textElements($text); # convert to markup $markup = $this->elements($Elements); # trim line breaks $markup = \trim($markup, "\n"); return $markup; } protected function textElements($text) { # iterate through lines to identify blocks return $this->linesElements(Lines::fromTextLines($text, 0)); } # # Setters # public function setBreaksEnabled($breaksEnabled) { $this->breaksEnabled = $breaksEnabled; return $this; } protected $breaksEnabled; public function setMarkupEscaped($markupEscaped) { $this->markupEscaped = $markupEscaped; return $this; } protected $markupEscaped; public function setUrlsLinked($urlsLinked) { $this->urlsLinked = $urlsLinked; return $this; } protected $urlsLinked = true; public function setSafeMode($safeMode) { $this->safeMode = (bool) $safeMode; return $this; } protected $safeMode; public function setStrictMode($strictMode) { $this->strictMode = (bool) $strictMode; return $this; } protected $strictMode; protected $safeLinksWhitelist = [ '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 = [ '#' => ['Header'], '*' => ['Rule', 'List'], '+' => ['List'], '-' => ['SetextHeader', 'Table', 'Rule', 'List'], '0' => ['List'], '1' => ['List'], '2' => ['List'], '3' => ['List'], '4' => ['List'], '5' => ['List'], '6' => ['List'], '7' => ['List'], '8' => ['List'], '9' => ['List'], ':' => ['Table'], '<' => ['Comment', 'Markup'], '=' => ['SetextHeader'], '>' => ['Quote'], '[' => ['Reference'], '_' => ['Rule'], '`' => ['FencedCode'], '|' => ['Table'], '~' => ['FencedCode'], ]; # ~ protected $unmarkedBlockTypes = [ 'Code', ]; # # Blocks # protected function lines(Lines $Lines) { return $this->elements($this->linesElements($Lines)); } /** @param int $indentOffset */ protected function linesElements(Lines $Lines, array $nonNestables = [], $indentOffset = 0) { $Elements = []; $CurrentBlock = null; foreach ($Lines->contexts() as $Context) { if (isset($CurrentBlock) && $Context->previousEmptyLines() > 0) { $CurrentBlock['interrupted'] = $Context->previousEmptyLines(); } $Line = $Context->line(); if (isset($CurrentBlock['continuable'])) { $methodName = 'block' . $CurrentBlock['type'] . 'Continue'; $Block = $this->$methodName($Context, $CurrentBlock); if (isset($Block)) { $CurrentBlock = $Block; continue; } else { if ($this->isBlockCompletable($CurrentBlock['type'])) { $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; $CurrentBlock = $this->$methodName($CurrentBlock); } } } # ~ $marker = $Line->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"}($Context, $CurrentBlock); if (isset($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 = $this->paragraphContinue($Context, $CurrentBlock); } if (isset($Block)) { $CurrentBlock = $Block; } else { if (isset($CurrentBlock)) { $Elements[] = $this->extractElement($CurrentBlock); } $CurrentBlock = $this->paragraph($Context); $CurrentBlock['identified'] = true; } } # ~ if (isset($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'] = ['rawHtml' => $Component['markup']]; } elseif (isset($Component['hidden'])) { $Component['element'] = []; } } 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'); } # # Inline Elements # protected $InlineTypes = [ '!' => ['Image'], '&' => ['SpecialCharacter'], '*' => ['Emphasis'], ':' => ['Url'], '<' => ['UrlTag', 'EmailTag', 'Markup'], '[' => ['Link'], '_' => ['Emphasis'], '`' => ['Code'], '~' => ['Strikethrough'], '\\' => ['EscapeSequence'], ]; # ~ protected $inlineMarkerList = '!*_&[:<`~\\'; # # ~ # public function line($text, $nonNestables = []) { return $this->elements($this->lineElements($text, $nonNestables)); } protected function lineElements($text, $nonNestables = []) { # standardize line breaks $text = \str_replace(["\r\n", "\r"], "\n", $text); $Elements = []; $nonNestables = ( empty($nonNestables) ? [] : \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 = ['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 $Elements; } protected function inlineUrl($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]; $Inline = [ 'extent' => \strlen($matches[0][0]), 'position' => $matches[0][1], 'element' => [ 'name' => 'a', 'text' => $url, 'attributes' => [ 'href' => $url, ], ], ]; return $Inline; } } protected function inlineUrlTag($Excerpt) { if (\strpos($Excerpt['text'], '>') !== false and \preg_match('/^<(\w++:\/{2}[^ >]++)>/i', $Excerpt['text'], $matches)) { $url = $matches[1]; return [ 'extent' => \strlen($matches[0]), 'element' => [ 'name' => 'a', 'text' => $url, 'attributes' => [ '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'])) { $Element['nonNestables'] = []; } if (\is_string($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 $this->elementApplyRecursive([$this, 'handle'], $Element); } protected function handleElementsRecursive(array $Elements) { return $this->elementsApplyRecursive([$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 .= $hasName ? '' : ''; } elseif ($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 $Lines) { $Elements = $this->linesElements($Lines); if (! $Lines->containsBlankLines() and isset($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) { $newElements = []; while (\preg_match($regexp, $text, $matches, \PREG_OFFSET_CAPTURE)) { $offset = $matches[0][1]; $before = \substr($text, 0, $offset); $after = \substr($text, $offset + \strlen($matches[0][0])); $newElements[] = ['text' => $before]; foreach ($Elements as $Element) { $newElements[] = $Element; } $text = $after; } $newElements[] = ['text' => $text]; return $newElements; } # # Deprecated Methods # public function parse($text) { $markup = $this->text($text); return $markup; } protected function sanitiseElement(array $Element) { static $goodAttribute = '/^[a-zA-Z0-9][a-zA-Z0-9-_]*+$/'; static $safeUrlNameToAtt = [ 'a' => 'href', 'img' => 'src', ]; if (! isset($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); } } public 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 = []; # # Read-Only protected $specialCharacters = [ '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', '~' ]; protected $StrongRegex = [ '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*+[*])+?)[*]{2}(?![*])/s', '_' => '/^__((?:\\\\_|[^_]|_[^_]*+_)+?)__(?!_)/us', ]; protected $EmRegex = [ '*' => '/^[*]((?:\\\\\*|[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s', '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', ]; protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*+(?:\s*+=\s*+(?:[^"\'=<>`\s]+|"[^"]*+"|\'[^\']*+\'))?+'; protected $voidElements = [ 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', ]; protected $textLevelElements = [ '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', ]; }