123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348 |
- <?php
- #
- # Markdown Extra - A text-to-HTML conversion tool for web writers
- #
- # PHP Markdown & Extra
- # Copyright (c) 2004-2013 Michel Fortin
- # <http://michelf.ca/projects/php-markdown/>
- #
- # Original Markdown
- # Copyright (c) 2004-2006 John Gruber
- # <http://daringfireball.net/projects/markdown/>
- #
- define( 'MARKDOWN_VERSION', "1.0.2" ); # 29 Nov 2013
- define( 'MARKDOWNEXTRA_VERSION', "1.2.8" ); # 29 Nov 2013
- #
- # Global default settings:
- #
- # Change to ">" for HTML output
- @define( 'MARKDOWN_EMPTY_ELEMENT_SUFFIX', " />");
- # Define the width of a tab for code blocks.
- @define( 'MARKDOWN_TAB_WIDTH', 4 );
- # Optional title attribute for footnote links and backlinks.
- @define( 'MARKDOWN_FN_LINK_TITLE', "" );
- @define( 'MARKDOWN_FN_BACKLINK_TITLE', "" );
- # Optional class attribute for footnote links and backlinks.
- @define( 'MARKDOWN_FN_LINK_CLASS', "" );
- @define( 'MARKDOWN_FN_BACKLINK_CLASS', "" );
- # Optional class prefix for fenced code block.
- @define( 'MARKDOWN_CODE_CLASS_PREFIX', "" );
- # Class attribute for code blocks goes on the `code` tag;
- # setting this to true will put attributes on the `pre` tag instead.
- @define( 'MARKDOWN_CODE_ATTR_ON_PRE', false );
- #
- # WordPress settings:
- #
- # Change to false to remove Markdown from posts and/or comments.
- @define( 'MARKDOWN_WP_POSTS', true );
- @define( 'MARKDOWN_WP_COMMENTS', true );
- ### Standard Function Interface ###
- @define( 'MARKDOWN_PARSER_CLASS', 'MarkdownExtra_Parser' );
- function Markdown($text) {
- #
- # Initialize the parser and return the result of its transform method.
- #
- # Setup static parser variable.
- static $parser;
- if (!isset($parser)) {
- $parser_class = MARKDOWN_PARSER_CLASS;
- $parser = new $parser_class;
- }
- # Transform text using parser.
- return $parser->transform($text);
- }
- ### WordPress Plugin Interface ###
- /*
- Plugin Name: Markdown Extra
- Plugin Name: Markdown
- Plugin URI: http://michelf.ca/projects/php-markdown/
- Description: <a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.ca/projects/php-markdown/">More...</a>
- Version: 1.2.8
- Author: Michel Fortin
- Author URI: http://michelf.ca/
- */
- if (isset($wp_version)) {
- # More details about how it works here:
- # <http://michelf.ca/weblog/2005/wordpress-text-flow-vs-markdown/>
-
- # Post content and excerpts
- # - Remove WordPress paragraph generator.
- # - Run Markdown on excerpt, then remove all tags.
- # - Add paragraph tag around the excerpt, but remove it for the excerpt rss.
- if (MARKDOWN_WP_POSTS) {
- remove_filter('the_content', 'wpautop');
- remove_filter('the_content_rss', 'wpautop');
- remove_filter('the_excerpt', 'wpautop');
- add_filter('the_content', 'mdwp_MarkdownPost', 6);
- add_filter('the_content_rss', 'mdwp_MarkdownPost', 6);
- add_filter('get_the_excerpt', 'mdwp_MarkdownPost', 6);
- add_filter('get_the_excerpt', 'trim', 7);
- add_filter('the_excerpt', 'mdwp_add_p');
- add_filter('the_excerpt_rss', 'mdwp_strip_p');
-
- remove_filter('content_save_pre', 'balanceTags', 50);
- remove_filter('excerpt_save_pre', 'balanceTags', 50);
- add_filter('the_content', 'balanceTags', 50);
- add_filter('get_the_excerpt', 'balanceTags', 9);
- }
-
- # Add a footnote id prefix to posts when inside a loop.
- function mdwp_MarkdownPost($text) {
- static $parser;
- if (!$parser) {
- $parser_class = MARKDOWN_PARSER_CLASS;
- $parser = new $parser_class;
- }
- if (is_single() || is_page() || is_feed()) {
- $parser->fn_id_prefix = "";
- } else {
- $parser->fn_id_prefix = get_the_ID() . ".";
- }
- return $parser->transform($text);
- }
-
- # Comments
- # - Remove WordPress paragraph generator.
- # - Remove WordPress auto-link generator.
- # - Scramble important tags before passing them to the kses filter.
- # - Run Markdown on excerpt then remove paragraph tags.
- if (MARKDOWN_WP_COMMENTS) {
- remove_filter('comment_text', 'wpautop', 30);
- remove_filter('comment_text', 'make_clickable');
- add_filter('pre_comment_content', 'Markdown', 6);
- add_filter('pre_comment_content', 'mdwp_hide_tags', 8);
- add_filter('pre_comment_content', 'mdwp_show_tags', 12);
- add_filter('get_comment_text', 'Markdown', 6);
- add_filter('get_comment_excerpt', 'Markdown', 6);
- add_filter('get_comment_excerpt', 'mdwp_strip_p', 7);
-
- global $mdwp_hidden_tags, $mdwp_placeholders;
- $mdwp_hidden_tags = explode(' ',
- '<p> </p> <pre> </pre> <ol> </ol> <ul> </ul> <li> </li>');
- $mdwp_placeholders = explode(' ', str_rot13(
- 'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR '.
- 'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli'));
- }
-
- function mdwp_add_p($text) {
- if (!preg_match('{^$|^<(p|ul|ol|dl|pre|blockquote)>}i', $text)) {
- $text = '<p>'.$text.'</p>';
- $text = preg_replace('{\n{2,}}', "</p>\n\n<p>", $text);
- }
- return $text;
- }
-
- function mdwp_strip_p($t) { return preg_replace('{</?p>}i', '', $t); }
- function mdwp_hide_tags($text) {
- global $mdwp_hidden_tags, $mdwp_placeholders;
- return str_replace($mdwp_hidden_tags, $mdwp_placeholders, $text);
- }
- function mdwp_show_tags($text) {
- global $mdwp_hidden_tags, $mdwp_placeholders;
- return str_replace($mdwp_placeholders, $mdwp_hidden_tags, $text);
- }
- }
- ### bBlog Plugin Info ###
- function identify_modifier_markdown() {
- return array(
- 'name' => 'markdown',
- 'type' => 'modifier',
- 'nicename' => 'PHP Markdown Extra',
- 'description' => 'A text-to-HTML conversion tool for web writers',
- 'authors' => 'Michel Fortin and John Gruber',
- 'licence' => 'GPL',
- 'version' => MARKDOWNEXTRA_VERSION,
- 'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.ca/projects/php-markdown/">More...</a>',
- );
- }
- ### Smarty Modifier Interface ###
- function smarty_modifier_markdown($text) {
- return Markdown($text);
- }
- ### Textile Compatibility Mode ###
- # Rename this file to "classTextile.php" and it can replace Textile everywhere.
- if (strcasecmp(substr(__FILE__, -16), "classTextile.php") == 0) {
- # Try to include PHP SmartyPants. Should be in the same directory.
- @include_once 'smartypants.php';
- # Fake Textile class. It calls Markdown instead.
- class Textile {
- function TextileThis($text, $lite='', $encode='') {
- if ($lite == '' && $encode == '') $text = Markdown($text);
- if (function_exists('SmartyPants')) $text = SmartyPants($text);
- return $text;
- }
- # Fake restricted version: restrictions are not supported for now.
- function TextileRestricted($text, $lite='', $noimage='') {
- return $this->TextileThis($text, $lite);
- }
- # Workaround to ensure compatibility with TextPattern 4.0.3.
- function blockLite($text) { return $text; }
- }
- }
- #
- # Markdown Parser Class
- #
- class Markdown_Parser {
- ### Configuration Variables ###
- # Change to ">" for HTML output.
- var $empty_element_suffix = MARKDOWN_EMPTY_ELEMENT_SUFFIX;
- var $tab_width = MARKDOWN_TAB_WIDTH;
-
- # Change to `true` to disallow markup or entities.
- var $no_markup = false;
- var $no_entities = false;
-
- # Predefined urls and titles for reference links and images.
- var $predef_urls = array();
- var $predef_titles = array();
- ### Parser Implementation ###
- # Regex to match balanced [brackets].
- # Needed to insert a maximum bracked depth while converting to PHP.
- var $nested_brackets_depth = 6;
- var $nested_brackets_re;
-
- var $nested_url_parenthesis_depth = 4;
- var $nested_url_parenthesis_re;
- # Table of hash values for escaped characters:
- var $escape_chars = '\`*_{}[]()>#+-.!';
- var $escape_chars_re;
- function Markdown_Parser() {
- #
- # Constructor function. Initialize appropriate member variables.
- #
- $this->_initDetab();
- $this->prepareItalicsAndBold();
-
- $this->nested_brackets_re =
- str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
- str_repeat('\])*', $this->nested_brackets_depth);
-
- $this->nested_url_parenthesis_re =
- str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth).
- str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth);
-
- $this->escape_chars_re = '['.preg_quote($this->escape_chars).']';
-
- # Sort document, block, and span gamut in ascendent priority order.
- asort($this->document_gamut);
- asort($this->block_gamut);
- asort($this->span_gamut);
- }
- # Internal hashes used during transformation.
- var $urls = array();
- var $titles = array();
- var $html_hashes = array();
-
- # Status flag to avoid invalid nesting.
- var $in_anchor = false;
-
-
- function setup() {
- #
- # Called before the transformation process starts to setup parser
- # states.
- #
- # Clear global hashes.
- $this->urls = $this->predef_urls;
- $this->titles = $this->predef_titles;
- $this->html_hashes = array();
-
- $this->in_anchor = false;
- }
-
- function teardown() {
- #
- # Called after the transformation process to clear any variable
- # which may be taking up memory unnecessarly.
- #
- $this->urls = array();
- $this->titles = array();
- $this->html_hashes = array();
- }
- function transform($text) {
- #
- # Main function. Performs some preprocessing on the input text
- # and pass it through the document gamut.
- #
- $this->setup();
-
- # Remove UTF-8 BOM and marker character in input, if present.
- $text = preg_replace('{^\xEF\xBB\xBF|\x1A}', '', $text);
- # Standardize line endings:
- # DOS to Unix and Mac to Unix
- $text = preg_replace('{\r\n?}', "\n", $text);
- # Make sure $text ends with a couple of newlines:
- $text .= "\n\n";
- # Convert all tabs to spaces.
- $text = $this->detab($text);
- # Turn block-level HTML blocks into hash entries
- $text = $this->hashHTMLBlocks($text);
- # Strip any lines consisting only of spaces and tabs.
- # This makes subsequent regexen easier to write, because we can
- # match consecutive blank lines with /\n+/ instead of something
- # contorted like /[ ]*\n+/ .
- $text = preg_replace('/^[ ]+$/m', '', $text);
- # Run document gamut methods.
- foreach ($this->document_gamut as $method => $priority) {
- $text = $this->$method($text);
- }
-
- $this->teardown();
- return $text . "\n";
- }
-
- var $document_gamut = array(
- # Strip link definitions, store in hashes.
