123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713 |
- <?php
- #
- #
- # Parsedown
- # http://parsedown.org
- #
- # (c) Emanuil Rusev
- # http://erusev.com
- #
- # For the full license information, view the LICENSE file that was distributed
- # with this source code.
- #
- #
- class Parsedown
- {
- # ~
- const version = '1.7.4';
- # ~
- function text($text)
- {
- # make sure no definitions are set
- $this->DefinitionData = array();
- # standardize line breaks
- $text = str_replace(array("\r\n", "\r"), "\n", $text);
- # remove surrounding line breaks
- $text = trim($text, "\n");
- # split text into lines
- $lines = explode("\n", $text);
- # iterate through lines to identify blocks
- $markup = $this->lines($lines);
- # trim line breaks
- $markup = trim($markup, "\n");
- return $markup;
- }
- #
- # Setters
- #
- function setBreaksEnabled($breaksEnabled)
- {
- $this->breaksEnabled = $breaksEnabled;
- return $this;
- }
- protected $breaksEnabled;
- function setMarkupEscaped($markupEscaped)
- {
- $this->markupEscaped = $markupEscaped;
- return $this;
- }
- protected $markupEscaped;
- function setUrlsLinked($urlsLinked)
- {
- $this->urlsLinked = $urlsLinked;
- return $this;
- }
- protected $urlsLinked = true;
- function setSafeMode($safeMode)
- {
- $this->safeMode = (bool) $safeMode;
- return $this;
- }
- protected $safeMode;
- protected $safeLinksWhitelist = array(
- 'http://',
- 'https://',
- 'ftp://',
- 'ftps://',
- 'mailto:',
- 'data:image/png;base64,',
- 'data:image/gif;base64,',
- 'data:image/jpeg;base64,',
- 'irc:',
- 'ircs:',
- 'git:',
- 'ssh:',
- 'news:',
- 'steam:',
- );
- #
- # Lines
- #
- protected $BlockTypes = array(
- '#' => array('Header'),
- '*' => array('Rule', 'List'),
- '+' => array('List'),
- '-' => array('SetextHeader', 'Table', 'Rule', 'List'),
- '0' => array('List'),
- '1' => array('List'),
- '2' => array('List'),
- '3' => array('List'),
- '4' => array('List'),
- '5' => array('List'),
- '6' => array('List'),
- '7' => array('List'),
- '8' => array('List'),
- '9' => array('List'),
- ':' => array('Table'),
- '<' => array('Comment', 'Markup'),
- '=' => array('SetextHeader'),
- '>' => array('Quote'),
- '[' => array('Reference'),
- '_' => array('Rule'),
- '`' => array('FencedCode'),
- '|' => array('Table'),
- '~' => array('FencedCode'),
- );
- # ~
- protected $unmarkedBlockTypes = array(
- 'Code',
- );
- #
- # Blocks
- #
- protected function lines(array $lines)
- {
- $CurrentBlock = null;
- foreach ($lines as $line)
- {
- if (chop($line) === '')
- {
- if (isset($CurrentBlock))
- {
- $CurrentBlock['interrupted'] = true;
- }
- continue;
- }
- if (strpos($line, "\t") !== false)
- {
- $parts = explode("\t", $line);
- $line = $parts[0];
- unset($parts[0]);
- foreach ($parts as $part)
- {
- $shortage = 4 - mb_strlen($line, 'utf-8') % 4;
- $line .= str_repeat(' ', $shortage);
- $line .= $part;
- }
- }
- $indent = 0;
- while (isset($line[$indent]) and $line[$indent] === ' ')
- {
- $indent ++;
- }
- $text = $indent > 0 ? substr($line, $indent) : $line;
- # ~
- $Line = array('body' => $line, 'indent' => $indent, 'text' => $text);
- # ~
- if (isset($CurrentBlock['continuable']))
- {
- $Block = $this->{'block'.$CurrentBlock['type'].'Continue'}($Line, $CurrentBlock);
- if (isset($Block))
- {
- $CurrentBlock = $Block;
- continue;
- }
- else
- {
- if ($this->isBlockCompletable($CurrentBlock['type']))
- {
- $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock);
- }
- }
- }
- # ~
- $marker = $text[0];
- # ~
- $blockTypes = $this->unmarkedBlockTypes;
- if (isset($this->BlockTypes[$marker]))
- {
- foreach ($this->BlockTypes[$marker] as $blockType)
- {
- $blockTypes []= $blockType;
- }
- }
- #
- # ~
