of the HTML attributes for the anchor (<a>)
- * tag being generated.
- *
- * @protected
- * @param match The Match instance to generate an anchor tag from.
- * @return A key/value Object (map) of the anchor tag's attributes.
- */
- AnchorTagBuilder.prototype.createAttrs = function (match) {
- var attrs = {
- href: match.getAnchorHref(), // we'll always have the `href` attribute
- };
- var cssClass = this.createCssClass(match);
- if (cssClass) {
- attrs['class'] = cssClass;
- }
- if (this.newWindow) {
- attrs['target'] = '_blank';
- attrs['rel'] = 'noopener noreferrer'; // Issue #149. See https://mathiasbynens.github.io/rel-noopener/
- }
- if (this.truncate) {
- if (this.truncate.length && this.truncate.length < match.getAnchorText().length) {
- attrs['title'] = match.getAnchorHref();
- }
- }
- return attrs;
- };
- /**
- * Creates the CSS class that will be used for a given anchor tag, based on
- * the `matchType` and the {@link #className} config.
- *
- * Example returns:
- *
- * - "" // no {@link #className}
- * - "myLink myLink-url" // url match
- * - "myLink myLink-email" // email match
- * - "myLink myLink-phone" // phone match
- * - "myLink myLink-hashtag" // hashtag match
- * - "myLink myLink-mention myLink-twitter" // mention match with Twitter service
- *
- * @protected
- * @param match The Match instance to generate an
- * anchor tag from.
- * @return The CSS class string for the link. Example return:
- * "myLink myLink-url". If no {@link #className} was configured, returns
- * an empty string.
- */
- AnchorTagBuilder.prototype.createCssClass = function (match) {
- var className = this.className;
- if (!className) {
- return '';
- }
- else {
- var returnClasses = [className], cssClassSuffixes = match.getCssClassSuffixes();
- for (var i = 0, len = cssClassSuffixes.length; i < len; i++) {
- returnClasses.push(className + '-' + cssClassSuffixes[i]);
- }
- return returnClasses.join(' ');
- }
- };
- /**
- * Processes the `anchorText` by truncating the text according to the
- * {@link #truncate} config.
- *
- * @private
- * @param anchorText The anchor tag's text (i.e. what will be
- * displayed).
- * @return The processed `anchorText`.
- */
- AnchorTagBuilder.prototype.processAnchorText = function (anchorText) {
- anchorText = this.doTruncate(anchorText);
- return anchorText;
- };
- /**
- * Performs the truncation of the `anchorText` based on the {@link #truncate}
- * option. If the `anchorText` is longer than the length specified by the
- * {@link #truncate} option, the truncation is performed based on the
- * `location` property. See {@link #truncate} for details.
- *
- * @private
- * @param anchorText The anchor tag's text (i.e. what will be
- * displayed).
- * @return The truncated anchor text.
- */
- AnchorTagBuilder.prototype.doTruncate = function (anchorText) {
- var truncate = this.truncate;
- if (!truncate || !truncate.length)
- return anchorText;
- var truncateLength = truncate.length, truncateLocation = truncate.location;
- if (truncateLocation === 'smart') {
- return truncateSmart(anchorText, truncateLength);
- }
- else if (truncateLocation === 'middle') {
- return truncateMiddle(anchorText, truncateLength);
- }
- else {
- return truncateEnd(anchorText, truncateLength);
- }
- };
- return AnchorTagBuilder;
- }());
- /*! *****************************************************************************
- Copyright (c) Microsoft Corporation.
- Permission to use, copy, modify, and/or distribute this software for any
- purpose with or without fee is hereby granted.
- THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
- REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
- AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
- INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
- LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
- OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
- PERFORMANCE OF THIS SOFTWARE.
- ***************************************************************************** */
- /* global Reflect, Promise */
- var extendStatics = function(d, b) {
- extendStatics = Object.setPrototypeOf ||
- ({ __proto__: [] } instanceof Array && function (d, b) { d.__proto__ = b; }) ||
- function (d, b) { for (var p in b) if (Object.prototype.hasOwnProperty.call(b, p)) d[p] = b[p]; };
- return extendStatics(d, b);
- };
- function __extends(d, b) {
- if (typeof b !== "function" && b !== null)
- throw new TypeError("Class extends value " + String(b) + " is not a constructor or null");
- extendStatics(d, b);
- function __() { this.constructor = d; }
- d.prototype = b === null ? Object.create(b) : (__.prototype = b.prototype, new __());
- }
- var __assign = function() {
- __assign = Object.assign || function __assign(t) {
- for (var s, i = 1, n = arguments.length; i < n; i++) {
- s = arguments[i];
- for (var p in s) if (Object.prototype.hasOwnProperty.call(s, p)) t[p] = s[p];
- }
- return t;
- };
- return __assign.apply(this, arguments);
- };
- /**
- * @abstract
- * @class Autolinker.match.AbstractMatch
- *
- * Represents a match found in an input string which should be Autolinked. A Match object is what is provided in a
- * {@link Autolinker#replaceFn replaceFn}, and may be used to query for details about the match.
- *
- * For example:
- *
- * var input = "..."; // string with URLs, Email Addresses, and Mentions (Twitter, Instagram, Soundcloud)
- *
- * var linkedText = Autolinker.link( input, {
- * replaceFn : function( match ) {
- * console.log( "href = ", match.getAnchorHref() );
- * console.log( "text = ", match.getAnchorText() );
- *
- * switch( match.getType() ) {
- * case 'url' :
- * console.log( "url: ", match.getUrl() );
- *
- * case 'email' :
- * console.log( "email: ", match.getEmail() );
- *
- * case 'mention' :
- * console.log( "mention: ", match.getMention() );
- * }
- * }
- * } );
- *
- * See the {@link Autolinker} class for more details on using the {@link Autolinker#replaceFn replaceFn}.
- */
- var AbstractMatch = /** @class */ (function () {
- /**
- * @member Autolinker.match.Match
- * @method constructor
- * @param {Object} cfg The configuration properties for the Match
- * instance, specified in an Object (map).
- */
- function AbstractMatch(cfg) {
- /**
- * @cfg {Autolinker.AnchorTagBuilder} tagBuilder (required)
- *
- * Reference to the AnchorTagBuilder instance to use to generate an anchor
- * tag for the Match.
- */
- // @ts-ignore
- this._ = null; // property used just to get the above doc comment into the ES5 output and documentation generator
- /**
- * @cfg {String} matchedText (required)
- *
- * The original text that was matched by the {@link Autolinker.matcher.Matcher}.
- */
- this.matchedText = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Number} offset (required)
- *
- * The offset of where the match was made in the input string.
- */
- this.offset = 0; // default value just to get the above doc comment in the ES5 output and documentation generator
- this.tagBuilder = cfg.tagBuilder;
- this.matchedText = cfg.matchedText;
- this.offset = cfg.offset;
- }
- /**
- * Returns the original text that was matched.
- *
- * @return {String}
- */
- AbstractMatch.prototype.getMatchedText = function () {
- return this.matchedText;
- };
- /**
- * Sets the {@link #offset} of where the match was made in the input string.
- *
- * A {@link Autolinker.matcher.Matcher} will be fed only HTML text nodes,
- * and will therefore set an original offset that is relative to the HTML
- * text node itself. However, we want this offset to be relative to the full
- * HTML input string, and thus if using {@link Autolinker#parse} (rather
- * than calling a {@link Autolinker.matcher.Matcher} directly), then this
- * offset is corrected after the Matcher itself has done its job.
- *
- * @private
- * @param {Number} offset
- */
- AbstractMatch.prototype.setOffset = function (offset) {
- this.offset = offset;
- };
- /**
- * Returns the offset of where the match was made in the input string. This
- * is the 0-based index of the match.
- *
- * @return {Number}
- */
- AbstractMatch.prototype.getOffset = function () {
- return this.offset;
- };
- /**
- * Returns the CSS class suffix(es) for this match.
- *
- * A CSS class suffix is appended to the {@link Autolinker#className} in
- * the {@link Autolinker.AnchorTagBuilder} when a match is translated into
- * an anchor tag.
- *
- * For example, if {@link Autolinker#className} was configured as 'myLink',
- * and this method returns `[ 'url' ]`, the final class name of the element
- * will become: 'myLink myLink-url'.
- *
- * The match may provide multiple CSS class suffixes to be appended to the
- * {@link Autolinker#className} in order to facilitate better styling
- * options for different match criteria. See {@link Autolinker.match.Mention}
- * for an example.
- *
- * By default, this method returns a single array with the match's
- * {@link #getType type} name, but may be overridden by subclasses.
- *
- * @return {String[]}
- */
- AbstractMatch.prototype.getCssClassSuffixes = function () {
- return [this.type];
- };
- /**
- * Builds and returns an {@link Autolinker.HtmlTag} instance based on the
- * Match.
- *
- * This can be used to easily generate anchor tags from matches, and either
- * return their HTML string, or modify them before doing so.
- *
- * Example Usage:
- *
- * var tag = match.buildTag();
- * tag.addClass( 'cordova-link' );
- * tag.setAttr( 'target', '_system' );
- *
- * tag.toAnchorString(); // <a href="http://google.com" class="cordova-link" target="_system">Google</a>
- *
- * Example Usage in {@link Autolinker#replaceFn}:
- *
- * var html = Autolinker.link( "Test google.com", {
- * replaceFn : function( match ) {
- * var tag = match.buildTag(); // returns an {@link Autolinker.HtmlTag} instance
- * tag.setAttr( 'rel', 'nofollow' );
- *
- * return tag;
- * }
- * } );
- *
- * // generated html:
- * // Test <a href="http://google.com" target="_blank" rel="nofollow">google.com</a>
- */
- AbstractMatch.prototype.buildTag = function () {
- return this.tagBuilder.build(this);
- };
- return AbstractMatch;
- }());
- // NOTE: THIS IS A GENERATED FILE
- // To update with the latest TLD list, run `npm run update-tld-regex`
- var tldRegexStr = '(?: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)';
- var tldRegex = new RegExp('^' + tldRegexStr + '$');
- /**
- * The set of characters that will start a URL suffix (i.e. the path, query, and
- * hash part of the URL)
- */
- var urlSuffixStartCharsRe = /[\/?#]/;
- /**
- * The set of characters that are allowed in the URL suffix (i.e. the path,
- * query, and hash part of the URL) which may also form the ending character of
- * the URL.
- *
- * The {@link #urlSuffixNotAllowedAsLastCharRe} are additional allowed URL
- * suffix characters, but (generally) should not be the last character of a URL.
- */
- var urlSuffixAllowedSpecialCharsRe = /[-+&@#/%=~_()|'$*\[\]{}\u2713]/;
- /**
- * URL suffix characters (i.e. path, query, and has part of the URL) that are
- * not allowed as the *last character* in the URL suffix as they would normally
- * form the end of a sentence.
- *
- * The {@link #urlSuffixAllowedSpecialCharsRe} contains additional allowed URL
- * suffix characters which are allowed as the last character.
- */
- var urlSuffixNotAllowedAsLastCharRe = /[?!:,.;^]/;
- /**
- * Regular expression to match an http:// or https:// scheme.
- */
- var httpSchemeRe = /https?:\/\//i;
- /**
- * Regular expression to match an http:// or https:// scheme as the prefix of
- * a string.
- */
- var httpSchemePrefixRe = new RegExp('^' + httpSchemeRe.source, 'i');
- var urlSuffixedCharsNotAllowedAtEndRe = new RegExp(urlSuffixNotAllowedAsLastCharRe.source + '$');
- /**
- * A regular expression used to determine the schemes we should not autolink
- */
- var invalidSchemeRe = /^(javascript|vbscript):/i;
- // A regular expression used to determine if the URL is a scheme match (such as
- // 'http://google.com', and as opposed to a "TLD match"). This regular
- // expression is used to parse out the host along with if the URL has an
- // authority component (i.e. '//')
- //
- // Capturing groups:
- // 1. '//' if the URL has an authority component, empty string otherwise
- // 2. The host (if one exists). Ex: 'google.com'
- //
- // See https://www.rfc-editor.org/rfc/rfc3986#appendix-A for terminology
- var schemeUrlRe = /^[A-Za-z][-.+A-Za-z0-9]*:(\/\/)?([^:/]*)/;
- // A regular expression used to determine if the URL is a TLD match (such as
- // 'google.com', and as opposed to a "scheme match"). This regular
- // expression is used to help parse out the TLD (top-level domain) of the host.
- //
- // See https://www.rfc-editor.org/rfc/rfc3986#appendix-A for terminology
- var tldUrlHostRe = /^(?:\/\/)?([^/#?:]+)/; // optionally prefixed with protocol-relative '//' chars
- /**
- * Determines if the given character may start a scheme (ex: 'http').
- */
- function isSchemeStartChar(char) {
- return letterRe.test(char);
- }
- /**
- * Determines if the given character is a valid character in a scheme (such as
- * 'http' or 'ssh+git'), but only after the start char (which is handled by
- * {@link isSchemeStartChar}.
- */
- function isSchemeChar(char) {
- return (letterRe.test(char) || digitRe.test(char) || char === '+' || char === '-' || char === '.');
- }
- /**
- * Determines if the character can begin a domain label, which must be an
- * alphanumeric character and not an underscore or dash.
- *
- * A domain label is a segment of a hostname such as subdomain.google.com.
- */
- function isDomainLabelStartChar(char) {
- return alphaNumericAndMarksRe.test(char);
- }
- /**
- * Determines if the character is part of a domain label (but not a domain label
- * start character).
- *
- * A domain label is a segment of a hostname such as subdomain.google.com.
- */
- function isDomainLabelChar(char) {
- return char === '_' || isDomainLabelStartChar(char);
- }
- /**
- * Determines if the character is a path character ("pchar") as defined by
- * https://tools.ietf.org/html/rfc3986#appendix-A
- *
- * pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
- *
- * unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
- * pct-encoded = "%" HEXDIG HEXDIG
- * sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
- * / "*" / "+" / "," / ";" / "="
- *
- * Note that this implementation doesn't follow the spec exactly, but rather
- * follows URL path characters found out in the wild (spec might be out of date?)
- */
- function isPathChar(char) {
- return (alphaNumericAndMarksRe.test(char) ||
- urlSuffixAllowedSpecialCharsRe.test(char) ||
- urlSuffixNotAllowedAsLastCharRe.test(char));
- }
- /**
- * Determines if the character given may begin the "URL Suffix" section of a
- * URI (i.e. the path, query, or hash section). These are the '/', '?' and '#'
- * characters.
- *
- * See https://tools.ietf.org/html/rfc3986#appendix-A
- */
- function isUrlSuffixStartChar(char) {
- return urlSuffixStartCharsRe.test(char);
- }
- /**
- * Determines if the TLD read in the host is a known TLD (Top-Level Domain).
- *
- * Example: 'com' would be a known TLD (for a host of 'google.com'), but
- * 'local' would not (for a domain name of 'my-computer.local').
- */
- function isKnownTld(tld) {
- return tldRegex.test(tld.toLowerCase()); // make sure the tld is lowercase for the regex
- }
- /**
- * Determines if the given `url` is a valid scheme-prefixed URL.
- */
- function isValidSchemeUrl(url) {
- // If the scheme is 'javascript:' or 'vbscript:', these link
- // types can be dangerous. Don't link them.
- if (invalidSchemeRe.test(url)) {
- return false;
- }
- var schemeMatch = url.match(schemeUrlRe);
- if (!schemeMatch) {
- return false;
- }
- var isAuthorityMatch = !!schemeMatch[1];
- var host = schemeMatch[2];
- if (isAuthorityMatch) {
- // Any match that has an authority ('//' chars) after the scheme is
- // valid, such as 'http://anything'
- return true;
- }
- // If there's no authority ('//' chars), check that we have a hostname
- // that looks valid.
- //
- // The host must contain at least one '.' char and have a domain label
- // with at least one letter to be considered valid.