- "stripLinkDefinitions" => 20,
-
- "runBasicBlockGamut" => 30,
- );
- function stripLinkDefinitions($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
- $less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: ^[id]: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
- [ ]*
- \n? # maybe *one* newline
- [ ]*
- (?:
- <(.+?)> # url = $2
- |
- (\S+?) # url = $3
- )
- [ ]*
- \n? # maybe one newline
- [ ]*
- (?:
- (?<=\s) # lookbehind for whitespace
- ["(]
- (.*?) # title = $4
- [")]
- [ ]*
- )? # title is optional
- (?:\n+|\Z)
- }xm',
- array(&$this, '_stripLinkDefinitions_callback'),
- $text);
- return $text;
- }
- function _stripLinkDefinitions_callback($matches) {
- $link_id = strtolower($matches[1]);
- $url = $matches[2] == '' ? $matches[3] : $matches[2];
- $this->urls[$link_id] = $url;
- $this->titles[$link_id] =& $matches[4];
- return ''; # String that will replace the block
- }
- function hashHTMLBlocks($text) {
- if ($this->no_markup) return $text;
- $less_than_tab = $this->tab_width - 1;
- # Hashify HTML blocks:
- # We only want to do this for block-level HTML tags, such as headers,
- # lists, and tables. That's because we still want to wrap <p>s around
- # "paragraphs" that are wrapped in non-block-level tags, such as anchors,
- # phrase emphasis, and spans. The list of tags we're looking for is
- # hard-coded:
- #
- # * List "a" is made of tags which can be both inline or block-level.
- # These will be treated block-level when the start tag is alone on
- # its line, otherwise they're not matched here and will be taken as
- # inline later.
- # * List "b" is made of tags which are always block-level;
- #
- $block_tags_a_re = 'ins|del';
- $block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
- 'script|noscript|form|fieldset|iframe|math|svg|'.
- 'article|section|nav|aside|hgroup|header|footer|'.
- 'figure';
- # Regular expression for the content of a block tag.
- $nested_tags_level = 4;
- $attr = '
- (?> # optional tag attributes
- \s # starts with whitespace
- (?>
- [^>"/]+ # text outside quotes
- |
- /+(?!>) # slash not followed by ">"
- |
- "[^"]*" # text inside double quotes (tolerate ">")
- |
- \'[^\']*\' # text inside single quotes (tolerate ">")
- )*
- )?
- ';
- $content =
- str_repeat('
- (?>
- [^<]+ # content without tag
- |
- <\2 # nested opening tag
- '.$attr.' # attributes
- (?>
- />
- |
- >', $nested_tags_level). # end of opening tag
- '.*?'. # last level nested tag content
- str_repeat('
- </\2\s*> # closing nested tag
- )
- |
- <(?!/\2\s*> # other tags with a different name
- )
- )*',
- $nested_tags_level);
- $content2 = str_replace('\2', '\3', $content);
- # First, look for nested blocks, e.g.:
- # <div>
- # <div>
- # tags for inner block must be indented.
- # </div>
- # </div>
- #
- # The outermost tags must start at the left margin for this to match, and
- # the inner nested divs must be indented.
- # We need to do this before the next, more liberal match, because the next
- # match will start at the first `<div>` and stop at the first `</div>`.
- $text = preg_replace_callback('{(?>
- (?>
- (?<=\n\n) # Starting after a blank line
- | # or
- \A\n? # the beginning of the doc
- )
- ( # save in $1
- # Match from `\n<tag>` to `</tag>\n`, handling nested tags
- # in between.
-
- [ ]{0,'.$less_than_tab.'}
- <('.$block_tags_b_re.')# start tag = $2
- '.$attr.'> # attributes followed by > and \n
- '.$content.' # content, support nesting
- </\2> # the matching end tag
- [ ]* # trailing spaces/tabs
- (?=\n+|\Z) # followed by a newline or end of document
- | # Special version for tags of group a.
- [ ]{0,'.$less_than_tab.'}
- <('.$block_tags_a_re.')# start tag = $3
- '.$attr.'>[ ]*\n # attributes followed by >
- '.$content2.' # content, support nesting
- </\3> # the matching end tag
- [ ]* # trailing spaces/tabs
- (?=\n+|\Z) # followed by a newline or end of document
-
- | # Special case just for <hr />. It was easier to make a special
- # case than to make the other regex more complicated.
-
- [ ]{0,'.$less_than_tab.'}
- <(hr) # start tag = $2
- '.$attr.' # attributes
- /?> # the matching end tag
- [ ]*
- (?=\n{2,}|\Z) # followed by a blank line or end of document
-
- | # Special case for standalone HTML comments:
-
- [ ]{0,'.$less_than_tab.'}
- (?s:
- <!-- .*? -->
- )
- [ ]*
- (?=\n{2,}|\Z) # followed by a blank line or end of document
-
- | # PHP and ASP-style processor instructions (<? and <%)
-
- [ ]{0,'.$less_than_tab.'}
- (?s:
- <([?%]) # $2
- .*?
- \2>
- )
- [ ]*
- (?=\n{2,}|\Z) # followed by a blank line or end of document
-
- )
- )}Sxmi',
- array(&$this, '_hashHTMLBlocks_callback'),
- $text);
- return $text;
- }
- function _hashHTMLBlocks_callback($matches) {
- $text = $matches[1];
- $key = $this->hashBlock($text);
- return "\n\n$key\n\n";
- }
-
-
- function hashPart($text, $boundary = 'X') {
- #
- # Called whenever a tag must be hashed when a function insert an atomic
- # element in the text stream. Passing $text to through this function gives
- # a unique text-token which will be reverted back when calling unhash.
- #
- # The $boundary argument specify what character should be used to surround
- # the token. By convension, "B" is used for block elements that needs not
- # to be wrapped into paragraph tags at the end, ":" is used for elements
- # that are word separators and "X" is used in the general case.
- #
- # Swap back any tag hash found in $text so we do not have to `unhash`
- # multiple times at the end.
- $text = $this->unhash($text);
-
- # Then hash the block.
- static $i = 0;
- $key = "$boundary\x1A" . ++$i . $boundary;
- $this->html_hashes[$key] = $text;
- return $key; # String that will replace the tag.
- }
- function hashBlock($text) {
- #
- # Shortcut function for hashPart with block-level boundaries.
- #
- return $this->hashPart($text, 'B');
- }
- var $block_gamut = array(
- #
- # These are all the transformations that form block-level
- # tags like paragraphs, headers, and list items.
- #
- "doHeaders" => 10,
- "doHorizontalRules" => 20,
-
- "doLists" => 40,
- "doCodeBlocks" => 50,
- "doBlockQuotes" => 60,
- );
- function runBlockGamut($text) {
- #
- # Run block gamut tranformations.
- #
- # We need to escape raw HTML in Markdown source before doing anything
- # else. This need to be done for each block, and not only at the
- # begining in the Markdown function since hashed blocks can be part of
- # list items and could have been indented. Indented blocks would have
- # been seen as a code block in a previous pass of hashHTMLBlocks.
- $text = $this->hashHTMLBlocks($text);
-
- return $this->runBasicBlockGamut($text);
- }
-
- function runBasicBlockGamut($text) {
- #
- # Run block gamut tranformations, without hashing HTML blocks. This is
- # useful when HTML blocks are known to be already hashed, like in the first
- # whole-document pass.
- #
- foreach ($this->block_gamut as $method => $priority) {
- $text = $this->$method($text);
- }
-
- # Finally form paragraph and restore hashed blocks.
- $text = $this->formParagraphs($text);
- return $text;
- }
-
-
- function doHorizontalRules($text) {
- # Do Horizontal Rules:
- return preg_replace(
- '{
- ^[ ]{0,3} # Leading space
- ([-*_]) # $1: First marker
- (?> # Repeated marker group
- [ ]{0,2} # Zero, one, or two spaces.
- \1 # Marker character
- ){2,} # Group repeated at least twice
- [ ]* # Tailing spaces
- $ # End of line.
- }mx',
- "\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n",
- $text);
- }
- var $span_gamut = array(
- #
- # These are all the transformations that occur *within* block-level
- # tags like paragraphs, headers, and list items.
- #
- # Process character escapes, code spans, and inline HTML
- # in one shot.
- "parseSpan" => -30,
- # Process anchor and image tags. Images must come first,
- # because ![foo][f] looks like an anchor.
- "doImages" => 10,
- "doAnchors" => 20,
-
- # Make links out of things like `<http://example.com/>`
- # Must come after doAnchors, because you can use < and >
- # delimiters in inline links like [this](<url>).
- "doAutoLinks" => 30,
- "encodeAmpsAndAngles" => 40,
- "doItalicsAndBold" => 50,
- "doHardBreaks" => 60,
- );
- function runSpanGamut($text) {
- #
- # Run span gamut tranformations.
- #
- foreach ($this->span_gamut as $method => $priority) {
- $text = $this->$method($text);
- }
- return $text;
- }
-
-
- function doHardBreaks($text) {
- # Do hard breaks:
- return preg_replace_callback('/ {2,}\n/',
- array(&$this, '_doHardBreaks_callback'), $text);
- }
- function _doHardBreaks_callback($matches) {
- return $this->hashPart("<br$this->empty_element_suffix\n");
- }
- function doAnchors($text) {
- #
- # Turn Markdown link shortcuts into XHTML <a> tags.
- #
- if ($this->in_anchor) return $text;
- $this->in_anchor = true;
-
- #
- # First, handle reference-style links: [link text] [id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
- \[
- (.*?) # id = $3
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
- #
- # Next, inline-style links: [link text](url "optional title")
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
- \( # literal paren
- [ \n]*
- (?:
- <(.+?)> # href = $3
- |
- ('.$this->nested_url_parenthesis_re.') # href = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # Title = $7
- \6 # matching quote
- [ \n]* # ignore any spaces/tabs between closing quote and )
- )? # title is optional
- \)
- )
- }xs',
- array(&$this, '_doAnchors_inline_callback'), $text);
- #
- # Last, handle reference-style shortcuts: [link text]
- # These must come last in case you've also got [link text][1]
- # or [link text](/foo)
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ([^\[\]]+) # link text = $2; can\'t contain [ or ]
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
- $this->in_anchor = false;
- return $text;
- }
- function _doAnchors_reference_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $matches[2];
- $link_id =& $matches[3];
- if ($link_id == "") {
- # for shortcut links like [this][] or [this].
- $link_id = $link_text;
- }
-
- # lower-case and turn embedded newlines into spaces
- $link_id = strtolower($link_id);
- $link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
- if (isset($this->urls[$link_id])) {
- $url = $this->urls[$link_id];
- $url = $this->encodeAttribute($url);
-
- $result = "<a href=\"$url\"";
- if ( isset( $this->titles[$link_id] ) ) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text</a>";
- $result = $this->hashPart($result);
- }
- else {
- $result = $whole_match;
- }
- return $result;
- }
- function _doAnchors_inline_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $this->runSpanGamut($matches[2]);
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
- $url = $this->encodeAttribute($url);
- $result = "<a href=\"$url\"";
- if (isset($title)) {
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text</a>";
- return $this->hashPart($result);
- }
- function doImages($text) {
- #
- # Turn Markdown image shortcuts into <img> tags.
- #
- #
- # First, handle reference-style labeled images: ![alt text][id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
- \[
- (.*?) # id = $3
- \]
- )
- }xs',
- array(&$this, '_doImages_reference_callback'), $text);
- #
- # Next, handle inline images: ![alt text](url "optional title")
- # Don't forget: encode * and _
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
- \s? # One optional whitespace character
- \( # literal paren
- [ \n]*
- (?:
- <(\S*)> # src url = $3
- |
- ('.$this->nested_url_parenthesis_re.') # src url = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # title = $7
- \6 # matching quote
- [ \n]*
- )? # title is optional
- \)
- )
- }xs',
- array(&$this, '_doImages_inline_callback'), $text);
- return $text;
- }
- function _doImages_reference_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $link_id = strtolower($matches[3]);
- if ($link_id == "") {
- $link_id = strtolower($alt_text); # for shortcut links like ![this][].
