BACK
- - - - \ No newline at end of file diff --git a/library/markdownify/markdownify.php b/library/markdownify/markdownify.php deleted file mode 100644 index 0d4429a01..000000000 --- a/library/markdownify/markdownify.php +++ /dev/null @@ -1,1197 +0,0 @@ -, tags
- $this->out($this->parser->node);
- static $indent;
- $indent = $this->indent;
- $this->indent = '';
- }
- } else {
- if (!$this->parser->keepWhitespace) {
- $this->output = rtrim($this->output);
- }
- if ($this->parser->tagName != 'pre') {
- $this->indent(' ');
- $this->out("\n".$this->indent.$this->parser->node);
- } else {
- # reset indentation
- $this->out($this->parser->node);
- static $indent;
- $this->indent = $indent;
- }
-
- if (in_array($this->parent(), array('ins', 'del'))) {
- # ins or del was block element
- $this->out("\n");
- $this->indent(' ');
- }
- if ($this->parser->tagName == 'li') {
- $this->setLineBreaks(1);
- } else {
- $this->setLineBreaks(2);
- }
- }
- } else {
- $this->out($this->parser->node);
- }
- if (in_array($this->parser->tagName, array('code', 'pre'))) {
- if ($this->parser->isStartTag) {
- $this->buffer();
- } else {
- # add stuff so cleanup just reverses this
- $this->out(str_replace('<', '<', str_replace('>', '>', $this->unbuffer())));
- }
- }
- }
- }
- /**
- * handle plain text
- *
- * @param void
- * @return void
- */
- function handleText() {
- if ($this->hasParent('pre') && strpos($this->parser->node, "\n") !== false) {
- $this->parser->node = str_replace("\n", "\n".$this->indent, $this->parser->node);
- }
- if (!$this->hasParent('code') && !$this->hasParent('pre')) {
- # entity decode
- $this->parser->node = $this->decode($this->parser->node);
- if (!$this->skipConversion) {
- # escape some chars in normal Text
- $this->parser->node = preg_replace($this->escapeInText['search'], $this->escapeInText['replace'], $this->parser->node);
- }
- } else {
- $this->parser->node = str_replace(array('"', '&apos'), array('"', '\''), $this->parser->node);
- }
- $this->out($this->parser->node);
- $this->lastClosedTag = '';
- }
- /**
- * handle and tags
- *
- * @param void
- * @return void
- */
- function handleTag_em() {
- $this->out('*', true);
- }
- function handleTag_i() {
- $this->handleTag_em();
- }
- /**
- * handle and tags
- *
- * @param void
- * @return void
- */
- function handleTag_strong() {
- $this->out('**', true);
- }
- function handleTag_b() {
- $this->handleTag_strong();
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_h1() {
- $this->handleHeader(1);
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_h2() {
- $this->handleHeader(2);
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_h3() {
- $this->handleHeader(3);
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_h4() {
- $this->handleHeader(4);
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_h5() {
- $this->handleHeader(5);
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_h6() {
- $this->handleHeader(6);
- }
- /**
- * number of line breaks before next inline output
- */
- var $lineBreaks = 0;
- /**
- * handle header tags ( - )
- *
- * @param int $level 1-6
- * @return void
- */
- function handleHeader($level) {
- if ($this->parser->isStartTag) {
- $this->out(str_repeat('#', $level).' ', true);
- } else {
- $this->setLineBreaks(2);
- }
- }
- /**
- * handle
tags
- *
- * @param void
- * @return void
- */
- function handleTag_p() {
- if (!$this->parser->isStartTag) {
- $this->setLineBreaks(2);
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_a() {
- if ($this->parser->isStartTag) {
- $this->buffer();
- if (isset($this->parser->tagAttributes['title'])) {
- $this->parser->tagAttributes['title'] = $this->decode($this->parser->tagAttributes['title']);
- } else {
- $this->parser->tagAttributes['title'] = null;
- }
- $this->parser->tagAttributes['href'] = $this->decode(trim($this->parser->tagAttributes['href']));
- $this->stack();
- } else {
- $tag = $this->unstack();
- $buffer = $this->unbuffer();
-
- if (empty($tag['href']) && empty($tag['title'])) {
- # empty links... testcase mania, who would possibly do anything like that?!
- $this->out('['.$buffer.']()', true);
- return;
- }
-
- if ($buffer == $tag['href'] && empty($tag['title'])) {
- #
- $this->out('<'.$buffer.'>', true);
- return;
- }
-
- $bufferDecoded = $this->decode(trim($buffer));
- if (substr($tag['href'], 0, 7) == 'mailto:' && 'mailto:'.$bufferDecoded == $tag['href']) {
- if (is_null($tag['title'])) {
- #
- $this->out('<'.$bufferDecoded.'>', true);
- return;
- }
- # [mail@example.com][1]
- # ...
- # [1]: mailto:mail@example.com Title
- $tag['href'] = 'mailto:'.$bufferDecoded;
- }
-
- $this->out('['.$buffer.']('.$tag['href'].' "'.$tag['title'].'")', true);
-
-/*
- # [This link][id]
- foreach ($this->stack['a'] as $tag2) {
- if ($tag2['href'] == $tag['href'] && $tag2['title'] === $tag['title']) {
- $tag['linkID'] = $tag2['linkID'];
- break;
- }
- }
- if (!isset($tag['linkID'])) {
- $tag['linkID'] = count($this->stack['a']) + 1;
- array_push($this->stack['a'], $tag);
- }
-
- $this->out('['.$buffer.']['.$tag['linkID'].']', true);
-*/
- }
- }
- /**
- * handle ![]()
tags
- *
- * @param void
- * @return void
- */
- function handleTag_img() {
- if (!$this->parser->isStartTag) {
- return; # just to be sure this is really an empty tag...
