first commit

repository/url/classes/privacy/provider.php

@@ -0,0 +1,46 @@
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Privacy Subsystem implementation for repository_url.
+ *
+ * @package    repository_url
+ * @copyright  2018 Zig Tan <zig@moodle.com>
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+namespace repository_url\privacy;
+
+defined('MOODLE_INTERNAL') || die();
+
+/**
+ * Privacy Subsystem for repository_url implementing null_provider.
+ *
+ * @copyright  2018 Zig Tan <zig@moodle.com>
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+class provider implements \core_privacy\local\metadata\null_provider {
+
+    /**
+     * Get the language string identifier with the component's language
+     * file to explain why this plugin stores no data.
+     *
+     * @return  string
+     */
+    public static function get_reason(): string {
+        return 'privacy:metadata';
+    }
+}

repository/url/db/access.php

@@ -0,0 +1,37 @@
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Plugin capabilities.
+ *
+ * @package    repository_url
+ * @copyright  2009 Dongsheng Cai
+ * @author     Dongsheng Cai <dongsheng@moodle.com>
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+defined('MOODLE_INTERNAL') || die();
+
+$capabilities = array(
+
+    'repository/url:view' => array(
+        'captype' => 'read',
+        'contextlevel' => CONTEXT_MODULE,
+        'archetypes' => array(
+            'user' => CAP_ALLOW
+        )
+    )
+);

repository/url/db/install.php

@@ -0,0 +1,39 @@
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Installation for the URL repository
+ *
+ * @package    repository_url
+ * @category   repository
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+/**
+ * Create a default instance of the URL repository
+ *
+ * @return bool A status indicating success or failure
+ */
+function xmldb_repository_url_install() {
+    global $CFG;
+    $result = true;
+    require_once($CFG->dirroot.'/repository/lib.php');
+    $urlplugin = new repository_type('url', array(), true);
+    if(!$id = $urlplugin->create(true)) {
+        $result = false;
+    }
+    return $result;
+}

repository/url/lang/en/repository_url.php

@@ -0,0 +1,34 @@
+<?php
+
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Strings for component 'repository_url', language 'en', branch 'MOODLE_20_STABLE'
+ *
+ * @package   repository_url
+ * @copyright 1999 onwards Martin Dougiamas  {@link http://moodle.com}
+ * @license   http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+$string['download'] = 'Download';
+$string['rename'] = 'Name';
+$string['pluginname'] = 'URL downloader';
+$string['url'] = 'URL';
+$string['url:view'] = 'Use URL downloader in file picker';
+$string['validname'] = 'You must provide a valid file name';
+$string['configplugin'] = 'URL repository type configuration';
+$string['validfiletype'] = 'You must provide a URL to an image file or a page containing images.';
+$string['privacy:metadata'] = 'The URL downloader repository plugin does not store or transmit any personal data.';

