1 Star 0 Fork 0

ScorPi0n / parsedown

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
克隆/下载
Parsedown.php 50.82 KB
一键复制 编辑 Web IDE 原始数据 按行查看 历史
Aidan Woods 提交于 2019-04-06 17:58 . Merge branch '1.8.x-beta'
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994
<?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 = '1.8.0-beta-7';
# ~
function text($text)
{
$Elements = $this->textElements($text);
# convert to markup
$markup = $this->elements($Elements);
# trim line breaks
$markup = trim($markup, "\n");
return $markup;
}
protected function textElements($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
return $this->linesElements($lines);
}
#
# 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 $safeMode;
function setStrictMode($strictMode)
{
$this->strictMode = (bool) $strictMode;
return $this;
}
protected $strictMode;
protected $safeLinksWhitelist = array(
'http://',
'https://',
'ftp://',
'ftps://',
'mailto:',
'tel:',
'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)
{
return $this->elements($this->linesElements($lines));
}
protected function linesElements(array $lines)
{
$Elements = array();
$CurrentBlock = null;
foreach ($lines as $line)
{
if (chop($line) === '')
{
if (isset($CurrentBlock))
{
$CurrentBlock['interrupted'] = (isset($CurrentBlock['interrupted'])
? $CurrentBlock['interrupted'] + 1 : 1
);
}
continue;
}
while (($beforeTab = strstr($line, "\t", true)) !== false)
{
$shortage = 4 - mb_strlen($beforeTab, 'utf-8') % 4;
$line = $beforeTab
. str_repeat(' ', $shortage)
. substr($line, strlen($beforeTab) + 1)
;
}
$indent = strspn($line, ' ');
$text = $indent > 0 ? substr($line, $indent) : $line;
# ~
$Line = array('body' => $line, 'indent' => $indent, 'text' => $text);
# ~
if (isset($CurrentBlock['continuable']))
{
$methodName = 'block' . $CurrentBlock['type'] . 'Continue';
$Block = $this->$methodName($Line, $CurrentBlock);
if (isset($Block))
{
$CurrentBlock = $Block;
continue;
}
else
{
if ($this->isBlockCompletable($CurrentBlock['type']))
{
$methodName = 'block' . $CurrentBlock['type'] . 'Complete';
$CurrentBlock = $this->$methodName($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']))
{
if (isset($CurrentBlock))
{
$Elements[] = $this->extractElement($CurrentBlock);
}
$Block['identified'] = true;
}
if ($this->isBlockContinuable($blockType))
{
$Block['continuable'] = true;
}
$CurrentBlock = $Block;
continue 2;
}
}
# ~
if (isset($CurrentBlock) and $CurrentBlock['type'] === 'Paragraph')
{
$Block = $this->paragraphContinue($Line, $CurrentBlock);
}
if (isset($Block))
{
$CurrentBlock = $Block;
}
else
{
if (isset($CurrentBlock))
{
$Elements[] = $this->extractElement($CurrentBlock);
}
$CurrentBlock = $this->paragraph($Line);
$CurrentBlock['identified'] = true;
}
}
# ~
if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type']))
{
$methodName = 'block' . $CurrentBlock['type'] . 'Complete';
$CurrentBlock = $this->$methodName($CurrentBlock);
}
# ~
if (isset($CurrentBlock))
{
$Elements[] = $this->extractElement($CurrentBlock);
}
# ~
return $Elements;
}
protected function extractElement(array $Component)
{
if ( ! isset($Component['element']))
{
if (isset($Component['markup']))
{
$Component['element'] = array('rawHtml' => $Component['markup']);
}
elseif (isset($Component['hidden']))
{
$Component['element'] = array();
}
}
return $Component['element'];
}
protected function isBlockContinuable($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 $Block['type'] === 'Paragraph' and ! isset($Block['interrupted']))
{
return;
}
if ($Line['indent'] >= 4)
{
$text = substr($Line['body'], 4);
$Block = array(
'element' => array(
'name' => 'pre',
'element' => array(
'name' => 'code',
'text' => $text,
),
),
);
return $Block;
}
}