- //
- // Accept:
- // - git:domain.com (scheme followed by a host
- // Do not accept:
- // - git:something ('something' doesn't look like a host)
- // - version:1.0 ('1.0' doesn't look like a host)
- if (host.indexOf('.') === -1 || !letterRe.test(host)) {
- return false;
- }
- return true;
- }
- /**
- * Determines if the given `url` is a match with a valid TLD.
- */
- function isValidTldMatch(url) {
- // TLD URL such as 'google.com', we need to confirm that we have a valid
- // top-level domain
- var tldUrlHostMatch = url.match(tldUrlHostRe);
- if (!tldUrlHostMatch) {
- // At this point, if the URL didn't match our TLD re, it must be invalid
- // (highly unlikely to happen, but just in case)
- return false;
- }
- var host = tldUrlHostMatch[0];
- var hostLabels = host.split('.');
- if (hostLabels.length < 2) {
- // 0 or 1 host label, there's no TLD. Ex: 'localhost'
- return false;
- }
- var tld = hostLabels[hostLabels.length - 1];
- if (!isKnownTld(tld)) {
- return false;
- }
- // TODO: Implement these conditions for TLD matcher:
- // (
- // this.longestDomainLabelLength <= 63 &&
- // this.domainNameLength <= 255
- // );
- return true;
- }
- // Regular expression to confirm a valid IPv4 address (ex: '192.168.0.1')
- var ipV4Re = /^(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$/;
- // Regular expression used to split the IPv4 address itself from any port/path/query/hash
- var ipV4PartRe = /[:/?#]/;
- /**
- * Determines if the given URL is a valid IPv4-prefixed URL.
- */
- function isValidIpV4Address(url) {
- // Grab just the IP address
- var ipV4Part = url.split(ipV4PartRe, 1)[0]; // only 1 result needed
- return ipV4Re.test(ipV4Part);
- }
- /**
- * A regular expression used to remove the 'www.' from URLs.
- */
- var wwwPrefixRegex = /^(https?:\/\/)?(www\.)?/i;
- /**
- * The regular expression used to remove the protocol-relative '//' from a URL
- * string, for purposes of formatting the anchor text. A protocol-relative URL
- * is, for example, "//yahoo.com"
- */
- var protocolRelativeRegex = /^\/\//;
- /**
- * @class Autolinker.match.Url
- * @extends Autolinker.match.AbstractMatch
- *
- * Represents a Url match found in an input string which should be Autolinked.
- *
- * See this class's superclass ({@link Autolinker.match.Match}) for more details.
- */
- var UrlMatch = /** @class */ (function (_super) {
- __extends(UrlMatch, _super);
- /**
- * @method constructor
- * @param {Object} cfg The configuration properties for the Match
- * instance, specified in an Object (map).
- */
- function UrlMatch(cfg) {
- var _this = _super.call(this, cfg) || this;
- /**
- * @public
- * @property {'url'} type
- *
- * A string name for the type of match that this class represents. Can be
- * used in a TypeScript discriminating union to type-narrow from the
- * `Match` type.
- */
- _this.type = 'url';
- /**
- * @cfg {String} url (required)
- *
- * The url that was matched.
- */
- _this.url = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {"scheme"/"www"/"tld"} urlMatchType (required)
- *
- * The type of URL match that this class represents. This helps to determine
- * if the match was made in the original text with a prefixed scheme (ex:
- * 'http://www.google.com'), a prefixed 'www' (ex: 'www.google.com'), or
- * was matched by a known top-level domain (ex: 'google.com').
- */
- _this.urlMatchType = 'scheme'; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} protocolRelativeMatch (required)
- *
- * `true` if the URL is a protocol-relative match. A protocol-relative match
- * is a URL that starts with '//', and will be either http:// or https://
- * based on the protocol that the site is loaded under.
- */
- _this.protocolRelativeMatch = false; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Object} stripPrefix (required)
- *
- * The Object form of {@link Autolinker#cfg-stripPrefix}.
- */
- _this.stripPrefix = {
- scheme: true,
- www: true,
- }; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} stripTrailingSlash (required)
- * @inheritdoc Autolinker#cfg-stripTrailingSlash
- */
- _this.stripTrailingSlash = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} decodePercentEncoding (required)
- * @inheritdoc Autolinker#cfg-decodePercentEncoding
- */
- _this.decodePercentEncoding = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @private
- * @property {Boolean} protocolPrepended
- *
- * Will be set to `true` if the 'http://' protocol has been prepended to the {@link #url} (because the
- * {@link #url} did not have a protocol)
- */
- _this.protocolPrepended = false;
- _this.urlMatchType = cfg.urlMatchType;
- _this.url = cfg.url;
- _this.protocolRelativeMatch = cfg.protocolRelativeMatch;
- _this.stripPrefix = cfg.stripPrefix;
- _this.stripTrailingSlash = cfg.stripTrailingSlash;
- _this.decodePercentEncoding = cfg.decodePercentEncoding;
- return _this;
- }
- /**
- * Returns a string name for the type of match that this class represents.
- * For the case of UrlMatch, returns 'url'.
- *
- * @return {String}
- */
- UrlMatch.prototype.getType = function () {
- return 'url';
- };
- /**
- * Returns a string name for the type of URL match that this class
- * represents.
- *
- * This helps to determine if the match was made in the original text with a
- * prefixed scheme (ex: 'http://www.google.com'), a prefixed 'www' (ex:
- * 'www.google.com'), or was matched by a known top-level domain (ex:
- * 'google.com').
- *
- * @return {"scheme"/"www"/"tld"}
- */
- UrlMatch.prototype.getUrlMatchType = function () {
- return this.urlMatchType;
- };
- /**
- * Returns the url that was matched, assuming the protocol to be 'http://' if the original
- * match was missing a protocol.
- *
- * @return {String}
- */
- UrlMatch.prototype.getUrl = function () {
- var url = this.url;
- // if the url string doesn't begin with a scheme, assume 'http://'
- if (!this.protocolRelativeMatch &&
- this.urlMatchType !== 'scheme' &&
- !this.protocolPrepended) {
- url = this.url = 'http://' + url;
- this.protocolPrepended = true;
- }
- return url;
- };
- /**
- * Returns the anchor href that should be generated for the match.
- *
- * @return {String}
- */
- UrlMatch.prototype.getAnchorHref = function () {
- var url = this.getUrl();
- return url.replace(/&/g, '&'); // any &'s in the URL should be converted back to '&' if they were displayed as & in the source html
- };
- /**
- * Returns the anchor text that should be generated for the match.
- *
- * @return {String}
- */
- UrlMatch.prototype.getAnchorText = function () {
- var anchorText = this.getMatchedText();
- if (this.protocolRelativeMatch) {
- // Strip off any protocol-relative '//' from the anchor text
- anchorText = stripProtocolRelativePrefix(anchorText);
- }
- if (this.stripPrefix.scheme) {
- anchorText = stripSchemePrefix(anchorText);
- }
- if (this.stripPrefix.www) {
- anchorText = stripWwwPrefix(anchorText);
- }
- if (this.stripTrailingSlash) {
- anchorText = removeTrailingSlash(anchorText); // remove trailing slash, if there is one
- }
- if (this.decodePercentEncoding) {
- anchorText = removePercentEncoding(anchorText);
- }
- return anchorText;
- };
- return UrlMatch;
- }(AbstractMatch));
- // Utility Functionality
- /**
- * Strips the scheme prefix (such as "http://" or "https://") from the given
- * `url`.
- *
- * @private
- * @param {String} url The text of the anchor that is being generated, for
- * which to strip off the url scheme.
- * @return {String} The `url`, with the scheme stripped.
- */
- function stripSchemePrefix(url) {
- return url.replace(httpSchemePrefixRe, '');
- }
- /**
- * Strips the 'www' prefix from the given `url`.
- *
- * @private
- * @param {String} url The text of the anchor that is being generated, for
- * which to strip off the 'www' if it exists.
- * @return {String} The `url`, with the 'www' stripped.
- */
- function stripWwwPrefix(url) {
- return url.replace(wwwPrefixRegex, '$1'); // leave any scheme ($1), it one exists
- }
- /**
- * Strips any protocol-relative '//' from the anchor text.
- *
- * @private
- * @param {String} text The text of the anchor that is being generated, for which to strip off the
- * protocol-relative prefix (such as stripping off "//")
- * @return {String} The `anchorText`, with the protocol-relative prefix stripped.
- */
- function stripProtocolRelativePrefix(text) {
- return text.replace(protocolRelativeRegex, '');
- }
- /**
- * Removes any trailing slash from the given `anchorText`, in preparation for the text to be displayed.
- *
- * @private
- * @param {String} anchorText The text of the anchor that is being generated, for which to remove any trailing
- * slash ('/') that may exist.
- * @return {String} The `anchorText`, with the trailing slash removed.
- */
- function removeTrailingSlash(anchorText) {
- if (anchorText.charAt(anchorText.length - 1) === '/') {
- anchorText = anchorText.slice(0, -1);
- }
- return anchorText;
- }
- /**
- * Decodes percent-encoded characters from the given `anchorText`, in
- * preparation for the text to be displayed.
- *
- * @private
- * @param {String} anchorText The text of the anchor that is being
- * generated, for which to decode any percent-encoded characters.
- * @return {String} The `anchorText`, with the percent-encoded characters
- * decoded.
- */
- function removePercentEncoding(anchorText) {
- // First, convert a few of the known % encodings to the corresponding
- // HTML entities that could accidentally be interpretted as special
- // HTML characters
- var preProcessedEntityAnchorText = anchorText
- .replace(/%22/gi, '"') // " char
- .replace(/%26/gi, '&') // & char
- .replace(/%27/gi, ''') // ' char
- .replace(/%3C/gi, '<') // < char
- .replace(/%3E/gi, '>'); // > char
- try {
- // Now attempt to decode the rest of the anchor text
- return decodeURIComponent(preProcessedEntityAnchorText);
- }
- catch (e) {
- // Invalid % escape sequence in the anchor text
- return preProcessedEntityAnchorText;
- }
- }
- /**
- * A regular expression to match a 'mailto:' prefix on an email address.
- */
- var mailtoSchemePrefixRe = /^mailto:/i;
- /**
- * Regular expression for all of the valid characters of the local part of an
- * email address.
- */
- var emailLocalPartCharRegex = new RegExp("[".concat(alphaNumericAndMarksCharsStr, "!#$%&'*+/=?^_`{|}~-]"));
- /**
- * Determines if the given character may start the "local part" of an email
- * address. The local part is the part to the left of the '@' sign.
- *
- * Technically according to the email spec, any of the characters in the
- * {@link emailLocalPartCharRegex} can start an email address (including any of
- * the special characters), but this is so rare in the wild and the
- * implementation is much simpler by only starting an email address with a word
- * character. This is especially important when matching the '{' character which
- * generally starts a brace that isn't part of the email address.
- */
- function isEmailLocalPartStartChar(char) {
- return alphaNumericAndMarksRe.test(char);
- }
- /**
- * Determines if the given character can be part of the "local part" of an email
- * address. The local part is the part to the left of the '@' sign.
- */
- function isEmailLocalPartChar(char) {
- return emailLocalPartCharRegex.test(char);
- }
- /**
- * Determines if the given email address is valid. We consider it valid if it
- * has a valid TLD in its host.
- *
- * @param emailAddress email address
- * @return true is email have valid TLD, false otherwise
- */
- function isValidEmail(emailAddress) {
- var emailAddressTld = emailAddress.split('.').pop() || '';
- return isKnownTld(emailAddressTld);
- }
- /**
- * @class Autolinker.match.Email
- * @extends Autolinker.match.AbstractMatch
- *
- * Represents a Email match found in an input string which should be Autolinked.
- *
- * See this class's superclass ({@link Autolinker.match.Match}) for more details.
- */
- var EmailMatch = /** @class */ (function (_super) {
- __extends(EmailMatch, _super);
- /**
- * @method constructor
- * @param {Object} cfg The configuration properties for the Match
- * instance, specified in an Object (map).
- */
- function EmailMatch(cfg) {
- var _this = _super.call(this, cfg) || this;
- /**
- * @public
- * @property {'email'} type
- *
- * A string name for the type of match that this class represents. Can be
- * used in a TypeScript discriminating union to type-narrow from the
- * `Match` type.
- */
- _this.type = 'email';
- /**
- * @cfg {String} email (required)
- *
- * The email address that was matched.
- */
- _this.email = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- _this.email = cfg.email;
- return _this;
- }
- /**
- * Returns a string name for the type of match that this class represents.
- * For the case of EmailMatch, returns 'email'.
- *
- * @return {String}
- */
- EmailMatch.prototype.getType = function () {
- return 'email';
- };
- /**
- * Returns the email address that was matched.
- *
- * @return {String}
- */
- EmailMatch.prototype.getEmail = function () {
- return this.email;
- };
- /**
- * Returns the anchor href that should be generated for the match.
- *
- * @return {String}
- */
- EmailMatch.prototype.getAnchorHref = function () {
- return 'mailto:' + this.email;
- };
- /**
- * Returns the anchor text that should be generated for the match.
- *
- * @return {String}
- */
- EmailMatch.prototype.getAnchorText = function () {
- return this.email;
- };
- return EmailMatch;
- }(AbstractMatch));
- /**
- * Determines if the given `char` is a an allowed character in a hashtag. These
- * are underscores or any alphanumeric char.
- */
- function isHashtagTextChar(char) {
- return char === '_' || alphaNumericAndMarksRe.test(char);
- }
- /**
- * Determines if a hashtag match is valid.
- */
- function isValidHashtag(hashtag) {
- // Max length of 140 for a hashtag ('#' char + 139 word chars)
- return hashtag.length <= 140;
- }
- var hashtagServices = ['twitter', 'facebook', 'instagram', 'tiktok'];
- /**
- * @class Autolinker.match.Hashtag
- * @extends Autolinker.match.AbstractMatch
- *
- * Represents a Hashtag match found in an input string which should be
- * Autolinked.
- *
- * See this class's superclass ({@link Autolinker.match.Match}) for more
- * details.
- */
- var HashtagMatch = /** @class */ (function (_super) {
- __extends(HashtagMatch, _super);
- /**
- * @method constructor
- * @param {Object} cfg The configuration properties for the Match
- * instance, specified in an Object (map).
- */
- function HashtagMatch(cfg) {
- var _this = _super.call(this, cfg) || this;
- /**
- * @public
- * @property {'hashtag'} type
- *
- * A string name for the type of match that this class represents. Can be
- * used in a TypeScript discriminating union to type-narrow from the
- * `Match` type.
- */
- _this.type = 'hashtag';
- /**
- * @cfg {String} serviceName
- *
- * The service to point hashtag matches to. See {@link Autolinker#hashtag}
- * for available values.
- */
- _this.serviceName = 'twitter'; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {String} hashtag (required)
- *
- * The HashtagMatch that was matched, without the '#'.
- */
- _this.hashtag = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- _this.serviceName = cfg.serviceName;
- _this.hashtag = cfg.hashtag;
- return _this;
- }
- /**
- * Returns a string name for the type of match that this class represents.
- * For the case of HashtagMatch, returns 'hashtag'.
- *
- * @return {String}
- */
- HashtagMatch.prototype.getType = function () {
- return 'hashtag';
- };
- /**
- * Returns the configured {@link #serviceName} to point the HashtagMatch to.
- * Ex: 'facebook', 'twitter'.
- *
- * @return {String}
- */
- HashtagMatch.prototype.getServiceName = function () {
- return this.serviceName;
- };
- /**
- * Returns the matched hashtag, without the '#' character.
- *
- * @return {String}
- */
- HashtagMatch.prototype.getHashtag = function () {
- return this.hashtag;
- };
- /**
- * Returns the anchor href that should be generated for the match.