- }
- $alt_text = $this->encodeAttribute($alt_text);
- if (isset($this->urls[$link_id])) {
- $url = $this->encodeAttribute($this->urls[$link_id]);
- $result = "<img src=\"$url\" alt=\"$alt_text\"";
- if (isset($this->titles[$link_id])) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- $result .= $this->empty_element_suffix;
- $result = $this->hashPart($result);
- }
- else {
- # If there's no such link ID, leave intact:
- $result = $whole_match;
- }
- return $result;
- }
- function _doImages_inline_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
- $alt_text = $this->encodeAttribute($alt_text);
- $url = $this->encodeAttribute($url);
- $result = "<img src=\"$url\" alt=\"$alt_text\"";
- if (isset($title)) {
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\""; # $title already quoted
- }
- $result .= $this->empty_element_suffix;
- return $this->hashPart($result);
- }
- function doHeaders($text) {
- # Setext-style headers:
- # Header 1
- # ========
- #
- # Header 2
- # --------
- #
- $text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx',
- array(&$this, '_doHeaders_callback_setext'), $text);
- # atx-style headers:
- # # Header 1
- # ## Header 2
- # ## Header 2 with closing hashes ##
- # ...
- # ###### Header 6
- #
- $text = preg_replace_callback('{
- ^(\#{1,6}) # $1 = string of #\'s
- [ ]*
- (.+?) # $2 = Header text
- [ ]*
- \#* # optional closing #\'s (not counted)
- \n+
- }xm',
- array(&$this, '_doHeaders_callback_atx'), $text);
- return $text;
- }
- function _doHeaders_callback_setext($matches) {
- # Terrible hack to check we haven't found an empty list item.
- if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1]))
- return $matches[0];
-
- $level = $matches[2]{0} == '=' ? 1 : 2;
- $block = "<h$level>".$this->runSpanGamut($matches[1])."</h$level>";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
- function _doHeaders_callback_atx($matches) {
- $level = strlen($matches[1]);
- $block = "<h$level>".$this->runSpanGamut($matches[2])."</h$level>";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
- function doLists($text) {
- #
- # Form HTML ordered (numbered) and unordered (bulleted) lists.
- #
- $less_than_tab = $this->tab_width - 1;
- # Re-usable patterns to match list item bullets and number markers:
- $marker_ul_re = '[*+-]';
- $marker_ol_re = '\d+[\.]';
- $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
- $markers_relist = array(
- $marker_ul_re => $marker_ol_re,
- $marker_ol_re => $marker_ul_re,
- );
- foreach ($markers_relist as $marker_re => $other_marker_re) {
- # Re-usable pattern to match any entirel ul or ol list:
- $whole_list_re = '
- ( # $1 = whole list
- ( # $2
- ([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces
- ('.$marker_re.') # $4 = first list item marker
- [ ]+
- )
- (?s:.+?)
- ( # $5
- \z
- |
- \n{2,}
- (?=\S)
- (?! # Negative lookahead for another list item marker
- [ ]*
- '.$marker_re.'[ ]+
- )
- |
- (?= # Lookahead for another kind of list
- \n
- \3 # Must have the same indentation
- '.$other_marker_re.'[ ]+
- )
- )
- )
- '; // mx
-
- # We use a different prefix before nested lists than top-level lists.
- # See extended comment in _ProcessListItems().
-
- if ($this->list_level) {
- $text = preg_replace_callback('{
- ^
- '.$whole_list_re.'
- }mx',
- array(&$this, '_doLists_callback'), $text);
- }
- else {
- $text = preg_replace_callback('{
- (?:(?<=\n)\n|\A\n?) # Must eat the newline
- '.$whole_list_re.'
- }mx',
- array(&$this, '_doLists_callback'), $text);
- }
- }
- return $text;
- }
- function _doLists_callback($matches) {
- # Re-usable patterns to match list item bullets and number markers:
- $marker_ul_re = '[*+-]';
- $marker_ol_re = '\d+[\.]';
- $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
-
- $list = $matches[1];
- $list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol";
-
- $marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
-
- $list .= "\n";
- $result = $this->processListItems($list, $marker_any_re);
-
- $result = $this->hashBlock("<$list_type>\n" . $result . "</$list_type>");
- return "\n". $result ."\n\n";
- }
- var $list_level = 0;
- function processListItems($list_str, $marker_any_re) {
- #
- # Process the contents of a single ordered or unordered list, splitting it
- # into individual list items.
- #
- # The $this->list_level global keeps track of when we're inside a list.
- # Each time we enter a list, we increment it; when we leave a list,
- # we decrement. If it's zero, we're not in a list anymore.
- #
- # We do this because when we're not inside a list, we want to treat
- # something like this:
- #
- # I recommend upgrading to version
- # 8. Oops, now this line is treated
- # as a sub-list.
- #
- # As a single paragraph, despite the fact that the second line starts
- # with a digit-period-space sequence.
- #
- # Whereas when we're inside a list (or sub-list), that line will be
- # treated as the start of a sub-list. What a kludge, huh? This is
- # an aspect of Markdown's syntax that's hard to parse perfectly
- # without resorting to mind-reading. Perhaps the solution is to
- # change the syntax rules such that sub-lists must start with a
- # starting cardinal number; e.g. "1." or "a.".
-
- $this->list_level++;
- # trim trailing blank lines:
- $list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
- $list_str = preg_replace_callback('{
- (\n)? # leading line = $1
- (^[ ]*) # leading whitespace = $2
- ('.$marker_any_re.' # list marker and space = $3
- (?:[ ]+|(?=\n)) # space only required if item is not empty
- )
- ((?s:.*?)) # list item text = $4
- (?:(\n+(?=\n))|\n) # tailing blank line = $5
- (?= \n* (\z | \2 ('.$marker_any_re.') (?:[ ]+|(?=\n))))
- }xm',
- array(&$this, '_processListItems_callback'), $list_str);
- $this->list_level--;
- return $list_str;
- }
- function _processListItems_callback($matches) {
- $item = $matches[4];
- $leading_line =& $matches[1];
- $leading_space =& $matches[2];
- $marker_space = $matches[3];
- $tailing_blank_line =& $matches[5];
- if ($leading_line || $tailing_blank_line ||
- preg_match('/\n{2,}/', $item))
- {
- # Replace marker with the appropriate whitespace indentation
- $item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
- $item = $this->runBlockGamut($this->outdent($item)."\n");
- }
- else {
- # Recursion for sub-lists:
- $item = $this->doLists($this->outdent($item));
- $item = preg_replace('/\n+$/', '', $item);
- $item = $this->runSpanGamut($item);
- }
- return "<li>" . $item . "</li>\n";
- }
- function doCodeBlocks($text) {
- #
- # Process Markdown `<pre><code>` blocks.
- #
- $text = preg_replace_callback('{
- (?:\n\n|\A\n?)
- ( # $1 = the code block -- one or more lines, starting with a space/tab
- (?>
- [ ]{'.$this->tab_width.'} # Lines must start with a tab or a tab-width of spaces
- .*\n+
- )+
- )
- ((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
- }xm',
- array(&$this, '_doCodeBlocks_callback'), $text);
- return $text;
- }
- function _doCodeBlocks_callback($matches) {
- $codeblock = $matches[1];
- $codeblock = $this->outdent($codeblock);
- $codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
- # trim leading newlines and trailing newlines
- $codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);
- $codeblock = "<pre><code>$codeblock\n</code></pre>";
- return "\n\n".$this->hashBlock($codeblock)."\n\n";
- }
- function makeCodeSpan($code) {
- #
- # Create a code span markup for $code. Called from handleSpanToken.
- #
- $code = htmlspecialchars(trim($code), ENT_NOQUOTES);
- return $this->hashPart("<code>$code</code>");
- }
- var $em_relist = array(
- '' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?=\S|$)(?![\.,:;]\s)',
- '*' => '(?<=\S|^)(?<!\*)\*(?!\*)',
- '_' => '(?<=\S|^)(?<!_)_(?!_)',
- );
- var $strong_relist = array(
- '' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?=\S|$)(?![\.,:;]\s)',
- '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)',
- '__' => '(?<=\S|^)(?<!_)__(?!_)',
- );
- var $em_strong_relist = array(
- '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?=\S|$)(?![\.,:;]\s)',
- '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)',
- '___' => '(?<=\S|^)(?<!_)___(?!_)',
- );
- var $em_strong_prepared_relist;
-
- function prepareItalicsAndBold() {
- #
- # Prepare regular expressions for searching emphasis tokens in any
- # context.
- #
- foreach ($this->em_relist as $em => $em_re) {
- foreach ($this->strong_relist as $strong => $strong_re) {
- # Construct list of allowed token expressions.
- $token_relist = array();
- if (isset($this->em_strong_relist["$em$strong"])) {
- $token_relist[] = $this->em_strong_relist["$em$strong"];
- }
- $token_relist[] = $em_re;
- $token_relist[] = $strong_re;
-
- # Construct master expression from list.
- $token_re = '{('. implode('|', $token_relist) .')}';
- $this->em_strong_prepared_relist["$em$strong"] = $token_re;
- }
- }
- }
-
- function doItalicsAndBold($text) {
- $token_stack = array('');
- $text_stack = array('');
- $em = '';
- $strong = '';
- $tree_char_em = false;
-
- while (1) {
- #
- # Get prepared regular expression for seraching emphasis tokens
- # in current context.
- #
- $token_re = $this->em_strong_prepared_relist["$em$strong"];
-
- #
- # Each loop iteration search for the next emphasis token.
- # Each token is then passed to handleSpanToken.
- #
- $parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
- $text_stack[0] .= $parts[0];
- $token =& $parts[1];
- $text =& $parts[2];
-
- if (empty($token)) {
- # Reached end of text span: empty stack without emitting.
- # any more emphasis.
- while ($token_stack[0]) {
- $text_stack[1] .= array_shift($token_stack);
- $text_stack[0] .= array_shift($text_stack);
- }
- break;
- }
-
- $token_len = strlen($token);
- if ($tree_char_em) {
- # Reached closing marker while inside a three-char emphasis.
- if ($token_len == 3) {
- # Three-char closing marker, close em and strong.
- array_shift($token_stack);
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "<strong><em>$span</em></strong>";
- $text_stack[0] .= $this->hashPart($span);
- $em = '';
- $strong = '';
- } else {
- # Other closing marker: close one em or strong and
- # change current token state to match the other
- $token_stack[0] = str_repeat($token{0}, 3-$token_len);
- $tag = $token_len == 2 ? "strong" : "em";
- $span = $text_stack[0];
- $span = $this->runSpanGamut($span);
- $span = "<$tag>$span</$tag>";
- $text_stack[0] = $this->hashPart($span);
- $$tag = ''; # $$tag stands for $em or $strong
- }
- $tree_char_em = false;
- } else if ($token_len == 3) {
- if ($em) {
- # Reached closing marker for both em and strong.
- # Closing strong marker:
- for ($i = 0; $i < 2; ++$i) {
- $shifted_token = array_shift($token_stack);
- $tag = strlen($shifted_token) == 2 ? "strong" : "em";
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "<$tag>$span</$tag>";
- $text_stack[0] .= $this->hashPart($span);
- $$tag = ''; # $$tag stands for $em or $strong
- }
- } else {
- # Reached opening three-char emphasis marker. Push on token
- # stack; will be handled by the special condition above.