- foreach ($blockTypes as $blockType)
- {
- $Block = $this->{'block'.$blockType}($Line, $CurrentBlock);
- if (isset($Block))
- {
- $Block['type'] = $blockType;
- if ( ! isset($Block['identified']))
- {
- $Blocks []= $CurrentBlock;
- $Block['identified'] = true;
- }
- if ($this->isBlockContinuable($blockType))
- {
- $Block['continuable'] = true;
- }
- $CurrentBlock = $Block;
- continue 2;
- }
- }
- # ~
- if (isset($CurrentBlock) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted']))
- {
- $CurrentBlock['element']['text'] .= "\n".$text;
- }
- else
- {
- $Blocks []= $CurrentBlock;
- $CurrentBlock = $this->paragraph($Line);
- $CurrentBlock['identified'] = true;
- }
- }
- # ~
- if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type']))
- {
- $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock);
- }
- # ~
- $Blocks []= $CurrentBlock;
- unset($Blocks[0]);
- # ~
- $markup = '';
- foreach ($Blocks as $Block)
- {
- if (isset($Block['hidden']))
- {
- continue;
- }
- $markup .= "\n";
- $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']);
- }
- $markup .= "\n";
- # ~
- return $markup;
- }
- protected function isBlockContinuable($Type)
- {
- return method_exists($this, 'block'.$Type.'Continue');
- }
- protected function isBlockCompletable($Type)
- {
- return method_exists($this, 'block'.$Type.'Complete');
- }
- #
- # Code
- protected function blockCode($Line, $Block = null)
- {
- if (isset($Block) and ! isset($Block['type']) and ! isset($Block['interrupted']))
- {
- return;
- }
- if ($Line['indent'] >= 4)
- {
- $text = substr($Line['body'], 4);
- $Block = array(
- 'element' => array(
- 'name' => 'pre',
- 'handler' => 'element',
- 'text' => array(
- 'name' => 'code',
- 'text' => $text,
- ),
- ),
- );
- return $Block;
- }
- }
- protected function blockCodeContinue($Line, $Block)
- {
- if ($Line['indent'] >= 4)
- {
- if (isset($Block['interrupted']))
- {
- $Block['element']['text']['text'] .= "\n";
- unset($Block['interrupted']);
- }
- $Block['element']['text']['text'] .= "\n";
- $text = substr($Line['body'], 4);
- $Block['element']['text']['text'] .= $text;
- return $Block;
- }
- }
- protected function blockCodeComplete($Block)
- {
- $text = $Block['element']['text']['text'];
- $Block['element']['text']['text'] = $text;
- return $Block;
- }
- #
- # Comment
- protected function blockComment($Line)
- {
- if ($this->markupEscaped or $this->safeMode)
- {
- return;
- }
- if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!')
- {
- $Block = array(
- 'markup' => $Line['body'],
- );
- if (preg_match('/-->$/', $Line['text']))
- {
- $Block['closed'] = true;
- }
- return $Block;
- }
- }
- protected function blockCommentContinue($Line, array $Block)
- {
- if (isset($Block['closed']))
- {
- return;
- }
- $Block['markup'] .= "\n" . $Line['body'];
- if (preg_match('/-->$/', $Line['text']))
- {
- $Block['closed'] = true;
- }
- return $Block;
- }
- #
- # Fenced Code
- protected function blockFencedCode($Line)
- {
- if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([^`]+)?[ ]*$/', $Line['text'], $matches))
- {
- $Element = array(
- 'name' => 'code',
- 'text' => '',
- );
- if (isset($matches[1]))
- {
- /**
- * https://www.w3.org/TR/2011/WD-html5-20110525/elements.html#classes
- * Every HTML element may have a class attribute specified.
- * The attribute, if specified, must have a value that is a set
- * of space-separated tokens representing the various classes
- * that the element belongs to.
- * [...]
- * The space characters, for the purposes of this specification,
- * are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab),
- * U+000A LINE FEED (LF), U+000C FORM FEED (FF), and
- * U+000D CARRIAGE RETURN (CR).