- *
- * @return {String}
- */
- HashtagMatch.prototype.getAnchorHref = function () {
- var serviceName = this.serviceName, hashtag = this.hashtag;
- switch (serviceName) {
- case 'twitter':
- return 'https://twitter.com/hashtag/' + hashtag;
- case 'facebook':
- return 'https://www.facebook.com/hashtag/' + hashtag;
- case 'instagram':
- return 'https://instagram.com/explore/tags/' + hashtag;
- case 'tiktok':
- return 'https://www.tiktok.com/tag/' + hashtag;
- default:
- // Shouldn't happen because Autolinker's constructor should block any invalid values, but just in case
- assertNever(serviceName);
- throw new Error("Invalid hashtag service: ".concat(serviceName));
- }
- };
- /**
- * Returns the anchor text that should be generated for the match.
- *
- * @return {String}
- */
- HashtagMatch.prototype.getAnchorText = function () {
- return '#' + this.hashtag;
- };
- /**
- * Returns the CSS class suffixes that should be used on a tag built with
- * the match. See {@link Autolinker.match.Match#getCssClassSuffixes} for
- * details.
- *
- * @return {String[]}
- */
- HashtagMatch.prototype.getCssClassSuffixes = function () {
- var cssClassSuffixes = _super.prototype.getCssClassSuffixes.call(this), serviceName = this.getServiceName();
- if (serviceName) {
- cssClassSuffixes.push(serviceName);
- }
- return cssClassSuffixes;
- };
- return HashtagMatch;
- }(AbstractMatch));
- var mentionRegexes = {
- twitter: /^@\w{1,15}$/,
- instagram: /^@[_\w]{1,30}$/,
- soundcloud: /^@[-a-z0-9_]{3,25}$/,
- // TikTok usernames are 1-24 characters containing letters, numbers, underscores
- // and periods, but cannot end in a period: https://support.tiktok.com/en/getting-started/setting-up-your-profile/changing-your-username
- tiktok: /^@[.\w]{1,23}[\w]$/,
- };
- // Regex that allows for all possible mention characters for any service. We'll
- // confirm the match based on the user-configured service name after a match is
- // found.
- var mentionTextCharRe = /[-\w.]/;
- /**
- * Determines if the given character can be part of a mention's text characters.
- */
- function isMentionTextChar(char) {
- return mentionTextCharRe.test(char);
- }
- /**
- * Determines if the given `mention` text is valid.
- */
- function isValidMention(mention, serviceName) {
- var re = mentionRegexes[serviceName];
- return re.test(mention);
- }
- var mentionServices = ['twitter', 'instagram', 'soundcloud', 'tiktok'];
- /**
- * @class Autolinker.match.Mention
- * @extends Autolinker.match.AbstractMatch
- *
- * Represents a Mention match found in an input string which should be Autolinked.
- *
- * See this class's superclass ({@link Autolinker.match.Match}) for more details.
- */
- var MentionMatch = /** @class */ (function (_super) {
- __extends(MentionMatch, _super);
- /**
- * @method constructor
- * @param {Object} cfg The configuration properties for the Match
- * instance, specified in an Object (map).
- */
- function MentionMatch(cfg) {
- var _this = _super.call(this, cfg) || this;
- /**
- * @public
- * @property {'mention'} type
- *
- * A string name for the type of match that this class represents. Can be
- * used in a TypeScript discriminating union to type-narrow from the
- * `Match` type.
- */
- _this.type = 'mention';
- /**
- * @cfg {String} serviceName
- *
- * The service to point mention matches to. See {@link Autolinker#mention}
- * for available values.
- */
- _this.serviceName = 'twitter'; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {String} mention (required)
- *
- * The Mention that was matched, without the '@' character.
- */
- _this.mention = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- _this.mention = cfg.mention;
- _this.serviceName = cfg.serviceName;
- return _this;
- }
- /**
- * Returns a string name for the type of match that this class represents.
- * For the case of MentionMatch, returns 'mention'.
- *
- * @return {String}
- */
- MentionMatch.prototype.getType = function () {
- return 'mention';
- };
- /**
- * Returns the mention, without the '@' character.
- *
- * @return {String}
- */
- MentionMatch.prototype.getMention = function () {
- return this.mention;
- };
- /**
- * Returns the configured {@link #serviceName} to point the mention to.
- * Ex: 'instagram', 'twitter', 'soundcloud'.
- *
- * @return {String}
- */
- MentionMatch.prototype.getServiceName = function () {
- return this.serviceName;
- };
- /**
- * Returns the anchor href that should be generated for the match.
- *
- * @return {String}
- */
- MentionMatch.prototype.getAnchorHref = function () {
- switch (this.serviceName) {
- case 'twitter':
- return 'https://twitter.com/' + this.mention;
- case 'instagram':
- return 'https://instagram.com/' + this.mention;
- case 'soundcloud':
- return 'https://soundcloud.com/' + this.mention;
- case 'tiktok':
- return 'https://www.tiktok.com/@' + this.mention;
- default:
- // Shouldn't happen because Autolinker's constructor should block any invalid values, but just in case.
- throw new Error('Unknown service name to point mention to: ' + this.serviceName);
- }
- };
- /**
- * Returns the anchor text that should be generated for the match.
- *
- * @return {String}
- */
- MentionMatch.prototype.getAnchorText = function () {
- return '@' + this.mention;
- };
- /**
- * Returns the CSS class suffixes that should be used on a tag built with
- * the match. See {@link Autolinker.match.Match#getCssClassSuffixes} for
- * details.
- *
- * @return {String[]}
- */
- MentionMatch.prototype.getCssClassSuffixes = function () {
- var cssClassSuffixes = _super.prototype.getCssClassSuffixes.call(this), serviceName = this.getServiceName();
- if (serviceName) {
- cssClassSuffixes.push(serviceName);
- }
- return cssClassSuffixes;
- };
- return MentionMatch;
- }(AbstractMatch));
- // Regex that holds the characters used to separate segments of a phone number
- var separatorCharRe = /[-. ]/;
- // Regex that specifies any delimiter char that allows us to treat the number as
- // a phone number rather than just any other number that could appear in text.
- var hasDelimCharsRe = /[-. ()]/;
- // "Pause" and "Wait" control chars
- var controlCharRe = /[,;]/;
- // Over the years, many people have added to this regex, but it should have been
- // split up by country. Maybe one day we can break this down.
- var mostPhoneNumbers = /(?:(?:(?:(\+)?\d{1,3}[-. ]?)?\(?\d{3}\)?[-. ]?\d{3}[-. ]?\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)[-. ]?(?:\d[-. ]?){6,12}\d+))([,;]+[0-9]+#?)*/;
- // Regex for Japanese phone numbers
- var japanesePhoneRe = /(0([1-9]-?[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})/;
- // Combined regex
- var validPhoneNumberRe = new RegExp("^".concat(mostPhoneNumbers.source, "|").concat(japanesePhoneRe.source, "$"));
- /**
- * Determines if the character is a phone number separator character (i.e.
- * '-', '.', or ' ' (space))
- */
- function isPhoneNumberSeparatorChar(char) {
- return separatorCharRe.test(char);
- }
- /**
- * Determines if the character is a control character in a phone number. Control
- * characters are as follows:
- *
- * - ',': A 1 second pause. Useful for dialing extensions once the main phone number has been reached
- * - ';': A "wait" that waits for the user to take action (tap something, for instance on a smart phone)
- */
- function isPhoneNumberControlChar(char) {
- return controlCharRe.test(char);
- }
- /**
- * Determines if the given phone number text found in a string is a valid phone
- * number.
- *
- * Our state machine parser is simplified to grab anything that looks like a
- * phone number, and this function confirms the match.
- */
- function isValidPhoneNumber(phoneNumberText) {
- // We'll only consider the match as a phone number if there is some kind of
- // delimiter character (a prefixed '+' sign, or separator chars).
- //
- // Accepts:
- // (123) 456-7890
- // +38755233976
- // Does not accept:
- // 1234567890 (no delimiter chars - may just be a random number that's not a phone number)
- var hasDelimiters = phoneNumberText.charAt(0) === '+' || hasDelimCharsRe.test(phoneNumberText);
- return hasDelimiters && validPhoneNumberRe.test(phoneNumberText);
- }
- /**
- * @class Autolinker.match.Phone
- * @extends Autolinker.match.AbstractMatch
- *
- * Represents a Phone number match found in an input string which should be
- * Autolinked.
- *
- * See this class's superclass ({@link Autolinker.match.Match}) for more
- * details.
- */
- var PhoneMatch = /** @class */ (function (_super) {
- __extends(PhoneMatch, _super);
- /**
- * @method constructor
- * @param {Object} cfg The configuration properties for the Match
- * instance, specified in an Object (map).
- */
- function PhoneMatch(cfg) {
- var _this = _super.call(this, cfg) || this;
- /**
- * @public
- * @property {'phone'} type
- *
- * A string name for the type of match that this class represents. Can be
- * used in a TypeScript discriminating union to type-narrow from the
- * `Match` type.
- */
- _this.type = 'phone';
- /**
- * @protected
- * @property {String} number (required)
- *
- * The phone number that was matched, without any delimiter characters.
- *
- * Note: This is a string to allow for prefixed 0's.
- */
- _this.number = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @protected
- * @property {Boolean} plusSign (required)
- *
- * `true` if the matched phone number started with a '+' sign. We'll include
- * it in the `tel:` URL if so, as this is needed for international numbers.
- *
- * Ex: '+1 (123) 456 7879'
- */
- _this.plusSign = false; // default value just to get the above doc comment in the ES5 output and documentation generator
- _this.number = cfg.number;
- _this.plusSign = cfg.plusSign;
- return _this;
- }
- /**
- * Returns a string name for the type of match that this class represents.
- * For the case of PhoneMatch, returns 'phone'.
- *
- * @return {String}
- */
- PhoneMatch.prototype.getType = function () {
- return 'phone';
- };
- /**
- * Returns the phone number that was matched as a string, without any
- * delimiter characters.
- *
- * Note: This is a string to allow for prefixed 0's.
- *
- * @return {String}
- */
- PhoneMatch.prototype.getPhoneNumber = function () {
- return this.number;
- };
- /**
- * Alias of {@link #getPhoneNumber}, returns the phone number that was
- * matched as a string, without any delimiter characters.
- *
- * Note: This is a string to allow for prefixed 0's.
- *
- * @return {String}
- */
- PhoneMatch.prototype.getNumber = function () {
- return this.getPhoneNumber();
- };
- /**
- * Returns the anchor href that should be generated for the match.
- *
- * @return {String}
- */
- PhoneMatch.prototype.getAnchorHref = function () {
- return 'tel:' + (this.plusSign ? '+' : '') + this.number;
- };
- /**
- * Returns the anchor text that should be generated for the match.
- *
- * @return {String}
- */
- PhoneMatch.prototype.getAnchorText = function () {
- return this.matchedText;
- };
- return PhoneMatch;
- }(AbstractMatch));
- // For debugging: search for and uncomment other "For debugging" lines
- // import CliTable from 'cli-table';
- /**
- * Parses URL, email, twitter, mention, and hashtag matches from the given
- * `text`.
- */
- function parseMatches(text, args) {
- var tagBuilder = args.tagBuilder;
- var stripPrefix = args.stripPrefix;
- var stripTrailingSlash = args.stripTrailingSlash;
- var decodePercentEncoding = args.decodePercentEncoding;
- var hashtagServiceName = args.hashtagServiceName;
- var mentionServiceName = args.mentionServiceName;
- var matches = [];
- var textLen = text.length;
- // An array of all active state machines. Empty array means we're in the
- // "no url" state
- var stateMachines = [];
- // For debugging: search for and uncomment other "For debugging" lines
- // const table = new CliTable({
- // head: ['charIdx', 'char', 'states', 'charIdx', 'startIdx', 'reached accept state'],
- // });
- var charIdx = 0;
- for (; charIdx < textLen; charIdx++) {
- var char = text.charAt(charIdx);
- if (stateMachines.length === 0) {
- stateNoMatch(char);
- }
- else {
- // Must loop through the state machines backwards for when one
- // is removed
- for (var stateIdx = stateMachines.length - 1; stateIdx >= 0; stateIdx--) {
- var stateMachine = stateMachines[stateIdx];
- switch (stateMachine.state) {
- // Protocol-relative URL states
- case 11 /* ProtocolRelativeSlash1 */:
- stateProtocolRelativeSlash1(stateMachine, char);
- break;
- case 12 /* ProtocolRelativeSlash2 */:
- stateProtocolRelativeSlash2(stateMachine, char);
- break;
- case 0 /* SchemeChar */:
- stateSchemeChar(stateMachine, char);
- break;
- case 1 /* SchemeHyphen */:
- stateSchemeHyphen(stateMachine, char);
- break;
- case 2 /* SchemeColon */:
- stateSchemeColon(stateMachine, char);
- break;
- case 3 /* SchemeSlash1 */:
- stateSchemeSlash1(stateMachine, char);
- break;
- case 4 /* SchemeSlash2 */:
- stateSchemeSlash2(stateMachine, char);
- break;
- case 5 /* DomainLabelChar */:
- stateDomainLabelChar(stateMachine, char);
- break;
- case 6 /* DomainHyphen */:
- stateDomainHyphen(stateMachine, char);
- break;
- case 7 /* DomainDot */:
- stateDomainDot(stateMachine, char);
- break;
- case 13 /* IpV4Digit */:
- stateIpV4Digit(stateMachine, char);
- break;
- case 14 /* IpV4Dot */:
- stateIPv4Dot(stateMachine, char);
- break;
- case 8 /* PortColon */:
- statePortColon(stateMachine, char);
- break;
- case 9 /* PortNumber */:
- statePortNumber(stateMachine, char);
- break;
- case 10 /* Path */:
- statePath(stateMachine, char);
- break;
- // Email States
- case 15 /* EmailMailto_M */:
- stateEmailMailto_M(stateMachine, char);
- break;
- case 16 /* EmailMailto_A */:
- stateEmailMailto_A(stateMachine, char);
- break;
- case 17 /* EmailMailto_I */:
- stateEmailMailto_I(stateMachine, char);
- break;
- case 18 /* EmailMailto_L */:
- stateEmailMailto_L(stateMachine, char);
- break;
- case 19 /* EmailMailto_T */:
- stateEmailMailto_T(stateMachine, char);
- break;
- case 20 /* EmailMailto_O */:
- stateEmailMailto_O(stateMachine, char);
- break;
- case 21 /* EmailMailto_Colon */:
- stateEmailMailtoColon(stateMachine, char);
- break;
- case 22 /* EmailLocalPart */:
- stateEmailLocalPart(stateMachine, char);
- break;
- case 23 /* EmailLocalPartDot */:
- stateEmailLocalPartDot(stateMachine, char);
- break;
- case 24 /* EmailAtSign */:
- stateEmailAtSign(stateMachine, char);
- break;
- case 25 /* EmailDomainChar */:
- stateEmailDomainChar(stateMachine, char);
- break;
- case 26 /* EmailDomainHyphen */:
- stateEmailDomainHyphen(stateMachine, char);
- break;
- case 27 /* EmailDomainDot */:
- stateEmailDomainDot(stateMachine, char);
- break;
- // Hashtag states
- case 28 /* HashtagHashChar */:
- stateHashtagHashChar(stateMachine, char);
- break;
- case 29 /* HashtagTextChar */:
- stateHashtagTextChar(stateMachine, char);
- break;
- // Mention states
- case 30 /* MentionAtChar */:
- stateMentionAtChar(stateMachine, char);
- break;
- case 31 /* MentionTextChar */:
- stateMentionTextChar(stateMachine, char);
- break;
- // Phone number states
- case 32 /* PhoneNumberOpenParen */:
- statePhoneNumberOpenParen(stateMachine, char);
- break;
- case 33 /* PhoneNumberAreaCodeDigit1 */:
- statePhoneNumberAreaCodeDigit1(stateMachine, char);
- break;
- case 34 /* PhoneNumberAreaCodeDigit2 */:
- statePhoneNumberAreaCodeDigit2(stateMachine, char);
- break;
- case 35 /* PhoneNumberAreaCodeDigit3 */:
- statePhoneNumberAreaCodeDigit3(stateMachine, char);
- break;
- case 36 /* PhoneNumberCloseParen */:
