New routines for markdown to html and html to markdown.

This commit is contained in:
Michael Vogel 2015-02-22 17:38:28 +01:00
parent c8a1057300
commit 2f46675a89
9 changed files with 2368 additions and 2936 deletions

View File

@ -5,7 +5,8 @@ require_once("include/event.php");
require_once("library/markdown.php"); require_once("library/markdown.php");
require_once("include/html2bbcode.php"); require_once("include/html2bbcode.php");
require_once("include/bbcode.php"); require_once("include/bbcode.php");
require_once("include/markdownify/markdownify.php"); require_once("library/html-to-markdown/HTML_To_Markdown.php");
//require_once("include/markdownify/markdownify.php");
// we don't want to support a bbcode specific markdown interpreter // we don't want to support a bbcode specific markdown interpreter
@ -21,15 +22,15 @@ function diaspora2bb($s) {
$s = str_replace("\r","",$s); $s = str_replace("\r","",$s);
// <br/> is invalid. Replace it with the valid expression // <br/> is invalid. Replace it with the valid expression
$s = str_replace(array("<br/>", "</p>", "<p>", '<p dir="ltr">'),array("<br />", "<br />", "<br />", "<br />"),$s); //$s = str_replace(array("<br/>", "</p>", "<p>", '<p dir="ltr">'),array("<br />", "<br />", "<br />", "<br />"),$s);
$s = preg_replace('/\@\{(.+?)\; (.+?)\@(.+?)\}/','@[url=https://$3/u/$2]$1[/url]',$s);
// Escaping the hash tags // Escaping the hash tags
$s = preg_replace('/\#([^\s\#])/','&#35;$1',$s); $s = preg_replace('/\#([^\s\#])/','&#35;$1',$s);
$s = Markdown($s); $s = Markdown($s);
$s = preg_replace('/\@\{(.+?)\; (.+?)\@(.+?)\}/','@[url=https://$3/u/$2]$1[/url]',$s);
$s = str_replace('&#35;','#',$s); $s = str_replace('&#35;','#',$s);
$s = html2bbcode($s); $s = html2bbcode($s);
@ -92,12 +93,15 @@ function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) {
$Text = bbcode($Text, $preserve_nl, false, 4); $Text = bbcode($Text, $preserve_nl, false, 4);
// Libertree doesn't convert a harizontal rule if there isn't a linefeed // Libertree doesn't convert a harizontal rule if there isn't a linefeed
$Text = str_replace(array("<hr />", "<hr>"), array("<br /><hr />", "<br><hr>"), $Text); //$Text = str_replace(array("<hr />", "<hr>"), array("<br /><hr />", "<br><hr>"), $Text);
} }
// Now convert HTML to Markdown // Now convert HTML to Markdown
$md = new Markdownify(false, false, false); $Text = new HTML_To_Markdown($Text);
$Text = $md->parseString($Text);
/*
//$md = new Markdownify(false, false, false);
//$Text = $md->parseString($Text);
// The Markdownify converter converts underscores '_' in URLs to '\_', which // The Markdownify converter converts underscores '_' in URLs to '\_', which
// messes up the URL. Manually fix these // messes up the URL. Manually fix these
@ -123,6 +127,7 @@ function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) {
// Remove all unconverted tags // Remove all unconverted tags
$Text = strip_tags($Text); $Text = strip_tags($Text);
*/
// Remove any leading or trailing whitespace, as this will mess up // Remove any leading or trailing whitespace, as this will mess up
// the Diaspora signature verification and cause the item to disappear // the Diaspora signature verification and cause the item to disappear