- }
-
- if (isset($this->parser->tagAttributes['title'])) {
- $this->parser->tagAttributes['title'] = $this->decode($this->parser->tagAttributes['title']);
- } else {
- $this->parser->tagAttributes['title'] = null;
- }
- if (isset($this->parser->tagAttributes['alt'])) {
- $this->parser->tagAttributes['alt'] = $this->decode($this->parser->tagAttributes['alt']);
- } else {
- $this->parser->tagAttributes['alt'] = null;
- }
-
- if (empty($this->parser->tagAttributes['src'])) {
- # support for "empty" images... dunno if this is really needed
- # but there are some testcases which do that...
- if (!empty($this->parser->tagAttributes['title'])) {
- $this->parser->tagAttributes['title'] = ' '.$this->parser->tagAttributes['title'].' ';
- }
- $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['title'].')', true);
- return;
- } else {
- $this->parser->tagAttributes['src'] = $this->decode($this->parser->tagAttributes['src']);
- }
-
-// 
- if ($this->parser->tagAttributes['title'] != "")
- $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['src'].' "'.$this->parser->tagAttributes['title'].'")', true);
- else
- $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['src'].')', true);
-
-/*
- # [This link][id]
- $link_id = false;
- if (!empty($this->stack['a'])) {
- foreach ($this->stack['a'] as $tag) {
- if ($tag['href'] == $this->parser->tagAttributes['src']
- && $tag['title'] === $this->parser->tagAttributes['title']) {
- $link_id = $tag['linkID'];
- break;
- }
- }
- } else {
- $this->stack['a'] = array();
- }
- if (!$link_id) {
- $link_id = count($this->stack['a']) + 1;
- $tag = array(
- 'href' => $this->parser->tagAttributes['src'],
- 'linkID' => $link_id,
- 'title' => $this->parser->tagAttributes['title']
- );
- array_push($this->stack['a'], $tag);
- }
-
- $this->out('!['.$this->parser->tagAttributes['alt'].']['.$link_id.']', true);
-*/
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_code() {
- if ($this->hasParent('pre')) {
- # ignore code blocks inside
- return;
- }
- if ($this->parser->isStartTag) {
- $this->buffer();
- } else {
- $buffer = $this->unbuffer();
- # use as many backticks as needed
- preg_match_all('#`+#', $buffer, $matches);
- if (!empty($matches[0])) {
- rsort($matches[0]);
-
- $ticks = '`';
- while (true) {
- if (!in_array($ticks, $matches[0])) {
- break;
- }
- $ticks .= '`';
- }
- } else {
- $ticks = '`';
- }
- if ($buffer[0] == '`' || substr($buffer, -1) == '`') {
- $buffer = ' '.$buffer.' ';
- }
- $this->out($ticks.$buffer.$ticks, true);
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_pre() {
- if ($this->keepHTML && $this->parser->isStartTag) {
- # check if a simple follows
- if (!preg_match('#^\s*#Us', $this->parser->html)) {
- # this is no standard markdown code block
- $this->handleTagToText();
- return;
- }
- }
- $this->indent(' ');
- if (!$this->parser->isStartTag) {
- $this->setLineBreaks(2);
- } else {
- $this->parser->html = ltrim($this->parser->html);
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_blockquote() {
- $this->indent('> ');
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_ul() {
- if ($this->parser->isStartTag) {
- $this->stack();
- if (!$this->keepHTML && $this->lastClosedTag == $this->parser->tagName) {
- $this->out("\n".$this->indent.''."\n".$this->indent."\n".$this->indent);
- }
- } else {
- $this->unstack();
- if ($this->parent() != 'li' || preg_match('#^\s*(\s*\s*)?<(p|blockquote)\s*>#sU', $this->parser->html)) {
- # dont make Markdown add unneeded paragraphs
- $this->setLineBreaks(2);
- }
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_ol() {
- # same as above
- $this->parser->tagAttributes['num'] = 0;
- $this->handleTag_ul();
- }
- /**
- * handle - tags
- *
- * @param void
- * @return void
- */
- function handleTag_li() {
- if ($this->parent() == 'ol') {
- $parent =& $this->getStacked('ol');
- if ($this->parser->isStartTag) {
- $parent['num']++;
- $this->out($parent['num'].'.'.str_repeat(' ', 3 - strlen($parent['num'])), true);
- }
- $this->indent(' ', false);
- } else {
- if ($this->parser->isStartTag) {
- $this->out('* ', true);
- }
- $this->indent(' ', false);
- }
- if (!$this->parser->isStartTag) {
- $this->setLineBreaks(1);
- }
- }
- /**
- * handle
tags
- *
- * @param void
- * @return void
- */
- function handleTag_hr() {
- if (!$this->parser->isStartTag) {
- return; # just to be sure this really is an empty tag
- }
- $this->out('* * *', true);
- $this->setLineBreaks(2);
- }
- /**
- * handle
tags
- *
- * @param void
- * @return void
- */
- function handleTag_br() {
- $this->out(" \n".$this->indent, true);
- $this->parser->html = ltrim($this->parser->html);
- }
- /**
- * node stack, e.g. for and tags
- *
- * @var array
- */
- var $stack = array();
- /**
- * add current node to the stack
- * this only stores the attributes
- *
- * @param void
- * @return void
- */
- function stack() {