- $em = $token{0};
- $strong = "$em$em";
- array_unshift($token_stack, $token);
- array_unshift($text_stack, '');
- $tree_char_em = true;
- }
- } else if ($token_len == 2) {
- if ($strong) {
- # Unwind any dangling emphasis marker:
- if (strlen($token_stack[0]) == 1) {
- $text_stack[1] .= array_shift($token_stack);
- $text_stack[0] .= array_shift($text_stack);
- }
- # Closing strong marker:
- array_shift($token_stack);
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "<strong>$span</strong>";
- $text_stack[0] .= $this->hashPart($span);
- $strong = '';
- } else {
- array_unshift($token_stack, $token);
- array_unshift($text_stack, '');
- $strong = $token;
- }
- } else {
- # Here $token_len == 1
- if ($em) {
- if (strlen($token_stack[0]) == 1) {
- # Closing emphasis marker:
- array_shift($token_stack);
- $span = array_shift($text_stack);
- $span = $this->runSpanGamut($span);
- $span = "<em>$span</em>";
- $text_stack[0] .= $this->hashPart($span);
- $em = '';
- } else {
- $text_stack[0] .= $token;
- }
- } else {
- array_unshift($token_stack, $token);
- array_unshift($text_stack, '');
- $em = $token;
- }
- }
- }
- return $text_stack[0];
- }
- function doBlockQuotes($text) {
- $text = preg_replace_callback('/
- ( # Wrap whole match in $1
- (?>
- ^[ ]*>[ ]? # ">" at the start of a line
- .+\n # rest of the first line
- (.+\n)* # subsequent consecutive lines
- \n* # blanks
- )+
- )
- /xm',
- array(&$this, '_doBlockQuotes_callback'), $text);
- return $text;
- }
- function _doBlockQuotes_callback($matches) {
- $bq = $matches[1];
- # trim one level of quoting - trim whitespace-only lines
- $bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
- $bq = $this->runBlockGamut($bq); # recurse
- $bq = preg_replace('/^/m', " ", $bq);
- # These leading spaces cause problem with <pre> content,
- # so we need to fix that:
- $bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx',
- array(&$this, '_doBlockQuotes_callback2'), $bq);
- return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n";
- }
- function _doBlockQuotes_callback2($matches) {
- $pre = $matches[1];
- $pre = preg_replace('/^ /m', '', $pre);
- return $pre;
- }
- function formParagraphs($text) {
- #
- # Params:
- # $text - string to process with html <p> tags
- #
- # Strip leading and trailing lines:
- $text = preg_replace('/\A\n+|\n+\z/', '', $text);
- $grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
- #
- # Wrap <p> tags and unhashify HTML blocks
- #
- foreach ($grafs as $key => $value) {
- if (!preg_match('/^B\x1A[0-9]+B$/', $value)) {
- # Is a paragraph.
- $value = $this->runSpanGamut($value);
- $value = preg_replace('/^([ ]*)/', "<p>", $value);
- $value .= "</p>";
- $grafs[$key] = $this->unhash($value);
- }
- else {
- # Is a block.
- # Modify elements of @grafs in-place...
- $graf = $value;
- $block = $this->html_hashes[$graf];
- $graf = $block;
- // if (preg_match('{
- // \A
- // ( # $1 = <div> tag
- // <div \s+
- // [^>]*
- // \b
- // markdown\s*=\s* ([\'"]) # $2 = attr quote char
- // 1
- // \2
- // [^>]*
- // >
- // )
- // ( # $3 = contents
- // .*
- // )
- // (</div>) # $4 = closing tag
- // \z
- // }xs', $block, $matches))
- // {
- // list(, $div_open, , $div_content, $div_close) = $matches;
- //
- // # We can't call Markdown(), because that resets the hash;
- // # that initialization code should be pulled into its own sub, though.
- // $div_content = $this->hashHTMLBlocks($div_content);
- //
- // # Run document gamut methods on the content.
- // foreach ($this->document_gamut as $method => $priority) {
- // $div_content = $this->$method($div_content);
- // }
- //
- // $div_open = preg_replace(
- // '{\smarkdown\s*=\s*([\'"]).+?\1}', '', $div_open);
- //
- // $graf = $div_open . "\n" . $div_content . "\n" . $div_close;
- // }
- $grafs[$key] = $graf;
- }
- }
- return implode("\n\n", $grafs);
- }
- function encodeAttribute($text) {
- #
- # Encode text for a double-quoted HTML attribute. This function
- # is *not* suitable for attributes enclosed in single quotes.
- #
- $text = $this->encodeAmpsAndAngles($text);
- $text = str_replace('"', '"', $text);
- return $text;
- }
-
-
- function encodeAmpsAndAngles($text) {
- #
- # Smart processing for ampersands and angle brackets that need to
- # be encoded. Valid character entities are left alone unless the
- # no-entities mode is set.
- #
- if ($this->no_entities) {
- $text = str_replace('&', '&', $text);
- } else {
- # Ampersand-encoding based entirely on Nat Irons's Amputator
- # MT plugin: <http://bumppo.net/projects/amputator/>
- $text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
- '&', $text);;
- }
- # Encode remaining <'s
- $text = str_replace('<', '<', $text);
- return $text;
- }
- function doAutoLinks($text) {
- $text = preg_replace_callback('{<((https?|ftp|dict):[^\'">\s]+)>}i',
- array(&$this, '_doAutoLinks_url_callback'), $text);
- # Email addresses: <address@domain.foo>
- $text = preg_replace_callback('{
- <
- (?:mailto:)?
- (
- (?:
- [-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+
- |
- ".*?"
- )
- \@
- (?:
- [-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
- |
- \[[\d.a-fA-F:]+\] # IPv4 & IPv6
- )
- )
- >
- }xi',
- array(&$this, '_doAutoLinks_email_callback'), $text);
- $text = preg_replace_callback('{<(tel:([^\'">\s]+))>}i',array(&$this, '_doAutoLinks_tel_callback'), $text);
- return $text;
- }
- function _doAutoLinks_tel_callback($matches) {
- $url = $this->encodeAttribute($matches[1]);
- $tel = $this->encodeAttribute($matches[2]);
- $link = "<a href=\"$url\">$tel</a>";
- return $this->hashPart($link);
- }
- function _doAutoLinks_url_callback($matches) {
- $url = $this->encodeAttribute($matches[1]);
- $link = "<a href=\"$url\">$url</a>";
- return $this->hashPart($link);
- }
- function _doAutoLinks_email_callback($matches) {
- $address = $matches[1];
- $link = $this->encodeEmailAddress($address);
- return $this->hashPart($link);
- }
- function encodeEmailAddress($addr) {
- #
- # Input: an email address, e.g. "foo@example.com"
- #
- # Output: the email address as a mailto link, with each character
- # of the address encoded as either a decimal or hex entity, in
- # the hopes of foiling most address harvesting spam bots. E.g.:
- #
- # <p><a href="mailto:foo
- # @example.co
- # m">foo@exampl
- # e.com</a></p>
- #
- # Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
- # With some optimizations by Milian Wolff.
- #
- $addr = "mailto:" . $addr;
- $chars = preg_split('/(?<!^)(?!$)/', $addr);
- $seed = (int)abs(crc32($addr) / strlen($addr)); # Deterministic seed.
-
- foreach ($chars as $key => $char) {
- $ord = ord($char);
- # Ignore non-ascii chars.
- if ($ord < 128) {
- $r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
- # roughly 10% raw, 45% hex, 45% dec
- # '@' *must* be encoded. I insist.
- if ($r > 90 && $char != '@') /* do nothing */;
- else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';';
- else $chars[$key] = '&#'.$ord.';';
- }
- }
-
- $addr = implode('', $chars);
- $text = implode('', array_slice($chars, 7)); # text without `mailto:`
- $addr = "<a href=\"$addr\">$text</a>";
- return $addr;
- }
- function parseSpan($str) {
- #
- # Take the string $str and parse it into tokens, hashing embeded HTML,
- # escaped characters and handling code spans.
- #
- $output = '';
-
- $span_re = '{
- (
- \\\\'.$this->escape_chars_re.'
- |
- (?<![`\\\\])
- `+ # code span marker
- '.( $this->no_markup ? '' : '
- |
- <!-- .*? --> # comment
- |
- <\?.*?\?> | <%.*?%> # processing instruction
- |
- <[!$]?[-a-zA-Z0-9:_]+ # regular tags
- (?>
- \s
- (?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
- )?
- >
- |
- <[-a-zA-Z0-9:_]+\s*/> # xml-style empty tag
- |
- </[-a-zA-Z0-9:_]+\s*> # closing tag
- ').'
- )
- }xs';
- while (1) {
- #
- # Each loop iteration seach for either the next tag, the next
- # openning code span marker, or the next escaped character.
- # Each token is then passed to handleSpanToken.
- #
- $parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
-
- # Create token from text preceding tag.
- if ($parts[0] != "") {
- $output .= $parts[0];
- }
-
- # Check if we reach the end.
- if (isset($parts[1])) {
- $output .= $this->handleSpanToken($parts[1], $parts[2]);
- $str = $parts[2];
- }
- else {
- break;
- }
- }
-
- return $output;
- }
-
-
- function handleSpanToken($token, &$str) {
- #
- # Handle $token provided by parseSpan by determining its nature and
- # returning the corresponding value that should replace it.
- #
- switch ($token{0}) {
- case "\\":
- return $this->hashPart("&#". ord($token{1}). ";");
- case "`":
- # Search for end marker in remaining text.
- if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm',
- $str, $matches))
- {
- $str = $matches[2];
- $codespan = $this->makeCodeSpan($matches[1]);
- return $this->hashPart($codespan);
- }
- return $token; // return as text since no ending marker found.
- default:
- return $this->hashPart($token);
- }
- }
- function outdent($text) {
- #
- # Remove one level of line-leading tabs or spaces
- #
- return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
- }
- # String length function for detab. `_initDetab` will create a function to
- # hanlde UTF-8 if the default function does not exist.
- var $utf8_strlen = 'mb_strlen';
-
- function detab($text) {
- #
- # Replace tabs with the appropriate amount of space.
- #
- # For each line we separate the line in blocks delemited by
- # tab characters. Then we reconstruct every line by adding the
- # appropriate number of space between each blocks.
-
- $text = preg_replace_callback('/^.*\t.*$/m',
- array(&$this, '_detab_callback'), $text);
- return $text;
- }
- function _detab_callback($matches) {
- $line = $matches[0];
- $strlen = $this->utf8_strlen; # strlen function for UTF-8.
-
- # Split in blocks.
- $blocks = explode("\t", $line);
- # Add each blocks to the line.
- $line = $blocks[0];
- unset($blocks[0]); # Do not add first block twice.
- foreach ($blocks as $block) {
- # Calculate amount of space, insert spaces, insert block.
- $amount = $this->tab_width -
- $strlen($line, 'UTF-8') % $this->tab_width;
- $line .= str_repeat(" ", $amount) . $block;
- }
- return $line;
- }
- function _initDetab() {
- #
- # Check for the availability of the function in the `utf8_strlen` property
- # (initially `mb_strlen`). If the function is not available, create a
- # function that will loosely count the number of UTF-8 characters with a
- # regular expression.
- #
- if (function_exists($this->utf8_strlen)) return;
- $this->utf8_strlen = create_function('$text', 'return preg_match_all(
- "/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
- $text, $m);');
- }
- function unhash($text) {
- #
- # Swap back in all the tags hashed by _HashHTMLBlocks.
- #
- return preg_replace_callback('/(.)\x1A[0-9]+\1/',
- array(&$this, '_unhash_callback'), $text);
- }
- function _unhash_callback($matches) {
- return $this->html_hashes[$matches[0]];
- }
- }
- #
- # Markdown Extra Parser Class
- #
- class MarkdownExtra_Parser extends Markdown_Parser {
- ### Configuration Variables ###
- # Prefix for footnote ids.
- var $fn_id_prefix = "";
-
- # Optional title attribute for footnote links and backlinks.