View File

@ -168,6 +168,8 @@ function bb_remove_share_information($Text, $plaintext = false, $nolink = false)
} }
function bb_cleanup_share($shared, $plaintext, $nolink) { function bb_cleanup_share($shared, $plaintext, $nolink) {
$shared[1] = trim($shared[1]);
if (!in_array($shared[2], array("type-link", "type-video"))) if (!in_array($shared[2], array("type-link", "type-video")))
return($shared[0]); return($shared[0]);
@ -178,7 +180,7 @@ function bb_cleanup_share($shared, $plaintext, $nolink) {
return($shared[0]); return($shared[0]);
if ($nolink) if ($nolink)
return(trim($shared[1])); return($shared[1]);
$title = ""; $title = "";
$link = ""; $link = "";
@ -189,6 +191,9 @@ function bb_cleanup_share($shared, $plaintext, $nolink) {
if (isset($bookmark[1][0])) if (isset($bookmark[1][0]))
$link = $bookmark[1][0]; $link = $bookmark[1][0];
if (($title != "") AND (strpos($title, $shared[1]) !== false))
$shared[1] = $title;
if (($title != "") AND ((strpos($shared[1],$title) !== false) OR if (($title != "") AND ((strpos($shared[1],$title) !== false) OR
(similar_text($shared[1],$title) / strlen($title)) > 0.9)) (similar_text($shared[1],$title) / strlen($title)) > 0.9))
$title = ""; $title = "";