- if (!isset($this->stack[$this->parser->tagName])) {
- $this->stack[$this->parser->tagName] = array();
- }
- array_push($this->stack[$this->parser->tagName], $this->parser->tagAttributes);
- }
- /**
- * remove current tag from stack
- *
- * @param void
- * @return array
- */
- function unstack() {
- if (!isset($this->stack[$this->parser->tagName]) || !is_array($this->stack[$this->parser->tagName])) {
- trigger_error('Trying to unstack from empty stack. This must not happen.', E_USER_ERROR);
- }
- return array_pop($this->stack[$this->parser->tagName]);
- }
- /**
- * get last stacked element of type $tagName
- *
- * @param string $tagName
- * @return array
- */
- function & getStacked($tagName) {
- // no end() so it can be referenced
- return $this->stack[$tagName][count($this->stack[$tagName])-1];
- }
- /**
- * set number of line breaks before next start tag
- *
- * @param int $number
- * @return void
- */
- function setLineBreaks($number) {
- if ($this->lineBreaks < $number) {
- $this->lineBreaks = $number;
- }
- }
- /**
- * stores current buffers
- *
- * @var array
- */
- var $buffer = array();
- /**
- * buffer next parser output until unbuffer() is called
- *
- * @param void
- * @return void
- */
- function buffer() {
- array_push($this->buffer, '');
- }
- /**
- * end current buffer and return buffered output
- *
- * @param void
- * @return string
- */
- function unbuffer() {
- return array_pop($this->buffer);
- }
- /**
- * append string to the correct var, either
- * directly to $this->output or to the current
- * buffers
- *
- * @param string $put
- * @return void
- */
- function out($put, $nowrap = false) {
- if (empty($put)) {
- return;
- }
- if (!empty($this->buffer)) {
- $this->buffer[count($this->buffer) - 1] .= $put;
- } else {
- if ($this->bodyWidth && !$this->parser->keepWhitespace) { # wrap lines
- // get last line
- $pos = strrpos($this->output, "\n");
- if ($pos === false) {
- $line = $this->output;
- } else {
- $line = substr($this->output, $pos);
- }
-
- if ($nowrap) {
- if ($put[0] != "\n" && $this->strlen($line) + $this->strlen($put) > $this->bodyWidth) {
- $this->output .= "\n".$this->indent.$put;
- } else {
- $this->output .= $put;
- }
- return;
- } else {
- $put .= "\n"; # make sure we get all lines in the while below
- $lineLen = $this->strlen($line);
- while ($pos = strpos($put, "\n")) {
- $putLine = substr($put, 0, $pos+1);
- $put = substr($put, $pos+1);
- $putLen = $this->strlen($putLine);
- if ($lineLen + $putLen < $this->bodyWidth) {
- $this->output .= $putLine;
- $lineLen = $putLen;
- } else {
- $split = preg_split('#^(.{0,'.($this->bodyWidth - $lineLen).'})\b#', $putLine, 2, PREG_SPLIT_OFFSET_CAPTURE | PREG_SPLIT_DELIM_CAPTURE);
- $this->output .= rtrim($split[1][0])."\n".$this->indent.$this->wordwrap(ltrim($split[2][0]), $this->bodyWidth, "\n".$this->indent, false);
- }
- }
- $this->output = substr($this->output, 0, -1);
- return;
- }
- } else {
- $this->output .= $put;
- }
- }
- }
- /**
- * current indentation
- *
- * @var string
- */
- var $indent = '';
- /**
- * indent next output (start tag) or unindent (end tag)
- *
- * @param string $str indentation
- * @param bool $output add indendation to output
- * @return void
- */
- function indent($str, $output = true) {
- if ($this->parser->isStartTag) {
- $this->indent .= $str;
- if ($output) {
- $this->out($str, true);
- }
- } else {
- $this->indent = substr($this->indent, 0, -strlen($str));
- }
- }
- /**
- * decode email addresses
- *
- * @author derernst@gmx.ch
- * @author Milian Wolff
- */
- function decode($text, $quote_style = ENT_QUOTES) {
- if (version_compare(PHP_VERSION, '5', '>=')) {
- # UTF-8 is only supported in PHP 5.x.x and above
- $text = html_entity_decode($text, $quote_style, 'UTF-8');
- } else {
- if (function_exists('html_entity_decode')) {
- $text = html_entity_decode($text, $quote_style, 'ISO-8859-1');
- } else {
- static $trans_tbl;
- if (!isset($trans_tbl)) {
- $trans_tbl = array_flip(get_html_translation_table(HTML_ENTITIES, $quote_style));
- }
- $text = strtr($text, $trans_tbl);
- }
- $text = preg_replace_callback('~&#x([0-9a-f]+);~i', array(&$this, '_decode_hex'), $text);
- $text = preg_replace_callback('~&#(\d{2,5});~', array(&$this, '_decode_numeric'), $text);
- }
- return $text;
- }
- /**
- * callback for decode() which converts a hexadecimal entity to UTF-8
- *
- * @param array $matches
- * @return string UTF-8 encoded
- */
- function _decode_hex($matches) {
- return $this->unichr(hexdec($matches[1]));
- }
- /**
- * callback for decode() which converts a numerical entity to UTF-8
- *
- * @param array $matches
- * @return string UTF-8 encoded
- */
- function _decode_numeric($matches) {
- return $this->unichr($matches[1]);
- }
- /**
- * UTF-8 chr() which supports numeric entities
- *
- * @author grey - greywyvern - com
- * @param array $matches
- * @return string UTF-8 encoded
- */