protected function blockCodeContinue($Line, $Block)
{
if ($Line['indent'] >= 4)
{
if (isset($Block['interrupted']))
{
$Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']);
unset($Block['interrupted']);
}
$Block['element']['element']['text'] .= "\n";
$text = substr($Line['body'], 4);
$Block['element']['element']['text'] .= $text;
return $Block;
}
}
protected function blockCodeComplete($Block)
{
return $Block;
}
#
# Comment
protected function blockComment($Line)
{
if ($this->markupEscaped or $this->safeMode)
{
return;
}
if (strpos($Line['text'], '<!--') === 0)
{
$Block = array(
'element' => array(
'rawHtml' => $Line['body'],
'autobreak' => true,
),
);
if (strpos($Line['text'], '-->') !== false)
{
$Block['closed'] = true;
}
return $Block;
}
}
protected function blockCommentContinue($Line, array $Block)
{
if (isset($Block['closed']))
{
return;
}
$Block['element']['rawHtml'] .= "\n" . $Line['body'];
if (strpos($Line['text'], '-->') !== false)
{
$Block['closed'] = true;
}
return $Block;
}
#
# Fenced Code
protected function blockFencedCode($Line)
{
$marker = $Line['text'][0];
$openerLength = strspn($Line['text'], $marker);
if ($openerLength < 3)
{
return;
}
$infostring = trim(substr($Line['text'], $openerLength), "\t ");
if (strpos($infostring, '`') !== false)
{
return;
}
$Element = array(
'name' => 'code',
'text' => '',
);
if ($infostring !== '')
{
/**
* 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).
*/
$language = substr($infostring, 0, strcspn($infostring, " \t\n\f\r"));
$Element['attributes'] = array('class' => "language-$language");
}
$Block = array(
'char' => $marker,
'openerLength' => $openerLength,
'element' => array(
'name' => 'pre',
'element' => $Element,
),
);
return $Block;
}
protected function blockFencedCodeContinue($Line, $Block)
{
if (isset($Block['complete']))
{
return;
}
if (isset($Block['interrupted']))
{
$Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']);
unset($Block['interrupted']);
}
if (($len = strspn($Line['text'], $Block['char'])) >= $Block['openerLength']
and chop(substr($Line['text'], $len), ' ') === ''
) {
$Block['element']['element']['text'] = substr($Block['element']['element']['text'], 1);
$Block['complete'] = true;
return $Block;
}
$Block['element']['element']['text'] .= "\n" . $Line['body'];
return $Block;
}
protected function blockFencedCodeComplete($Block)
{
return $Block;
}
#
# Header
protected function blockHeader($Line)
{
$level = strspn($Line['text'], '#');
if ($level > 6)
{
return;
}
$text = trim($Line['text'], '#');
if ($this->strictMode and isset($text[0]) and $text[0] !== ' ')
{
return;
}
$text = trim($text, ' ');
$Block = array(
'element' => array(
'name' => 'h' . $level,
'handler' => array(
'function' => 'lineElements',
'argument' => $text,
'destination' => 'elements',
)
),
);
return $Block;
}
#
# List
protected function blockList($Line, array $CurrentBlock = null)
{
list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]{1,9}+[.\)]');
if (preg_match('/^('.$pattern.'([ ]++|$))(.*+)/', $Line['text'], $matches))
{
$contentIndent = strlen($matches[2]);
if ($contentIndent >= 5)
{
$contentIndent -= 1;
$matches[1] = substr($matches[1], 0, -$contentIndent);
$matches[3] = str_repeat(' ', $contentIndent) . $matches[3];
}
elseif ($contentIndent === 0)
{
$matches[1] .= ' ';
}
$markerWithoutWhitespace = strstr($matches[1], ' ', true);
$Block = array(
'indent' => $Line['indent'],
'pattern' => $pattern,
'data' => array(
'type' => $name,
'marker' => $matches[1],
'markerType' => ($name === 'ul' ? $markerWithoutWhitespace : substr($markerWithoutWhitespace, -1)),
),
'element' => array(
'name' => $name,
'elements' => array(),
),
);
$Block['data']['markerTypeRegex'] = preg_quote($Block['data']['markerType'], '/');
if ($name === 'ol')