View File

@ -0,0 +1,592 @@
<?php
/**
* Class HTML_To_Markdown
*
* A helper class to convert HTML to Markdown.
*
* @version 2.1.2
* @author Nick Cernis <nick@cern.is>
* @link https://github.com/nickcernis/html2markdown/ Latest version on GitHub.
* @link http://twitter.com/nickcernis Nick on twitter.
* @license http://www.opensource.org/licenses/mit-license.php MIT
*/
class HTML_To_Markdown
{
/**
* @var DOMDocument The root of the document tree that holds our HTML.
*/
private $document;
/**
* @var string|boolean The Markdown version of the original HTML, or false if conversion failed
*/
private $output;
/**
* @var array Class-wide options users can override.
*/
private $options = array(
'header_style' => 'setext', // Set to "atx" to output H1 and H2 headers as # Header1 and ## Header2
'suppress_errors' => true, // Set to false to show warnings when loading malformed HTML
'strip_tags' => false, // Set to true to strip tags that don't have markdown equivalents. N.B. Strips tags, not their content. Useful to clean MS Word HTML output.
'bold_style' => '**', // Set to '__' if you prefer the underlined style
'italic_style' => '*', // Set to '_' if you prefer the underlined style
'remove_nodes' => '', // space-separated list of dom nodes that should be removed. example: "meta style script"
);
/**
* Constructor
*
* Set up a new DOMDocument from the supplied HTML, convert it to Markdown, and store it in $this->$output.
*
* @param string $html The HTML to convert to Markdown.
* @param array $overrides [optional] List of style and error display overrides.
*/
public function __construct($html = null, $overrides = null)
{
if ($overrides)
$this->options = array_merge($this->options, $overrides);
if ($html)
$this->convert($html);
}
/**
* Setter for conversion options
*
* @param $name
* @param $value
*/
public function set_option($name, $value)
{
$this->options[$name] = $value;
}
/**
* Convert
*
* Loads HTML and passes to get_markdown()
*
* @param $html
* @return string The Markdown version of the html
*/
public function convert($html)
{
$html = preg_replace('~>\s+<~', '><', $html); // Strip white space between tags to prevent creation of empty #text nodes
$this->document = new DOMDocument();
if ($this->options['suppress_errors'])
libxml_use_internal_errors(true); // Suppress conversion errors (from http://bit.ly/pCCRSX )
$this->document->loadHTML('<?xml encoding="UTF-8">' . $html); // Hack to load utf-8 HTML (from http://bit.ly/pVDyCt )
$this->document->encoding = 'UTF-8';
if ($this->options['suppress_errors'])
libxml_clear_errors();
return $this->get_markdown($html);
}
/**
* Is Child Of?
*
* Is the node a child of the given parent tag?
*
* @param $parent_name string The name of the parent node to search for (e.g. 'code')
* @param $node
* @return bool
*/
private static function is_child_of($parent_name, $node)
{
for ($p = $node->parentNode; $p != false; $p = $p->parentNode) {
if (is_null($p))
return false;
if ($p->nodeName == $parent_name)
return true;
}
return false;
}
/**
* Convert Children
*
* Recursive function to drill into the DOM and convert each node into Markdown from the inside out.
*
* Finds children of each node and convert those to #text nodes containing their Markdown equivalent,
* starting with the innermost element and working up to the outermost element.
*
* @param $node
*/
private function convert_children($node)
{
// Don't convert HTML code inside <code> and <pre> blocks to Markdown - that should stay as HTML
if (self::is_child_of('pre', $node) || self::is_child_of('code', $node))
return;
// If the node has children, convert those to Markdown first
if ($node->hasChildNodes()) {
$length = $node->childNodes->length;
for ($i = 0; $i < $length; $i++) {
$child = $node->childNodes->item($i);
$this->convert_children($child);
}
}
// Now that child nodes have been converted, convert the original node
$markdown = $this->convert_to_markdown($node);
// Create a DOM text node containing the Markdown equivalent of the original node
$markdown_node = $this->document->createTextNode($markdown);
// Replace the old $node e.g. "<h3>Title</h3>" with the new $markdown_node e.g. "### Title"
$node->parentNode->replaceChild($markdown_node, $node);
}
/**
* Get Markdown
*
* Sends the body node to convert_children() to change inner nodes to Markdown #text nodes, then saves and
* returns the resulting converted document as a string in Markdown format.
*
* @return string|boolean The converted HTML as Markdown, or false if conversion failed
*/
private function get_markdown()
{
// Work on the entire DOM tree (including head and body)
$input = $this->document->getElementsByTagName("html")->item(0);
if (!$input)
return false;
// Convert all children of this root element. The DOMDocument stored in $this->doc will
// then consist of #text nodes, each containing a Markdown version of the original node
// that it replaced.