- statePhoneNumberCloseParen(stateMachine, char);
- break;
- case 37 /* PhoneNumberPlus */:
- statePhoneNumberPlus(stateMachine, char);
- break;
- case 38 /* PhoneNumberDigit */:
- statePhoneNumberDigit(stateMachine, char);
- break;
- case 39 /* PhoneNumberSeparator */:
- statePhoneNumberSeparator(stateMachine, char);
- break;
- case 40 /* PhoneNumberControlChar */:
- statePhoneNumberControlChar(stateMachine, char);
- break;
- case 41 /* PhoneNumberPoundChar */:
- statePhoneNumberPoundChar(stateMachine, char);
- break;
- default:
- assertNever(stateMachine.state);
- }
- }
- }
- // For debugging: search for and uncomment other "For debugging" lines
- // table.push([
- // charIdx,
- // char,
- // stateMachines.map(machine => State[machine.state]).join('\n') || '(none)',
- // charIdx,
- // stateMachines.map(m => m.startIdx).join('\n'),
- // stateMachines.map(m => m.acceptStateReached).join('\n'),
- // ]);
- }
- // Capture any valid match at the end of the string
- // Note: this loop must happen in reverse because
- // captureMatchIfValidAndRemove() removes state machines from the array
- // and we'll end up skipping every other one if we remove while looping
- // forward
- for (var i = stateMachines.length - 1; i >= 0; i--) {
- stateMachines.forEach(function (stateMachine) { return captureMatchIfValidAndRemove(stateMachine); });
- }
- // For debugging: search for and uncomment other "For debugging" lines
- // console.log(`\nRead string:\n ${text}`);
- // console.log(table.toString());
- return matches;
- // Handles the state when we're not in a URL/email/etc. (i.e. when no state machines exist)
- function stateNoMatch(char) {
- if (char === '#') {
- // Hash char, start a Hashtag match
- stateMachines.push(createHashtagStateMachine(charIdx, 28 /* HashtagHashChar */));
- }
- else if (char === '@') {
- // '@' char, start a Mention match
- stateMachines.push(createMentionStateMachine(charIdx, 30 /* MentionAtChar */));
- }
- else if (char === '/') {
- // A slash could begin a protocol-relative URL
- stateMachines.push(createTldUrlStateMachine(charIdx, 11 /* ProtocolRelativeSlash1 */));
- }
- else if (char === '+') {
- // A '+' char can start a Phone number
- stateMachines.push(createPhoneNumberStateMachine(charIdx, 37 /* PhoneNumberPlus */));
- }
- else if (char === '(') {
- stateMachines.push(createPhoneNumberStateMachine(charIdx, 32 /* PhoneNumberOpenParen */));
- }
- else {
- if (digitRe.test(char)) {
- // A digit could start a phone number
- stateMachines.push(createPhoneNumberStateMachine(charIdx, 38 /* PhoneNumberDigit */));
- // A digit could start an IP address
- stateMachines.push(createIpV4UrlStateMachine(charIdx, 13 /* IpV4Digit */));
- }
- if (isEmailLocalPartStartChar(char)) {
- // Any email local part. An 'm' character in particular could
- // start a 'mailto:' match
- var startState = char.toLowerCase() === 'm' ? 15 /* EmailMailto_M */ : 22 /* EmailLocalPart */;
- stateMachines.push(createEmailStateMachine(charIdx, startState));
- }
- if (isSchemeStartChar(char)) {
- // An uppercase or lowercase letter may start a scheme match
- stateMachines.push(createSchemeUrlStateMachine(charIdx, 0 /* SchemeChar */));
- }
- if (alphaNumericAndMarksRe.test(char)) {
- // A unicode alpha character or digit could start a domain name
- // label for a TLD match
- stateMachines.push(createTldUrlStateMachine(charIdx, 5 /* DomainLabelChar */));
- }
- }
- // Anything else, remain in the "non-url" state by not creating any
- // state machines
- }
- // Implements ABNF: ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
- function stateSchemeChar(stateMachine, char) {
- if (char === ':') {
- stateMachine.state = 2 /* SchemeColon */;
- }
- else if (char === '-') {
- stateMachine.state = 1 /* SchemeHyphen */;
- }
- else if (isSchemeChar(char)) ;
- else {
- // Any other character, not a scheme
- remove(stateMachines, stateMachine);
- }
- }
- function stateSchemeHyphen(stateMachine, char) {
- if (char === '-') ;
- else if (char === '/') {
- // Not a valid scheme match, but may be the start of a
- // protocol-relative match (such as //google.com)
- remove(stateMachines, stateMachine);
- stateMachines.push(createTldUrlStateMachine(charIdx, 11 /* ProtocolRelativeSlash1 */));
- }
- else if (isSchemeChar(char)) {
- stateMachine.state = 0 /* SchemeChar */;
- }
- else {
- // Any other character, not a scheme
- remove(stateMachines, stateMachine);
- }
- }
- function stateSchemeColon(stateMachine, char) {
- if (char === '/') {
- stateMachine.state = 3 /* SchemeSlash1 */;
- }
- else if (char === '.') {
- // We've read something like 'hello:.' - don't capture
- remove(stateMachines, stateMachine);
- }
- else if (isDomainLabelStartChar(char)) {
- stateMachine.state = 5 /* DomainLabelChar */;
- // It's possible that we read an "introduction" piece of text,
- // and the character after the current colon actually starts an
- // actual scheme. An example of this is:
- // "The link:http://google.com"
- // Hence, start a new machine to capture this match if so
- if (isSchemeStartChar(char)) {
- stateMachines.push(createSchemeUrlStateMachine(charIdx, 0 /* SchemeChar */));
- }
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- function stateSchemeSlash1(stateMachine, char) {
- if (char === '/') {
- stateMachine.state = 4 /* SchemeSlash2 */;
- }
- else if (isPathChar(char)) {
- stateMachine.state = 10 /* Path */;
- stateMachine.acceptStateReached = true;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateSchemeSlash2(stateMachine, char) {
- if (char === '/') {
- // 3rd slash, must be an absolute path (path-absolute in the
- // ABNF), such as in a file:///c:/windows/etc. See
- // https://tools.ietf.org/html/rfc3986#appendix-A
- stateMachine.state = 10 /* Path */;
- }
- else if (isDomainLabelStartChar(char)) {
- // start of "authority" section - see https://tools.ietf.org/html/rfc3986#appendix-A
- stateMachine.state = 5 /* DomainLabelChar */;
- stateMachine.acceptStateReached = true;
- }
- else {
- // not valid
- remove(stateMachines, stateMachine);
- }
- }
- // Handles reading a '/' from the NonUrl state
- function stateProtocolRelativeSlash1(stateMachine, char) {
- if (char === '/') {
- stateMachine.state = 12 /* ProtocolRelativeSlash2 */;
- }
- else {
- // Anything else, cannot be the start of a protocol-relative
- // URL.
- remove(stateMachines, stateMachine);
- }
- }
- // Handles reading a second '/', which could start a protocol-relative URL
- function stateProtocolRelativeSlash2(stateMachine, char) {
- if (isDomainLabelStartChar(char)) {
- stateMachine.state = 5 /* DomainLabelChar */;
- }
- else {
- // Anything else, not a URL
- remove(stateMachines, stateMachine);
- }
- }
- // Handles when we have read a domain label character
- function stateDomainLabelChar(stateMachine, char) {
- if (char === '.') {
- stateMachine.state = 7 /* DomainDot */;
- }
- else if (char === '-') {
- stateMachine.state = 6 /* DomainHyphen */;
- }
- else if (char === ':') {
- // Beginning of a port number, end the domain name
- stateMachine.state = 8 /* PortColon */;
- }
- else if (isUrlSuffixStartChar(char)) {
- // '/', '?', or '#'
- stateMachine.state = 10 /* Path */;
- }
- else if (isDomainLabelChar(char)) ;
- else {
- // Anything else, end the domain name
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateDomainHyphen(stateMachine, char) {
- if (char === '-') ;
- else if (char === '.') {
- // Not valid to have a '-.' in a domain label
- captureMatchIfValidAndRemove(stateMachine);
- }
- else if (isDomainLabelStartChar(char)) {
- stateMachine.state = 5 /* DomainLabelChar */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateDomainDot(stateMachine, char) {
- if (char === '.') {
- // domain names cannot have multiple '.'s next to each other.
- // It's possible we've already read a valid domain name though,
- // and that the '..' sequence just forms an ellipsis at the end
- // of a sentence
- captureMatchIfValidAndRemove(stateMachine);
- }
- else if (isDomainLabelStartChar(char)) {
- stateMachine.state = 5 /* DomainLabelChar */;
- stateMachine.acceptStateReached = true; // after hitting a dot, and then another domain label, we've reached an accept state
- }
- else {
- // Anything else, end the domain name
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateIpV4Digit(stateMachine, char) {
- if (char === '.') {
- stateMachine.state = 14 /* IpV4Dot */;
- }
- else if (char === ':') {
- // Beginning of a port number
- stateMachine.state = 8 /* PortColon */;
- }
- else if (digitRe.test(char)) ;
- else if (isUrlSuffixStartChar(char)) {
- stateMachine.state = 10 /* Path */;
- }
- else if (alphaNumericAndMarksRe.test(char)) {
- // If we hit an alpha character, must not be an IPv4
- // Example of this: 1.2.3.4abc
- remove(stateMachines, stateMachine);
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateIPv4Dot(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.octetsEncountered++;
- // Once we have encountered 4 octets, it's *potentially* a valid
- // IPv4 address. Our IPv4 regex will confirm the match later
- // though to make sure each octet is in the 0-255 range, and
- // there's exactly 4 octets (not 5 or more)
- if (stateMachine.octetsEncountered === 4) {
- stateMachine.acceptStateReached = true;
- }
- stateMachine.state = 13 /* IpV4Digit */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function statePortColon(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 9 /* PortNumber */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function statePortNumber(stateMachine, char) {
- if (digitRe.test(char)) ;
- else if (isUrlSuffixStartChar(char)) {
- // '/', '?', or '#'
- stateMachine.state = 10 /* Path */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function statePath(stateMachine, char) {
- if (isPathChar(char)) ;
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- // Handles if we're reading a 'mailto:' prefix on the string
- function stateEmailMailto_M(stateMachine, char) {
- if (char.toLowerCase() === 'a') {
- stateMachine.state = 16 /* EmailMailto_A */;
- }
- else {
- stateEmailLocalPart(stateMachine, char);
- }
- }
- function stateEmailMailto_A(stateMachine, char) {
- if (char.toLowerCase() === 'i') {
- stateMachine.state = 17 /* EmailMailto_I */;
- }
- else {
- stateEmailLocalPart(stateMachine, char);
- }
- }
- function stateEmailMailto_I(stateMachine, char) {
- if (char.toLowerCase() === 'l') {
- stateMachine.state = 18 /* EmailMailto_L */;
- }
- else {
- stateEmailLocalPart(stateMachine, char);
- }
- }
- function stateEmailMailto_L(stateMachine, char) {
- if (char.toLowerCase() === 't') {
- stateMachine.state = 19 /* EmailMailto_T */;
- }
- else {
- stateEmailLocalPart(stateMachine, char);
- }
- }
- function stateEmailMailto_T(stateMachine, char) {
- if (char.toLowerCase() === 'o') {
- stateMachine.state = 20 /* EmailMailto_O */;
- }
- else {
- stateEmailLocalPart(stateMachine, char);
- }
- }
- function stateEmailMailto_O(stateMachine, char) {
- if (char.toLowerCase() === ':') {
- stateMachine.state = 21 /* EmailMailto_Colon */;
- }
- else {
- stateEmailLocalPart(stateMachine, char);
- }
- }
- function stateEmailMailtoColon(stateMachine, char) {
- if (isEmailLocalPartChar(char)) {
- stateMachine.state = 22 /* EmailLocalPart */;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- // Handles the state when we're currently in the "local part" of an
- // email address (as opposed to the "domain part")
- function stateEmailLocalPart(stateMachine, char) {
- if (char === '.') {
- stateMachine.state = 23 /* EmailLocalPartDot */;
- }
- else if (char === '@') {
- stateMachine.state = 24 /* EmailAtSign */;
- }
- else if (isEmailLocalPartChar(char)) {
- // stay in the "local part" of the email address
- // Note: because stateEmailLocalPart() is called from the
- // 'mailto' states (when the 'mailto' prefix itself has been
- // broken), make sure to set the state to EmailLocalPart
- stateMachine.state = 22 /* EmailLocalPart */;
- }
- else {
- // not an email address character
- remove(stateMachines, stateMachine);
- }
- }
- // Handles the state where we've read
- function stateEmailLocalPartDot(stateMachine, char) {
- if (char === '.') {
- // We read a second '.' in a row, not a valid email address
- // local part
- remove(stateMachines, stateMachine);
- }
- else if (char === '@') {
- // We read the '@' character immediately after a dot ('.'), not
- // an email address
- remove(stateMachines, stateMachine);
- }
- else if (isEmailLocalPartChar(char)) {
- stateMachine.state = 22 /* EmailLocalPart */;
- }
- else {
- // Anything else, not an email address
- remove(stateMachines, stateMachine);
- }
- }
- function stateEmailAtSign(stateMachine, char) {
- if (isDomainLabelStartChar(char)) {
- stateMachine.state = 25 /* EmailDomainChar */;
- }
- else {
- // Anything else, not an email address
- remove(stateMachines, stateMachine);
- }
- }
- function stateEmailDomainChar(stateMachine, char) {
- if (char === '.') {
- stateMachine.state = 27 /* EmailDomainDot */;
- }
- else if (char === '-') {
- stateMachine.state = 26 /* EmailDomainHyphen */;
- }
- else if (isDomainLabelChar(char)) ;
- else {
- // Anything else, we potentially matched if the criteria has
- // been met
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateEmailDomainHyphen(stateMachine, char) {
- if (char === '-' || char === '.') {
- // Not valid to have two hyphens ("--") or hypen+dot ("-.")
- captureMatchIfValidAndRemove(stateMachine);
- }
- else if (isDomainLabelChar(char)) {
- stateMachine.state = 25 /* EmailDomainChar */;
- }
- else {
- // Anything else
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function stateEmailDomainDot(stateMachine, char) {
- if (char === '.' || char === '-') {
- // not valid to have two dots ("..") or dot+hypen (".-")
- captureMatchIfValidAndRemove(stateMachine);
- }
- else if (isDomainLabelStartChar(char)) {
- stateMachine.state = 25 /* EmailDomainChar */;
- // After having read a '.' and then a valid domain character,
- // we now know that the domain part of the email is valid, and
- // we have found at least a partial EmailMatch (however, the
- // email address may have additional characters from this point)
- stateMachine.acceptStateReached = true;
- }
- else {
- // Anything else
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- // Handles the state when we've just encountered a '#' character
- function stateHashtagHashChar(stateMachine, char) {
- if (isHashtagTextChar(char)) {
- // '#' char with valid hash text char following
- stateMachine.state = 29 /* HashtagTextChar */;
- stateMachine.acceptStateReached = true;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- // Handles the state when we're currently in the hash tag's text chars
- function stateHashtagTextChar(stateMachine, char) {
- if (isHashtagTextChar(char)) ;
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- // Handles the state when we've just encountered a '@' character
- function stateMentionAtChar(stateMachine, char) {
- if (isMentionTextChar(char)) {
- // '@' char with valid mention text char following
- stateMachine.state = 31 /* MentionTextChar */;
- stateMachine.acceptStateReached = true;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- // Handles the state when we're currently in the mention's text chars
- function stateMentionTextChar(stateMachine, char) {
- if (isMentionTextChar(char)) ;
- else if (alphaNumericAndMarksRe.test(char)) {
- // Char is invalid for a mention text char, not a valid match.