- function unichr($dec) {
- if ($dec < 128) {
- $utf = chr($dec);
- } else if ($dec < 2048) {
- $utf = chr(192 + (($dec - ($dec % 64)) / 64));
- $utf .= chr(128 + ($dec % 64));
- } else {
- $utf = chr(224 + (($dec - ($dec % 4096)) / 4096));
- $utf .= chr(128 + ((($dec % 4096) - ($dec % 64)) / 64));
- $utf .= chr(128 + ($dec % 64));
- }
- return $utf;
- }
- /**
- * UTF-8 strlen()
- *
- * @param string $str
- * @return int
- *
- * @author dtorop 932 at hotmail dot com
- * @author Milian Wolff
- */
- function strlen($str) {
- if (function_exists('mb_strlen')) {
- return mb_strlen($str, 'UTF-8');
- } else {
- return preg_match_all('/[\x00-\x7F\xC0-\xFD]/', $str, $var_empty);
- }
- }
- /**
- * wordwrap for utf8 encoded strings
- *
- * @param string $str
- * @param integer $len
- * @param string $what
- * @return string
- */
- function wordwrap($str, $width, $break, $cut = false){
- if (!$cut) {
- $regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){1,'.$width.'}\b#';
- } else {
- $regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){'.$width.'}#';
- }
- $return = '';
- while (preg_match($regexp, $str, $matches)) {
- $string = $matches[0];
- $str = ltrim(substr($str, strlen($string)));
- if (!$cut && isset($str[0]) && in_array($str[0], array('.', '!', ';', ':', '?', ','))) {
- $string .= $str[0];
- $str = ltrim(substr($str, 1));
- }
- $return .= $string.$break;
- }
- return $return.ltrim($str);
- }
- /**
- * check if current node has a $tagName as parent (somewhere, not only the direct parent)
- *
- * @param string $tagName
- * @return bool
- */
- function hasParent($tagName) {
- return in_array($tagName, $this->parser->openTags);
- }
- /**
- * get tagName of direct parent tag
- *
- * @param void
- * @return string $tagName
- */
- function parent() {
- return end($this->parser->openTags);
- }
-}
diff --git a/library/markdownify/markdownify_cli.php b/library/markdownify/markdownify_cli.php
deleted file mode 100755
index b3fffbd5c..000000000
--- a/library/markdownify/markdownify_cli.php
+++ /dev/null
@@ -1,33 +0,0 @@
-#!/usr/bin/php
-parseString($input) ."\n";
\ No newline at end of file
diff --git a/library/markdownify/markdownify_extra.php b/library/markdownify/markdownify_extra.php
deleted file mode 100644
index e978a1c8a..000000000
--- a/library/markdownify/markdownify_extra.php
+++ /dev/null
@@ -1,489 +0,0 @@
-, )
- * @license LGPL, see LICENSE_LGPL.txt and the summary below
- * @copyright (C) 2007 Milian Wolff
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-/**
- * standard Markdownify class
- */
-require_once dirname(__FILE__).'/markdownify.php';
-
-class Markdownify_Extra extends Markdownify {
- /**
- * table data, including rows with content and the maximum width of each col
- *
- * @var array
- */
- var $table = array();
- /**
- * current col
- *
- * @var int
- */
- var $col = -1;
- /**
- * current row
- *
- * @var int
- */
- var $row = 0;
- /**
- * constructor, see Markdownify::Markdownify() for more information
- */
- function Markdownify_Extra($linksAfterEachParagraph = MDFY_LINKS_EACH_PARAGRAPH, $bodyWidth = MDFY_BODYWIDTH, $keepHTML = MDFY_KEEPHTML) {
- parent::Markdownify($linksAfterEachParagraph, $bodyWidth, $keepHTML);
-
- ### new markdownable tags & attributes
- # header ids: # foo {bar}
- $this->isMarkdownable['h1']['id'] = 'optional';
- $this->isMarkdownable['h2']['id'] = 'optional';
- $this->isMarkdownable['h3']['id'] = 'optional';
- $this->isMarkdownable['h4']['id'] = 'optional';
- $this->isMarkdownable['h5']['id'] = 'optional';
- $this->isMarkdownable['h6']['id'] = 'optional';
- # tables
- $this->isMarkdownable['table'] = array();
- $this->isMarkdownable['th'] = array(
- 'align' => 'optional',
- );
- $this->isMarkdownable['td'] = array(
- 'align' => 'optional',
- );
- $this->isMarkdownable['tr'] = array();
- array_push($this->ignore, 'thead');
- array_push($this->ignore, 'tbody');
- array_push($this->ignore, 'tfoot');
- # definition lists
- $this->isMarkdownable['dl'] = array();
- $this->isMarkdownable['dd'] = array();
- $this->isMarkdownable['dt'] = array();
- # footnotes
- $this->isMarkdownable['fnref'] = array(
- 'target' => 'required',
- );
- $this->isMarkdownable['footnotes'] = array();
- $this->isMarkdownable['fn'] = array(
- 'name' => 'required',
- );
- $this->parser->blockElements['fnref'] = false;
- $this->parser->blockElements['fn'] = true;
- $this->parser->blockElements['footnotes'] = true;
- # abbr
- $this->isMarkdownable['abbr'] = array(
- 'title' => 'required',
- );
- # build RegEx lookahead to decide wether table can pe parsed or not
- $inlineTags = array_keys($this->parser->blockElements, false);
- $colContents = '(?:[^<]|<(?:'.implode('|', $inlineTags).'|[^a-z]))+';
- $this->tableLookaheadHeader = '{
- ^\s*(?:)?\s* # open optional thead
- \s*(?: # start required row with headers
- # header with optional align
- \s*'.$colContents.'\s* # contents