{
$listStart = ltrim(strstr($matches[1], $Block['data']['markerType'], true), '0') ?: '0';
if ($listStart !== '1')
{
if (
isset($CurrentBlock)
and $CurrentBlock['type'] === 'Paragraph'
and ! isset($CurrentBlock['interrupted'])
) {
return;
}
$Block['element']['attributes'] = array('start' => $listStart);
}
}
$Block['li'] = array(
'name' => 'li',
'handler' => array(
'function' => 'li',
'argument' => !empty($matches[3]) ? array($matches[3]) : array(),
'destination' => 'elements'
)
);
$Block['element']['elements'] []= & $Block['li'];
return $Block;
}
}
protected function blockListContinue($Line, array $Block)
{
if (isset($Block['interrupted']) and empty($Block['li']['handler']['argument']))
{
return null;
}
$requiredIndent = ($Block['indent'] + strlen($Block['data']['marker']));
if ($Line['indent'] < $requiredIndent
and (
(
$Block['data']['type'] === 'ol'
and preg_match('/^[0-9]++'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches)
) or (
$Block['data']['type'] === 'ul'
and preg_match('/^'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches)
)
)
) {
if (isset($Block['interrupted']))
{
$Block['li']['handler']['argument'] []= '';
$Block['loose'] = true;
unset($Block['interrupted']);
}
unset($Block['li']);
$text = isset($matches[1]) ? $matches[1] : '';
$Block['indent'] = $Line['indent'];
$Block['li'] = array(
'name' => 'li',
'handler' => array(
'function' => 'li',
'argument' => array($text),
'destination' => 'elements'
)
);
$Block['element']['elements'] []= & $Block['li'];
return $Block;
}
elseif ($Line['indent'] < $requiredIndent and $this->blockList($Line))
{
return null;
}
if ($Line['text'][0] === '[' and $this->blockReference($Line))
{
return $Block;
}
if ($Line['indent'] >= $requiredIndent)
{
if (isset($Block['interrupted']))
{
$Block['li']['handler']['argument'] []= '';
$Block['loose'] = true;
unset($Block['interrupted']);
}
$text = substr($Line['body'], $requiredIndent);
$Block['li']['handler']['argument'] []= $text;
return $Block;
}
if ( ! isset($Block['interrupted']))
{
$text = preg_replace('/^[ ]{0,'.$requiredIndent.'}+/', '', $Line['body']);
$Block['li']['handler']['argument'] []= $text;
return $Block;
}
}
protected function blockListComplete(array $Block)
{
if (isset($Block['loose']))
{
foreach ($Block['element']['elements'] as &$li)
{
if (end($li['handler']['argument']) !== '')
{
$li['handler']['argument'] []= '';
}
}
}
return $Block;
}
#
# Quote
protected function blockQuote($Line)
{
if (preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches))
{
$Block = array(
'element' => array(
'name' => 'blockquote',
'handler' => array(
'function' => 'linesElements',
'argument' => (array) $matches[1],
'destination' => 'elements',
)
),
);
return $Block;
}
}
protected function blockQuoteContinue($Line, array $Block)
{
if (isset($Block['interrupted']))
{
return;
}
if ($Line['text'][0] === '>' and preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches))
{
$Block['element']['handler']['argument'] []= $matches[1];
return $Block;
}
if ( ! isset($Block['interrupted']))
{
$Block['element']['handler']['argument'] []= $Line['text'];
return $Block;
}
}
#
# Rule
protected function blockRule($Line)
{
$marker = $Line['text'][0];
if (substr_count($Line['text'], $marker) >= 3 and chop($Line['text'], " $marker") === '')
{
$Block = array(
'element' => array(
'name' => 'hr',
),
);
return $Block;
}
}
#
# Setext
protected function blockSetextHeader($Line, array $Block = null)
{
if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted']))
{
return;
}
if ($Line['indent'] < 4 and chop(chop($Line['text'], ' '), $Line['text'][0]) === '')
{
$Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2';
return $Block;
}
}
#
# Markup
protected function blockMarkup($Line)