- var $fn_link_title = MARKDOWN_FN_LINK_TITLE;
- var $fn_backlink_title = MARKDOWN_FN_BACKLINK_TITLE;
-
- # Optional class attribute for footnote links and backlinks.
- var $fn_link_class = MARKDOWN_FN_LINK_CLASS;
- var $fn_backlink_class = MARKDOWN_FN_BACKLINK_CLASS;
- # Optional class prefix for fenced code block.
- var $code_class_prefix = MARKDOWN_CODE_CLASS_PREFIX;
- # Class attribute for code blocks goes on the `code` tag;
- # setting this to true will put attributes on the `pre` tag instead.
- var $code_attr_on_pre = MARKDOWN_CODE_ATTR_ON_PRE;
-
- # Predefined abbreviations.
- var $predef_abbr = array();
- ### Parser Implementation ###
- function MarkdownExtra_Parser() {
- #
- # Constructor function. Initialize the parser object.
- #
- # Add extra escapable characters before parent constructor
- # initialize the table.
- $this->escape_chars .= ':|';
-
- # Insert extra document, block, and span transformations.
- # Parent constructor will do the sorting.
- $this->document_gamut += array(
- "doFencedCodeBlocks" => 5,
- "stripFootnotes" => 15,
- "stripAbbreviations" => 25,
- "appendFootnotes" => 50,
- );
- $this->block_gamut += array(
- "doFencedCodeBlocks" => 5,
- "doTables" => 15,
- "doDefLists" => 45,
- );
- $this->span_gamut += array(
- "doFootnotes" => 5,
- "doAbbreviations" => 70,
- );
-
- parent::Markdown_Parser();
- }
-
-
- # Extra variables used during extra transformations.
- var $footnotes = array();
- var $footnotes_ordered = array();
- var $footnotes_ref_count = array();
- var $footnotes_numbers = array();
- var $abbr_desciptions = array();
- var $abbr_word_re = '';
-
- # Give the current footnote number.
- var $footnote_counter = 1;
-
-
- function setup() {
- #
- # Setting up Extra-specific variables.
- #
- parent::setup();
-
- $this->footnotes = array();
- $this->footnotes_ordered = array();
- $this->footnotes_ref_count = array();
- $this->footnotes_numbers = array();
- $this->abbr_desciptions = array();
- $this->abbr_word_re = '';
- $this->footnote_counter = 1;
-
- foreach ($this->predef_abbr as $abbr_word => $abbr_desc) {
- if ($this->abbr_word_re)
- $this->abbr_word_re .= '|';
- $this->abbr_word_re .= preg_quote($abbr_word);
- $this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
- }
- }
-
- function teardown() {
- #
- # Clearing Extra-specific variables.
- #
- $this->footnotes = array();
- $this->footnotes_ordered = array();
- $this->footnotes_ref_count = array();
- $this->footnotes_numbers = array();
- $this->abbr_desciptions = array();
- $this->abbr_word_re = '';
-
- parent::teardown();
- }
-
-
- ### Extra Attribute Parser ###
- # Expression to use to catch attributes (includes the braces)
- var $id_class_attr_catch_re = '\{((?:[ ]*[#.][-_:a-zA-Z0-9]+){1,})[ ]*\}';
- # Expression to use when parsing in a context when no capture is desired
- var $id_class_attr_nocatch_re = '\{(?:[ ]*[#.][-_:a-zA-Z0-9]+){1,}[ ]*\}';
- function doExtraAttributes($tag_name, $attr) {
- #
- # Parse attributes caught by the $this->id_class_attr_catch_re expression
- # and return the HTML-formatted list of attributes.
- #
- # Currently supported attributes are .class and #id.
- #
- if (empty($attr)) return "";
-
- # Split on components
- preg_match_all('/[#.][-_:a-zA-Z0-9]+/', $attr, $matches);
- $elements = $matches[0];
- # handle classes and ids (only first id taken into account)
- $classes = array();
- $id = false;
- foreach ($elements as $element) {
- if ($element{0} == '.') {
- $classes[] = substr($element, 1);
- } else if ($element{0} == '#') {
- if ($id === false) $id = substr($element, 1);
- }
- }
- # compose attributes as string
- $attr_str = "";
- if (!empty($id)) {
- $attr_str .= ' id="'.$id.'"';
- }
- if (!empty($classes)) {
- $attr_str .= ' class="'.implode(" ", $classes).'"';
- }
- return $attr_str;
- }
- function stripLinkDefinitions($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
- $less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: ^[id]: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
- [ ]*
- \n? # maybe *one* newline
- [ ]*
- (?:
- <(.+?)> # url = $2
- |
- (\S+?) # url = $3
- )
- [ ]*
- \n? # maybe one newline
- [ ]*
- (?:
- (?<=\s) # lookbehind for whitespace
- ["(]
- (.*?) # title = $4
- [")]
- [ ]*
- )? # title is optional
- (?:[ ]* '.$this->id_class_attr_catch_re.' )? # $5 = extra id & class attr
- (?:\n+|\Z)
- }xm',
- array(&$this, '_stripLinkDefinitions_callback'),
- $text);
- return $text;
- }
- function _stripLinkDefinitions_callback($matches) {
- $link_id = strtolower($matches[1]);
- $url = $matches[2] == '' ? $matches[3] : $matches[2];
- $this->urls[$link_id] = $url;
- $this->titles[$link_id] =& $matches[4];
- $this->ref_attr[$link_id] = $this->doExtraAttributes("", $dummy =& $matches[5]);
- return ''; # String that will replace the block
- }
- ### HTML Block Parser ###
-
- # Tags that are always treated as block tags:
- var $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption';
-
- # Tags treated as block tags only if the opening tag is alone on its line:
- var $context_block_tags_re = 'script|noscript|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
-
- # Tags where markdown="1" default to span mode:
- var $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
-
- # Tags which must not have their contents modified, no matter where
- # they appear:
- var $clean_tags_re = 'script|math|svg';
-
- # Tags that do not need to be closed.
- var $auto_close_tags_re = 'hr|img|param|source|track';
-
- function hashHTMLBlocks($text) {
- #
- # Hashify HTML Blocks and "clean tags".
- #
- # We only want to do this for block-level HTML tags, such as headers,
- # lists, and tables. That's because we still want to wrap <p>s around
- # "paragraphs" that are wrapped in non-block-level tags, such as anchors,
- # phrase emphasis, and spans. The list of tags we're looking for is
- # hard-coded.
- #
- # This works by calling _HashHTMLBlocks_InMarkdown, which then calls
- # _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
- # attribute is found within a tag, _HashHTMLBlocks_InHTML calls back
- # _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
- # These two functions are calling each other. It's recursive!
- #
- if ($this->no_markup) return $text;
- #
- # Call the HTML-in-Markdown hasher.
- #
- list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
-
- return $text;
- }
- function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
- $enclosing_tag_re = '', $span = false)
- {
- #
- # Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
- #
- # * $indent is the number of space to be ignored when checking for code
- # blocks. This is important because if we don't take the indent into
- # account, something like this (which looks right) won't work as expected:
- #
- # <div>
- # <div markdown="1">
- # Hello World. <-- Is this a Markdown code block or text?
- # </div> <-- Is this a Markdown code block or a real tag?
- # <div>
- #
- # If you don't like this, just don't indent the tag on which
- # you apply the markdown="1" attribute.
- #
- # * If $enclosing_tag_re is not empty, stops at the first unmatched closing
- # tag with that name. Nested tags supported.
- #
- # * If $span is true, text inside must treated as span. So any double
- # newline will be replaced by a single newline so that it does not create
- # paragraphs.
- #
- # Returns an array of that form: ( processed text , remaining text )
- #
- if ($text === '') return array('', '');
- # Regex to check for the presense of newlines around a block tag.
- $newline_before_re = '/(?:^\n?|\n\n)*$/';
- $newline_after_re =
- '{
- ^ # Start of text following the tag.
- (?>[ ]*<!--.*?-->)? # Optional comment.
- [ ]*\n # Must be followed by newline.
- }xs';
-
- # Regex to match any tag.
- $block_tag_re =
- '{
- ( # $2: Capture whole tag.
- </? # Any opening or closing tag.
- (?> # Tag name.
- '.$this->block_tags_re.' |
- '.$this->context_block_tags_re.' |
- '.$this->clean_tags_re.' |
- (?!\s)'.$enclosing_tag_re.'
- )
- (?:
- (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
- (?>
- ".*?" | # Double quotes (can contain `>`)
- \'.*?\' | # Single quotes (can contain `>`)
- .+? # Anything but quotes and `>`.
- )*?
- )?
- > # End of tag.
- |
- <!-- .*? --> # HTML Comment
- |
- <\?.*?\?> | <%.*?%> # Processing instruction
- |
- <!\[CDATA\[.*?\]\]> # CData Block
- '. ( !$span ? ' # If not in span.
- |
- # Indented code block
- (?: ^[ ]*\n | ^ | \n[ ]*\n )
- [ ]{'.($indent+4).'}[^\n]* \n
- (?>
- (?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
- )*
- |
- # Fenced code block marker
- (?<= ^ | \n )
- [ ]{0,'.($indent+3).'}(?:~{3,}|`{3,})
- [ ]*
- (?:
- \.?[-_:a-zA-Z0-9]+ # standalone class name
- |
- '.$this->id_class_attr_nocatch_re.' # extra attributes
- )?
- [ ]*
- (?= \n )
- ' : '' ). ' # End (if not is span).
- |
- # Code span marker
- # Note, this regex needs to go after backtick fenced
- # code blocks but it should also be kept outside of the
- # "if not in span" condition adding backticks to the parser
- `+
- )
- }xs';
-
- $depth = 0; # Current depth inside the tag tree.
- $parsed = ""; # Parsed text that will be returned.
- #
- # Loop through every tag until we find the closing tag of the parent
- # or loop until reaching the end of text if no parent tag specified.
- #
- do {
- #
- # Split the text using the first $tag_match pattern found.
- # Text before pattern will be first in the array, text after
- # pattern will be at the end, and between will be any catches made
- # by the pattern.
- #
- $parts = preg_split($block_tag_re, $text, 2,
- PREG_SPLIT_DELIM_CAPTURE);
-
- # If in Markdown span mode, add a empty-string span-level hash
- # after each newline to prevent triggering any block element.
- if ($span) {
- $void = $this->hashPart("", ':');
- $newline = "$void\n";
- $parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
- }
-
- $parsed .= $parts[0]; # Text before current tag.
-
- # If end of $text has been reached. Stop loop.
- if (count($parts) < 3) {
- $text = "";
- break;
- }
-
- $tag = $parts[1]; # Tag to handle.
- $text = $parts[2]; # Remaining text after current tag.
- $tag_re = preg_quote($tag); # For use in a regular expression.
-
- #
- # Check for: Fenced code block marker.
- # Note: need to recheck the whole tag to disambiguate backtick
- # fences from code spans
- #
- if (preg_match('{^\n?([ ]{0,'.($indent+3).'})(~{3,}|`{3,})[ ]*(?:\.?[-_:a-zA-Z0-9]+|'.$this->id_class_attr_nocatch_re.')?[ ]*\n?$}', $tag, $capture)) {
- # Fenced code block marker: find matching end marker.
- $fence_indent = strlen($capture[1]); # use captured indent in re
- $fence_re = $capture[2]; # use captured fence in re
- if (preg_match('{^(?>.*\n)*?[ ]{'.($fence_indent).'}'.$fence_re.'[ ]*(?:\n|$)}', $text,
- $matches))
- {
- # End marker found: pass text unchanged until marker.
- $parsed .= $tag . $matches[0];
- $text = substr($text, strlen($matches[0]));
- }
- else {
- # No end marker: just skip it.
- $parsed .= $tag;
- }
- }
- #
- # Check for: Indented code block.