- \s* # close header
- )+ # close row with headers
- \s*(?:)? # close optional thead
- }sxi';
- $this->tdSubstitute = '\s*'.$colContents.'\s* # contents
- \s*';
- $this->tableLookaheadBody = '{
- \s*(?:)?\s* # open optional tbody
- (?:\s* # start row
- %s # cols to be substituted
- )+ # close row
- \s*(?:)? # close optional tbody
- \s* # close table
- }sxi';
- }
- /**
- * handle header tags ( - )
- *
- * @param int $level 1-6
- * @return void
- */
- function handleHeader($level) {
- static $id = null;
- if ($this->parser->isStartTag) {
- if (isset($this->parser->tagAttributes['id'])) {
- $id = $this->parser->tagAttributes['id'];
- }
- } else {
- if (!is_null($id)) {
- $this->out(' {#'.$id.'}');
- $id = null;
- }
- }
- parent::handleHeader($level);
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_abbr() {
- if ($this->parser->isStartTag) {
- $this->stack();
- $this->buffer();
- } else {
- $tag = $this->unstack();
- $tag['text'] = $this->unbuffer();
- $add = true;
- foreach ($this->stack['abbr'] as $stacked) {
- if ($stacked['text'] == $tag['text']) {
- /** TODO: differing abbr definitions, i.e. different titles for same text **/
- $add = false;
- break;
- }
- }
- $this->out($tag['text']);
- if ($add) {
- array_push($this->stack['abbr'], $tag);
- }
- }
- }
- /**
- * flush stacked abbr tags
- *
- * @param void
- * @return void
- */
- function flushStacked_abbr() {
- $out = array();
- foreach ($this->stack['abbr'] as $k => $tag) {
- if (!isset($tag['unstacked'])) {
- array_push($out, ' *['.$tag['text'].']: '.$tag['title']);
- $tag['unstacked'] = true;
- $this->stack['abbr'][$k] = $tag;
- }
- }
- if (!empty($out)) {
- $this->out("\n\n".implode("\n", $out));
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_table() {
- if ($this->parser->isStartTag) {
- # check if upcoming table can be converted
- if ($this->keepHTML) {
- if (preg_match($this->tableLookaheadHeader, $this->parser->html, $matches)) {
- # header seems good, now check body
- # get align & number of cols
- preg_match_all('##si', $matches[0], $cols);
- $regEx = '';
- $i = 1;
- $aligns = array();
- foreach ($cols[2] as $align) {
- $align = strtolower($align);
- array_push($aligns, $align);
- if (empty($align)) {
- $align = 'left'; # default value
- }
- $td = '\s+align=("|\')'.$align.'\\'.$i;
- $i++;
- if ($align == 'left') {
- # look for empty align or left
- $td = '(?:'.$td.')?';
- }
- $td = '';
- $regEx .= $td.$this->tdSubstitute;
- }
- $regEx = sprintf($this->tableLookaheadBody, $regEx);
- if (preg_match($regEx, $this->parser->html, $matches, null, strlen($matches[0]))) {
- # this is a markdownable table tag!
- $this->table = array(
- 'rows' => array(),
- 'col_widths' => array(),
- 'aligns' => $aligns,
- );
- $this->row = 0;
- } else {
- # non markdownable table
- $this->handleTagToText();
- }
- } else {
- # non markdownable table
- $this->handleTagToText();
- }
- } else {
- $this->table = array(
- 'rows' => array(),
- 'col_widths' => array(),
- 'aligns' => array(),
- );
- $this->row = 0;
- }
- } else {
- # finally build the table in Markdown Extra syntax
- $separator = array();
- # seperator with correct align identifikators
- foreach($this->table['aligns'] as $col => $align) {
- if (!$this->keepHTML && !isset($this->table['col_widths'][$col])) {
- break;
- }
- $left = ' ';
- $right = ' ';
- switch ($align) {
- case 'left':
- $left = ':';
- break;
- case 'center':
- $right = ':';
- $left = ':';
- case 'right':
- $right = ':';
- break;
- }
- array_push($separator, $left.str_repeat('-', $this->table['col_widths'][$col]).$right);
- }
- $separator = '|'.implode('|', $separator).'|';
-
- $rows = array();
- # add padding
- array_walk_recursive($this->table['rows'], array(&$this, 'alignTdContent'));
- $header = array_shift($this->table['rows']);
- array_push($rows, '| '.implode(' | ', $header).' |');
- array_push($rows, $separator);
- foreach ($this->table['rows'] as $row) {
- array_push($rows, '| '.implode(' | ', $row).' |');
- }
- $this->out(implode("\n".$this->indent, $rows));
- $this->table = array();
- $this->setLineBreaks(2);
- }
- }
- /**
- * properly pad content so it is aligned as whished
- * should be used with array_walk_recursive on $this->table['rows']
- *
- * @param string &$content
- * @param int $col
- * @return void
- */
- function alignTdContent(&$content, $col) {
- switch ($this->table['aligns'][$col]) {
- default:
- case 'left':
- $content .= str_repeat(' ', $this->table['col_widths'][$col] - $this->strlen($content));
- break;
- case 'right':
- $content = str_repeat(' ', $this->table['col_widths'][$col] - $this->strlen($content)).$content;
- break;
- case 'center':
- $paddingNeeded = $this->table['col_widths'][$col] - $this->strlen($content);
- $left = floor($paddingNeeded / 2);
- $right = $paddingNeeded - $left;
- $content = str_repeat(' ', $left).$content.str_repeat(' ', $right);
- break;