{
if ($this->markupEscaped or $this->safeMode)
{
return;
}
if (preg_match('/^<[\/]?+(\w*)(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+(\/)?>/', $Line['text'], $matches))
{
$element = strtolower($matches[1]);
if (in_array($element, $this->textLevelElements))
{
return;
}
$Block = array(
'name' => $matches[1],
'element' => array(
'rawHtml' => $Line['text'],
'autobreak' => true,
),
);
return $Block;
}
}
protected function blockMarkupContinue($Line, array $Block)
{
if (isset($Block['closed']) or isset($Block['interrupted']))
{
return;
}
$Block['element']['rawHtml'] .= "\n" . $Line['body'];
return $Block;
}
#
# Reference
protected function blockReference($Line)
{
if (strpos($Line['text'], ']') !== false
and preg_match('/^\[(.+?)\]:[ ]*+<?(\S+?)>?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $Line['text'], $matches)
) {
$id = strtolower($matches[1]);
$Data = array(
'url' => $matches[2],
'title' => isset($matches[3]) ? $matches[3] : null,
);
$this->DefinitionData['Reference'][$id] = $Data;
$Block = array(
'element' => array(),
);
return $Block;
}
}
#
# Table
protected function blockTable($Line, array $Block = null)
{
if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted']))
{
return;
}
if (
strpos($Block['element']['handler']['argument'], '|') === false
and strpos($Line['text'], '|') === false
and strpos($Line['text'], ':') === false
or strpos($Block['element']['handler']['argument'], "\n") !== false
) {
return;
}
if (chop($Line['text'], ' -:|') !== '')
{
return;
}
$alignments = array();
$divider = $Line['text'];
$divider = trim($divider);
$divider = trim($divider, '|');
$dividerCells = explode('|', $divider);
foreach ($dividerCells as $dividerCell)
{
$dividerCell = trim($dividerCell);
if ($dividerCell === '')
{
return;
}
$alignment = null;
if ($dividerCell[0] === ':')
{
$alignment = 'left';
}
if (substr($dividerCell, - 1) === ':')
{
$alignment = $alignment === 'left' ? 'center' : 'right';
}
$alignments []= $alignment;
}
# ~
$HeaderElements = array();
$header = $Block['element']['handler']['argument'];
$header = trim($header);
$header = trim($header, '|');
$headerCells = explode('|', $header);
if (count($headerCells) !== count($alignments))
{
return;
}
foreach ($headerCells as $index => $headerCell)
{
$headerCell = trim($headerCell);
$HeaderElement = array(
'name' => 'th',
'handler' => array(
'function' => 'lineElements',
'argument' => $headerCell,
'destination' => 'elements',
)
);
if (isset($alignments[$index]))
{
$alignment = $alignments[$index];
$HeaderElement['attributes'] = array(
'style' => "text-align: $alignment;",
);
}
$HeaderElements []= $HeaderElement;
}
# ~
$Block = array(
'alignments' => $alignments,
'identified' => true,
'element' => array(
'name' => 'table',
'elements' => array(),
),
);
$Block['element']['elements'] []= array(
'name' => 'thead',
);
$Block['element']['elements'] []= array(
'name' => 'tbody',
'elements' => array(),
);
$Block['element']['elements'][0]['elements'] []= array(
'name' => 'tr',
'elements' => $HeaderElements,
);
return $Block;
}
protected function blockTableContinue($Line, array $Block)
{
if (isset($Block['interrupted']))
{
return;
}
if (count($Block['alignments']) === 1 or $Line['text'][0] === '|' or strpos($Line['text'], '|'))
{
$Elements = array();
$row = $Line['text'];
$row = trim($row);
$row = trim($row, '|');
preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]++`|`)++/', $row, $matches);
$cells = array_slice($matches[0], 0, count($Block['alignments']));
foreach ($cells as $index => $cell)
{
$cell = trim($cell);
$Element = array(
'name' => 'td',
'handler' => array(
'function' => 'lineElements',
'argument' => $cell,
'destination' => 'elements',
)
);
if (isset($Block['alignments'][$index]))