repository/url/lib.php

@@ -0,0 +1,300 @@
+<?php
+
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * This plugin is used to access files by providing an url
+ *
+ * @since Moodle 2.0
+ * @package    repository_url
+ * @copyright  2010 Dongsheng Cai {@link http://dongsheng.org}
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+require_once($CFG->dirroot . '/repository/lib.php');
+require_once(__DIR__.'/locallib.php');
+
+/**
+ * repository_url class
+ * A subclass of repository, which is used to download a file from a specific url
+ *
+ * @since Moodle 2.0
+ * @package    repository_url
+ * @copyright  2009 Dongsheng Cai {@link http://dongsheng.org}
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+class repository_url extends repository {
+    /** @var int Maximum time of recursion. */
+    const MAX_RECURSION_TIME = 5;
+    /** @var int Maximum number of CSS imports. */
+    protected const MAX_CSS_IMPORTS = 10;
+    /** @var int CSS import counter. */
+    protected int $cssimportcounter = 0;
+    var $processedfiles = array();
+    /** @var int Recursion counter. */
+    var $recursioncounter = 0;
+    /** @var string file URL. */
+    public $file_url;
+
+    /**
+     * @param int $repositoryid
+     * @param object $context
+     * @param array $options
+     */
+    public function __construct($repositoryid, $context = SYSCONTEXTID, $options = array()){
+        global $CFG;
+        parent::__construct($repositoryid, $context, $options);
+        $this->file_url = optional_param('file', '', PARAM_RAW);
+        $this->file_url = $this->escape_url($this->file_url);
+    }
+
+    public function check_login() {
+        if (!empty($this->file_url)) {
+            return true;
+        } else {
+            return false;
+        }
+    }
+    /**
+     * @return mixed
+     */
+    public function print_login() {
+        $strdownload = get_string('download', 'repository');
+        $strname     = get_string('rename', 'repository_url');
+        $strurl      = get_string('url', 'repository_url');
+        if ($this->options['ajax']) {
+            $url = new stdClass();
+            $url->label = $strurl.': ';
+            $url->id   = 'fileurl';
+            $url->type = 'text';
+            $url->name = 'file';
+
+            $ret['login'] = array($url);
+            $ret['login_btn_label'] = get_string('download', 'repository_url');
+            $ret['allowcaching'] = true; // indicates that login form can be cached in filepicker.js
+            return $ret;
+        } else {
+            echo <<<EOD
+<table>
+<tr>
+<td>{$strurl}: </td><td><input name="file" type="text" /></td>
+</tr>
+</table>
+<input type="submit" value="{$strdownload}" />
+EOD;
+
+        }
+    }
+
+    /**
+     * @param mixed $path
+     * @param string $search
+     * @return array
+     */
+    public function get_listing($path='', $page='') {
+        $ret = array();
+        $ret['list'] = array();
+        $ret['nosearch'] = true;
+        $ret['norefresh'] = true;
+        $ret['nologin'] = true;
+
+        $this->file_url = clean_param($this->file_url, PARAM_URL);
+        if (empty($this->file_url)) {
+            throw new repository_exception('validfiletype', 'repository_url');
+        }
+
+        $this->parse_file(null, $this->file_url, $ret, true);
+        return $ret;
+    }
+
+    /**
+     * Parses one file (either html or css)
+     *
+     * @param string $baseurl (optional) URL of the file where link to this file was found
+     * @param string $relativeurl relative or absolute link to the file
+     * @param array $list
+     * @param bool $mainfile true only for main HTML false and false for all embedded/linked files
+     */
+    protected function parse_file($baseurl, $relativeurl, &$list, $mainfile = false) {
+        if (preg_match('/([\'"])(.*)\1/', $relativeurl, $matches)) {
+            $relativeurl = $matches[2];
+        }
+        if (empty($baseurl)) {
+            $url = $relativeurl;
+        } else {
+            $url = htmlspecialchars_decode(url_to_absolute($baseurl, $relativeurl), ENT_COMPAT);
+        }
+        if (in_array($url, $this->processedfiles)) {
+            // Avoid endless recursion for the same URL with same parameters.
+            return;
+        }
+        // Remove the query string and anchors before check.
+        $recursioncheckurl = (new moodle_url($url))->out_omit_querystring();
+        if (in_array($recursioncheckurl, $this->processedfiles)) {
+            $this->recursioncounter++;
+        }
+        if ($this->recursioncounter >= self::MAX_RECURSION_TIME) {
+            // Avoid endless recursion for the same URL with different parameters.
+            return;
+        }
+        $this->processedfiles[] = $url;
+        $curl = new curl;
+        $curl->setopt(array('CURLOPT_FOLLOWLOCATION' => true, 'CURLOPT_MAXREDIRS' => 3));
+        $msg = $curl->head($url);
+        $info = $curl->get_info();
+        if ($info['http_code'] != 200) {
+            if ($mainfile) {
+                $list['error'] = $msg;
+            }
+        } else {
+            $csstoanalyze = '';