$this->convert_children($input);
// Sanitize and return the body contents as a string.
$markdown = $this->document->saveHTML(); // stores the DOMDocument as a string
$markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8');
$markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8'); // Double decode to cover cases like &amp;nbsp; http://www.php.net/manual/en/function.htmlentities.php#99984
$markdown = preg_replace("/<!DOCTYPE [^>]+>/", "", $markdown); // Strip doctype declaration
$unwanted = array('<html>', '</html>', '<body>', '</body>', '<head>', '</head>', '<?xml encoding="UTF-8">', '&#xD;');
$markdown = str_replace($unwanted, '', $markdown); // Strip unwanted tags
$markdown = trim($markdown, "\n\r\0\x0B");
$this->output = $markdown;
return $markdown;
}
/**
* Convert to Markdown
*
* Converts an individual node into a #text node containing a string of its Markdown equivalent.
*
* Example: An <h3> node with text content of "Title" becomes a text node with content of "### Title"
*
* @param $node
* @return string The converted HTML as Markdown
*/
private function convert_to_markdown($node)
{
$tag = $node->nodeName; // the type of element, e.g. h1
$value = $node->nodeValue; // the value of that element, e.g. The Title
// Strip nodes named in remove_nodes
$tags_to_remove = explode(' ', $this->options['remove_nodes']);
if ( in_array($tag, $tags_to_remove) )
return false;
switch ($tag) {
case "p":
$markdown = (trim($value)) ? rtrim($value) . PHP_EOL . PHP_EOL : '';
break;
case "pre":
$markdown = PHP_EOL . $this->convert_code($node) . PHP_EOL;
break;
case "h1":
case "h2":
$markdown = $this->convert_header($tag, $node);
break;
case "h3":
$markdown = "### " . $value . PHP_EOL . PHP_EOL;
break;
case "h4":
$markdown = "#### " . $value . PHP_EOL . PHP_EOL;
break;
case "h5":
$markdown = "##### " . $value . PHP_EOL . PHP_EOL;
break;
case "h6":
$markdown = "###### " . $value . PHP_EOL . PHP_EOL;
break;
case "em":
case "i":
case "strong":
case "b":
$markdown = $this->convert_emphasis($tag, $value);
break;
case "hr":
$markdown = "- - - - - -" . PHP_EOL . PHP_EOL;
break;
case "br":
$markdown = " " . PHP_EOL;
break;
case "blockquote":
$markdown = $this->convert_blockquote($node);
break;
case "code":
$markdown = $this->convert_code($node);
break;
case "ol":
case "ul":
$markdown = $value . PHP_EOL;
break;
case "li":
$markdown = $this->convert_list($node);
break;
case "img":
$markdown = $this->convert_image($node);
break;
case "a":
$markdown = $this->convert_anchor($node);
break;
case "#text":
$markdown = preg_replace('~\s+~', ' ', $value);
$markdown = preg_replace('~^#~', '\\\\#', $markdown);
break;
case "#comment":
$markdown = '';
break;
case "div":
$markdown = ($this->options['strip_tags']) ? $value . PHP_EOL . PHP_EOL : html_entity_decode($node->C14N());
break;
default:
// If strip_tags is false (the default), preserve tags that don't have Markdown equivalents,
// such as <span> nodes on their own. C14N() canonicalizes the node to a string.
// See: http://www.php.net/manual/en/domnode.c14n.php
$markdown = ($this->options['strip_tags']) ? $value : html_entity_decode($node->C14N());
}
return $markdown;
}
/**
* Convert Header
*
* Converts h1 and h2 headers to Markdown-style headers in setext style,
* matching the number of underscores with the length of the title.
*
* e.g. Header 1 Header Two
* ======== ----------
*
* Returns atx headers instead if $this->options['header_style'] is "atx"
*
* e.g. # Header 1 ## Header Two
*
* @param string $level The header level, including the "h". e.g. h1
* @param string $node The node to convert.
* @return string The Markdown version of the header.
*/
private function convert_header($level, $node)
{
$content = $node->nodeValue;
if (!$this->is_child_of('blockquote', $node) && $this->options['header_style'] == "setext") {
$length = (function_exists('mb_strlen')) ? mb_strlen($content, 'utf-8') : strlen($content);
$underline = ($level == "h1") ? "=" : "-";
$markdown = $content . PHP_EOL . str_repeat($underline, $length) . PHP_EOL . PHP_EOL; // setext style
} else {
$prefix = ($level == "h1") ? "# " : "## ";
$markdown = $prefix . $content . PHP_EOL . PHP_EOL; // atx style
}
return $markdown;
}
/**
* Converts inline styles
* This function is used to render strong and em tags
*
* eg <strong>bold text</strong> becomes **bold text** or __bold text__
*
* @param string $tag
* @param string $value
* @return string
*/
private function convert_emphasis($tag, $value)
{
if ($tag == 'i' || $tag == 'em') {
$markdown = $this->options['italic_style'] . $value . $this->options['italic_style'];
} else {
$markdown = $this->options['bold_style'] . $value . $this->options['bold_style'];
}
return $markdown;
}
/**
* Convert Image
*
* Converts <img /> tags to Markdown.
*
* e.g. <img src="/path/img.jpg" alt="alt text" title="Title" />
* becomes ![alt text](/path/img.jpg "Title")
*
* @param $node
* @return string
*/