{
$Element['attributes'] = array(
'style' => 'text-align: ' . $Block['alignments'][$index] . ';',
);
}
$Elements []= $Element;
}
$Element = array(
'name' => 'tr',
'elements' => $Elements,
);
$Block['element']['elements'][1]['elements'] []= $Element;
return $Block;
}
}
#
# ~
#
protected function paragraph($Line)
{
return array(
'type' => 'Paragraph',
'element' => array(
'name' => 'p',
'handler' => array(
'function' => 'lineElements',
'argument' => $Line['text'],
'destination' => 'elements',
),
),
);
}
protected function paragraphContinue($Line, array $Block)
{
if (isset($Block['interrupted']))
{
return;
}
$Block['element']['handler']['argument'] .= "\n".$Line['text'];
return $Block;
}
#
# Inline Elements
#
protected $InlineTypes = array(
'!' => array('Image'),
'&' => array('SpecialCharacter'),
'*' => array('Emphasis'),
':' => array('Url'),
'<' => array('UrlTag', 'EmailTag', 'Markup'),
'[' => array('Link'),
'_' => array('Emphasis'),
'`' => array('Code'),
'~' => array('Strikethrough'),
'\\' => array('EscapeSequence'),
);
# ~
protected $inlineMarkerList = '!*_&[:<`~\\';
#
# ~
#
public function line($text, $nonNestables = array())
{
return $this->elements($this->lineElements($text, $nonNestables));
}
protected function lineElements($text, $nonNestables = array())
{
# standardize line breaks
$text = str_replace(array("\r\n", "\r"), "\n", $text);
$Elements = array();
$nonNestables = (empty($nonNestables)
? array()
: array_combine($nonNestables, $nonNestables)
);
# $excerpt is based on the first occurrence of a marker
while ($excerpt = strpbrk($text, $this->inlineMarkerList))
{
$marker = $excerpt[0];
$markerPosition = strlen($text) - strlen($excerpt);
$Excerpt = array('text' => $excerpt, 'context' => $text);
foreach ($this->InlineTypes[$marker] as $inlineType)
{
# check to see if the current inline type is nestable in the current context
if (isset($nonNestables[$inlineType]))
{
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
$Inline['element']['nonNestables'] = isset($Inline['element']['nonNestables'])
? array_merge($Inline['element']['nonNestables'], $nonNestables)
: $nonNestables
;
# the text that comes before the inline
$unmarkedText = substr($text, 0, $Inline['position']);
# compile the unmarked text
$InlineText = $this->inlineText($unmarkedText);
$Elements[] = $InlineText['element'];
# compile the inline
$Elements[] = $this->extractElement($Inline);
# 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);
$InlineText = $this->inlineText($unmarkedText);
$Elements[] = $InlineText['element'];
$text = substr($text, $markerPosition + 1);
}
$InlineText = $this->inlineText($text);
$Elements[] = $InlineText['element'];
foreach ($Elements as &$Element)
{
if ( ! isset($Element['autobreak']))
{
$Element['autobreak'] = false;
}
}
return $Elements;
}
#
# ~
#
protected function inlineText($text)
{
$Inline = array(
'extent' => strlen($text),
'element' => array(),
);
$Inline['element']['elements'] = self::pregReplaceElements(
$this->breaksEnabled ? '/[ ]*+\n/' : '/(?:[ ]*+\\\\|[ ]{2,}+)\n/',
array(
array('name' => 'br'),
array('text' => "\n"),
),
$text
);
return $Inline;
}
protected function inlineCode($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)
{
$hostnameLabel = '[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?';
$commonMarkEmail = '[a-zA-Z0-9.!#$%&\'*+\/=?^_`{|}~-]++@'
. $hostnameLabel . '(?:\.' . $hostnameLabel . ')*';
if (strpos($Excerpt['text'], '>') !== false
and preg_match("/^<((mailto:)?$commonMarkEmail)>/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' => array(
'function' => 'lineElements',
'argument' => $matches[1],
'destination' => 'elements',
)
),
);
}
protected function inlineEscapeSequence($Excerpt)
{