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_tr() {
- if ($this->parser->isStartTag) {
- $this->col = -1;
- } else {
- $this->row++;
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_td() {
- if ($this->parser->isStartTag) {
- $this->col++;
- if (!isset($this->table['col_widths'][$this->col])) {
- $this->table['col_widths'][$this->col] = 0;
- }
- $this->buffer();
- } else {
- $buffer = trim($this->unbuffer());
- $this->table['col_widths'][$this->col] = max($this->table['col_widths'][$this->col], $this->strlen($buffer));
- $this->table['rows'][$this->row][$this->col] = $buffer;
- }
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_th() {
- if (!$this->keepHTML && !isset($this->table['rows'][1]) && !isset($this->table['aligns'][$this->col+1])) {
- if (isset($this->parser->tagAttributes['align'])) {
- $this->table['aligns'][$this->col+1] = $this->parser->tagAttributes['align'];
- } else {
- $this->table['aligns'][$this->col+1] = '';
- }
- }
- $this->handleTag_td();
- }
- /**
- * handle tags
- *
- * @param void
- * @return void
- */
- function handleTag_dl() {
- if (!$this->parser->isStartTag) {
- $this->setLineBreaks(2);
- }
- }
- /**
- * handle - tags
- *
- * @param void
- * @return void
- **/
- function handleTag_dt() {
- if (!$this->parser->isStartTag) {
- $this->setLineBreaks(1);
- }
- }
- /**
- * handle
- tags
- *
- * @param void
- * @return void
- */
- function handleTag_dd() {
- if ($this->parser->isStartTag) {
- if (substr(ltrim($this->parser->html), 0, 3) == '
') {
- # next comes a paragraph, so we'll need an extra line
- $this->out("\n".$this->indent);
- } elseif (substr($this->output, -2) == "\n\n") {
- $this->output = substr($this->output, 0, -1);
- }
- $this->out(': ');
- $this->indent(' ', false);
- } else {
- # lookahead for next dt
- if (substr(ltrim($this->parser->html), 0, 4) == '
- ') {
- $this->setLineBreaks(2);
- } else {
- $this->setLineBreaks(1);
- }
- $this->indent(' ');
- }
- }
- /**
- * handle
tags (custom footnotes, see markdownify_extra::parseString()
- * and markdownify_extra::_makeFootnotes())
- *
- * @param void
- * @return void
- */
- function handleTag_fn() {
- if ($this->parser->isStartTag) {
- $this->out('[^'.$this->parser->tagAttributes['name'].']:');
- $this->setLineBreaks(1);
- } else {
- $this->setLineBreaks(2);
- }
- $this->indent(' ');
- }
- /**
- * handle tag (custom footnotes, see markdownify_extra::parseString()
- * and markdownify_extra::_makeFootnotes())
- *
- * @param void
- * @return void
- */
- function handleTag_footnotes() {
- if (!$this->parser->isStartTag) {
- $this->setLineBreaks(2);
- }
- }
- /**
- * parse a HTML string, clean up footnotes prior
- *
- * @param string $HTML input
- * @return string Markdown formatted output
- */
- function parseString($html) {
- /** TODO: custom markdown-extra options, e.g. titles & classes **/
- # ...
- # =>
- #
- #
- # - ...
- # ...
- #
- #
- #
- # =>
- #
- # ...
- # ...
- #
- $html = preg_replace_callback('#\s*
\s*\s*(.+)\s*
\s*#Us', array(&$this, '_makeFootnotes'), $html);
- return parent::parseString($html);
- }
- /**
- * replace HTML representation of footnotes with something more easily parsable
- *
- * @note this is a callback to be used in parseString()
- *
- * @param array $matches
- * @return string
- */
- function _makeFootnotes($matches) {
- # -
- # ...
- # ↩
- #
- # => ...
- # remove footnote link
- $fns = preg_replace('@\s*( \s*)?]*>↩\s*@s', '', $matches[1]);
- # remove empty paragraph
- $fns = preg_replace('@\s*
@s', '', $fns);
- # - ...
-> ...
- $fns = str_replace('- ';
- return preg_replace('#
\s*(?=(?:))#s', ' $1', $fns);
- }
-}
\ No newline at end of file
diff --git a/library/markdownify/parsehtml/parsehtml.php b/library/markdownify/parsehtml/parsehtml.php
deleted file mode 100644
index 1a8ecacda..000000000
--- a/library/markdownify/parsehtml/parsehtml.php
+++ /dev/null
@@ -1,618 +0,0 @@
- etc.)
- *
- * @var array
- */
- var $emptyTags = array(
- 'br',
- 'hr',
- 'input',
- 'img',
- 'area',
- 'link',
- 'meta',
- 'param',
- );
- /**
- * tags with preformatted text
- * whitespaces wont be touched in them
- *
- * @var array
- */
- var $preformattedTags = array(
- 'script',
- 'style',
- 'pre',
- 'code',
- );
- /**
- * supress HTML tags inside preformatted tags (see above)
- *
- * @var bool
- */
- var $noTagsInCode = false;
- /**
- * html to be parsed
- *
- * @var string
- */
- var $html = '';
- /**
- * node type:
- *
- * - tag (see isStartTag)
- * - text (includes cdata)
- * - comment
- * - doctype
- * - pi (processing instruction)
- *
- * @var string
- */
- var $nodeType = '';
- /**
- * current node content, i.e. either a
- * simple string (text node), or something like
- *
- *
- * @var string
- */
- var $node = '';
- /**
- * wether current node is an opening tag () or not ()
- * set to NULL if current node is not a tag
- * NOTE: empty tags (
) set this to true as well!