private function convert_image($node)
{
$src = $node->getAttribute('src');
$alt = $node->getAttribute('alt');
$title = $node->getAttribute('title');
if ($title != "") {
$markdown = '![' . $alt . '](' . $src . ' "' . $title . '")'; // No newlines added. <img> should be in a block-level element.
} else {
$markdown = '![' . $alt . '](' . $src . ')';
}
return $markdown;
}
/**
* Convert Anchor
*
* Converts <a> tags to Markdown.
*
* e.g. <a href="http://modernnerd.net" title="Title">Modern Nerd</a>
* becomes [Modern Nerd](http://modernnerd.net "Title")
*
* @param $node
* @return string
*/
private function convert_anchor($node)
{
$href = $node->getAttribute('href');
$title = $node->getAttribute('title');
$text = $node->nodeValue;
if ($title != "") {
$markdown = '[' . $text . '](' . $href . ' "' . $title . '")';
} else {
$markdown = '[' . $text . '](' . $href . ')';
}
// Append a space if the node after this one is also an anchor
$next_node_name = $this->get_next_node_name($node);
if ($next_node_name == 'a')
$markdown = $markdown . ' ';
return $markdown;
}
/**
* Convert List
*
* Converts <ul> and <ol> lists to Markdown.
*
* @param $node
* @return string
*/
private function convert_list($node)
{
// If parent is an ol, use numbers, otherwise, use dashes
$list_type = $node->parentNode->nodeName;
$value = $node->nodeValue;
if ($list_type == "ul") {
$markdown = "- " . trim($value) . PHP_EOL;
} else {
$number = $this->get_position($node);
$markdown = $number . ". " . trim($value) . PHP_EOL;
}
return $markdown;
}
/**
* Convert Code
*
* Convert code tags by indenting blocks of code and wrapping single lines in backticks.
*
* @param DOMNode $node
* @return string
*/
private function convert_code($node)
{
// Store the content of the code block in an array, one entry for each line
$markdown = '';
$code_content = html_entity_decode($this->document->saveHTML($node));
$code_content = str_replace(array("<code>", "</code>"), "", $code_content);
$code_content = str_replace(array("<pre>", "</pre>"), "", $code_content);
$lines = preg_split('/\r\n|\r|\n/', $code_content);
$total = count($lines);
// If there's more than one line of code, prepend each line with four spaces and no backticks.
if ($total > 1 || $node->nodeName === 'pre') {
// Remove the first and last line if they're empty
$first_line = trim($lines[0]);
$last_line = trim($lines[$total - 1]);
$first_line = trim($first_line, "&#xD;"); //trim XML style carriage returns too
$last_line = trim($last_line, "&#xD;");
if (empty($first_line))
array_shift($lines);
if (empty($last_line))
array_pop($lines);
$count = 1;
foreach ($lines as $line) {
$line = str_replace('&#xD;', '', $line);
$markdown .= " " . $line;
// Add newlines, except final line of the code
if ($count != $total)
$markdown .= PHP_EOL;
$count++;
}
$markdown .= PHP_EOL;
} else { // There's only one line of code. It's a code span, not a block. Just wrap it with backticks.
$markdown .= "`" . $lines[0] . "`";
}
return $markdown;
}
/**
* Convert blockquote
*
* Prepend blockquotes with > chars.
*
* @param $node
* @return string
*/
private function convert_blockquote($node)
{
// Contents should have already been converted to Markdown by this point,
// so we just need to add ">" symbols to each line.
$markdown = '';
$quote_content = trim($node->nodeValue);
$lines = preg_split('/\r\n|\r|\n/', $quote_content);
$total_lines = count($lines);
foreach ($lines as $i => $line) {
$markdown .= "> " . $line . PHP_EOL;
if ($i + 1 == $total_lines)
$markdown .= PHP_EOL;
}
return $markdown;
}
/**
* Get Position
*
* Returns the numbered position of a node inside its parent
*
* @param $node
* @return int The numbered position of the node, starting at 1.
*/
private function get_position($node)
{
// Get all of the nodes inside the parent
$list_nodes = $node->parentNode->childNodes;
$total_nodes = $list_nodes->length;
$position = 1;
// Loop through all nodes and find the given $node
for ($a = 0; $a < $total_nodes; $a++) {
$current_node = $list_nodes->item($a);
if ($current_node->isSameNode($node))
$position = $a + 1;
}
return $position;
}
/**
* Get Next Node Name
*
* Return the name of the node immediately after the passed one.
*
* @param $node
* @return string|null The node name (e.g. 'h1') or null.
*/
private function get_next_node_name($node)
{
$next_node_name = null;
$current_position = $this->get_position($node);
$next_node = $node->parentNode->childNodes->item($current_position);
if ($next_node)
$next_node_name = $next_node->nodeName;
return $next_node_name;
}
/**
* To String
*
* Magic method to return Markdown output when HTML_To_Markdown instance is treated as a string.
*
* @return string
*/
public function __toString()
{
return $this->output();
}
/**
* Output
*
* Getter for the converted Markdown contents stored in $this->output
*
* @return string
*/
public function output()
{
if (!$this->output) {
return '';
} else {
return $this->output;
}
}
}