if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters))
{
return array(
'element' => array('rawHtml' => $Excerpt['text'][1]),
'extent' => 2,
);
}
}
protected function inlineImage($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']['handler']['argument'],
),
'autobreak' => true,
),
);
$Inline['element']['attributes'] += $Link['element']['attributes'];
unset($Inline['element']['attributes']['href']);
return $Inline;
}
protected function inlineLink($Excerpt)
{
$Element = array(
'name' => 'a',
'handler' => array(
'function' => 'lineElements',
'argument' => null,
'destination' => 'elements',
),
'nonNestables' => array('Url', 'Link'),
'attributes' => array(
'href' => null,
'title' => null,
),
);
$extent = 0;
$remainder = $Excerpt['text'];
if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches))
{
$Element['handler']['argument'] = $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['handler']['argument'];
$definition = strtolower($definition);
$extent += strlen($matches[0]);
}
else
{
$definition = strtolower($Element['handler']['argument']);
}
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(
'element' => array('rawHtml' => $matches[0]),
'extent' => strlen($matches[0]),
);
}
if ($Excerpt['text'][1] === '!' and preg_match('/^<!---?[^>-](?:-?+[^-])*-->/s', $Excerpt['text'], $matches))
{
return array(
'element' => array('rawHtml' => $matches[0]),
'extent' => strlen($matches[0]),
);
}
if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*+(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+\/?>/s', $Excerpt['text'], $matches))
{
return array(
'element' => array('rawHtml' => $matches[0]),
'extent' => strlen($matches[0]),
);
}
}
protected function inlineSpecialCharacter($Excerpt)
{
if (substr($Excerpt['text'], 1, 1) !== ' ' and strpos($Excerpt['text'], ';') !== false
and preg_match('/^&(#?+[0-9a-zA-Z]++);/', $Excerpt['text'], $matches)
) {
return array(
'element' => array('rawHtml' => '&' . $matches[1] . ';'),
'extent' => strlen($matches[0]),
);
}
return;
}
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',
'handler' => array(
'function' => 'lineElements',
'argument' => $matches[1],
'destination' => 'elements',
)
),
);
}
}
protected function inlineUrl($Excerpt)
{
if ($this->urlsLinked !== true or ! isset($Excerpt['text'][2]) or $Excerpt['text'][2] !== '/')
{
return;
}
if (strpos($Excerpt['context'], 'http') !== false
and 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)
{
$Inline = $this->inlineText($text);
return $this->element($Inline['element']);
}
#
# Handlers
#
protected function handle(array $Element)
{
if (isset($Element['handler']))
{
if (!isset($Element['nonNestables']))
{
$Element['nonNestables'] = array();
}
if (is_string($Element['handler']))
{
$function = $Element['handler'];
$argument = $Element['text'];
unset($Element['text']);
$destination = 'rawHtml';
}
else
{
$function = $Element['handler']['function'];
$argument = $Element['handler']['argument'];
$destination = $Element['handler']['destination'];
}
$Element[$destination] = $this->{$function}($argument, $Element['nonNestables']);
if ($destination === 'handler')
{
$Element = $this->handle($Element);
}
unset($Element['handler']);
}
return $Element;
}
protected function handleElementRecursive(array $Element)
{
return $this->elementApplyRecursive(array($this, 'handle'), $Element);
}
protected function handleElementsRecursive(array $Elements)
{
return $this->elementsApplyRecursive(array($this, 'handle'), $Elements);
}
protected function elementApplyRecursive($closure, array $Element)
{
$Element = call_user_func($closure, $Element);
if (isset($Element['elements']))
{
$Element['elements'] = $this->elementsApplyRecursive($closure, $Element['elements']);
}
elseif (isset($Element['element']))