- #
- else if ($tag{0} == "\n" || $tag{0} == " ") {
- # Indented code block: pass it unchanged, will be handled
- # later.
- $parsed .= $tag;
- }
- #
- # Check for: Code span marker
- # Note: need to check this after backtick fenced code blocks
- #
- else if ($tag{0} == "`") {
- # Find corresponding end marker.
- $tag_re = preg_quote($tag);
- if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}',
- $text, $matches))
- {
- # End marker found: pass text unchanged until marker.
- $parsed .= $tag . $matches[0];
- $text = substr($text, strlen($matches[0]));
- }
- else {
- # Unmatched marker: just skip it.
- $parsed .= $tag;
- }
- }
- #
- # Check for: Opening Block level tag or
- # Opening Context Block tag (like ins and del)
- # used as a block tag (tag is alone on it's line).
- #
- else if (preg_match('{^<(?:'.$this->block_tags_re.')\b}', $tag) ||
- ( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
- preg_match($newline_before_re, $parsed) &&
- preg_match($newline_after_re, $text) )
- )
- {
- # Need to parse tag and following text using the HTML parser.
- list($block_text, $text) =
- $this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
-
- # Make sure it stays outside of any paragraph by adding newlines.
- $parsed .= "\n\n$block_text\n\n";
- }
- #
- # Check for: Clean tag (like script, math)
- # HTML Comments, processing instructions.
- #
- else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
- $tag{1} == '!' || $tag{1} == '?')
- {
- # Need to parse tag and following text using the HTML parser.
- # (don't check for markdown attribute)
- list($block_text, $text) =
- $this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
-
- $parsed .= $block_text;
- }
- #
- # Check for: Tag with same name as enclosing tag.
- #
- else if ($enclosing_tag_re !== '' &&
- # Same name as enclosing tag.
- preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag))
- {
- #
- # Increase/decrease nested tag count.
- #
- if ($tag{1} == '/') $depth--;
- else if ($tag{strlen($tag)-2} != '/') $depth++;
- if ($depth < 0) {
- #
- # Going out of parent element. Clean up and break so we
- # return to the calling function.
- #
- $text = $tag . $text;
- break;
- }
-
- $parsed .= $tag;
- }
- else {
- $parsed .= $tag;
- }
- } while ($depth >= 0);
-
- return array($parsed, $text);
- }
- function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) {
- #
- # Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
- #
- # * Calls $hash_method to convert any blocks.
- # * Stops when the first opening tag closes.
- # * $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
- # (it is not inside clean tags)
- #
- # Returns an array of that form: ( processed text , remaining text )
- #
- if ($text === '') return array('', '');
-
- # Regex to match `markdown` attribute inside of a tag.
- $markdown_attr_re = '
- {
- \s* # Eat whitespace before the `markdown` attribute
- markdown
- \s*=\s*
- (?>
- (["\']) # $1: quote delimiter
- (.*?) # $2: attribute value
- \1 # matching delimiter
- |
- ([^\s>]*) # $3: unquoted attribute value
- )
- () # $4: make $3 always defined (avoid warnings)
- }xs';
-
- # Regex to match any tag.
- $tag_re = '{
- ( # $2: Capture whole tag.
- </? # Any opening or closing tag.
- [\w:$]+ # Tag name.
- (?:
- (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
- (?>
- ".*?" | # Double quotes (can contain `>`)
- \'.*?\' | # Single quotes (can contain `>`)
- .+? # Anything but quotes and `>`.
- )*?
- )?
- > # End of tag.
- |
- <!-- .*? --> # HTML Comment
- |
- <\?.*?\?> | <%.*?%> # Processing instruction
- |
- <!\[CDATA\[.*?\]\]> # CData Block
- )
- }xs';
-
- $original_text = $text; # Save original text in case of faliure.
-
- $depth = 0; # Current depth inside the tag tree.
- $block_text = ""; # Temporary text holder for current text.
- $parsed = ""; # Parsed text that will be returned.
- #
- # Get the name of the starting tag.
- # (This pattern makes $base_tag_name_re safe without quoting.)
- #
- if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
- $base_tag_name_re = $matches[1];
- #
- # Loop through every tag until we find the corresponding closing tag.
- #
- do {
- #
- # Split the text using the first $tag_match pattern found.
- # Text before pattern will be first in the array, text after
- # pattern will be at the end, and between will be any catches made
- # by the pattern.
- #
- $parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
-
- if (count($parts) < 3) {
- #
- # End of $text reached with unbalenced tag(s).
- # In that case, we return original text unchanged and pass the
- # first character as filtered to prevent an infinite loop in the
- # parent function.
- #
- return array($original_text{0}, substr($original_text, 1));
- }
-
- $block_text .= $parts[0]; # Text before current tag.
- $tag = $parts[1]; # Tag to handle.
- $text = $parts[2]; # Remaining text after current tag.
-
- #
- # Check for: Auto-close tag (like <hr/>)
- # Comments and Processing Instructions.
- #
- if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
- $tag{1} == '!' || $tag{1} == '?')
- {
- # Just add the tag to the block as if it was text.
- $block_text .= $tag;
- }
- else {
- #
- # Increase/decrease nested tag count. Only do so if
- # the tag's name match base tag's.
- #
- if (preg_match('{^</?'.$base_tag_name_re.'\b}', $tag)) {
- if ($tag{1} == '/') $depth--;
- else if ($tag{strlen($tag)-2} != '/') $depth++;
- }
-
- #
- # Check for `markdown="1"` attribute and handle it.
- #
- if ($md_attr &&
- preg_match($markdown_attr_re, $tag, $attr_m) &&
- preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3]))
- {
- # Remove `markdown` attribute from opening tag.
- $tag = preg_replace($markdown_attr_re, '', $tag);
-
- # Check if text inside this tag must be parsed in span mode.
- $this->mode = $attr_m[2] . $attr_m[3];
- $span_mode = $this->mode == 'span' || $this->mode != 'block' &&
- preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
-
- # Calculate indent before tag.
- if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
- $strlen = $this->utf8_strlen;
- $indent = $strlen($matches[1], 'UTF-8');
- } else {
- $indent = 0;
- }
-
- # End preceding block with this tag.
- $block_text .= $tag;
- $parsed .= $this->$hash_method($block_text);
-
- # Get enclosing tag name for the ParseMarkdown function.
- # (This pattern makes $tag_name_re safe without quoting.)
- preg_match('/^<([\w:$]*)\b/', $tag, $matches);
- $tag_name_re = $matches[1];
-
- # Parse the content using the HTML-in-Markdown parser.
- list ($block_text, $text)
- = $this->_hashHTMLBlocks_inMarkdown($text, $indent,
- $tag_name_re, $span_mode);
-
- # Outdent markdown text.
- if ($indent > 0) {
- $block_text = preg_replace("/^[ ]{1,$indent}/m", "",
- $block_text);
- }
-
- # Append tag content to parsed text.
- if (!$span_mode) $parsed .= "\n\n$block_text\n\n";
- else $parsed .= "$block_text";
-
- # Start over with a new block.
- $block_text = "";
- }
- else $block_text .= $tag;
- }
-
- } while ($depth > 0);
-
- #
- # Hash last block text that wasn't processed inside the loop.
- #
- $parsed .= $this->$hash_method($block_text);
-
- return array($parsed, $text);
- }
- function hashClean($text) {
- #
- # Called whenever a tag must be hashed when a function inserts a "clean" tag
- # in $text, it passes through this function and is automaticaly escaped,
- # blocking invalid nested overlap.
- #
- return $this->hashPart($text, 'C');
- }
- function doAnchors($text) {
- #
- # Turn Markdown link shortcuts into XHTML <a> tags.
- #
- if ($this->in_anchor) return $text;
- $this->in_anchor = true;
-
- #
- # First, handle reference-style links: [link text] [id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
- \[
- (.*?) # id = $3
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
- #
- # Next, inline-style links: [link text](url "optional title")
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ('.$this->nested_brackets_re.') # link text = $2
- \]
- \( # literal paren
- [ \n]*
- (?:
- <(.+?)> # href = $3
- |
- ('.$this->nested_url_parenthesis_re.') # href = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # Title = $7
- \6 # matching quote
- [ \n]* # ignore any spaces/tabs between closing quote and )
- )? # title is optional
- \)
- (?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
- )
- }xs',
- array(&$this, '_doAnchors_inline_callback'), $text);
- #
- # Last, handle reference-style shortcuts: [link text]
- # These must come last in case you've also got [link text][1]
- # or [link text](/foo)
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- \[
- ([^\[\]]+) # link text = $2; can\'t contain [ or ]
- \]
- )
- }xs',
- array(&$this, '_doAnchors_reference_callback'), $text);
- $this->in_anchor = false;
- return $text;
- }
- function _doAnchors_reference_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $matches[2];
- $link_id =& $matches[3];
- if ($link_id == "") {
- # for shortcut links like [this][] or [this].
- $link_id = $link_text;
- }
-
- # lower-case and turn embedded newlines into spaces
- $link_id = strtolower($link_id);
- $link_id = preg_replace('{[ ]?\n}', ' ', $link_id);
- if (isset($this->urls[$link_id])) {
- $url = $this->urls[$link_id];
- $url = $this->encodeAttribute($url);
-
- $result = "<a href=\"$url\"";
- if ( isset( $this->titles[$link_id] ) ) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- if (isset($this->ref_attr[$link_id]))
- $result .= $this->ref_attr[$link_id];
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text</a>";
- $result = $this->hashPart($result);
- }
- else {
- $result = $whole_match;
- }
- return $result;
- }
- function _doAnchors_inline_callback($matches) {
- $whole_match = $matches[1];
- $link_text = $this->runSpanGamut($matches[2]);
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
- $attr = $this->doExtraAttributes("a", $dummy =& $matches[8]);
- $url = $this->encodeAttribute($url);
- $result = "<a href=\"$url\"";
- if (isset($title)) {
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- $result .= $attr;
-
- $link_text = $this->runSpanGamut($link_text);
- $result .= ">$link_text</a>";
- return $this->hashPart($result);
- }
- function doImages($text) {
- #
- # Turn Markdown image shortcuts into <img> tags.
- #
- #
- # First, handle reference-style labeled images: ![alt text][id]
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
- [ ]? # one optional space
- (?:\n[ ]*)? # one optional newline followed by spaces
- \[
- (.*?) # id = $3
- \]
- )
- }xs',
- array(&$this, '_doImages_reference_callback'), $text);
- #
- # Next, handle inline images: ![alt text](url "optional title")
- # Don't forget: encode * and _
- #
- $text = preg_replace_callback('{
- ( # wrap whole match in $1
- !\[
- ('.$this->nested_brackets_re.') # alt text = $2
- \]
- \s? # One optional whitespace character
- \( # literal paren
- [ \n]*
- (?:
- <(\S*)> # src url = $3
- |
- ('.$this->nested_url_parenthesis_re.') # src url = $4
- )
- [ \n]*
- ( # $5
- ([\'"]) # quote char = $6
- (.*?) # title = $7
- \6 # matching quote
- [ \n]*
- )? # title is optional
- \)
- (?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
- )
- }xs',
- array(&$this, '_doImages_inline_callback'), $text);
- return $text;
- }
- function _doImages_reference_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $link_id = strtolower($matches[3]);
- if ($link_id == "") {
- $link_id = strtolower($alt_text); # for shortcut links like ![this][].