+            if ($mainfile && (strstr($info['content_type'], 'text/html') || empty($info['content_type']))) {
+                // parse as html
+                $htmlcontent = $curl->get($info['url']);
+                $ddoc = new DOMDocument();
+                @$ddoc->loadHTML($htmlcontent);
+                // extract <img>
+                $tags = $ddoc->getElementsByTagName('img');
+                foreach ($tags as $tag) {
+                    $url = $tag->getAttribute('src');
+                    $this->add_image_to_list($info['url'], $url, $list);
+                }
+                // analyse embedded css (<style>)
+                $tags = $ddoc->getElementsByTagName('style');
+                foreach ($tags as $tag) {
+                    if ($tag->getAttribute('type') == 'text/css') {
+                        $csstoanalyze .= $tag->textContent."\n";
+                    }
+                }
+                // analyse links to css (<link type='text/css' href='...'>)
+                $tags = $ddoc->getElementsByTagName('link');
+                foreach ($tags as $tag) {
+                    if ($tag->getAttribute('type') == 'text/css' && strlen($tag->getAttribute('href'))) {
+                        $this->parse_file($info['url'], $tag->getAttribute('href'), $list);
+                    }
+                }
+            } else if (strstr($info['content_type'], 'css')) {
+                // parse as css
+                $csscontent = $curl->get($info['url']);
+                $csstoanalyze .= $csscontent."\n";
+            } else if (strstr($info['content_type'], 'image/')) {
+                // download this file
+                $this->add_image_to_list($info['url'], $info['url'], $list);
+            } else {
+                $list['error'] = get_string('validfiletype', 'repository_url');
+            }
+
+            // parse all found css styles
+            if (strlen($csstoanalyze)) {
+                $urls = extract_css_urls($csstoanalyze);
+                if (!empty($urls['property'])) {
+                    foreach ($urls['property'] as $url) {
+                        $this->add_image_to_list($info['url'], $url, $list);
+                    }
+                }
+                if (!empty($urls['import'])) {
+                    foreach ($urls['import'] as $cssurl) {
+                        // Limit the number of CSS imports to avoid infinite imports.
+                        if ($this->cssimportcounter >= self::MAX_CSS_IMPORTS) {
+                            return;
+                        }
+                        $this->cssimportcounter++;
+                        $this->parse_file($info['url'], $cssurl, $list);
+                    }
+                }
+            }
+        }
+    }
+    protected function add_image_to_list($baseurl, $url, &$list) {
+        if (empty($list['list'])) {
+            $list['list'] = array();
+        }
+        $src = url_to_absolute($baseurl, htmlspecialchars_decode($url, ENT_COMPAT));
+        foreach ($list['list'] as $image) {
+            if ($image['source'] == $src) {
+                return;
+            }
+        }
+        $list['list'][] = array(
+            'title'=>$this->guess_filename($url, ''),
+            'source'=>$src,
+            'thumbnail'=>$src,
+            'thumbnail_height'=>84,
+            'thumbnail_width'=>84
+        );
+    }
+    public function guess_filename($url, $type) {
+        $pattern = '#\/([\w_\?\-.]+)$#';
+        $matches = null;
+        preg_match($pattern, $url, $matches);
+        if (empty($matches[1])) {
+            return $url;
+        } else {
+            return $matches[1];
+        }
+    }
+
+    /**
+     * Escapes a url by replacing spaces with %20.
+     *
+     * Note: In general moodle does not automatically escape urls, but for the purposes of making this plugin more user friendly
+     * and make it consistent with some other areas in moodle (such as mod_url), urls will automatically be escaped.
+     *
+     * If moodle_url or PARAM_URL is changed to clean characters that need to be escaped, then this function can be removed
+     *
+     * @param string $url An unescaped url.
+     * @return string The escaped url
+     */
+    protected function escape_url($url) {
+        $url = str_replace('"', '%22', $url);
+        $url = str_replace('\'', '%27', $url);
+        $url = str_replace(' ', '%20', $url);
+        $url = str_replace('<', '%3C', $url);
+        $url = str_replace('>', '%3E', $url);
+        return $url;
+    }
+
+    public function supported_returntypes() {
+        return (FILE_INTERNAL | FILE_EXTERNAL);
+    }
+
+    /**
+     * Return the source information
+     *
+     * @param stdClass $url
+     * @return string|null
+     */
+    public function get_file_source_info($url) {
+        return $url;
+    }
+
+    /**
+     * file types supported by url downloader plugin
+     *
+     * @return array
+     */
+    public function supported_filetypes() {
+        return array('web_image');
+    }
+
+    /**
+     * Is this repository accessing private data?
+     *
+     * @return bool
+     */
+    public function contains_private_data() {
+        return false;
+    }
+}