- // Note that ascii alphanumeric chars are okay (which are tested
- // in the previous 'if' statement, but others are not)
- remove(stateMachines, stateMachine);
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- function statePhoneNumberPlus(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 38 /* PhoneNumberDigit */;
- }
- else {
- remove(stateMachines, stateMachine);
- // This character may start a new match. Add states for it
- stateNoMatch(char);
- }
- }
- function statePhoneNumberOpenParen(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 33 /* PhoneNumberAreaCodeDigit1 */;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- // It's also possible that the paren was just an open brace for
- // a piece of text. Start other machines
- stateNoMatch(char);
- }
- function statePhoneNumberAreaCodeDigit1(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 34 /* PhoneNumberAreaCodeDigit2 */;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- function statePhoneNumberAreaCodeDigit2(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 35 /* PhoneNumberAreaCodeDigit3 */;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- function statePhoneNumberAreaCodeDigit3(stateMachine, char) {
- if (char === ')') {
- stateMachine.state = 36 /* PhoneNumberCloseParen */;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- function statePhoneNumberCloseParen(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 38 /* PhoneNumberDigit */;
- }
- else if (isPhoneNumberSeparatorChar(char)) {
- stateMachine.state = 39 /* PhoneNumberSeparator */;
- }
- else {
- remove(stateMachines, stateMachine);
- }
- }
- function statePhoneNumberDigit(stateMachine, char) {
- // For now, if we've reached any digits, we'll say that the machine
- // has reached its accept state. The phone regex will confirm the
- // match later.
- // Alternatively, we could count the number of digits to avoid
- // invoking the phone number regex
- stateMachine.acceptStateReached = true;
- if (isPhoneNumberControlChar(char)) {
- stateMachine.state = 40 /* PhoneNumberControlChar */;
- }
- else if (char === '#') {
- stateMachine.state = 41 /* PhoneNumberPoundChar */;
- }
- else if (digitRe.test(char)) ;
- else if (char === '(') {
- stateMachine.state = 32 /* PhoneNumberOpenParen */;
- }
- else if (isPhoneNumberSeparatorChar(char)) {
- stateMachine.state = 39 /* PhoneNumberSeparator */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- // The transition from a digit character to a letter can be the
- // start of a new scheme URL match
- if (isSchemeStartChar(char)) {
- stateMachines.push(createSchemeUrlStateMachine(charIdx, 0 /* SchemeChar */));
- }
- }
- }
- function statePhoneNumberSeparator(stateMachine, char) {
- if (digitRe.test(char)) {
- stateMachine.state = 38 /* PhoneNumberDigit */;
- }
- else if (char === '(') {
- stateMachine.state = 32 /* PhoneNumberOpenParen */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- // This character may start a new match. Add states for it
- stateNoMatch(char);
- }
- }
- // The ";" characters is "wait" in a phone number
- // The "," characters is "pause" in a phone number
- function statePhoneNumberControlChar(stateMachine, char) {
- if (isPhoneNumberControlChar(char)) ;
- else if (char === '#') {
- stateMachine.state = 41 /* PhoneNumberPoundChar */;
- }
- else if (digitRe.test(char)) {
- stateMachine.state = 38 /* PhoneNumberDigit */;
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- // The "#" characters is "pound" in a phone number
- function statePhoneNumberPoundChar(stateMachine, char) {
- if (isPhoneNumberControlChar(char)) {
- stateMachine.state = 40 /* PhoneNumberControlChar */;
- }
- else if (digitRe.test(char)) {
- // According to some of the older tests, if there's a digit
- // after a '#' sign, the match is invalid. TODO: Revisit if this is true
- remove(stateMachines, stateMachine);
- }
- else {
- captureMatchIfValidAndRemove(stateMachine);
- }
- }
- /*
- * Captures a match if it is valid (i.e. has a full domain name for a
- * TLD match). If a match is not valid, it is possible that we want to
- * keep reading characters in order to make a full match.
- */
- function captureMatchIfValidAndRemove(stateMachine) {
- // Remove the state machine first. There are a number of code paths
- // which return out of this function early, so make sure we have
- // this done
- remove(stateMachines, stateMachine);
- // Make sure the state machine being checked has actually reached an
- // "accept" state. If it hasn't reach one, it can't be a match
- if (!stateMachine.acceptStateReached) {
- return;
- }
- var startIdx = stateMachine.startIdx;
- var matchedText = text.slice(stateMachine.startIdx, charIdx);
- // Handle any unbalanced braces (parens, square brackets, or curly
- // brackets) inside the URL. This handles situations like:
- // The link (google.com)
- // and
- // Check out this link here (en.wikipedia.org/wiki/IANA_(disambiguation))
- //
- // And also remove any punctuation chars at the end such as:
- // '?', ',', ':', '.', etc.
- matchedText = excludeUnbalancedTrailingBracesAndPunctuation(matchedText);
- if (stateMachine.type === 'url') {
- // We don't want to accidentally match a URL that is preceded by an
- // '@' character, which would be an email address
- var charBeforeUrlMatch = text.charAt(stateMachine.startIdx - 1);
- if (charBeforeUrlMatch === '@') {
- return;
- }
- // For the purpose of this parser, we've generalized 'www'
- // matches as part of 'tld' matches. However, for backward
- // compatibility, we distinguish beween TLD matches and matches
- // that begin with 'www.' so that users may turn off 'www'
- // matches. As such, we need to correct for that now if the
- // URL begins with 'www.'
- var urlMatchType = stateMachine.matchType;
- if (urlMatchType === 'scheme') {
- // Autolinker accepts many characters in a url's scheme (like `fake://test.com`).
- // However, in cases where a URL is missing whitespace before an obvious link,
- // (for example: `nowhitespacehttp://www.test.com`), we only want the match to start
- // at the http:// part. We will check if the match contains a common scheme and then
- // shift the match to start from there.
- var httpSchemeMatch = httpSchemeRe.exec(matchedText);
- if (httpSchemeMatch) {
- // If we found an overmatched URL, we want to find the index
- // of where the match should start and shift the match to
- // start from the beginning of the common scheme
- startIdx = startIdx + httpSchemeMatch.index;
- matchedText = matchedText.slice(httpSchemeMatch.index);
- }
- if (!isValidSchemeUrl(matchedText)) {
- return; // not a valid match
- }
- }
- else if (urlMatchType === 'tld') {
- if (!isValidTldMatch(matchedText)) {
- return; // not a valid match
- }
- }
- else if (urlMatchType === 'ipV4') {
- if (!isValidIpV4Address(matchedText)) {
- return; // not a valid match
- }
- }
- else {
- assertNever(urlMatchType);
- }
- matches.push(new UrlMatch({
- tagBuilder: tagBuilder,
- matchedText: matchedText,
- offset: startIdx,
- urlMatchType: urlMatchType,
- url: matchedText,
- protocolRelativeMatch: matchedText.slice(0, 2) === '//',
- // TODO: Do these settings need to be passed to the match,
- // or should we handle them here in UrlMatcher?
- stripPrefix: stripPrefix,
- stripTrailingSlash: stripTrailingSlash,
- decodePercentEncoding: decodePercentEncoding,
- }));
- }
- else if (stateMachine.type === 'email') {
- // if the email address has a valid TLD, add it to the list of matches
- if (isValidEmail(matchedText)) {
- matches.push(new EmailMatch({
- tagBuilder: tagBuilder,
- matchedText: matchedText,
- offset: startIdx,
- email: matchedText.replace(mailtoSchemePrefixRe, ''),
- }));
- }
- }
- else if (stateMachine.type === 'hashtag') {
- if (isValidHashtag(matchedText)) {
- matches.push(new HashtagMatch({
- tagBuilder: tagBuilder,
- matchedText: matchedText,
- offset: startIdx,
- serviceName: hashtagServiceName,
- hashtag: matchedText.slice(1),
- }));
- }
- }
- else if (stateMachine.type === 'mention') {
- if (isValidMention(matchedText, mentionServiceName)) {
- matches.push(new MentionMatch({
- tagBuilder: tagBuilder,
- matchedText: matchedText,
- offset: startIdx,
- serviceName: mentionServiceName,
- mention: matchedText.slice(1), // strip off the '@' character at the beginning
- }));
- }
- }
- else if (stateMachine.type === 'phone') {
- // remove any trailing spaces that were considered as "separator"
- // chars by the state machine
- matchedText = matchedText.replace(/ +$/g, '');
- if (isValidPhoneNumber(matchedText)) {
- var cleanNumber = matchedText.replace(/[^0-9,;#]/g, ''); // strip out non-digit characters exclude comma semicolon and #
- matches.push(new PhoneMatch({
- tagBuilder: tagBuilder,
- matchedText: matchedText,
- offset: startIdx,
- number: cleanNumber,
- plusSign: matchedText.charAt(0) === '+',
- }));
- }
- }
- else {
- assertNever(stateMachine);
- }
- }
- }
- var openBraceRe = /[\(\{\[]/;
- var closeBraceRe = /[\)\}\]]/;
- var oppositeBrace = {
- ')': '(',
- '}': '{',
- ']': '[',
- };
- /**
- * Determines if a match found has unmatched closing parenthesis,
- * square brackets or curly brackets. If so, these unbalanced symbol(s) will be
- * removed from the URL match itself.
- *
- * A match may have an extra closing parenthesis/square brackets/curly brackets
- * at the end of the match because these are valid URL path characters. For
- * example, "wikipedia.com/something_(disambiguation)" should be auto-linked.
- *
- * However, an extra parenthesis *will* be included when the URL itself is
- * wrapped in parenthesis, such as in the case of:
- *
- * "(wikipedia.com/something_(disambiguation))"
- *
- * In this case, the last closing parenthesis should *not* be part of the
- * URL itself, and this method will exclude it from the returned URL.
- *
- * For square brackets in URLs such as in PHP arrays, the same behavior as
- * parenthesis discussed above should happen:
- *
- * "[http://www.example.com/foo.php?bar[]=1&bar[]=2&bar[]=3]"
- *
- * The very last closing square bracket should not be part of the URL itself,
- * and therefore this method will remove it.
- *
- * @param matchedText The full matched URL/email/hashtag/etc. from the state
- * machine parser.
- * @return The updated matched text with extraneous suffix characters removed.
- */
- function excludeUnbalancedTrailingBracesAndPunctuation(matchedText) {
- var braceCounts = {
- '(': 0,
- '{': 0,
- '[': 0,
- };
- for (var i = 0; i < matchedText.length; i++) {
- var char_1 = matchedText.charAt(i);
- if (openBraceRe.test(char_1)) {
- braceCounts[char_1]++;
- }
- else if (closeBraceRe.test(char_1)) {
- braceCounts[oppositeBrace[char_1]]--;
- }
- }
- var endIdx = matchedText.length - 1;
- var char;
- while (endIdx >= 0) {
- char = matchedText.charAt(endIdx);
- if (closeBraceRe.test(char)) {
- var oppositeBraceChar = oppositeBrace[char];
- if (braceCounts[oppositeBraceChar] < 0) {
- braceCounts[oppositeBraceChar]++;
- endIdx--;
- }
- else {
- break;
- }
- }
- else if (urlSuffixedCharsNotAllowedAtEndRe.test(char)) {
- // Walk back a punctuation char like '?', ',', ':', '.', etc.
- endIdx--;
- }
- else {
- break;
- }
- }
- return matchedText.slice(0, endIdx + 1);
- }
- function createSchemeUrlStateMachine(startIdx, state) {
- return {
- type: 'url',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- matchType: 'scheme',
- };
- }
- function createTldUrlStateMachine(startIdx, state) {
- return {
- type: 'url',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- matchType: 'tld',
- };
- }
- function createIpV4UrlStateMachine(startIdx, state) {
- return {
- type: 'url',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- matchType: 'ipV4',
- octetsEncountered: 1, // starts at 1 because we create this machine when encountering the first octet
- };
- }
- function createEmailStateMachine(startIdx, state) {
- return {
- type: 'email',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- };
- }
- function createHashtagStateMachine(startIdx, state) {
- return {
- type: 'hashtag',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- };
- }
- function createMentionStateMachine(startIdx, state) {
- return {
- type: 'mention',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- };
- }
- function createPhoneNumberStateMachine(startIdx, state) {
- return {
- type: 'phone',
- startIdx: startIdx,
- state: state,
- acceptStateReached: false,
- };
- }
- // For debugging: search for other "For debugging" lines
- // import CliTable from 'cli-table';
- /**
- * Parses an HTML string, calling the callbacks to notify of tags and text.
- *
- * ## History
- *
- * This file previously used a regular expression to find html tags in the input
- * text. Unfortunately, we ran into a bunch of catastrophic backtracking issues
- * with certain input text, causing Autolinker to either hang or just take a
- * really long time to parse the string.
- *
- * The current code is intended to be a O(n) algorithm that walks through
- * the string in one pass, and tries to be as cheap as possible. We don't need
- * to implement the full HTML spec, but rather simply determine where the string
- * looks like an HTML tag, and where it looks like text (so that we can autolink
- * that).
- *
- * This state machine parser is intended just to be a simple but performant
- * parser of HTML for the subset of requirements we have. We simply need to:
- *
- * 1. Determine where HTML tags are
- * 2. Determine the tag name (Autolinker specifically only cares about <a>,
- * <script>, and <style> tags, so as not to link any text within them)
- *
- * We don't need to:
- *
- * 1. Create a parse tree
- * 2. Auto-close tags with invalid markup
- * 3. etc.
- *
- * The other intention behind this is that we didn't want to add external
- * dependencies on the Autolinker utility which would increase its size. For
- * instance, adding htmlparser2 adds 125kb to the minified output file,
- * increasing its final size from 47kb to 172kb (at the time of writing). It
- * also doesn't work exactly correctly, treating the string "<3 blah blah blah"
- * as an HTML tag.
- *
- * Reference for HTML spec:
- *
- * https://www.w3.org/TR/html51/syntax.html#sec-tokenization
- *
- * @param {String} html The HTML to parse
- * @param {Object} callbacks
- * @param {Function} callbacks.onOpenTag Callback function to call when an open
- * tag is parsed. Called with the tagName as its argument.
- * @param {Function} callbacks.onCloseTag Callback function to call when a close
- * tag is parsed. Called with the tagName as its argument. If a self-closing
- * tag is found, `onCloseTag` is called immediately after `onOpenTag`.
- * @param {Function} callbacks.onText Callback function to call when text (i.e
- * not an HTML tag) is parsed. Called with the text (string) as its first
- * argument, and offset (number) into the string as its second.