- */
- $language = substr($matches[1], 0, strcspn($matches[1], " \t\n\f\r"));
- $class = 'language-'.$language;
- $Element['attributes'] = array(
- 'class' => $class,
- );
- }
- $Block = array(
- 'char' => $Line['text'][0],
- 'element' => array(
- 'name' => 'pre',
- 'handler' => 'element',
- 'text' => $Element,
- ),
- );
- return $Block;
- }
- }
- protected function blockFencedCodeContinue($Line, $Block)
- {
- if (isset($Block['complete']))
- {
- return;
- }
- if (isset($Block['interrupted']))
- {
- $Block['element']['text']['text'] .= "\n";
- unset($Block['interrupted']);
- }
- if (preg_match('/^'.$Block['char'].'{3,}[ ]*$/', $Line['text']))
- {
- $Block['element']['text']['text'] = substr($Block['element']['text']['text'], 1);
- $Block['complete'] = true;
- return $Block;
- }
- $Block['element']['text']['text'] .= "\n".$Line['body'];
- return $Block;
- }
- protected function blockFencedCodeComplete($Block)
- {
- $text = $Block['element']['text']['text'];
- $Block['element']['text']['text'] = $text;
- return $Block;
- }
- #
- # Header
- protected function blockHeader($Line)
- {
- if (isset($Line['text'][1]))
- {
- $level = 1;
- while (isset($Line['text'][$level]) and $Line['text'][$level] === '#')
- {
- $level ++;
- }
- if ($level > 6)
- {
- return;
- }
- $text = trim($Line['text'], '# ');
- $Block = array(
- 'element' => array(
- 'name' => 'h' . min(6, $level),
- 'text' => $text,
- 'handler' => 'line',
- ),
- );
- return $Block;
- }
- }
- #
- # List
- protected function blockList($Line)
- {
- list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]');
- if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches))
- {
- $Block = array(
- 'indent' => $Line['indent'],
- 'pattern' => $pattern,
- 'element' => array(
- 'name' => $name,
- 'handler' => 'elements',
- ),
- );
- if($name === 'ol')
- {
- $listStart = stristr($matches[0], '.', true);
- if($listStart !== '1')
- {
- $Block['element']['attributes'] = array('start' => $listStart);
- }
- }
- $Block['li'] = array(
- 'name' => 'li',
- 'handler' => 'li',
- 'text' => array(
- $matches[2],
- ),
- );
- $Block['element']['text'] []= & $Block['li'];
- return $Block;
- }
- }
- protected function blockListContinue($Line, array $Block)
- {
- if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches))
- {
- if (isset($Block['interrupted']))
- {
- $Block['li']['text'] []= '';
- $Block['loose'] = true;
- unset($Block['interrupted']);
- }
- unset($Block['li']);
- $text = isset($matches[1]) ? $matches[1] : '';
- $Block['li'] = array(
- 'name' => 'li',
- 'handler' => 'li',
- 'text' => array(
- $text,
- ),
- );
- $Block['element']['text'] []= & $Block['li'];
- return $Block;
- }
- if ($Line['text'][0] === '[' and $this->blockReference($Line))
- {
- return $Block;
- }
- if ( ! isset($Block['interrupted']))
- {
- $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']);
- $Block['li']['text'] []= $text;
- return $Block;
- }
- if ($Line['indent'] > 0)
- {
- $Block['li']['text'] []= '';
- $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']);
- $Block['li']['text'] []= $text;
- unset($Block['interrupted']);
- return $Block;
- }
- }
- protected function blockListComplete(array $Block)
- {
- if (isset($Block['loose']))
- {
- foreach ($Block['element']['text'] as &$li)
- {
- if (end($li['text']) !== '')
- {
- $li['text'] []= '';
- }
- }
- }
- return $Block;
- }
- #
- # Quote
- protected function blockQuote($Line)
- {
- if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches))
- {
- $Block = array(
- 'element' => array(
- 'name' => 'blockquote',
- 'handler' => 'lines',
- 'text' => (array) $matches[1],
- ),
- );
- return $Block;
- }
- }
- protected function blockQuoteContinue($Line, array $Block)
- {
- if ($Line['text'][0] === '>' and preg_match('/^>[ ]?(.*)/', $Line['text'], $matches))
- {