repository/url/locallib.php

@@ -0,0 +1,756 @@
+<?php
+
+/**
+ * Copyright (c) 2008, David R. Nadeau, NadeauSoftware.com.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *	* Redistributions of source code must retain the above copyright
+ *	  notice, this list of conditions and the following disclaimer.
+ *
+ *	* Redistributions in binary form must reproduce the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer in the documentation and/or other materials provided
+ *	  with the distribution.
+ *
+ *	* Neither the names of David R. Nadeau or NadeauSoftware.com, nor
+ *	  the names of its contributors may be used to endorse or promote
+ *	  products derived from this software without specific prior
+ *	  written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+ * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+ * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+ * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+ * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY
+ * WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY
+ * OF SUCH DAMAGE.
+ */
+
+/*
+ * This is a BSD License approved by the Open Source Initiative (OSI).
+ * See:  http://www.opensource.org/licenses/bsd-license.php
+ */
+
+defined('MOODLE_INTERNAL') || die();
+
+/**
+ * Combine a base URL and a relative URL to produce a new
+ * absolute URL.  The base URL is often the URL of a page,
+ * and the relative URL is a URL embedded on that page.
+ *
+ * This function implements the "absolutize" algorithm from
+ * the RFC3986 specification for URLs.
+ *
+ * This function supports multi-byte characters with the UTF-8 encoding,
+ * per the URL specification.
+ *
+ * Parameters:
+ * 	baseUrl		the absolute base URL.
+ *
+ * 	url		the relative URL to convert.
+ *
+ * Return values:
+ * 	An absolute URL that combines parts of the base and relative
+ * 	URLs, or FALSE if the base URL is not absolute or if either
+ * 	URL cannot be parsed.
+ */
+function url_to_absolute( $baseUrl, $relativeUrl )
+{
+	// If relative URL has a scheme, clean path and return.
+	$r = split_url( $relativeUrl );
+	if ( $r === FALSE )
+		return FALSE;
+	if ( !empty( $r['scheme'] ) )
+	{
+		if ( !empty( $r['path'] ) && $r['path'][0] == '/' )
+			$r['path'] = url_remove_dot_segments( $r['path'] );
+		return join_url( $r );
+	}
+
+	// Make sure the base URL is absolute.
+	$b = split_url( $baseUrl );
+	if ( $b === FALSE || empty( $b['scheme'] ) || empty( $b['host'] ) )
+		return FALSE;
+	$r['scheme'] = $b['scheme'];
+	if (empty($b['path'])) {
+		$b['path'] = '';
+	}
+
+	// If relative URL has an authority, clean path and return.
+	if ( isset( $r['host'] ) )
+	{
+		if ( !empty( $r['path'] ) )
+			$r['path'] = url_remove_dot_segments( $r['path'] );
+		return join_url( $r );
+	}
+	unset( $r['port'] );
+	unset( $r['user'] );
+	unset( $r['pass'] );
+
+	// Copy base authority.
+	$r['host'] = $b['host'];
+	if ( isset( $b['port'] ) ) $r['port'] = $b['port'];
+	if ( isset( $b['user'] ) ) $r['user'] = $b['user'];
+	if ( isset( $b['pass'] ) ) $r['pass'] = $b['pass'];
+
+	// If relative URL has no path, use base path
+	if ( empty( $r['path'] ) )
+	{
+		if ( !empty( $b['path'] ) )
+			$r['path'] = $b['path'];
+		if ( !isset( $r['query'] ) && isset( $b['query'] ) )
+			$r['query'] = $b['query'];
+		return join_url( $r );
+	}
+
+	// If relative URL path doesn't start with /, merge with base path.
+	if ($r['path'][0] != '/') {
+		$base = core_text::strrchr($b['path'], '/', TRUE);
+		if ($base === FALSE) {
+			$base = '';
+		}
+		$r['path'] = $base . '/' . $r['path'];
+	}
+	$r['path'] = url_remove_dot_segments($r['path']);
+	return join_url($r);
+}
+
+/**
+ * Filter out "." and ".." segments from a URL's path and return
+ * the result.
+ *
+ * This function implements the "remove_dot_segments" algorithm from