- */
- function parseHtml(html, _a) {
- var onOpenTag = _a.onOpenTag, onCloseTag = _a.onCloseTag, onText = _a.onText, onComment = _a.onComment, onDoctype = _a.onDoctype;
- var noCurrentTag = new CurrentTag();
- var charIdx = 0, len = html.length, state = 0 /* Data */, currentDataIdx = 0, // where the current data start index is
- currentTag = noCurrentTag; // describes the current tag that is being read
- // For debugging: search for other "For debugging" lines
- // const table = new CliTable( {
- // head: [ 'charIdx', 'char', 'state', 'currentDataIdx', 'currentOpenTagIdx', 'tag.type' ]
- // } );
- while (charIdx < len) {
- var char = html.charAt(charIdx);
- // For debugging: search for other "For debugging" lines
- // ALSO: Temporarily remove the 'const' keyword on the State enum
- // table.push(
- // [ charIdx, char, State[ state ], currentDataIdx, currentTag.idx, currentTag.idx === -1 ? '' : currentTag.type ]
- // );
- switch (state) {
- case 0 /* Data */:
- stateData(char);
- break;
- case 1 /* TagOpen */:
- stateTagOpen(char);
- break;
- case 2 /* EndTagOpen */:
- stateEndTagOpen(char);
- break;
- case 3 /* TagName */:
- stateTagName(char);
- break;
- case 4 /* BeforeAttributeName */:
- stateBeforeAttributeName(char);
- break;
- case 5 /* AttributeName */:
- stateAttributeName(char);
- break;
- case 6 /* AfterAttributeName */:
- stateAfterAttributeName(char);
- break;
- case 7 /* BeforeAttributeValue */:
- stateBeforeAttributeValue(char);
- break;
- case 8 /* AttributeValueDoubleQuoted */:
- stateAttributeValueDoubleQuoted(char);
- break;
- case 9 /* AttributeValueSingleQuoted */:
- stateAttributeValueSingleQuoted(char);
- break;
- case 10 /* AttributeValueUnquoted */:
- stateAttributeValueUnquoted(char);
- break;
- case 11 /* AfterAttributeValueQuoted */:
- stateAfterAttributeValueQuoted(char);
- break;
- case 12 /* SelfClosingStartTag */:
- stateSelfClosingStartTag(char);
- break;
- case 13 /* MarkupDeclarationOpenState */:
- stateMarkupDeclarationOpen();
- break;
- case 14 /* CommentStart */:
- stateCommentStart(char);
- break;
- case 15 /* CommentStartDash */:
- stateCommentStartDash(char);
- break;
- case 16 /* Comment */:
- stateComment(char);
- break;
- case 17 /* CommentEndDash */:
- stateCommentEndDash(char);
- break;
- case 18 /* CommentEnd */:
- stateCommentEnd(char);
- break;
- case 19 /* CommentEndBang */:
- stateCommentEndBang(char);
- break;
- case 20 /* Doctype */:
- stateDoctype(char);
- break;
- default:
- assertNever(state);
- }
- // For debugging: search for other "For debugging" lines
- // ALSO: Temporarily remove the 'const' keyword on the State enum
- // table.push(
- // [ charIdx, char, State[ state ], currentDataIdx, currentTag.idx, currentTag.idx === -1 ? '' : currentTag.type ]
- // );
- charIdx++;
- }
- if (currentDataIdx < charIdx) {
- emitText();
- }
- // For debugging: search for other "For debugging" lines
- // console.log( '\n' + table.toString() );
- // Called when non-tags are being read (i.e. the text around HTML †ags)
- // https://www.w3.org/TR/html51/syntax.html#data-state
- function stateData(char) {
- if (char === '<') {
- startNewTag();
- }
- }
- // Called after a '<' is read from the Data state
- // https://www.w3.org/TR/html51/syntax.html#tag-open-state
- function stateTagOpen(char) {
- if (char === '!') {
- state = 13 /* MarkupDeclarationOpenState */;
- }
- else if (char === '/') {
- state = 2 /* EndTagOpen */;
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { isClosing: true }));
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else if (letterRe.test(char)) {
- // tag name start (and no '/' read)
- state = 3 /* TagName */;
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { isOpening: true }));
- }
- else {
- // Any other
- state = 0 /* Data */;
- currentTag = noCurrentTag;
- }
- }
- // After a '<x', '</x' sequence is read (where 'x' is a letter character),
- // this is to continue reading the tag name
- // https://www.w3.org/TR/html51/syntax.html#tag-name-state
- function stateTagName(char) {
- if (whitespaceRe.test(char)) {
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { name: captureTagName() }));
- state = 4 /* BeforeAttributeName */;
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else if (char === '/') {
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { name: captureTagName() }));
- state = 12 /* SelfClosingStartTag */;
- }
- else if (char === '>') {
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { name: captureTagName() }));
- emitTagAndPreviousTextNode(); // resets to Data state as well
- }
- else if (!letterRe.test(char) && !digitRe.test(char) && char !== ':') {
- // Anything else that does not form an html tag. Note: the colon
- // character is accepted for XML namespaced tags
- resetToDataState();
- }
- else ;
- }
- // Called after the '/' is read from a '</' sequence
- // https://www.w3.org/TR/html51/syntax.html#end-tag-open-state
- function stateEndTagOpen(char) {
- if (char === '>') {
- // parse error. Encountered "</>". Skip it without treating as a tag
- resetToDataState();
- }
- else if (letterRe.test(char)) {
- state = 3 /* TagName */;
- }
- else {
- // some other non-tag-like character, don't treat this as a tag
- resetToDataState();
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#before-attribute-name-state
- function stateBeforeAttributeName(char) {
- if (whitespaceRe.test(char)) ;
- else if (char === '/') {
- state = 12 /* SelfClosingStartTag */;
- }
- else if (char === '>') {
- emitTagAndPreviousTextNode(); // resets to Data state as well
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else if (char === "=" || quoteRe.test(char) || controlCharsRe.test(char)) {
- // "Parse error" characters that, according to the spec, should be
- // appended to the attribute name, but we'll treat these characters
- // as not forming a real HTML tag
- resetToDataState();
- }
- else {
- // Any other char, start of a new attribute name
- state = 5 /* AttributeName */;
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#attribute-name-state
- function stateAttributeName(char) {
- if (whitespaceRe.test(char)) {
- state = 6 /* AfterAttributeName */;
- }
- else if (char === '/') {
- state = 12 /* SelfClosingStartTag */;
- }
- else if (char === '=') {
- state = 7 /* BeforeAttributeValue */;
- }
- else if (char === '>') {
- emitTagAndPreviousTextNode(); // resets to Data state as well
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else if (quoteRe.test(char)) {
- // "Parse error" characters that, according to the spec, should be
- // appended to the attribute name, but we'll treat these characters
- // as not forming a real HTML tag
- resetToDataState();
- }
- else ;
- }
- // https://www.w3.org/TR/html51/syntax.html#after-attribute-name-state
- function stateAfterAttributeName(char) {
- if (whitespaceRe.test(char)) ;
- else if (char === '/') {
- state = 12 /* SelfClosingStartTag */;
- }
- else if (char === '=') {
- state = 7 /* BeforeAttributeValue */;
- }
- else if (char === '>') {
- emitTagAndPreviousTextNode();
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else if (quoteRe.test(char)) {
- // "Parse error" characters that, according to the spec, should be
- // appended to the attribute name, but we'll treat these characters
- // as not forming a real HTML tag
- resetToDataState();
- }
- else {
- // Any other character, start a new attribute in the current tag
- state = 5 /* AttributeName */;
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#before-attribute-value-state
- function stateBeforeAttributeValue(char) {
- if (whitespaceRe.test(char)) ;
- else if (char === "\"") {
- state = 8 /* AttributeValueDoubleQuoted */;
- }
- else if (char === "'") {
- state = 9 /* AttributeValueSingleQuoted */;
- }
- else if (/[>=`]/.test(char)) {
- // Invalid chars after an '=' for an attribute value, don't count
- // the current tag as an HTML tag
- resetToDataState();
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else {
- // Any other character, consider it an unquoted attribute value
- state = 10 /* AttributeValueUnquoted */;
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#attribute-value-double-quoted-state
- function stateAttributeValueDoubleQuoted(char) {
- if (char === "\"") {
- // end the current double-quoted attribute
- state = 11 /* AfterAttributeValueQuoted */;
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#attribute-value-single-quoted-state
- function stateAttributeValueSingleQuoted(char) {
- if (char === "'") {
- // end the current single-quoted attribute
- state = 11 /* AfterAttributeValueQuoted */;
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#attribute-value-unquoted-state
- function stateAttributeValueUnquoted(char) {
- if (whitespaceRe.test(char)) {
- state = 4 /* BeforeAttributeName */;
- }
- else if (char === '>') {
- emitTagAndPreviousTextNode();
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else ;
- }
- // https://www.w3.org/TR/html51/syntax.html#after-attribute-value-quoted-state
- function stateAfterAttributeValueQuoted(char) {
- if (whitespaceRe.test(char)) {
- state = 4 /* BeforeAttributeName */;
- }
- else if (char === '/') {
- state = 12 /* SelfClosingStartTag */;
- }
- else if (char === '>') {
- emitTagAndPreviousTextNode();
- }
- else if (char === '<') {
- // start of another tag (ignore the previous, incomplete one)
- startNewTag();
- }
- else {
- // Any other character, "parse error". Spec says to switch to the
- // BeforeAttributeState and re-consume the character, as it may be
- // the start of a new attribute name
- state = 4 /* BeforeAttributeName */;
- reconsumeCurrentCharacter();
- }
- }
- // A '/' has just been read in the current tag (presumably for '/>'), and
- // this handles the next character
- // https://www.w3.org/TR/html51/syntax.html#self-closing-start-tag-state
- function stateSelfClosingStartTag(char) {
- if (char === '>') {
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { isClosing: true }));
- emitTagAndPreviousTextNode(); // resets to Data state as well
- }
- else {
- state = 4 /* BeforeAttributeName */;
- }
- }
- // https://www.w3.org/TR/html51/syntax.html#markup-declaration-open-state
- // (HTML Comments or !DOCTYPE)
- function stateMarkupDeclarationOpen(char) {
- if (html.substr(charIdx, 2) === '--') {
- // html comment
- charIdx += 2; // "consume" characters
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { type: 'comment' }));
- state = 14 /* CommentStart */;
- }
- else if (html.substr(charIdx, 7).toUpperCase() === 'DOCTYPE') {
- charIdx += 7; // "consume" characters
- currentTag = new CurrentTag(__assign(__assign({}, currentTag), { type: 'doctype' }));
- state = 20 /* Doctype */;
- }
- else {
- // At this point, the spec specifies that the state machine should
- // enter the "bogus comment" state, in which case any character(s)
- // after the '<!' that were read should become an HTML comment up
- // until the first '>' that is read (or EOF). Instead, we'll assume
- // that a user just typed '<!' as part of text data
- resetToDataState();
- }
- }
- // Handles after the sequence '<!--' has been read
- // https://www.w3.org/TR/html51/syntax.html#comment-start-state
- function stateCommentStart(char) {
- if (char === '-') {
- // We've read the sequence '<!---' at this point (3 dashes)
- state = 15 /* CommentStartDash */;
- }
- else if (char === '>') {
- // At this point, we'll assume the comment wasn't a real comment
- // so we'll just emit it as data. We basically read the sequence
- // '<!-->'
- resetToDataState();
- }
- else {
- // Any other char, take it as part of the comment
- state = 16 /* Comment */;
- }
- }
- // We've read the sequence '<!---' at this point (3 dashes)
- // https://www.w3.org/TR/html51/syntax.html#comment-start-dash-state
- function stateCommentStartDash(char) {
- if (char === '-') {
- // We've read '<!----' (4 dashes) at this point
- state = 18 /* CommentEnd */;
- }
- else if (char === '>') {
- // At this point, we'll assume the comment wasn't a real comment
- // so we'll just emit it as data. We basically read the sequence
- // '<!--->'
- resetToDataState();
- }
- else {
- // Anything else, take it as a valid comment
- state = 16 /* Comment */;
- }
- }
- // Currently reading the comment's text (data)
- // https://www.w3.org/TR/html51/syntax.html#comment-state
- function stateComment(char) {
- if (char === '-') {
- state = 17 /* CommentEndDash */;
- }
- }
- // When we we've read the first dash inside a comment, it may signal the
- // end of the comment if we read another dash
- // https://www.w3.org/TR/html51/syntax.html#comment-end-dash-state
- function stateCommentEndDash(char) {
- if (char === '-') {
- state = 18 /* CommentEnd */;
- }
- else {
- // Wasn't a dash, must still be part of the comment
- state = 16 /* Comment */;
- }
- }
- // After we've read two dashes inside a comment, it may signal the end of
- // the comment if we then read a '>' char
- // https://www.w3.org/TR/html51/syntax.html#comment-end-state
- function stateCommentEnd(char) {
- if (char === '>') {
- emitTagAndPreviousTextNode();
- }
- else if (char === '!') {
- state = 19 /* CommentEndBang */;
- }
- else if (char === '-') ;
- else {
- // Anything else, switch back to the comment state since we didn't
- // read the full "end comment" sequence (i.e. '-->')
- state = 16 /* Comment */;
- }
- }
- // We've read the sequence '--!' inside of a comment
- // https://www.w3.org/TR/html51/syntax.html#comment-end-bang-state
- function stateCommentEndBang(char) {
- if (char === '-') {
- // We read the sequence '--!-' inside of a comment. The last dash
- // could signify that the comment is going to close
- state = 17 /* CommentEndDash */;
- }
- else if (char === '>') {
- // End of comment with the sequence '--!>'
- emitTagAndPreviousTextNode();
- }
- else {
- // The '--!' was not followed by a '>', continue reading the
- // comment's text
- state = 16 /* Comment */;
- }
- }
- /**
- * For DOCTYPES in particular, we don't care about the attributes. Just
- * advance to the '>' character and emit the tag, unless we find a '<'
- * character in which case we'll start a new tag.
- *
- * Example doctype tag:
- * <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
- *
- * Actual spec: https://www.w3.org/TR/html51/syntax.html#doctype-state
- */
- function stateDoctype(char) {
- if (char === '>') {
- emitTagAndPreviousTextNode();
- }
- else if (char === '<') {
- startNewTag();
- }
- else ;
- }
- /**
- * Resets the state back to the Data state, and removes the current tag.
- *
- * We'll generally run this function whenever a "parse error" is
- * encountered, where the current tag that is being read no longer looks
- * like a real HTML tag.
- */
- function resetToDataState() {
- state = 0 /* Data */;
- currentTag = noCurrentTag;
- }
- /**
- * Starts a new HTML tag at the current index, ignoring any previous HTML
- * tag that was being read.
- *
- * We'll generally run this function whenever we read a new '<' character,
- * including when we read a '<' character inside of an HTML tag that we were
- * previously reading.
- */
- function startNewTag() {
- state = 1 /* TagOpen */;
- currentTag = new CurrentTag({ idx: charIdx });
- }
- /**
- * Once we've decided to emit an open tag, that means we can also emit the
- * text node before it.
- */
- function emitTagAndPreviousTextNode() {
- var textBeforeTag = html.slice(currentDataIdx, currentTag.idx);
- if (textBeforeTag) {
- // the html tag was the first element in the html string, or two
- // tags next to each other, in which case we should not emit a text
- // node
- onText(textBeforeTag, currentDataIdx);
- }
- if (currentTag.type === 'comment') {
- onComment(currentTag.idx);
- }
- else if (currentTag.type === 'doctype') {
- onDoctype(currentTag.idx);
- }
- else {
- if (currentTag.isOpening) {
- onOpenTag(currentTag.name, currentTag.idx);
- }
- if (currentTag.isClosing) {
- // note: self-closing tags will emit both opening and closing
- onCloseTag(currentTag.name, currentTag.idx);
- }
- }
- // Since we just emitted a tag, reset to the data state for the next char
- resetToDataState();
- currentDataIdx = charIdx + 1;
- }
- function emitText() {
- var text = html.slice(currentDataIdx, charIdx);
- onText(text, currentDataIdx);
- currentDataIdx = charIdx + 1;
- }
- /**
- * Captures the tag name from the start of the tag to the current character
- * index, and converts it to lower case
- */
- function captureTagName() {
- var startIdx = currentTag.idx + (currentTag.isClosing ? 2 : 1);
- return html.slice(startIdx, charIdx).toLowerCase();
- }
- /**
- * Causes the main loop to re-consume the current character, such as after
- * encountering a "parse error" that changed state and needs to reconsume
- * the same character in that new state.
- */
- function reconsumeCurrentCharacter() {
- charIdx--;
- }
- }
- var CurrentTag = /** @class */ (function () {
- function CurrentTag(cfg) {
- if (cfg === void 0) { cfg = {}; }
- this.idx = cfg.idx !== undefined ? cfg.idx : -1;
- this.type = cfg.type || 'tag';
- this.name = cfg.name || '';
- this.isOpening = !!cfg.isOpening;
- this.isClosing = !!cfg.isClosing;
- }
- return CurrentTag;
- }());
- /**
- * @class Autolinker
- * @extends Object
- *
- * Utility class used to process a given string of text, and wrap the matches in
- * the appropriate anchor (<a>) tags to turn them into links.