- }
- $alt_text = $this->encodeAttribute($alt_text);
- if (isset($this->urls[$link_id])) {
- $url = $this->encodeAttribute($this->urls[$link_id]);
- $result = "<img src=\"$url\" alt=\"$alt_text\"";
- if (isset($this->titles[$link_id])) {
- $title = $this->titles[$link_id];
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\"";
- }
- if (isset($this->ref_attr[$link_id]))
- $result .= $this->ref_attr[$link_id];
- $result .= $this->empty_element_suffix;
- $result = $this->hashPart($result);
- }
- else {
- # If there's no such link ID, leave intact:
- $result = $whole_match;
- }
- return $result;
- }
- function _doImages_inline_callback($matches) {
- $whole_match = $matches[1];
- $alt_text = $matches[2];
- $url = $matches[3] == '' ? $matches[4] : $matches[3];
- $title =& $matches[7];
- $attr = $this->doExtraAttributes("img", $dummy =& $matches[8]);
- $alt_text = $this->encodeAttribute($alt_text);
- $url = $this->encodeAttribute($url);
- $result = "<img src=\"$url\" alt=\"$alt_text\"";
- if (isset($title)) {
- $title = $this->encodeAttribute($title);
- $result .= " title=\"$title\""; # $title already quoted
- }
- $result .= $attr;
- $result .= $this->empty_element_suffix;
- return $this->hashPart($result);
- }
- function doHeaders($text) {
- #
- # Redefined to add id and class attribute support.
- #
- # Setext-style headers:
- # Header 1 {#header1}
- # ========
- #
- # Header 2 {#header2 .class1 .class2}
- # --------
- #
- $text = preg_replace_callback(
- '{
- (^.+?) # $1: Header text
- (?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
- [ ]*\n(=+|-+)[ ]*\n+ # $3: Header footer
- }mx',
- array(&$this, '_doHeaders_callback_setext'), $text);
- # atx-style headers:
- # # Header 1 {#header1}
- # ## Header 2 {#header2}
- # ## Header 2 with closing hashes ## {#header3.class1.class2}
- # ...
- # ###### Header 6 {.class2}
- #
- $text = preg_replace_callback('{
- ^(\#{1,6}) # $1 = string of #\'s
- [ ]*
- (.+?) # $2 = Header text
- [ ]*
- \#* # optional closing #\'s (not counted)
- (?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
- [ ]*
- \n+
- }xm',
- array(&$this, '_doHeaders_callback_atx'), $text);
- return $text;
- }
- function _doHeaders_callback_setext($matches) {
- if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
- return $matches[0];
- $level = $matches[3]{0} == '=' ? 1 : 2;
- $attr = $this->doExtraAttributes("h$level", $dummy =& $matches[2]);
- $block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
- function _doHeaders_callback_atx($matches) {
- $level = strlen($matches[1]);
- $attr = $this->doExtraAttributes("h$level", $dummy =& $matches[3]);
- $block = "<h$level$attr>".$this->runSpanGamut($matches[2])."</h$level>";
- return "\n" . $this->hashBlock($block) . "\n\n";
- }
- function doTables($text) {
- #
- # Form HTML tables.
- #
- $less_than_tab = $this->tab_width - 1;
- #
- # Find tables with leading pipe.
- #
- # | Header 1 | Header 2
- # | -------- | --------
- # | Cell 1 | Cell 2
- # | Cell 3 | Cell 4
- #
- $text = preg_replace_callback('
- {
- ^ # Start of a line
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- [|] # Optional leading pipe (present)
- (.+) \n # $1: Header row (at least one pipe)
-
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- [|] ([ ]*[-:]+[-| :]*) \n # $2: Header underline
-
- ( # $3: Cells
- (?>
- [ ]* # Allowed whitespace.
- [|] .* \n # Row content.
- )*
- )
- (?=\n|\Z) # Stop at final double newline.
- }xm',
- array(&$this, '_doTable_leadingPipe_callback'), $text);
-
- #
- # Find tables without leading pipe.
- #
- # Header 1 | Header 2
- # -------- | --------
- # Cell 1 | Cell 2
- # Cell 3 | Cell 4
- #
- $text = preg_replace_callback('
- {
- ^ # Start of a line
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- (\S.*[|].*) \n # $1: Header row (at least one pipe)
-
- [ ]{0,'.$less_than_tab.'} # Allowed whitespace.
- ([-:]+[ ]*[|][-| :]*) \n # $2: Header underline
-
- ( # $3: Cells
- (?>
- .* [|] .* \n # Row content
- )*
- )
- (?=\n|\Z) # Stop at final double newline.
- }xm',
- array(&$this, '_DoTable_callback'), $text);
- return $text;
- }
- function _doTable_leadingPipe_callback($matches) {
- $head = $matches[1];
- $underline = $matches[2];
- $content = $matches[3];
-
- # Remove leading pipe for each row.
- $content = preg_replace('/^ *[|]/m', '', $content);
-
- return $this->_doTable_callback(array($matches[0], $head, $underline, $content));
- }
- function _doTable_callback($matches) {
- $head = $matches[1];
- $underline = $matches[2];
- $content = $matches[3];
- # Remove any tailing pipes for each line.
- $head = preg_replace('/[|] *$/m', '', $head);
- $underline = preg_replace('/[|] *$/m', '', $underline);
- $content = preg_replace('/[|] *$/m', '', $content);
-
- # Reading alignement from header underline.
- $separators = preg_split('/ *[|] */', $underline);
- foreach ($separators as $n => $s) {
- if (preg_match('/^ *-+: *$/', $s)) $attr[$n] = ' align="right"';
- else if (preg_match('/^ *:-+: *$/', $s))$attr[$n] = ' align="center"';
- else if (preg_match('/^ *:-+ *$/', $s)) $attr[$n] = ' align="left"';
- else $attr[$n] = '';
- }
-
- # Parsing span elements, including code spans, character escapes,
- # and inline HTML tags, so that pipes inside those gets ignored.
- $head = $this->parseSpan($head);
- $headers = preg_split('/ *[|] */', $head);
- $col_count = count($headers);
- $attr = array_pad($attr, $col_count, '');
-
- # Write column headers.
- $text = "<table>\n";
- $text .= "<thead>\n";
- $text .= "<tr>\n";
- foreach ($headers as $n => $header)
- $text .= " <th$attr[$n]>".$this->runSpanGamut(trim($header))."</th>\n";
- $text .= "</tr>\n";
- $text .= "</thead>\n";
-
- # Split content by row.
- $rows = explode("\n", trim($content, "\n"));
-
- $text .= "<tbody>\n";
- foreach ($rows as $row) {
- # Parsing span elements, including code spans, character escapes,
- # and inline HTML tags, so that pipes inside those gets ignored.
- $row = $this->parseSpan($row);
-
- # Split row by cell.
- $row_cells = preg_split('/ *[|] */', $row, $col_count);
- $row_cells = array_pad($row_cells, $col_count, '');
-
- $text .= "<tr>\n";
- foreach ($row_cells as $n => $cell)
- $text .= " <td$attr[$n]>".$this->runSpanGamut(trim($cell))."</td>\n";
- $text .= "</tr>\n";
- }
- $text .= "</tbody>\n";
- $text .= "</table>";
-
- return $this->hashBlock($text) . "\n";
- }
-
- function doDefLists($text) {
- #
- # Form HTML definition lists.
- #
- $less_than_tab = $this->tab_width - 1;
- # Re-usable pattern to match any entire dl list:
- $whole_list_re = '(?>
- ( # $1 = whole list
- ( # $2
- [ ]{0,'.$less_than_tab.'}
- ((?>.*\S.*\n)+) # $3 = defined term
- \n?
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
- )
- (?s:.+?)
- ( # $4
- \z
- |
- \n{2,}
- (?=\S)
- (?! # Negative lookahead for another term
- [ ]{0,'.$less_than_tab.'}
- (?: \S.*\n )+? # defined term
- \n?
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
- )
- (?! # Negative lookahead for another definition
- [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition
- )
- )
- )
- )'; // mx
- $text = preg_replace_callback('{
- (?>\A\n?|(?<=\n\n))
- '.$whole_list_re.'
- }mx',
- array(&$this, '_doDefLists_callback'), $text);
- return $text;
- }
- function _doDefLists_callback($matches) {
- # Re-usable patterns to match list item bullets and number markers:
- $list = $matches[1];
-
- # Turn double returns into triple returns, so that we can make a
- # paragraph for the last item in a list, if necessary:
- $result = trim($this->processDefListItems($list));
- $result = "<dl>\n" . $result . "\n</dl>";
- return $this->hashBlock($result) . "\n\n";
- }
- function processDefListItems($list_str) {
- #
- # Process the contents of a single definition list, splitting it
- # into individual term and definition list items.
- #
- $less_than_tab = $this->tab_width - 1;
-
- # trim trailing blank lines:
- $list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
- # Process definition terms.
- $list_str = preg_replace_callback('{
- (?>\A\n?|\n\n+) # leading line
- ( # definition terms = $1
- [ ]{0,'.$less_than_tab.'} # leading whitespace
- (?!\:[ ]|[ ]) # negative lookahead for a definition
- # mark (colon) or more whitespace.
- (?> \S.* \n)+? # actual term (not whitespace).
- )
- (?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
- # with a definition mark.
- }xm',
- array(&$this, '_processDefListItems_callback_dt'), $list_str);
- # Process actual definitions.
- $list_str = preg_replace_callback('{
- \n(\n+)? # leading line = $1
- ( # marker space = $2
- [ ]{0,'.$less_than_tab.'} # whitespace before colon
- \:[ ]+ # definition mark (colon)
- )
- ((?s:.+?)) # definition text = $3
- (?= \n+ # stop at next definition mark,
- (?: # next term or end of text
- [ ]{0,'.$less_than_tab.'} \:[ ] |
- <dt> | \z
- )
- )
- }xm',
- array(&$this, '_processDefListItems_callback_dd'), $list_str);
- return $list_str;
- }
- function _processDefListItems_callback_dt($matches) {
- $terms = explode("\n", trim($matches[1]));
- $text = '';
- foreach ($terms as $term) {
- $term = $this->runSpanGamut(trim($term));
- $text .= "\n<dt>" . $term . "</dt>";
- }
- return $text . "\n";
- }
- function _processDefListItems_callback_dd($matches) {
- $leading_line = $matches[1];
- $marker_space = $matches[2];
- $def = $matches[3];
- if ($leading_line || preg_match('/\n{2,}/', $def)) {
- # Replace marker with the appropriate whitespace indentation
- $def = str_repeat(' ', strlen($marker_space)) . $def;
- $def = $this->runBlockGamut($this->outdent($def . "\n\n"));
- $def = "\n". $def ."\n";
- }
- else {
- $def = rtrim($def);
- $def = $this->runSpanGamut($this->outdent($def));
- }
- return "\n<dd>" . $def . "</dd>\n";
- }
- function doFencedCodeBlocks($text) {
- #
- # Adding the fenced code block syntax to regular Markdown:
- #
- # ~~~
- # Code block
- # ~~~
- #
- $less_than_tab = $this->tab_width;
-
- $text = preg_replace_callback('{
- (?:\n|\A)
- # 1: Opening marker
- (
- (?:~{3,}|`{3,}) # 3 or more tildes/backticks.
- )
- [ ]*
- (?:
- \.?([-_:a-zA-Z0-9]+) # 2: standalone class name
- |
- '.$this->id_class_attr_catch_re.' # 3: Extra attributes
- )?
- [ ]* \n # Whitespace and newline following marker.
-
- # 4: Content
- (
- (?>
- (?!\1 [ ]* \n) # Not a closing marker.
- .*\n+
- )+
- )
-
- # Closing marker.
- \1 [ ]* (?= \n )
- }xm',
- array(&$this, '_doFencedCodeBlocks_callback'), $text);
- return $text;
- }
- function _doFencedCodeBlocks_callback($matches) {
- $classname =& $matches[2];
- $attrs =& $matches[3];
- $codeblock = $matches[4];
- $codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
- $codeblock = preg_replace_callback('/^\n+/',
- array(&$this, '_doFencedCodeBlocks_newlines'), $codeblock);
- if ($classname != "") {
- if ($classname{0} == '.')