- if (isset($Block['interrupted']))
- {
- $Block['element']['text'] []= '';
- unset($Block['interrupted']);
- }
- $Block['element']['text'] []= $matches[1];
- return $Block;
- }
- if ( ! isset($Block['interrupted']))
- {
- $Block['element']['text'] []= $Line['text'];
- return $Block;
- }
- }
- #
- # Rule
- protected function blockRule($Line)
- {
- if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text']))
- {
- $Block = array(
- 'element' => array(
- 'name' => 'hr'
- ),
- );
- return $Block;
- }
- }
- #
- # Setext
- protected function blockSetextHeader($Line, array $Block = null)
- {
- if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted']))
- {
- return;
- }
- if (chop($Line['text'], $Line['text'][0]) === '')
- {
- $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2';
- return $Block;
- }
- }
- #
- # Markup
- protected function blockMarkup($Line)
- {
- if ($this->markupEscaped or $this->safeMode)
- {
- return;
- }
- if (preg_match('/^<(\w[\w-]*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches))
- {
- $element = strtolower($matches[1]);
- if (in_array($element, $this->textLevelElements))
- {
- return;
- }
- $Block = array(
- 'name' => $matches[1],
- 'depth' => 0,
- 'markup' => $Line['text'],
- );
- $length = strlen($matches[0]);
- $remainder = substr($Line['text'], $length);
- if (trim($remainder) === '')
- {
- if (isset($matches[2]) or in_array($matches[1], $this->voidElements))
- {
- $Block['closed'] = true;
- $Block['void'] = true;
- }
- }
- else
- {
- if (isset($matches[2]) or in_array($matches[1], $this->voidElements))
- {
- return;
- }
- if (preg_match('/<\/'.$matches[1].'>[ ]*$/i', $remainder))
- {
- $Block['closed'] = true;
- }
- }
- return $Block;
- }
- }
- protected function blockMarkupContinue($Line, array $Block)
- {
- if (isset($Block['closed']))
- {
- return;
- }
- if (preg_match('/^<'.$Block['name'].'(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*>/i', $Line['text'])) # open
- {
- $Block['depth'] ++;
- }
- if (preg_match('/(.*?)<\/'.$Block['name'].'>[ ]*$/i', $Line['text'], $matches)) # close
- {
- if ($Block['depth'] > 0)
- {
- $Block['depth'] --;
- }
- else
- {
- $Block['closed'] = true;
- }
- }
- if (isset($Block['interrupted']))
- {
- $Block['markup'] .= "\n";
- unset($Block['interrupted']);
- }
- $Block['markup'] .= "\n".$Line['body'];
- return $Block;
- }
- #
- # Reference
- protected function blockReference($Line)
- {
- if (preg_match('/^\[(.+?)\]:[ ]*<?(\S+?)>?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches))
- {
- $id = strtolower($matches[1]);
- $Data = array(
- 'url' => $matches[2],
- 'title' => null,
- );
- if (isset($matches[3]))
- {
- $Data['title'] = $matches[3];
- }
- $this->DefinitionData['Reference'][$id] = $Data;
- $Block = array(
- 'hidden' => true,
- );
- return $Block;
- }
- }
- #
- # Table
- protected function blockTable($Line, array $Block = null)
- {
- if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted']))
- {
- return;
- }
- if (strpos($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '')
- {
- $alignments = array();
- $divider = $Line['text'];
- $divider = trim($divider);
- $divider = trim($divider, '|');
- $dividerCells = explode('|', $divider);
- foreach ($dividerCells as $dividerCell)
- {
- $dividerCell = trim($dividerCell);
- if ($dividerCell === '')
- {
- continue;
- }
- $alignment = null;
- if ($dividerCell[0] === ':')
- {
- $alignment = 'left';
- }
- if (substr($dividerCell, - 1) === ':')
- {
- $alignment = $alignment === 'left' ? 'center' : 'right';
- }
- $alignments []= $alignment;
- }
- # ~
- $HeaderElements = array();
- $header = $Block['element']['text'];
- $header = trim($header);
- $header = trim($header, '|');
- $headerCells = explode('|', $header);
- foreach ($headerCells as $index => $headerCell)
- {
- $headerCell = trim($headerCell);