View File

@ -0,0 +1,20 @@
The MIT License (MIT)
Copyright (c) 2013 Nick Cernis
Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

View File

@ -0,0 +1,138 @@
HTML To Markdown for PHP
========================
A helper class that converts HTML to [Markdown](http://daringfireball.net/projects/markdown/) for your sanity and convenience.
[![Build Status](https://travis-ci.org/nickcernis/html-to-markdown.png?branch=master)](https://travis-ci.org/nickcernis/html-to-markdown)
**Version**: 2.2.0
**Requires**: PHP 5.3+
**Author**: [@nickcernis](http://twitter.com/nickcernis)
**License**: [MIT](http://www.opensource.org/licenses/mit-license.php)
### Why convert HTML to Markdown?
*"What alchemy is this?"* you mutter. *"I can see why you'd convert [Markdown to HTML](http://michelf.com/projects/php-markdown/),"* you continue, already labouring the question somewhat, *"but why go the other way?"*
Typically you would convert HTML to Markdown if:
1. You have an existing HTML document that needs to be edited by people with good taste.
2. You want to store new content in HTML format but edit it as Markdown.
3. You want to convert HTML email to plain text email.
4. You know a guy who's been converting HTML to Markdown for years, and now he can speak Elvish. You'd quite like to be able to speak Elvish.
5. You just really like Markdown.
### How to use it
Either include HTML_To_Markdown.php directly:
require_once( dirname( __FILE__) . '/HTML_To_Markdown.php' );
Or, require the library in your composer.json:
{
"require": {
"nickcernis/html-to-markdown": "dev-master"
}
}
Then `composer install` and add `require 'vendor/autoload.php';` to the top of your script.
Next, create a new HTML_To_Markdown instance, passing in your valid HTML code:
$html = "<h3>Quick, to the Batpoles!</h3>";
$markdown = new HTML_To_Markdown($html);
The `$markdown` object now contains the Markdown version of your HTML. Use it like a string:
echo $markdown; // ==> ### Quick, to the Batpoles!
Or access the Markdown output directly:
$string = $markdown->output();
The included `demo` directory contains an HTML->Markdown conversion form to try out.
### Conversion options
By default, HTML To Markdown preserves HTML tags without Markdown equivalents, like `<span>` and `<div>`.
To strip HTML tags that don't have a Markdown equivalent while preserving the content inside them, set `strip_tags` to true, like this:
$html = '<span>Turnips!</span>';
$markdown = new HTML_To_Markdown($html, array('strip_tags' => true)); // $markdown now contains "Turnips!"
Or more explicitly, like this:
$html = '<span>Turnips!</span>';
$markdown = new HTML_To_Markdown();
$markdown->set_option('strip_tags', true);
$markdown->convert($html); // $markdown now contains "Turnips!"
Note that only the tags themselves are stripped, not the content they hold.
To strip tags and their content, pass a space-separated list of tags in `remove_nodes`, like this:
$html = '<span>Turnips!</span><div>Monkeys!</div>';
$markdown = new HTML_To_Markdown($html, array('remove_nodes' => 'span div')); // $markdown now contains ""
### Style options
Bold and italic tags are converted using the asterisk syntax by default. Change this to the underlined syntax using the `bold_style` and `italic_style` options.
$html = '<em>Italic</em> and a <strong>bold</strong>';
$markdown = new HTML_To_Markdown();
$markdown->set_option('italic_style', '_');
$markdown->set_option('bold_style', '__');
$markdown->convert($html); // $markdown now contains "_Italic_ and a __bold__"
### Limitations
- Markdown Extra, MultiMarkdown and other variants aren't supported just Markdown.
### Known issues
- Nested lists and lists containing multiple paragraphs aren't converted correctly.
- Lists inside blockquotes aren't converted correctly.
- Any reported [open issues here](https://github.com/nickcernis/html-to-markdown/issues?state=open).
[Report your issue or request a feature here.](https://github.com/nickcernis/html2markdown/issues/new) Issues with patches or failing tests are especially welcome.
### Style notes
- Setext (underlined) headers are the default for H1 and H2. If you prefer the ATX style for H1 and H2 (# Header 1 and ## Header 2), set `header_style` to 'atx' in the options array when you instantiate the object:
`$markdown = new HTML_To_Markdown( $html, array('header_style'=>'atx') );`
Headers of H3 priority and lower always use atx style.
- Links and images are referenced inline. Footnote references (where image src and anchor href attributes are listed in the footnotes) are not used.
- Blockquotes aren't line wrapped it makes the converted Markdown easier to edit.
### Dependencies
HTML To Markdown requires PHP's [xml](http://www.php.net/manual/en/xml.installation.php), [lib-xml](http://www.php.net/manual/en/libxml.installation.php), and [dom](http://www.php.net/manual/en/dom.installation.php) extensions, all of which are enabled by default on most distributions.
Errors such as "Fatal error: Class 'DOMDocument' not found" on distributions such as CentOS that disable PHP's xml extension can be resolved by installing php-xml.
### Architecture notes
HTML To Markdown is a single file that uses native DOM manipulation libraries (DOMDocument), not regex voodoo, to convert code.
### Contributors
Many thanks to all [contributors](https://github.com/nickcernis/html2markdown/graphs/contributors) so far. Further improvements and feature suggestions are very welcome.
### How it works
HTML To Markdown creates a DOMDocument from the supplied HTML, walks through the tree, and converts each node to a text node containing the equivalent markdown, starting from the most deeply nested node and working inwards towards the root node.
### To-do
- Support for nested lists and lists inside blockquotes.
- Offer an option to preserve tags as HTML if they contain attributes that can't be represented with Markdown (e.g. `style`).
### Trying to convert Markdown to HTML?
Use [PHP Markdown](http://michelf.com/projects/php-markdown/) from Michel Fortin. No guarantees about the Elvish, though.