- $classname = substr($classname, 1);
- $attr_str = ' class="'.$this->code_class_prefix.$classname.'"';
- } else {
- $attr_str = $this->doExtraAttributes($this->code_attr_on_pre ? "pre" : "code", $attrs);
- }
- $pre_attr_str = $this->code_attr_on_pre ? $attr_str : '';
- $code_attr_str = $this->code_attr_on_pre ? '' : $attr_str;
- $codeblock = "<pre$pre_attr_str><code$code_attr_str>$codeblock</code></pre>";
-
- return "\n\n".$this->hashBlock($codeblock)."\n\n";
- }
- function _doFencedCodeBlocks_newlines($matches) {
- return str_repeat("<br$this->empty_element_suffix",
- strlen($matches[0]));
- }
- #
- # Redefining emphasis markers so that emphasis by underscore does not
- # work in the middle of a word.
- #
- var $em_relist = array(
- '' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?=\S|$)(?![\.,:;]\s)',
- '*' => '(?<=\S|^)(?<!\*)\*(?!\*)',
- '_' => '(?<=\S|^)(?<!_)_(?![a-zA-Z0-9_])',
- );
- var $strong_relist = array(
- '' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?=\S|$)(?![\.,:;]\s)',
- '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)',
- '__' => '(?<=\S|^)(?<!_)__(?![a-zA-Z0-9_])',
- );
- var $em_strong_relist = array(
- '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?=\S|$)(?![\.,:;]\s)',
- '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)',
- '___' => '(?<=\S|^)(?<!_)___(?![a-zA-Z0-9_])',
- );
- function formParagraphs($text) {
- #
- # Params:
- # $text - string to process with html <p> tags
- #
- # Strip leading and trailing lines:
- $text = preg_replace('/\A\n+|\n+\z/', '', $text);
-
- $grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
- #
- # Wrap <p> tags and unhashify HTML blocks
- #
- foreach ($grafs as $key => $value) {
- $value = trim($this->runSpanGamut($value));
-
- # Check if this should be enclosed in a paragraph.
- # Clean tag hashes & block tag hashes are left alone.
- $is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
-
- if ($is_p) {
- $value = "<p>$value</p>";
- }
- $grafs[$key] = $value;
- }
-
- # Join grafs in one text, then unhash HTML tags.
- $text = implode("\n\n", $grafs);
-
- # Finish by removing any tag hashes still present in $text.
- $text = $this->unhash($text);
-
- return $text;
- }
-
-
- ### Footnotes
-
- function stripFootnotes($text) {
- #
- # Strips link definitions from text, stores the URLs and titles in
- # hash references.
- #
- $less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: [^id]: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1
- [ ]*
- \n? # maybe *one* newline
- ( # text = $2 (no blank lines allowed)
- (?:
- .+ # actual text
- |
- \n # newlines but
- (?!\[\^.+?\]:\s)# negative lookahead for footnote marker.
- (?!\n+[ ]{0,3}\S)# ensure line is not blank and followed
- # by non-indented content
- )*
- )
- }xm',
- array(&$this, '_stripFootnotes_callback'),
- $text);
- return $text;
- }
- function _stripFootnotes_callback($matches) {
- $note_id = $this->fn_id_prefix . $matches[1];
- $this->footnotes[$note_id] = $this->outdent($matches[2]);
- return ''; # String that will replace the block
- }
- function doFootnotes($text) {
- #
- # Replace footnote references in $text [^id] with a special text-token
- # which will be replaced by the actual footnote marker in appendFootnotes.
- #
- if (!$this->in_anchor) {
- $text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
- }
- return $text;
- }
-
- function appendFootnotes($text) {
- #
- # Append footnote list to text.
- #
- $text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
- array(&$this, '_appendFootnotes_callback'), $text);
-
- if (!empty($this->footnotes_ordered)) {
- $text .= "\n\n";
- $text .= "<div class=\"footnotes\">\n";
- $text .= "<hr". $this->empty_element_suffix ."\n";
- $text .= "<ol>\n\n";
-
- $attr = " rev=\"footnote\"";
- if ($this->fn_backlink_class != "") {
- $class = $this->fn_backlink_class;
- $class = $this->encodeAttribute($class);
- $attr .= " class=\"$class\"";
- }
- if ($this->fn_backlink_title != "") {
- $title = $this->fn_backlink_title;
- $title = $this->encodeAttribute($title);
- $attr .= " title=\"$title\"";
- }
- $num = 0;
-
- while (!empty($this->footnotes_ordered)) {
- $footnote = reset($this->footnotes_ordered);
- $note_id = key($this->footnotes_ordered);
- unset($this->footnotes_ordered[$note_id]);
- $ref_count = $this->footnotes_ref_count[$note_id];
- unset($this->footnotes_ref_count[$note_id]);
- unset($this->footnotes[$note_id]);
-
- $footnote .= "\n"; # Need to append newline before parsing.
- $footnote = $this->runBlockGamut("$footnote\n");
- $footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
- array(&$this, '_appendFootnotes_callback'), $footnote);
-
- $attr = str_replace("%%", ++$num, $attr);
- $note_id = $this->encodeAttribute($note_id);
- # Prepare backlink, multiple backlinks if multiple references
- $backlink = "<a href=\"#fnref:$note_id\"$attr>↩</a>";
- for ($ref_num = 2; $ref_num <= $ref_count; ++$ref_num) {
- $backlink .= " <a href=\"#fnref$ref_num:$note_id\"$attr>↩</a>";
- }
- # Add backlink to last paragraph; create new paragraph if needed.
- if (preg_match('{</p>$}', $footnote)) {
- $footnote = substr($footnote, 0, -4) . " $backlink</p>";
- } else {
- $footnote .= "\n\n<p>$backlink</p>";
- }
-
- $text .= "<li id=\"fn:$note_id\">\n";
- $text .= $footnote . "\n";
- $text .= "</li>\n\n";
- }
-
- $text .= "</ol>\n";
- $text .= "</div>";
- }
- return $text;
- }
- function _appendFootnotes_callback($matches) {
- $node_id = $this->fn_id_prefix . $matches[1];
-
- # Create footnote marker only if it has a corresponding footnote *and*
- # the footnote hasn't been used by another marker.
- if (isset($this->footnotes[$node_id])) {
- $num =& $this->footnotes_numbers[$node_id];
- if (!isset($num)) {
- # Transfer footnote content to the ordered list and give it its
- # number
- $this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
- $this->footnotes_ref_count[$node_id] = 1;
- $num = $this->footnote_counter++;
- $ref_count_mark = '';
- } else {
- $ref_count_mark = $this->footnotes_ref_count[$node_id] += 1;
- }
-
- $attr = " rel=\"footnote\"";
- if ($this->fn_link_class != "") {
- $class = $this->fn_link_class;
- $class = $this->encodeAttribute($class);
- $attr .= " class=\"$class\"";
- }
- if ($this->fn_link_title != "") {
- $title = $this->fn_link_title;
- $title = $this->encodeAttribute($title);
- $attr .= " title=\"$title\"";
- }
-
- $attr = str_replace("%%", $num, $attr);
- $node_id = $this->encodeAttribute($node_id);
-
- return
- "<sup id=\"fnref$ref_count_mark:$node_id\">".
- "<a href=\"#fn:$node_id\"$attr>$num</a>".
- "</sup>";
- }
-
- return "[^".$matches[1]."]";
- }
-
-
- ### Abbreviations ###
-
- function stripAbbreviations($text) {
- #
- # Strips abbreviations from text, stores titles in hash references.
- #
- $less_than_tab = $this->tab_width - 1;
- # Link defs are in the form: [id]*: url "optional title"
- $text = preg_replace_callback('{
- ^[ ]{0,'.$less_than_tab.'}\*\[(.+?)\][ ]?: # abbr_id = $1
- (.*) # text = $2 (no blank lines allowed)
- }xm',
- array(&$this, '_stripAbbreviations_callback'),
- $text);
- return $text;
- }
- function _stripAbbreviations_callback($matches) {
- $abbr_word = $matches[1];
- $abbr_desc = $matches[2];
- if ($this->abbr_word_re)
- $this->abbr_word_re .= '|';
- $this->abbr_word_re .= preg_quote($abbr_word);
- $this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
- return ''; # String that will replace the block
- }
-
-
- function doAbbreviations($text) {
- #
- # Find defined abbreviations in text and wrap them in <abbr> elements.
- #
- if ($this->abbr_word_re) {
- // cannot use the /x modifier because abbr_word_re may
- // contain significant spaces:
- $text = preg_replace_callback('{'.
- '(?<![\w\x1A])'.
- '(?:'.$this->abbr_word_re.')'.
- '(?![\w\x1A])'.
- '}',
- array(&$this, '_doAbbreviations_callback'), $text);
- }
- return $text;
- }
- function _doAbbreviations_callback($matches) {
- $abbr = $matches[0];
- if (isset($this->abbr_desciptions[$abbr])) {
- $desc = $this->abbr_desciptions[$abbr];
- if (empty($desc)) {
- return $this->hashPart("<abbr>$abbr</abbr>");
- } else {
- $desc = $this->encodeAttribute($desc);
- return $this->hashPart("<abbr title=\"$desc\">$abbr</abbr>");
- }
- } else {
- return $matches[0];
- }
- }
- }
- /*
- PHP Markdown Extra
- ==================
- Description
- -----------
- This is a PHP port of the original Markdown formatter written in Perl
- by John Gruber. This special "Extra" version of PHP Markdown features
- further enhancements to the syntax for making additional constructs
- such as tables and definition list.
- Markdown is a text-to-HTML filter; it translates an easy-to-read /
- easy-to-write structured text format into HTML. Markdown's text format
- is mostly similar to that of plain text email, and supports features such
- as headers, *emphasis*, code blocks, blockquotes, and links.
- Markdown's syntax is designed not as a generic markup language, but
- specifically to serve as a front-end to (X)HTML. You can use span-level
- HTML tags anywhere in a Markdown document, and you can use block level
- HTML tags (like <div> and <table> as well).
- For more information about Markdown's syntax, see:
- <http://daringfireball.net/projects/markdown/>
- Bugs
- ----
- To file bug reports please send email to:
- <michel.fortin@michelf.ca>
- Please include with your report: (1) the example input; (2) the output you
- expected; (3) the output Markdown actually produced.
- Version History
- ---------------
- See the readme file for detailed release notes for this version.
- Copyright and License
- ---------------------
- PHP Markdown & Extra
- Copyright (c) 2004-2013 Michel Fortin
- <http://michelf.ca/>
- All rights reserved.
- Based on Markdown
- Copyright (c) 2003-2006 John Gruber
- <http://daringfireball.net/>
- All rights reserved.
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions are
- met:
- * Redistributions of source code must retain the above copyright notice,
- this list of conditions and the following disclaimer.
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in the
- documentation and/or other materials provided with the distribution.
- * Neither the name "Markdown" nor the names of its contributors may
- be used to endorse or promote products derived from this software
- without specific prior written permission.
- This software is provided by the copyright holders and contributors "as
- is" and any express or implied warranties, including, but not limited
- to, the implied warranties of merchantability and fitness for a
- particular purpose are disclaimed. In no event shall the copyright owner
- or contributors be liable for any direct, indirect, incidental, special,
- exemplary, or consequential damages (including, but not limited to,
- procurement of substitute goods or services; loss of use, data, or
- profits; or business interruption) however caused and on any theory of
- liability, whether in contract, strict liability, or tort (including
- negligence or otherwise) arising in any way out of the use of this
- software, even if advised of the possibility of such damage.
- */
- ?>
|