Recursively search through a directory (and it's children directories) to find Markdown files and convert the list of files and their content and into an XML document. Dependent on PHP-Markdown and YAML Front Matter for PHP (https://github.com/Blaxus/YAML-FrontMatter)

recursive-md-dom.php

<?php
#
# INSPIRATION FROM Nick Dunn (in the Symphony CMS forum)
# "Convert a Directory of Markdown Text Files for Dynamic XML Datasource Use"
# http://getsymphony.com/discuss/thread/60701/#position-2
#
# AND FROM Stack Overflow
# http://stackoverflow.com/questions/8545010/php-reading-first-2-lines-of-file-into-variable-and-cylce-through-subfolders/8545451#8545451
#


#
# configuration
#

$path = '.';
$fileFilter = '~\.(md|markdown)$~';
$pattern = '~^(?:Title: (.*))?(?:(?:\r\n|\n)(?:Description: (.*)))?~u';

#
# main
#

# init result array (the nice one)
$result = array();

# recursive iterator for files
$iterator = new RecursiveIteratorIterator(
               new RecursiveDirectoryIterator($path, FilesystemIterator::KEY_AS_PATHNAME | FilesystemIterator::CURRENT_AS_FILEINFO), 
               RecursiveIteratorIterator::SELF_FIRST);

foreach($iterator as $path => $info)
{
    # filter out files that don't match
    if (!preg_match($fileFilter, $path)) continue;

    # get first two lines
    try
    {
        for
        (
            $maxLines = 2,
            $lines = '',
            $file = $info->openFile()
            ; 
            !$file->eof() && $maxLines--
            ; 
            $lines .= $file->fgets()
        );
        $lines = rtrim($lines, "\n");

        if (!strlen($lines)) # skip empty files 
            continue;
    }
    catch (RuntimeException $e)
    {
        continue; # files which are not readable are skipped.
    }

    # parse md file
    $r = preg_match($pattern, $lines, $matches);
    if (FALSE === $r)
    {
        throw new Exception('Regular expression failed.');
    }
    list(, $title, $description) = $matches + array('', '', '');

    # grow result array
    $result[dirname($path)][] = array($path, $title, $description);
}



#
# output
#

// adding Content Type
header("Content-type: text/xml");

// create a new XML document
$doc = new DOMDocument('1.0', 'utf-8');

$doc->formatOutput = true;


include_once('includes/lib/frontmatter.php');
include_once('includes/lib/markdown.php');

//$dirCounter = 0;

$currentdate = date("Y-m-d");
$currenttime = date("H:i");



$r = $doc->createElement('data');
$doc-> appendChild($r);

$r->setAttribute("date-created", $currentdate  );
$r->setAttribute("time-created", $currenttime  );

foreach ($result as $name => $dirs)
{
    $directoryname = $doc->createElement('directory');
    $r->appendChild($directoryname);
    $directoryname->setAttribute("name", basename($name) );
    $directoryname->setAttribute("path", $name );

    foreach ($dirs as $entry)
    {
        list($path, $title, $description) = $entry;
        $page = new FrontMatter($path);
        $text = file_get_contents($path);

        // fetching markdown content and appending as XML
        $fragment = $doc->createDocumentFragment();
        $fragment->appendXML(Markdown($page->fetch('content')));


        $fileentry = $doc->createElement('file');
        $directoryname->appendChild($fileentry);
        $fileentry->setAttribute("path", $path);
        $fileentry->setAttribute("name", basename($path));

            $meta = $doc->createElement('meta');
            $fileentry->appendChild($meta);

                // 'title' and 'uri' are YAML Front Matter keys
                // NOTE: entered in here statically right now 
                // would like for this dynamically createElement() based on 
                // whatever keys it is given in the YAML Front Matter

                $metatitle = $doc->createElement('title');
                $metatitle->appendChild( $doc->createTextNode( $page->fetch('title') ) );
                $meta->appendChild($metatitle);

                
                $metauri = $doc->createElement('uri');
                $metauri->appendChild( $doc->createTextNode( $page->fetch('uri') ) );
                $meta->appendChild($metauri);
                

        
           $contentoutput = $doc->createElement('content');
           $contentoutput->appendChild($fragment);
           $fileentry->appendChild($contentoutput); 

    }

}

// get completed xml document
$xml_string = $doc->saveXML();

echo $xml_string;