- $HeaderElement = array(
- 'name' => 'th',
- 'text' => $headerCell,
- 'handler' => 'line',
- );
- if (isset($alignments[$index]))
- {
- $alignment = $alignments[$index];
- $HeaderElement['attributes'] = array(
- 'style' => 'text-align: '.$alignment.';',
- );
- }
- $HeaderElements []= $HeaderElement;
- }
- # ~
- $Block = array(
- 'alignments' => $alignments,
- 'identified' => true,
- 'element' => array(
- 'name' => 'table',
- 'handler' => 'elements',
- ),
- );
- $Block['element']['text'] []= array(
- 'name' => 'thead',
- 'handler' => 'elements',
- );
- $Block['element']['text'] []= array(
- 'name' => 'tbody',
- 'handler' => 'elements',
- 'text' => array(),
- );
- $Block['element']['text'][0]['text'] []= array(
- 'name' => 'tr',
- 'handler' => 'elements',
- 'text' => $HeaderElements,
- );
- return $Block;
- }
- }
- protected function blockTableContinue($Line, array $Block)
- {
- if (isset($Block['interrupted']))
- {
- return;
- }
- if ($Line['text'][0] === '|' or strpos($Line['text'], '|'))
- {
- $Elements = array();
- $row = $Line['text'];
- $row = trim($row);
- $row = trim($row, '|');
- preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches);
- foreach ($matches[0] as $index => $cell)
- {
- $cell = trim($cell);
- $Element = array(
- 'name' => 'td',
- 'handler' => 'line',
- 'text' => $cell,
- );
- if (isset($Block['alignments'][$index]))
- {
- $Element['attributes'] = array(
- 'style' => 'text-align: '.$Block['alignments'][$index].';',
- );
- }
- $Elements []= $Element;
- }
- $Element = array(
- 'name' => 'tr',
- 'handler' => 'elements',
- 'text' => $Elements,
- );
- $Block['element']['text'][1]['text'] []= $Element;
- return $Block;
- }
- }
- #
- # ~
- #
- protected function paragraph($Line)
- {
- $Block = array(
- 'element' => array(
- 'name' => 'p',
- 'text' => $Line['text'],
- 'handler' => 'line',
- ),
- );
- return $Block;
- }
- #
- # Inline Elements
- #
- protected $InlineTypes = array(
- '"' => array('SpecialCharacter'),
- '!' => array('Image'),
- '&' => array('SpecialCharacter'),
- '*' => array('Emphasis'),
- ':' => array('Url'),
- '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'),
- '>' => array('SpecialCharacter'),
- '[' => array('Link'),
- '_' => array('Emphasis'),
- '`' => array('Code'),
- '~' => array('Strikethrough'),
- '\\' => array('EscapeSequence'),
- );
- # ~
- protected $inlineMarkerList = '!"*_&[:<>`~\\';
- #
- # ~
- #
- public function line($text, $nonNestables=array())
- {
- $markup = '';
- # $excerpt is based on the first occurrence of a marker
- while ($excerpt = strpbrk($text, $this->inlineMarkerList))
- {
- $marker = $excerpt[0];
- $markerPosition = strpos($text, $marker);
- $Excerpt = array('text' => $excerpt, 'context' => $text);
- foreach ($this->InlineTypes[$marker] as $inlineType)
- {
- # check to see if the current inline type is nestable in the current context
- if ( ! empty($nonNestables) and in_array($inlineType, $nonNestables))
- {
- continue;
- }
- $Inline = $this->{'inline'.$inlineType}($Excerpt);
- if ( ! isset($Inline))
- {
- continue;
- }
- # makes sure that the inline belongs to "our" marker
- if (isset($Inline['position']) and $Inline['position'] > $markerPosition)
- {
- continue;
- }
- # sets a default inline position
- if ( ! isset($Inline['position']))
- {
- $Inline['position'] = $markerPosition;
- }
- # cause the new element to 'inherit' our non nestables
- foreach ($nonNestables as $non_nestable)
- {
- $Inline['element']['nonNestables'][] = $non_nestable;
- }
- # the text that comes before the inline
- $unmarkedText = substr($text, 0, $Inline['position']);
- # compile the unmarked text
- $markup .= $this->unmarkedText($unmarkedText);
- # compile the inline
- $markup .= isset($Inline['markup']) ? $Inline['markup'] : $this->element($Inline['element']);
- # remove the examined text