- *
- * Any of the configuration options may be provided in an Object provided
- * to the Autolinker constructor, which will configure how the {@link #link link()}
- * method will process the links.
- *
- * For example:
- *
- * var autolinker = new Autolinker( {
- * newWindow : false,
- * truncate : 30
- * } );
- *
- * var html = autolinker.link( "Joe went to www.yahoo.com" );
- * // produces: 'Joe went to <a href="http://www.yahoo.com">yahoo.com</a>'
- *
- *
- * The {@link #static-link static link()} method may also be used to inline
- * options into a single call, which may be more convenient for one-off uses.
- * For example:
- *
- * var html = Autolinker.link( "Joe went to www.yahoo.com", {
- * newWindow : false,
- * truncate : 30
- * } );
- * // produces: 'Joe went to <a href="http://www.yahoo.com">yahoo.com</a>'
- *
- *
- * ## Custom Replacements of Links
- *
- * If the configuration options do not provide enough flexibility, a {@link #replaceFn}
- * may be provided to fully customize the output of Autolinker. This function is
- * called once for each URL/Email/Phone#/Hashtag/Mention (Twitter, Instagram, Soundcloud)
- * match that is encountered.
- *
- * For example:
- *
- * var input = "..."; // string with URLs, Email Addresses, Phone #s, Hashtags, and Mentions (Twitter, Instagram, Soundcloud)
- *
- * var linkedText = Autolinker.link( input, {
- * replaceFn : function( match ) {
- * console.log( "href = ", match.getAnchorHref() );
- * console.log( "text = ", match.getAnchorText() );
- *
- * switch( match.getType() ) {
- * case 'url' :
- * console.log( "url: ", match.getUrl() );
- *
- * if( match.getUrl().indexOf( 'mysite.com' ) === -1 ) {
- * var tag = match.buildTag(); // returns an `Autolinker.HtmlTag` instance, which provides mutator methods for easy changes
- * tag.setAttr( 'rel', 'nofollow' );
- * tag.addClass( 'external-link' );
- *
- * return tag;
- *
- * } else {
- * return true; // let Autolinker perform its normal anchor tag replacement
- * }
- *
- * case 'email' :
- * var email = match.getEmail();
- * console.log( "email: ", email );
- *
- * if( email === "my@own.address" ) {
- * return false; // don't auto-link this particular email address; leave as-is
- * } else {
- * return; // no return value will have Autolinker perform its normal anchor tag replacement (same as returning `true`)
- * }
- *
- * case 'phone' :
- * var phoneNumber = match.getPhoneNumber();
- * console.log( phoneNumber );
- *
- * return '<a href="http://newplace.to.link.phone.numbers.to/">' + phoneNumber + '</a>';
- *
- * case 'hashtag' :
- * var hashtag = match.getHashtag();
- * console.log( hashtag );
- *
- * return '<a href="http://newplace.to.link.hashtag.handles.to/">' + hashtag + '</a>';
- *
- * case 'mention' :
- * var mention = match.getMention();
- * console.log( mention );
- *
- * return '<a href="http://newplace.to.link.mention.to/">' + mention + '</a>';
- * }
- * }
- * } );
- *
- *
- * The function may return the following values:
- *
- * - `true` (Boolean): Allow Autolinker to replace the match as it normally
- * would.
- * - `false` (Boolean): Do not replace the current match at all - leave as-is.
- * - Any String: If a string is returned from the function, the string will be
- * used directly as the replacement HTML for the match.
- * - An {@link Autolinker.HtmlTag} instance, which can be used to build/modify
- * an HTML tag before writing out its HTML text.
- */
- var Autolinker = /** @class */ (function () {
- /**
- * @method constructor
- * @param {Object} [cfg] The configuration options for the Autolinker instance,
- * specified in an Object (map).
- */
- function Autolinker(cfg) {
- if (cfg === void 0) { cfg = {}; }
- /**
- * The Autolinker version number exposed on the instance itself.
- *
- * Ex: 0.25.1
- *
- * @property {String} version
- */
- this.version = Autolinker.version;
- /**
- * @cfg {Boolean/Object} [urls]
- *
- * `true` if URLs should be automatically linked, `false` if they should not
- * be. Defaults to `true`.
- *
- * Examples:
- *
- * urls: true
- *
- * // or
- *
- * urls: {
- * schemeMatches : true,
- * tldMatches : true,
- * ipV4Matches : true
- * }
- *
- * As shown above, this option also accepts an Object form with 3 properties
- * to allow for more customization of what exactly gets linked. All default
- * to `true`:
- *
- * @cfg {Boolean} [urls.schemeMatches] `true` to match URLs found prefixed
- * with a scheme, i.e. `http://google.com`, or `other+scheme://google.com`,
- * `false` to prevent these types of matches.
- * @cfg {Boolean} [urls.tldMatches] `true` to match URLs with known top
- * level domains (.com, .net, etc.) that are not prefixed with a scheme
- * (such as 'http://'). This option attempts to match anything that looks
- * like a URL in the given text. Ex: `google.com`, `asdf.org/?page=1`, etc.
- * `false` to prevent these types of matches.
- * @cfg {Boolean} [urls.ipV4Matches] `true` to match IPv4 addresses in text
- * that are not prefixed with a scheme (such as 'http://'). This option
- * attempts to match anything that looks like an IPv4 address in text. Ex:
- * `192.168.0.1`, `10.0.0.1/?page=1`, etc. `false` to prevent these types
- * of matches.
- */
- this.urls = {}; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} [email=true]
- *
- * `true` if email addresses should be automatically linked, `false` if they
- * should not be.
- */
- this.email = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} [phone=true]
- *
- * `true` if Phone numbers ("(555)555-5555") should be automatically linked,
- * `false` if they should not be.
- */
- this.phone = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean/String} [hashtag=false]
- *
- * A string for the service name to have hashtags (ex: "#myHashtag")
- * auto-linked to. The currently-supported values are:
- *
- * - 'twitter'
- * - 'facebook'
- * - 'instagram'
- *
- * Pass `false` to skip auto-linking of hashtags.
- */
- this.hashtag = false; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {String/Boolean} [mention=false]
- *
- * A string for the service name to have mentions (ex: "@myuser")
- * auto-linked to. The currently supported values are:
- *
- * - 'twitter'
- * - 'instagram'
- * - 'soundcloud'
- * - 'tiktok'
- *
- * Defaults to `false` to skip auto-linking of mentions.
- */
- this.mention = false; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} [newWindow=true]
- *
- * `true` if the links should open in a new window, `false` otherwise.
- */
- this.newWindow = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean/Object} [stripPrefix=true]
- *
- * `true` if 'http://' (or 'https://') and/or the 'www.' should be stripped
- * from the beginning of URL links' text, `false` otherwise. Defaults to
- * `true`.
- *
- * Examples:
- *
- * stripPrefix: true
- *
- * // or
- *
- * stripPrefix: {
- * scheme : true,
- * www : true
- * }
- *
- * As shown above, this option also accepts an Object form with 2 properties
- * to allow for more customization of what exactly is prevented from being
- * displayed. Both default to `true`:
- *
- * @cfg {Boolean} [stripPrefix.scheme] `true` to prevent the scheme part of
- * a URL match from being displayed to the user. Example:
- * `'http://google.com'` will be displayed as `'google.com'`. `false` to
- * not strip the scheme. NOTE: Only an `'http://'` or `'https://'` scheme
- * will be removed, so as not to remove a potentially dangerous scheme
- * (such as `'file://'` or `'javascript:'`)
- * @cfg {Boolean} [stripPrefix.www] www (Boolean): `true` to prevent the
- * `'www.'` part of a URL match from being displayed to the user. Ex:
- * `'www.google.com'` will be displayed as `'google.com'`. `false` to not
- * strip the `'www'`.
- */
- this.stripPrefix = {
- scheme: true,
- www: true,
- }; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} [stripTrailingSlash=true]
- *
- * `true` to remove the trailing slash from URL matches, `false` to keep
- * the trailing slash.
- *
- * Example when `true`: `http://google.com/` will be displayed as
- * `http://google.com`.
- */
- this.stripTrailingSlash = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} [decodePercentEncoding=true]
- *
- * `true` to decode percent-encoded characters in URL matches, `false` to keep
- * the percent-encoded characters.
- *
- * Example when `true`: `https://en.wikipedia.org/wiki/San_Jos%C3%A9` will
- * be displayed as `https://en.wikipedia.org/wiki/San_José`.
- */
- this.decodePercentEncoding = true; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Number/Object} [truncate=0]
- *
- * ## Number Form
- *
- * A number for how many characters matched text should be truncated to
- * inside the text of a link. If the matched text is over this number of
- * characters, it will be truncated to this length by adding a two period
- * ellipsis ('..') to the end of the string.
- *
- * For example: A url like 'http://www.yahoo.com/some/long/path/to/a/file'
- * truncated to 25 characters might look something like this:
- * 'yahoo.com/some/long/pat..'
- *
- * Example Usage:
- *
- * truncate: 25
- *
- *
- * Defaults to `0` for "no truncation."
- *
- *
- * ## Object Form
- *
- * An Object may also be provided with two properties: `length` (Number) and
- * `location` (String). `location` may be one of the following: 'end'
- * (default), 'middle', or 'smart'.
- *
- * Example Usage:
- *
- * truncate: { length: 25, location: 'middle' }
- *
- * @cfg {Number} [truncate.length=0] How many characters to allow before
- * truncation will occur. Defaults to `0` for "no truncation."
- * @cfg {"end"/"middle"/"smart"} [truncate.location="end"]
- *
- * - 'end' (default): will truncate up to the number of characters, and then
- * add an ellipsis at the end. Ex: 'yahoo.com/some/long/pat..'
- * - 'middle': will truncate and add the ellipsis in the middle. Ex:
- * 'yahoo.com/s..th/to/a/file'
- * - 'smart': for URLs where the algorithm attempts to strip out unnecessary
- * parts first (such as the 'www.', then URL scheme, hash, etc.),
- * attempting to make the URL human-readable before looking for a good
- * point to insert the ellipsis if it is still too long. Ex:
- * 'yahoo.com/some..to/a/file'. For more details, see
- * {@link Autolinker.truncate.TruncateSmart}.
- */
- this.truncate = {
- length: 0,
- location: 'end',
- }; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {String} className
- *
- * A CSS class name to add to the generated links. This class will be added
- * to all links, as well as this class plus match suffixes for styling
- * url/email/phone/hashtag/mention links differently.
- *
- * For example, if this config is provided as "myLink", then:
- *
- * - URL links will have the CSS classes: "myLink myLink-url"
- * - Email links will have the CSS classes: "myLink myLink-email", and
- * - Phone links will have the CSS classes: "myLink myLink-phone"
- * - Hashtag links will have the CSS classes: "myLink myLink-hashtag"
- * - Mention links will have the CSS classes: "myLink myLink-mention myLink-[type]"
- * where [type] is either "instagram", "twitter" or "soundcloud"
- */
- this.className = ''; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Function} replaceFn
- *
- * A function to individually process each match found in the input string.
- *
- * See the class's description for usage.
- *
- * The `replaceFn` can be called with a different context object (`this`
- * reference) using the {@link #context} cfg.
- *
- * This function is called with the following parameter:
- *
- * @cfg {Autolinker.match.Match} replaceFn.match The Match instance which
- * can be used to retrieve information about the match that the `replaceFn`
- * is currently processing. See {@link Autolinker.match.Match} subclasses
- * for details.
- */
- this.replaceFn = null; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Object} context
- *
- * The context object (`this` reference) to call the `replaceFn` with.
- *
- * Defaults to this Autolinker instance.
- */
- this.context = undefined; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @cfg {Boolean} [sanitizeHtml=false]
- *
- * `true` to HTML-encode the start and end brackets of existing HTML tags found
- * in the input string. This will escape `<` and `>` characters to `<` and
- * `>`, respectively.
- *
- * Setting this to `true` will prevent XSS (Cross-site Scripting) attacks,
- * but will remove the significance of existing HTML tags in the input string. If
- * you would like to maintain the significance of existing HTML tags while also
- * making the output HTML string safe, leave this option as `false` and use a
- * tool like https://github.com/cure53/DOMPurify (or others) on the input string
- * before running Autolinker.
- */
- this.sanitizeHtml = false; // default value just to get the above doc comment in the ES5 output and documentation generator
- /**
- * @private
- * @property {Autolinker.AnchorTagBuilder} tagBuilder
- *
- * The AnchorTagBuilder instance used to build match replacement anchor tags.
- * Note: this is lazily instantiated in the {@link #getTagBuilder} method.
- */
- this.tagBuilder = null;
- // Note: when `this.something` is used in the rhs of these assignments,
- // it refers to the default values set above the constructor
- this.urls = normalizeUrlsCfg(cfg.urls);
- this.email = isBoolean(cfg.email) ? cfg.email : this.email;
- this.phone = isBoolean(cfg.phone) ? cfg.phone : this.phone;
- this.hashtag = cfg.hashtag || this.hashtag;
- this.mention = cfg.mention || this.mention;
- this.newWindow = isBoolean(cfg.newWindow) ? cfg.newWindow : this.newWindow;
- this.stripPrefix = normalizeStripPrefixCfg(cfg.stripPrefix);
- this.stripTrailingSlash = isBoolean(cfg.stripTrailingSlash)
- ? cfg.stripTrailingSlash
- : this.stripTrailingSlash;
- this.decodePercentEncoding = isBoolean(cfg.decodePercentEncoding)
- ? cfg.decodePercentEncoding
- : this.decodePercentEncoding;
- this.sanitizeHtml = cfg.sanitizeHtml || false;
- // Validate the value of the `mention` cfg
- var mention = this.mention;
- if (mention !== false && mentionServices.indexOf(mention) === -1) {
- throw new Error("invalid `mention` cfg '".concat(mention, "' - see docs"));
- }
- // Validate the value of the `hashtag` cfg
- var hashtag = this.hashtag;
- if (hashtag !== false && hashtagServices.indexOf(hashtag) === -1) {
- throw new Error("invalid `hashtag` cfg '".concat(hashtag, "' - see docs"));
- }
- this.truncate = normalizeTruncateCfg(cfg.truncate);
- this.className = cfg.className || this.className;
- this.replaceFn = cfg.replaceFn || this.replaceFn;
- this.context = cfg.context || this;
- }
- /**
- * Automatically links URLs, Email addresses, Phone Numbers, Twitter handles,
- * Hashtags, and Mentions found in the given chunk of HTML. Does not link URLs
- * found within HTML tags.
- *
- * For instance, if given the text: `You should go to http://www.yahoo.com`,
- * then the result will be `You should go to <a href="http://www.yahoo.com">http://www.yahoo.com</a>`
- *
- * Example:
- *
- * var linkedText = Autolinker.link( "Go to google.com", { newWindow: false } );
- * // Produces: "Go to <a href="http://google.com">google.com</a>"
- *
- * @static
- * @param {String} textOrHtml The HTML or text to find matches within (depending
- * on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #mention},
- * {@link #hashtag}, and {@link #mention} options are enabled).
- * @param {Object} [options] Any of the configuration options for the Autolinker
- * class, specified in an Object (map). See the class description for an
- * example call.
- * @return {String} The HTML text, with matches automatically linked.
- */
- Autolinker.link = function (textOrHtml, options) {
- var autolinker = new Autolinker(options);
- return autolinker.link(textOrHtml);
- };
- /**
- * Parses the input `textOrHtml` looking for URLs, email addresses, phone
- * numbers, username handles, and hashtags (depending on the configuration
- * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match}
- * objects describing those matches (without making any replacements).