- *
- * @var bool | null
- */
- var $isStartTag = null;
- /**
- * wether current node is an empty tag (
) or not ()
- *
- * @var bool | null
- */
- var $isEmptyTag = null;
- /**
- * tag name
- *
- * @var string | null
- */
- var $tagName = '';
- /**
- * attributes of current tag
- *
- * @var array (attribName=>value) | null
- */
- var $tagAttributes = null;
- /**
- * wether the current tag is a block element
- *
- * @var bool | null
- */
- var $isBlockElement = null;
-
- /**
- * keep whitespace
- *
- * @var int
- */
- var $keepWhitespace = 0;
- /**
- * list of open tags
- * count this to get current depth
- *
- * @var array
- */
- var $openTags = array();
- /**
- * list of block elements
- *
- * @var array
- * TODO: what shall we do with and ?!
- */
- var $blockElements = array (
- # tag name => is block
- # block elements
- 'address' => true,
- 'blockquote' => true,
- 'center' => true,
- 'del' => true,
- 'dir' => true,
- 'div' => true,
- 'dl' => true,
- 'fieldset' => true,
- 'form' => true,
- 'h1' => true,
- 'h2' => true,
- 'h3' => true,
- 'h4' => true,
- 'h5' => true,
- 'h6' => true,
- 'hr' => true,
- 'ins' => true,
- 'isindex' => true,
- 'menu' => true,
- 'noframes' => true,
- 'noscript' => true,
- 'ol' => true,
- 'p' => true,
- 'pre' => true,
- 'table' => true,
- 'ul' => true,
- # set table elements and list items to block as well
- 'thead' => true,
- 'tbody' => true,
- 'tfoot' => true,
- 'td' => true,
- 'tr' => true,
- 'th' => true,
- 'li' => true,
- 'dd' => true,
- 'dt' => true,
- # header items and html / body as well
- 'html' => true,
- 'body' => true,
- 'head' => true,
- 'meta' => true,
- 'link' => true,
- 'style' => true,
- 'title' => true,
- # unfancy media tags, when indented should be rendered as block
- 'map' => true,
- 'object' => true,
- 'param' => true,
- 'embed' => true,
- 'area' => true,
- # inline elements
- 'a' => false,
- 'abbr' => false,
- 'acronym' => false,
- 'applet' => false,
- 'b' => false,
- 'basefont' => false,
- 'bdo' => false,
- 'big' => false,
- 'br' => false,
- 'button' => false,
- 'cite' => false,
- 'code' => false,
- 'del' => false,
- 'dfn' => false,
- 'em' => false,
- 'font' => false,
- 'i' => false,
- 'img' => false,
- 'ins' => false,
- 'input' => false,
- 'iframe' => false,
- 'kbd' => false,
- 'label' => false,
- 'q' => false,
- 'samp' => false,
- 'script' => false,
- 'select' => false,
- 'small' => false,
- 'span' => false,
- 'strong' => false,
- 'sub' => false,
- 'sup' => false,
- 'textarea' => false,
- 'tt' => false,
- 'var' => false,
- );
- /**
- * get next node, set $this->html prior!
- *
- * @param void
- * @return bool
- */
- function nextNode() {
- if (empty($this->html)) {
- # we are done with parsing the html string
- return false;
- }
- static $skipWhitespace = true;
- if ($this->isStartTag && !$this->isEmptyTag) {
- array_push($this->openTags, $this->tagName);
- if (in_array($this->tagName, $this->preformattedTags)) {
- # dont truncate whitespaces for or contents
- $this->keepWhitespace++;
- }
- }
-
- if ($this->html[0] == '<') {
- $token = substr($this->html, 0, 9);
- if (substr($token, 0, 2) == 'html, '>');
- $this->setNode('pi', $pos + 1);
- return true;
- }
- if (substr($token, 0, 4) == '');
- if ($pos === false) {
- # could not find a closing -->, use next gt instead
- # this is firefox' behaviour
- $pos = strpos($this->html, '>') + 1;
- } else {
- $pos += 3;
- }
- $this->setNode('comment', $pos);
-
- $skipWhitespace = true;
- return true;
- }
- if ($token == 'setNode('doctype', strpos($this->html, '>')+1);
-
- $skipWhitespace = true;
- return true;
- }
- if ($token == 'html = substr($this->html, 9);
-
- $this->setNode('text', strpos($this->html, ']]>')+3);
-
- # remove trailing ]]> and trim
- $this->node = substr($this->node, 0, -3);
- $this->handleWhitespaces();
-
- $skipWhitespace = true;
- return true;
- }
- if ($this->parseTag()) {
- # seems to be a tag
- # handle whitespaces
- if ($this->isBlockElement) {
- $skipWhitespace = true;
- } else {
- $skipWhitespace = false;
- }
- return true;
- }
- }
- if ($this->keepWhitespace) {
- $skipWhitespace = false;
- }
- # when we get here it seems to be a text node
- $pos = strpos($this->html, '<');
- if ($pos === false) {
- $pos = strlen($this->html);
- }
- $this->setNode('text', $pos);
- $this->handleWhitespaces();
- if ($skipWhitespace && $this->node == ' ') {
- return $this->nextNode();
- }
- $skipWhitespace = false;
- return true;
- }
- /**
- * parse tag, set tag name and attributes, see if it's a closing tag and so forth...