- $text = substr($text, $Inline['position'] + $Inline['extent']);
- continue 2;
- }
- # the marker does not belong to an inline
- $unmarkedText = substr($text, 0, $markerPosition + 1);
- $markup .= $this->unmarkedText($unmarkedText);
- $text = substr($text, $markerPosition + 1);
- }
- $markup .= $this->unmarkedText($text);
- return $markup;
- }
- #
- # ~
- #
- protected function inlineCode($Excerpt)
- {
- $marker = $Excerpt['text'][0];
- if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(?<!'.$marker.')\1(?!'.$marker.')/s', $Excerpt['text'], $matches))
- {
- $text = $matches[2];
- $text = preg_replace("/[ ]*\n/", ' ', $text);
- return array(
- 'extent' => strlen($matches[0]),
- 'element' => array(
- 'name' => 'code',
- 'text' => $text,
- ),
- );
- }
- }
- protected function inlineEmailTag($Excerpt)
- {
- if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/i', $Excerpt['text'], $matches))
- {
- $url = $matches[1];
- if ( ! isset($matches[2]))
- {
- $url = 'mailto:' . $url;
- }
- return array(
- 'extent' => strlen($matches[0]),
- 'element' => array(
- 'name' => 'a',
- 'text' => $matches[1],
- 'attributes' => array(
- 'href' => $url,
- ),
- ),
- );
- }
- }
- protected function inlineEmphasis($Excerpt)
- {
- if ( ! isset($Excerpt['text'][1]))
- {
- return;
- }
- $marker = $Excerpt['text'][0];
- if ($Excerpt['text'][1] === $marker and preg_match($this->StrongRegex[$marker], $Excerpt['text'], $matches))
- {
- $emphasis = 'strong';
- }
- elseif (preg_match($this->EmRegex[$marker], $Excerpt['text'], $matches))
- {
- $emphasis = 'em';
- }
- else
- {
- return;
- }
- return array(
- 'extent' => strlen($matches[0]),
- 'element' => array(
- 'name' => $emphasis,
- 'handler' => 'line',
- 'text' => $matches[1],
- ),
- );
- }
- protected function inlineEscapeSequence($Excerpt)
- {
- if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters))
- {
- return array(
- 'markup' => $Excerpt['text'][1],
- 'extent' => 2,
- );
- }
- }
- protected function inlineImage($Excerpt)
- {
- if ( ! isset($Excerpt['text'][1]) or $Excerpt['text'][1] !== '[')
- {
- return;
- }
- $Excerpt['text']= substr($Excerpt['text'], 1);
- $Link = $this->inlineLink($Excerpt);
- if ($Link === null)
- {
- return;
- }
- $Inline = array(
- 'extent' => $Link['extent'] + 1,
- 'element' => array(
- 'name' => 'img',
- 'attributes' => array(
- 'src' => $Link['element']['attributes']['href'],
- 'alt' => $Link['element']['text'],
- ),
- ),
- );
- $Inline['element']['attributes'] += $Link['element']['attributes'];
- unset($Inline['element']['attributes']['href']);
- return $Inline;
- }
- protected function inlineLink($Excerpt)
- {
- $Element = array(
- 'name' => 'a',
- 'handler' => 'line',
- 'nonNestables' => array('Url', 'Link'),
- 'text' => null,
- 'attributes' => array(
- 'href' => null,
- 'title' => null,
- ),
- );
- $extent = 0;
- $remainder = $Excerpt['text'];
- if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches))
- {
- $Element['text'] = $matches[1];
- $extent += strlen($matches[0]);
- $remainder = substr($remainder, $extent);
- }
- else
- {
- return;
- }
- if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*"|\'[^\']*\'))?\s*[)]/', $remainder, $matches))
- {
- $Element['attributes']['href'] = $matches[1];
- if (isset($matches[2]))
- {
- $Element['attributes']['title'] = substr($matches[2], 1, - 1);
- }
- $extent += strlen($matches[0]);
- }
- else
- {
- if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches))
- {
- $definition = strlen($matches[1]) ? $matches[1] : $Element['text'];
- $definition = strtolower($definition);
- $extent += strlen($matches[0]);
- }
- else
- {
- $definition = strtolower($Element['text']);
- }
- if ( ! isset($this->DefinitionData['Reference'][$definition]))
- {
- return;
- }
- $Definition = $this->DefinitionData['Reference'][$definition];