- *
- * Note that if parsing multiple pieces of text, it is slightly more efficient
- * to create an Autolinker instance, and use the instance-level {@link #parse}
- * method.
- *
- * Example:
- *
- * var matches = Autolinker.parse( "Hello google.com, I am asdf@asdf.com", {
- * urls: true,
- * email: true
- * } );
- *
- * console.log( matches.length ); // 2
- * console.log( matches[ 0 ].getType() ); // 'url'
- * console.log( matches[ 0 ].getUrl() ); // 'google.com'
- * console.log( matches[ 1 ].getType() ); // 'email'
- * console.log( matches[ 1 ].getEmail() ); // 'asdf@asdf.com'
- *
- * @static
- * @param {String} textOrHtml The HTML or text to find matches within
- * (depending on if the {@link #urls}, {@link #email}, {@link #phone},
- * {@link #hashtag}, and {@link #mention} options are enabled).
- * @param {Object} [options] Any of the configuration options for the Autolinker
- * class, specified in an Object (map). See the class description for an
- * example call.
- * @return {Autolinker.match.Match[]} The array of Matches found in the
- * given input `textOrHtml`.
- */
- Autolinker.parse = function (textOrHtml, options) {
- var autolinker = new Autolinker(options);
- return autolinker.parse(textOrHtml);
- };
- /**
- * Parses the input `textOrHtml` looking for URLs, email addresses, phone
- * numbers, username handles, and hashtags (depending on the configuration
- * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match}
- * objects describing those matches (without making any replacements).
- *
- * This method is used by the {@link #link} method, but can also be used to
- * simply do parsing of the input in order to discover what kinds of links
- * there are and how many.
- *
- * Example usage:
- *
- * var autolinker = new Autolinker( {
- * urls: true,
- * email: true
- * } );
- *
- * var matches = autolinker.parse( "Hello google.com, I am asdf@asdf.com" );
- *
- * console.log( matches.length ); // 2
- * console.log( matches[ 0 ].getType() ); // 'url'
- * console.log( matches[ 0 ].getUrl() ); // 'google.com'
- * console.log( matches[ 1 ].getType() ); // 'email'
- * console.log( matches[ 1 ].getEmail() ); // 'asdf@asdf.com'
- *
- * @param {String} textOrHtml The HTML or text to find matches within
- * (depending on if the {@link #urls}, {@link #email}, {@link #phone},
- * {@link #hashtag}, and {@link #mention} options are enabled).
- * @return {Autolinker.match.Match[]} The array of Matches found in the
- * given input `textOrHtml`.
- */
- Autolinker.prototype.parse = function (textOrHtml) {
- var _this = this;
- 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
- matches = [];
- // Find all matches within the `textOrHtml` (but not matches that are
- // already nested within <a>, <style> and <script> tags)
- parseHtml(textOrHtml, {
- onOpenTag: function (tagName) {
- if (skipTagNames.indexOf(tagName) >= 0) {
- skipTagsStackCount++;
- }
- },
- onText: function (text, offset) {
- // Only process text nodes that are not within an <a>, <style> or <script> tag
- if (skipTagsStackCount === 0) {
- // "Walk around" common HTML entities. An ' ' (for example)
- // could be at the end of a URL, but we don't want to
- // include the trailing '&' in the URL. See issue #76
- // TODO: Handle HTML entities separately in parseHtml() and
- // don't emit them as "text" except for & entities
- var htmlCharacterEntitiesRegex = /( | |<|<|>|>|"|"|')/gi; // NOTE: capturing group is significant to include the split characters in the .split() call below
- var textSplit = text.split(htmlCharacterEntitiesRegex);
- var currentOffset_1 = offset;
- textSplit.forEach(function (splitText, i) {
- // even number matches are text, odd numbers are html entities
- if (i % 2 === 0) {
- var textNodeMatches = _this.parseText(splitText, currentOffset_1);
- matches.push.apply(matches, textNodeMatches);
- }
- currentOffset_1 += splitText.length;
- });
- }
- },
- onCloseTag: function (tagName) {
- if (skipTagNames.indexOf(tagName) >= 0) {
- skipTagsStackCount = Math.max(skipTagsStackCount - 1, 0); // attempt to handle extraneous </a> tags by making sure the stack count never goes below 0
- }
- },
- onComment: function (_offset) { },
- onDoctype: function (_offset) { }, // no need to process doctype nodes
- });
- // After we have found all matches, remove subsequent matches that
- // overlap with a previous match. This can happen for instance with URLs,
- // where the url 'google.com/#link' would match '#link' as a hashtag.
- matches = this.compactMatches(matches);
- // And finally, remove matches for match types that have been turned
- // off. We needed to have all match types turned on initially so that
- // things like hashtags could be filtered out if they were really just
- // part of a URL match (for instance, as a named anchor).
- matches = this.removeUnwantedMatches(matches);
- return matches;
- };
- /**
- * After we have found all matches, we need to remove matches that overlap
- * with a previous match. This can happen for instance with URLs, where the
- * url 'google.com/#link' would match '#link' as a hashtag. Because the
- * '#link' part is contained in a larger match that comes before the HashTag
- * match, we'll remove the HashTag match.
- *
- * @private
- * @param {Autolinker.match.Match[]} matches
- * @return {Autolinker.match.Match[]}
- */
- Autolinker.prototype.compactMatches = function (matches) {
- // First, the matches need to be sorted in order of offset
- matches.sort(function (a, b) {
- return a.getOffset() - b.getOffset();
- });
- var i = 0;
- while (i < matches.length - 1) {
- var match = matches[i], offset = match.getOffset(), matchedTextLength = match.getMatchedText().length, endIdx = offset + matchedTextLength;
- if (i + 1 < matches.length) {
- // Remove subsequent matches that equal offset with current match
- if (matches[i + 1].getOffset() === offset) {
- var removeIdx = matches[i + 1].getMatchedText().length > matchedTextLength ? i : i + 1;
- matches.splice(removeIdx, 1);
- continue;
- }
- // Remove subsequent matches that overlap with the current match
- if (matches[i + 1].getOffset() < endIdx) {
- matches.splice(i + 1, 1);
- continue;
- }
- }
- i++;
- }
- return matches;
- };
- /**
- * Removes matches for matchers that were turned off in the options. For
- * example, if {@link #hashtag hashtags} were not to be matched, we'll
- * remove them from the `matches` array here.
- *
- * Note: we *must* use all Matchers on the input string, and then filter
- * them out later. For example, if the options were `{ url: false, hashtag: true }`,
- * we wouldn't want to match the text '#link' as a HashTag inside of the text
- * 'google.com/#link'. The way the algorithm works is that we match the full
- * URL first (which prevents the accidental HashTag match), and then we'll
- * simply throw away the URL match.
- *
- * @private
- * @param {Autolinker.match.Match[]} matches The array of matches to remove
- * the unwanted matches from. Note: this array is mutated for the
- * removals.
- * @return {Autolinker.match.Match[]} The mutated input `matches` array.
- */
- Autolinker.prototype.removeUnwantedMatches = function (matches) {
- if (!this.hashtag)
- removeWithPredicate(matches, function (match) {
- return match.getType() === 'hashtag';
- });
- if (!this.email)
- removeWithPredicate(matches, function (match) {
- return match.getType() === 'email';
- });
- if (!this.phone)
- removeWithPredicate(matches, function (match) {
- return match.getType() === 'phone';
- });
- if (!this.mention)
- removeWithPredicate(matches, function (match) {
- return match.getType() === 'mention';
- });
- if (!this.urls.schemeMatches) {
- removeWithPredicate(matches, function (m) {
- return m.getType() === 'url' && m.getUrlMatchType() === 'scheme';
- });
- }
- if (!this.urls.tldMatches) {
- removeWithPredicate(matches, function (m) { return m.getType() === 'url' && m.getUrlMatchType() === 'tld'; });
- }
- if (!this.urls.ipV4Matches) {
- removeWithPredicate(matches, function (m) { return m.getType() === 'url' && m.getUrlMatchType() === 'ipV4'; });
- }
- return matches;
- };
- /**
- * Parses the input `text` looking for URLs, email addresses, phone
- * numbers, username handles, and hashtags (depending on the configuration
- * of the Autolinker instance), and returns an array of {@link Autolinker.match.Match}
- * objects describing those matches.
- *
- * This method processes a **non-HTML string**, and is used to parse and
- * match within the text nodes of an HTML string. This method is used
- * internally by {@link #parse}.
- *
- * @private
- * @param {String} text The text to find matches within (depending on if the
- * {@link #urls}, {@link #email}, {@link #phone},
- * {@link #hashtag}, and {@link #mention} options are enabled). This must be a non-HTML string.
- * @param {Number} [offset=0] The offset of the text node within the
- * original string. This is used when parsing with the {@link #parse}
- * method to generate correct offsets within the {@link Autolinker.match.Match}
- * instances, but may be omitted if calling this method publicly.
- * @return {Autolinker.match.Match[]} The array of Matches found in the
- * given input `text`.
- */
- Autolinker.prototype.parseText = function (text, offset) {
- if (offset === void 0) { offset = 0; }
- offset = offset || 0;
- var matches = parseMatches(text, {
- tagBuilder: this.getTagBuilder(),
- stripPrefix: this.stripPrefix,
- stripTrailingSlash: this.stripTrailingSlash,
- decodePercentEncoding: this.decodePercentEncoding,
- hashtagServiceName: this.hashtag,
- mentionServiceName: this.mention || 'twitter',
- });
- // Correct the offset of each of the matches. They are originally
- // the offset of the match within the provided text node, but we
- // need to correct them to be relative to the original HTML input
- // string (i.e. the one provided to #parse).
- for (var i = 0, numTextMatches = matches.length; i < numTextMatches; i++) {
- matches[i].setOffset(offset + matches[i].getOffset());
- }
- return matches;
- };
- /**
- * Automatically links URLs, Email addresses, Phone numbers, Hashtags,
- * and Mentions (Twitter, Instagram, Soundcloud) found in the given chunk of HTML. Does not link
- * URLs found within HTML tags.
- *
- * For instance, if given the text: `You should go to http://www.yahoo.com`,
- * then the result will be `You should go to
- * <a href="http://www.yahoo.com">http://www.yahoo.com</a>`
- *
- * This method finds the text around any HTML elements in the input
- * `textOrHtml`, which will be the text that is processed. Any original HTML
- * elements will be left as-is, as well as the text that is already wrapped
- * in anchor (<a>) tags.
- *
- * @param {String} textOrHtml The HTML or text to autolink matches within
- * (depending on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #hashtag}, and {@link #mention} options are enabled).
- * @return {String} The HTML, with matches automatically linked.
- */
- Autolinker.prototype.link = function (textOrHtml) {
- if (!textOrHtml) {
- return '';
- } // handle `null` and `undefined` (for JavaScript users that don't have TypeScript support)
- /* We would want to sanitize the start and end characters of a tag
- * before processing the string in order to avoid an XSS scenario.
- * This behaviour can be changed by toggling the sanitizeHtml option.
- */
- if (this.sanitizeHtml) {
- textOrHtml = textOrHtml.replace(/</g, '<').replace(/>/g, '>');
- }
- var matches = this.parse(textOrHtml), newHtml = [], lastIndex = 0;
- for (var i = 0, len = matches.length; i < len; i++) {
- var match = matches[i];
- newHtml.push(textOrHtml.substring(lastIndex, match.getOffset()));
- newHtml.push(this.createMatchReturnVal(match));
- lastIndex = match.getOffset() + match.getMatchedText().length;
- }
- newHtml.push(textOrHtml.substring(lastIndex)); // handle the text after the last match
- return newHtml.join('');
- };
- /**
- * Creates the return string value for a given match in the input string.
- *
- * This method handles the {@link #replaceFn}, if one was provided.
- *
- * @private
- * @param {Autolinker.match.Match} match The Match object that represents
- * the match.
- * @return {String} The string that the `match` should be replaced with.
- * This is usually the anchor tag string, but may be the `matchStr` itself
- * if the match is not to be replaced.
- */
- Autolinker.prototype.createMatchReturnVal = function (match) {
- // Handle a custom `replaceFn` being provided
- var replaceFnResult;
- if (this.replaceFn) {
- replaceFnResult = this.replaceFn.call(this.context, match); // Autolinker instance is the context
- }
- if (typeof replaceFnResult === 'string') {
- return replaceFnResult; // `replaceFn` returned a string, use that
- }
- else if (replaceFnResult === false) {
- return match.getMatchedText(); // no replacement for the match
- }
- else if (replaceFnResult instanceof HtmlTag) {
- return replaceFnResult.toAnchorString();
- }
- else {
- // replaceFnResult === true, or no/unknown return value from function
- // Perform Autolinker's default anchor tag generation
- var anchorTag = match.buildTag(); // returns an Autolinker.HtmlTag instance
- return anchorTag.toAnchorString();
- }
- };
- /**
- * Returns the {@link #tagBuilder} instance for this Autolinker instance,
- * lazily instantiating it if it does not yet exist.
- *
- * @private
- * @return {Autolinker.AnchorTagBuilder}
- */
- Autolinker.prototype.getTagBuilder = function () {
- var tagBuilder = this.tagBuilder;
- if (!tagBuilder) {
- tagBuilder = this.tagBuilder = new AnchorTagBuilder({
- newWindow: this.newWindow,
- truncate: this.truncate,
- className: this.className,
- });
- }
- return tagBuilder;
- };
- // NOTE: must be 'export default' here for UMD module
- /**
- * @static
- * @property {String} version
- *
- * The Autolinker version number in the form major.minor.patch
- *
- * Ex: 3.15.0
- */
- Autolinker.version = version;
- return Autolinker;
- }());
- /**
- * Normalizes the {@link #urls} config into an Object with its 2 properties:
- * `schemeMatches` and `tldMatches`, both booleans.
- *
- * See {@link #urls} config for details.
- *
- * @private
- * @param {Boolean/Object} urls
- * @return {Object}
- */
- function normalizeUrlsCfg(urls) {
- if (urls == null)
- urls = true; // default to `true`
- if (isBoolean(urls)) {
- return { schemeMatches: urls, tldMatches: urls, ipV4Matches: urls };
- }
- else {
- // object form
- return {
- schemeMatches: isBoolean(urls.schemeMatches) ? urls.schemeMatches : true,
- tldMatches: isBoolean(urls.tldMatches) ? urls.tldMatches : true,
- ipV4Matches: isBoolean(urls.ipV4Matches) ? urls.ipV4Matches : true,
- };
- }
- }
- /**
- * Normalizes the {@link #stripPrefix} config into an Object with 2
- * properties: `scheme`, and `www` - both Booleans.
- *
- * See {@link #stripPrefix} config for details.
- *
- * @private
- * @param {Boolean/Object} stripPrefix
- * @return {Object}
- */
- function normalizeStripPrefixCfg(stripPrefix) {
- if (stripPrefix == null)
- stripPrefix = true; // default to `true`
- if (isBoolean(stripPrefix)) {
- return { scheme: stripPrefix, www: stripPrefix };
- }
- else {
- // object form
- return {
- scheme: isBoolean(stripPrefix.scheme) ? stripPrefix.scheme : true,
- www: isBoolean(stripPrefix.www) ? stripPrefix.www : true,
- };
- }
- }
- /**
- * Normalizes the {@link #truncate} config into an Object with 2 properties:
- * `length` (Number), and `location` (String).
- *
- * See {@link #truncate} config for details.
- *
- * @private
- * @param {Number/Object} truncate
- * @return {Object}
- */
- function normalizeTruncateCfg(truncate) {
- if (typeof truncate === 'number') {
- return { length: truncate, location: 'end' };
- }
- else {
- // object, or undefined/null
- return defaults(truncate || {}, {
- length: Number.POSITIVE_INFINITY,
- location: 'end',
- });
- }
- }
- return Autolinker;
- }));
- //# sourceMappingURL=autolinker.js.map
|