{
$Element['element'] = $this->elementApplyRecursive($closure, $Element['element']);
}
return $Element;
}
protected function elementApplyRecursiveDepthFirst($closure, array $Element)
{
if (isset($Element['elements']))
{
$Element['elements'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['elements']);
}
elseif (isset($Element['element']))
{
$Element['element'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['element']);
}
$Element = call_user_func($closure, $Element);
return $Element;
}
protected function elementsApplyRecursive($closure, array $Elements)
{
foreach ($Elements as &$Element)
{
$Element = $this->elementApplyRecursive($closure, $Element);
}
return $Elements;
}
protected function elementsApplyRecursiveDepthFirst($closure, array $Elements)
{
foreach ($Elements as &$Element)
{
$Element = $this->elementApplyRecursiveDepthFirst($closure, $Element);
}
return $Elements;
}
protected function element(array $Element)
{
if ($this->safeMode)
{
$Element = $this->sanitiseElement($Element);
}
# identity map if element has no handler
$Element = $this->handle($Element);
$hasName = isset($Element['name']);
$markup = '';
if ($hasName)
{
$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;
}
$hasContent = isset($text) || isset($Element['element']) || isset($Element['elements']);
if ($hasContent)
{
$markup .= $hasName ? '>' : '';
if (isset($Element['elements']))
{
$markup .= $this->elements($Element['elements']);
}
elseif (isset($Element['element']))
{
$markup .= $this->element($Element['element']);
}
else
{
if (!$permitRawHtml)
{
$markup .= self::escape($text, true);
}
else
{
$markup .= $text;
}
}
$markup .= $hasName ? '</' . $Element['name'] . '>' : '';
}
elseif ($hasName)
{
$markup .= ' />';
}
return $markup;
}
protected function elements(array $Elements)
{
$markup = '';
$autoBreak = true;
foreach ($Elements as $Element)
{
if (empty($Element))
{
continue;
}
$autoBreakNext = (isset($Element['autobreak'])
? $Element['autobreak'] : isset($Element['name'])
);
// (autobreak === false) covers both sides of an element
$autoBreak = !$autoBreak ? $autoBreak : $autoBreakNext;
$markup .= ($autoBreak ? "\n" : '') . $this->element($Element);
$autoBreak = $autoBreakNext;
}
$markup .= $autoBreak ? "\n" : '';
return $markup;
}
# ~
protected function li($lines)
{
$Elements = $this->linesElements($lines);
if ( ! in_array('', $lines)
and isset($Elements[0]) and isset($Elements[0]['name'])
and $Elements[0]['name'] === 'p'
) {
unset($Elements[0]['name']);
}
return $Elements;
}
#
# AST Convenience
#
/**
* Replace occurrences $regexp with $Elements in $text. Return an array of
* elements representing the replacement.
*/
protected static function pregReplaceElements($regexp, $Elements, $text)
{
$newElements = array();
while (preg_match($regexp, $text, $matches, PREG_OFFSET_CAPTURE))
{
$offset = $matches[0][1];
$before = substr($text, 0, $offset);
$after = substr($text, $offset + strlen($matches[0][0]));
$newElements[] = array('text' => $before);
foreach ($Elements as $Element)
{
$newElements[] = $Element;
}
$text = $after;
}
$newElements[] = array('text' => $text);
return $newElements;
}
#
# Deprecated Methods
#
function parse($text)
{
$markup = $this->text($text);
return $markup;
}
protected function sanitiseElement(array $Element)
{
static $goodAttribute = '/^[a-zA-Z0-9][a-zA-Z0-9-_]*+$/';
static $safeUrlNameToAtt = array(
'a' => 'href',
'img' => 'src',
);
if ( ! isset($Element['name']))
{
unset($Element['attributes']);
return $Element;
}
if (isset($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',
);
}
1
https://gitee.com/JonahXie/parsedown.git
git@gitee.com:JonahXie/parsedown.git
JonahXie
parsedown
parsedown
master

搜索帮助

14c37bed 8189591 565d56ea 8189591