- $Element['attributes']['href'] = $Definition['url'];
- $Element['attributes']['title'] = $Definition['title'];
- }
- return array(
- 'extent' => $extent,
- 'element' => $Element,
- );
- }
- protected function inlineMarkup($Excerpt)
- {
- if ($this->markupEscaped or $this->safeMode or strpos($Excerpt['text'], '>') === false)
- {
- return;
- }
- if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*[ ]*>/s', $Excerpt['text'], $matches))
- {
- return array(
- 'markup' => $matches[0],
- 'extent' => strlen($matches[0]),
- );
- }
- if ($Excerpt['text'][1] === '!' and preg_match('/^<!---?[^>-](?:-?[^-])*-->/s', $Excerpt['text'], $matches))
- {
- return array(
- 'markup' => $matches[0],
- 'extent' => strlen($matches[0]),
- );
- }
- if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches))
- {
- return array(
- 'markup' => $matches[0],
- 'extent' => strlen($matches[0]),
- );
- }
- }
- protected function inlineSpecialCharacter($Excerpt)
- {
- if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text']))
- {
- return array(
- 'markup' => '&',
- 'extent' => 1,
- );
- }
- $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot');
- if (isset($SpecialCharacter[$Excerpt['text'][0]]))
- {
- return array(
- 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';',
- 'extent' => 1,
- );
- }
- }
- protected function inlineStrikethrough($Excerpt)
- {
- if ( ! isset($Excerpt['text'][1]))
- {
- return;
- }
- if ($Excerpt['text'][1] === '~' and preg_match('/^~~(?=\S)(.+?)(?<=\S)~~/', $Excerpt['text'], $matches))
- {
- return array(
- 'extent' => strlen($matches[0]),
- 'element' => array(
- 'name' => 'del',
- 'text' => $matches[1],
- 'handler' => 'line',
- ),
- );
- }
- }
- protected function inlineUrl($Excerpt)
- {
- if ($this->urlsLinked !== true or ! isset($Excerpt['text'][2]) or $Excerpt['text'][2] !== '/')
- {
- return;
- }
- if (preg_match('/\bhttps?:[\/]{2}[^\s<]+\b\/*/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE))
- {
- $url = $matches[0][0];
- $Inline = array(
- 'extent' => strlen($matches[0][0]),
- 'position' => $matches[0][1],
- 'element' => array(
- 'name' => 'a',
- 'text' => $url,
- 'attributes' => array(
- 'href' => $url,
- ),
- ),
- );
- return $Inline;
- }
- }
- protected function inlineUrlTag($Excerpt)
- {
- if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches))
- {
- $url = $matches[1];
- return array(
- 'extent' => strlen($matches[0]),
- 'element' => array(
- 'name' => 'a',
- 'text' => $url,
- 'attributes' => array(
- 'href' => $url,
- ),
- ),
- );
- }
- }
- # ~
- protected function unmarkedText($text)
- {
- if ($this->breaksEnabled)
- {
- $text = preg_replace('/[ ]*\n/', "<br />\n", $text);
- }
- else
- {
- $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "<br />\n", $text);
- $text = str_replace(" \n", "\n", $text);
- }
- return $text;
- }
- #
- # Handlers
- #
- protected function element(array $Element)
- {
- if ($this->safeMode)
- {
- $Element = $this->sanitiseElement($Element);
- }
- $markup = '<'.$Element['name'];
- if (isset($Element['attributes']))
- {
- foreach ($Element['attributes'] as $name => $value)
- {
- if ($value === null)
- {
- continue;
- }
- $markup .= ' '.$name.'="'.self::escape($value).'"';
- }
- }
- $permitRawHtml = false;
- if (isset($Element['text']))
- {
- $text = $Element['text'];
- }
- // very strongly consider an alternative if you're writing an
- // extension
- elseif (isset($Element['rawHtml']))
- {
- $text = $Element['rawHtml'];
- $allowRawHtmlInSafeMode = isset($Element['allowRawHtmlInSafeMode']) && $Element['allowRawHtmlInSafeMode'];
- $permitRawHtml = !$this->safeMode || $allowRawHtmlInSafeMode;
- }
- if (isset($text))
- {
- $markup .= '>';
- if (!isset($Element['nonNestables']))
- {
- $Element['nonNestables'] = array();
- }
- if (isset($Element['handler']))
- {