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,20 @@
The MIT License (MIT)
Copyright (c) 2013 Emanuil Rusev, erusev.com
Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

1528
library/parsedown/Parsedown.php Executable file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,48 @@
## Parsedown
Better Markdown Parser in PHP
[[ demo ]](http://parsedown.org/demo)
### Features
* [Fast](http://parsedown.org/speed)
* [Consistent](http://parsedown.org/consistency)
* [GitHub flavored](https://help.github.com/articles/github-flavored-markdown)
* [Tested](http://parsedown.org/tests/) in PHP 5.2, 5.3, 5.4, 5.5, 5.6 and [hhvm](http://www.hhvm.com/)
* [Extensible](https://github.com/erusev/parsedown/wiki/Writing-Extensions)
* [Markdown Extra extension](https://github.com/erusev/parsedown-extra)
### Installation
Include `Parsedown.php` or install [the composer package](https://packagist.org/packages/erusev/parsedown).
### Example
``` php
$Parsedown = new Parsedown();
echo $Parsedown->text('Hello _Parsedown_!'); # prints: <p>Hello <em>Parsedown</em>!</p>
```
More examples in [the wiki](https://github.com/erusev/parsedown/wiki/Usage) and in [this video tutorial](http://youtu.be/wYZBY8DEikI).
### Questions
**How does Parsedown work?**
It tries to read Markdown like a human. First, it looks at the lines. Its interested in how the lines start. This helps it recognise blocks. It knows, for example, that if a line start with a `-` then it perhaps belong to a list. Once it recognises the blocks, it continues to the content. As it reads, it watches out for special characters. This helps it recognise inline elements (or inlines).
We call this approach "line based". We believe that Parsedown is the first Markdown parser to use it. Since the release of Parsedown, other developers have used the same approach to develop other Markdown parsers in PHP and in other languages.
**Is it compliant with CommonMark?**
It passes most of the CommonMark tests. Most of the tests that don't pass deal with cases that are quite uncommon. Still, as CommonMark matures, compliance should improve.
**Who uses it?**
[phpDocumentor](http://www.phpdoc.org/), [October CMS](http://octobercms.com/), [Bolt CMS](http://bolt.cm/), [Kirby CMS](http://getkirby.com/), [Grav CMS](http://getgrav.org/), [Statamic CMS](http://www.statamic.com/), [RaspberryPi.org](http://www.raspberrypi.org/) and [more](https://www.versioneye.com/php/erusev:parsedown/references).
**How can I help?**
Use it, star it, share it and if you feel generous, [donate some money](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=528P3NZQMP8N2).