From 9214ca5f2ce7dff98580055e5a0233b3fbb03eb7 Mon Sep 17 00:00:00 2001 From: kleper Date: Fri, 11 Nov 2022 03:06:06 +0000 Subject: [PATCH] Web Sustrato --- index.html | 46 ++ web.php | 2143 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 2189 insertions(+) create mode 100644 index.html create mode 100644 web.php diff --git a/index.html b/index.html new file mode 100644 index 0000000..bb878ee --- /dev/null +++ b/index.html @@ -0,0 +1,46 @@ + + + + + + + + + + + + + Sustrato RED + + + + + + + + + + + + + + + + + +
+ +
+ + diff --git a/web.php b/web.php new file mode 100644 index 0000000..8a85942 --- /dev/null +++ b/web.php @@ -0,0 +1,2143 @@ +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'], '') !== 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('/^\[(.+?)\]:[ ]*+?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $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.']++)[ ]*+(.+?)[ ]*+(? 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 .= $hasName ? '' : ''; + } + elseif ($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 $textLevelElements = array( + 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont', + 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing', + 'i', 'rp', 'del', 'code', 'strike', 'marquee', + 'q', 'rt', 'ins', 'font', 'strong', + 's', 'tt', 'kbd', 'mark', + 'u', 'xm', 'sub', 'nobr', + 'sup', 'ruby', + 'var', 'span', + 'wbr', 'time', + ); +} +/****** PARSE DOWN ********/ + +/***** TRUNCATE HTML *****/ +function truncateHtml($text, $length = 100, $ending = '...', $exact = false, $considerHtml = true) { + if ($considerHtml) { + // if the plain text is shorter than the maximum length, return the whole text + if (strlen(preg_replace('/<.*?>/', '', $text)) <= $length) { + return $text; + } + // splits all html-tags to scanable lines + preg_match_all('/(<.+?>)?([^<>]*)/s', $text, $lines, PREG_SET_ORDER); + $total_length = strlen($ending); + $open_tags = array(); + $truncate = ''; + foreach ($lines as $line_matchings) { + // if there is any html-tag in this line, handle it and add it (uncounted) to the output + if (!empty($line_matchings[1])) { + // if it's an "empty element" with or without xhtml-conform closing slash + if (preg_match('/^<(\s*.+?\/\s*|\s*(img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param)(\s.+?)?)>$/is', $line_matchings[1])) { + // do nothing + // if tag is a closing tag + } else if (preg_match('/^<\s*\/([^\s]+?)\s*>$/s', $line_matchings[1], $tag_matchings)) { + // delete tag from $open_tags list + $pos = array_search($tag_matchings[1], $open_tags); + if ($pos !== false) { + unset($open_tags[$pos]); + } + // if tag is an opening tag + } else if (preg_match('/^<\s*([^\s>!]+).*?>$/s', $line_matchings[1], $tag_matchings)) { + // add tag to the beginning of $open_tags list + array_unshift($open_tags, strtolower($tag_matchings[1])); + } + // add html-tag to $truncate'd text + $truncate .= $line_matchings[1]; + } + // calculate the length of the plain text part of the line; handle entities as one character + $content_length = strlen(preg_replace('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|[0-9a-f]{1,6};/i', ' ', $line_matchings[2])); + if ($total_length+$content_length> $length) { + // the number of characters which are left + $left = $length - $total_length; + $entities_length = 0; + // search for html entities + if (preg_match_all('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|[0-9a-f]{1,6};/i', $line_matchings[2], $entities, PREG_OFFSET_CAPTURE)) { + // calculate the real length of all entities in the legal range + foreach ($entities[0] as $entity) { + if ($entity[1]+1-$entities_length <= $left) { + $left--; + $entities_length += strlen($entity[0]); + } else { + // no more characters left + break; + } + } + } + $truncate .= substr($line_matchings[2], 0, $left+$entities_length); + // maximum lenght is reached, so get off the loop + break; + } else { + $truncate .= $line_matchings[2]; + $total_length += $content_length; + } + // if the maximum length is reached, get off the loop + if($total_length>= $length) { + break; + } + } + } else { + if (strlen($text) <= $length) { + return $text; + } else { + $truncate = substr($text, 0, $length - strlen($ending)); + } + } + // if the words shouldn't be cut in the middle... + if (!$exact) { + // ...search the last occurance of a space... + $spacepos = strrpos($truncate, ' '); + if (isset($spacepos)) { + // ...and cut the text in this position + $truncate = substr($truncate, 0, $spacepos); + } + } + // add the defined ending to the text + $truncate .= $ending; + if($considerHtml) { + // close all unclosed html-tags + foreach ($open_tags as $tag) { + $truncate .= ''; + } + } + return $truncate; +} +/***** TRUNCATE HTML *****/ +/**** GET CONTENTS *****/ +function url_get_contents($url, $useragent='cURL', $headers=false, $follow_redirects=true, $debug=false) { + + // initialise the CURL library + $ch = curl_init(); + + // specify the URL to be retrieved + curl_setopt($ch, CURLOPT_URL,$url); + + // we want to get the contents of the URL and store it in a variable + curl_setopt($ch, CURLOPT_RETURNTRANSFER,1); + + // specify the useragent: this is a required courtesy to site owners + curl_setopt($ch, CURLOPT_USERAGENT, $useragent); + + // ignore SSL errors + curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); + + // return headers as requested + if ($headers==true){ + curl_setopt($ch, CURLOPT_HEADER,1); + } + + // only return headers + if ($headers=='headers only') { + curl_setopt($ch, CURLOPT_NOBODY ,1); + } + + // follow redirects - note this is disabled by default in most PHP installs from 4.4.4 up + if ($follow_redirects==true) { + curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); + } + + // if debugging, return an array with CURL's debug info and the URL contents + if ($debug==true) { + $result['contents']=curl_exec($ch); + $result['info']=curl_getinfo($ch); + } + + // otherwise just return the contents as a variable + else $result=curl_exec($ch); + + // free resources + curl_close($ch); + + // send back the data + return $result; +} +function html_to_obj($html) { + $dom = new DOMDocument(); + $dom->loadHTML($html); + $lis = $dom->getElementById('doc'); + return $lis->nodeValue; +} + +function bgpLink(){ + $news1 = html_to_obj(url_get_contents(trim("https://docutopia.sustrato.red/s/SustratoWeb"))); + // // // TRANSFORM TO HTML + $Parsedown = new Parsedown(); + echo '
'.$Parsedown->text($news1).'
'; +} + +bgpLink();