- $markup .= $this->{$Element['handler']}($text, $Element['nonNestables']);
- }
- elseif (!$permitRawHtml)
- {
- $markup .= self::escape($text, true);
- }
- else
- {
- $markup .= $text;
- }
- $markup .= '</'.$Element['name'].'>';
- }
- else
- {
- $markup .= ' />';
- }
- return $markup;
- }
- protected function elements(array $Elements)
- {
- $markup = '';
- foreach ($Elements as $Element)
- {
- $markup .= "\n" . $this->element($Element);
- }
- $markup .= "\n";
- return $markup;
- }
- # ~
- protected function li($lines)
- {
- $markup = $this->lines($lines);
- $trimmedMarkup = trim($markup);
- if ( ! in_array('', $lines) and substr($trimmedMarkup, 0, 3) === '<p>')
- {
- $markup = $trimmedMarkup;
- $markup = substr($markup, 3);
- $position = strpos($markup, "</p>");
- $markup = substr_replace($markup, '', $position, 4);
- }
- return $markup;
- }
- #
- # Deprecated Methods
- #
- function parse($text)
- {
- $markup = $this->text($text);
- return $markup;
- }
- protected function sanitiseElement(array $Element)
- {
- static $goodAttribute = '/^[a-zA-Z0-9][a-zA-Z0-9-_]*+$/';
- static $safeUrlNameToAtt = array(
- 'a' => 'href',
- 'img' => 'src',
- );
- if (isset($safeUrlNameToAtt[$Element['name']]))
- {
- $Element = $this->filterUnsafeUrlInAttribute($Element, $safeUrlNameToAtt[$Element['name']]);
- }
- if ( ! empty($Element['attributes']))
- {
- foreach ($Element['attributes'] as $att => $val)
- {
- # filter out badly parsed attribute
- if ( ! preg_match($goodAttribute, $att))
- {
- unset($Element['attributes'][$att]);
- }
- # dump onevent attribute
- elseif (self::striAtStart($att, 'on'))
- {
- unset($Element['attributes'][$att]);
- }
- }
- }
- return $Element;
- }
- protected function filterUnsafeUrlInAttribute(array $Element, $attribute)
- {
- foreach ($this->safeLinksWhitelist as $scheme)
- {
- if (self::striAtStart($Element['attributes'][$attribute], $scheme))
- {
- return $Element;
- }
- }
- $Element['attributes'][$attribute] = str_replace(':', '%3A', $Element['attributes'][$attribute]);
- return $Element;
- }
- #
- # Static Methods
- #
- protected static function escape($text, $allowQuotes = false)
- {
- return htmlspecialchars($text, $allowQuotes ? ENT_NOQUOTES : ENT_QUOTES, 'UTF-8');
- }
- protected static function striAtStart($string, $needle)
- {
- $len = strlen($needle);
- if ($len > strlen($string))
- {
- return false;
- }
- else
- {
- return strtolower(substr($string, 0, $len)) === strtolower($needle);
- }
- }
- static function instance($name = 'default')
- {
- if (isset(self::$instances[$name]))
- {
- return self::$instances[$name];
- }
- $instance = new static();
- self::$instances[$name] = $instance;
- return $instance;
- }
- private static $instances = array();
- #
- # Fields
- #
- protected $DefinitionData;
- #
- # Read-Only
- protected $specialCharacters = array(
- '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|',
- );
- protected $StrongRegex = array(
- '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s',
- '_' => '/^__((?:\\\\_|[^_]|_[^_]*_)+?)__(?!_)/us',
- );
- protected $EmRegex = array(
- '*' => '/^[*]((?:\\\\\*|[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s',
- '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us',
- );
- protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*(?:\s*=\s*(?:[^"\'=<>`\s]+|"[^"]*"|\'[^\']*\'))?';
- protected $voidElements = array(
- 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source',
- );
- protected $textLevelElements = array(
- 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont',
- 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing',
- 'i', 'rp', 'del', 'code', 'strike', 'marquee',
- 'q', 'rt', 'ins', 'font', 'strong',
- 's', 'tt', 'kbd', 'mark',
- 'u', 'xm', 'sub', 'nobr',
- 'sup', 'ruby',
- 'var', 'span',
- 'wbr', 'time',
- );
- }
|