- *
- * @param void
- * @return bool
- */
- function parseTag() {
- static $a_ord, $z_ord, $special_ords;
- if (!isset($a_ord)) {
- $a_ord = ord('a');
- $z_ord = ord('z');
- $special_ords = array(
- ord(':'), // for xml:lang
- ord('-'), // for http-equiv
- );
- }
-
- $tagName = '';
-
- $pos = 1;
- $isStartTag = $this->html[$pos] != '/';
- if (!$isStartTag) {
- $pos++;
- }
- # get tagName
- while (isset($this->html[$pos])) {
- $pos_ord = ord(strtolower($this->html[$pos]));
- if (($pos_ord >= $a_ord && $pos_ord <= $z_ord) || (!empty($tagName) && is_numeric($this->html[$pos]))) {
- $tagName .= $this->html[$pos];
- $pos++;
- } else {
- $pos--;
- break;
- }
- }
-
- $tagName = strtolower($tagName);
- if (empty($tagName) || !isset($this->blockElements[$tagName])) {
- # something went wrong => invalid tag
- $this->invalidTag();
- return false;
- }
- if ($this->noTagsInCode && end($this->openTags) == 'code' && !($tagName == 'code' && !$isStartTag)) {
- # we supress all HTML tags inside code tags
- $this->invalidTag();
- return false;
- }
-
- # get tag attributes
- /** TODO: in html 4 attributes do not need to be quoted **/
- $isEmptyTag = false;
- $attributes = array();
- $currAttrib = '';
- while (isset($this->html[$pos+1])) {
- $pos++;
- # close tag
- if ($this->html[$pos] == '>' || $this->html[$pos].$this->html[$pos+1] == '/>') {
- if ($this->html[$pos] == '/') {
- $isEmptyTag = true;
- $pos++;
- }
- break;
- }
-
- $pos_ord = ord(strtolower($this->html[$pos]));
- if ( ($pos_ord >= $a_ord && $pos_ord <= $z_ord) || in_array($pos_ord, $special_ords)) {
- # attribute name
- $currAttrib .= $this->html[$pos];
- } elseif (in_array($this->html[$pos], array(' ', "\t", "\n"))) {
- # drop whitespace
- } elseif (in_array($this->html[$pos].$this->html[$pos+1], array('="', "='"))) {
- # get attribute value
- $pos++;
- $await = $this->html[$pos]; # single or double quote
- $pos++;
- $value = '';
- while (isset($this->html[$pos]) && $this->html[$pos] != $await) {
- $value .= $this->html[$pos];
- $pos++;
- }
- $attributes[$currAttrib] = $value;
- $currAttrib = '';
- } else {
- $this->invalidTag();
- return false;
- }
- }
- if ($this->html[$pos] != '>') {
- $this->invalidTag();
- return false;
- }
-
- if (!empty($currAttrib)) {
- # html 4 allows something like
\s* # close header
+ )+ # close row with headers
+ \s*(?:)? # close optional thead
+ }sxi';
+ $this->tdSubstitute = '\s*' . $colContents . '\s* # contents
+ \s*';
+ $this->tableLookaheadBody = '{
+ \s*(?:)?\s* # open optional tbody
+ (?:\s* # start row
+ %s # cols to be substituted
+ )+ # close row
+ \s*(?:)? # close optional tbody
+ \s*
# close table
+ }sxi';
+ }
+
+ /**
+ * handle header tags ( - )
+ *
+ * @param int $level 1-6
+ * @return void
+ */
+ protected function handleHeader($level)
+ {
+ if ($this->parser->isStartTag) {
+ $this->parser->tagAttributes['cssSelector'] = $this->getCurrentCssSelector();
+ $this->stack();
+ } else {
+ $tag = $this->unstack();
+ if (!empty($tag['cssSelector'])) {
+ // {#id.class}
+ $this->out(' {' . $tag['cssSelector'] . '}');
+ }
+ }
+ parent::handleHeader($level);
+ }
+
+ /**
+ * handle tags parsing
+ *
+ * @param void
+ * @return void
+ */
+ protected function handleTag_a_parser()
+ {
+ parent::handleTag_a_parser();
+ $this->parser->tagAttributes['cssSelector'] = $this->getCurrentCssSelector();
+ }
+
+ /**
+ * handle tags conversion
+ *
+ * @param array $tag
+ * @param string $buffer
+ * @return string The markdownified link
+ */
+ protected function handleTag_a_converter($tag, $buffer)
+ {
+ $output = parent::handleTag_a_converter($tag, $buffer);
+ if (!empty($tag['cssSelector'])) {
+ // [This link][id]{#id.class}
+ $output .= '{' . $tag['cssSelector'] . '}';
+ }
+
+ return $output;
+ }
+
+ /**
+ * handle tags
+ *
+ * @param void
+ * @return void
+ */
+ protected function handleTag_abbr()
+ {
+ if ($this->parser->isStartTag) {
+ $this->stack();
+ $this->buffer();
+ } else {
+ $tag = $this->unstack();
+ $tag['text'] = $this->unbuffer();
+ $add = true;
+ foreach ($this->stack['abbr'] as $stacked) {
+ if ($stacked['text'] == $tag['text']) {
+ /** TODO: differing abbr definitions, i.e. different titles for same text **/
+ $add = false;
+ break;
+ }
+ }
+ $this->out($tag['text']);
+ if ($add) {
+ array_push($this->stack['abbr'], $tag);
+ }
+ }
+ }
+
+ /**
+ * flush stacked abbr tags
+ *
+ * @param void
+ * @return void
+ */
+ protected function flushStacked_abbr()
+ {
+ $out = array();
+ foreach ($this->stack['abbr'] as $k => $tag) {
+ if (!isset($tag['unstacked'])) {
+ array_push($out, ' *[' . $tag['text'] . ']: ' . $tag['title']);
+ $tag['unstacked'] = true;
+ $this->stack['abbr'][$k] = $tag;
+ }
+ }
+ if (!empty($out)) {
+ $this->out("\n\n" . implode("\n", $out));
+ }
+ }
+
+ /**
+ * handle