+ * the RFC3986 specification for URLs.
+ *
+ * This function supports multi-byte characters with the UTF-8 encoding,
+ * per the URL specification.
+ *
+ * Parameters:
+ * 	path	the path to filter
+ *
+ * Return values:
+ * 	The filtered path with "." and ".." removed.
+ */
+function url_remove_dot_segments( $path )
+{
+	// multi-byte character explode
+	$inSegs  = preg_split( '!/!u', $path );
+	$outSegs = array( );
+	foreach ( $inSegs as $seg )
+	{
+		if ( $seg == '' || $seg == '.')
+			continue;
+		if ( $seg == '..' )
+			array_pop( $outSegs );
+		else
+			array_push( $outSegs, $seg );
+	}
+	$outPath = implode( '/', $outSegs );
+
+	if ($path[0] == '/') {
+		$outPath = '/' . $outPath;
+	}
+
+	// Compare last multi-byte character against '/'.
+	if ($outPath != '/' && (core_text::strlen($path) - 1) == core_text::strrpos($path, '/', 'UTF-8')) {
+		$outPath .= '/';
+	}
+	return $outPath;
+}
+
+/**
+ * This function parses an absolute or relative URL and splits it
+ * into individual components.
+ *
+ * RFC3986 specifies the components of a Uniform Resource Identifier (URI).
+ * A portion of the ABNFs are repeated here:
+ *
+ *	URI-reference	= URI
+ *			/ relative-ref
+ *
+ *	URI		= scheme ":" hier-part [ "?" query ] [ "#" fragment ]
+ *
+ *	relative-ref	= relative-part [ "?" query ] [ "#" fragment ]
+ *
+ *	hier-part	= "//" authority path-abempty
+ *			/ path-absolute
+ *			/ path-rootless
+ *			/ path-empty
+ *
+ *	relative-part	= "//" authority path-abempty
+ *			/ path-absolute
+ *			/ path-noscheme
+ *			/ path-empty
+ *
+ *	authority	= [ userinfo "@" ] host [ ":" port ]
+ *
+ * So, a URL has the following major components:
+ *
+ *	scheme
+ *		The name of a method used to interpret the rest of
+ *		the URL.  Examples:  "http", "https", "mailto", "file'.
+ *
+ *	authority
+ *		The name of the authority governing the URL's name
+ *		space.  Examples:  "example.com", "user@example.com",
+ *		"example.com:80", "user:password@example.com:80".
+ *
+ *		The authority may include a host name, port number,
+ *		user name, and password.
+ *
+ *		The host may be a name, an IPv4 numeric address, or
+ *		an IPv6 numeric address.
+ *
+ *	path
+ *		The hierarchical path to the URL's resource.
+ *		Examples:  "/index.htm", "/scripts/page.php".
+ *
+ *	query
+ *		The data for a query.  Examples:  "?search=google.com".
+ *
+ *	fragment
+ *		The name of a secondary resource relative to that named
+ *		by the path.  Examples:  "#section1", "#header".
+ *
+ * An "absolute" URL must include a scheme and path.  The authority, query,
+ * and fragment components are optional.
+ *
+ * A "relative" URL does not include a scheme and must include a path.  The
+ * authority, query, and fragment components are optional.
+ *
+ * This function splits the $url argument into the following components
+ * and returns them in an associative array.  Keys to that array include:
+ *
+ *	"scheme"	The scheme, such as "http".
+ *	"host"		The host name, IPv4, or IPv6 address.
+ *	"port"		The port number.
+ *	"user"		The user name.
+ *	"pass"		The user password.
+ *	"path"		The path, such as a file path for "http".
+ *	"query"		The query.
+ *	"fragment"	The fragment.
+ *
+ * One or more of these may not be present, depending upon the URL.
+ *
+ * Optionally, the "user", "pass", "host" (if a name, not an IP address),
+ * "path", "query", and "fragment" may have percent-encoded characters
+ * decoded.  The "scheme" and "port" cannot include percent-encoded
+ * characters and are never decoded.  Decoding occurs after the URL has
+ * been parsed.
+ *
+ * Parameters:
+ * 	url		the URL to parse.
+ *
+ * 	decode		an optional boolean flag selecting whether
+ * 			to decode percent encoding or not.  Default = TRUE.
+ *
+ * Return values:
+ * 	the associative array of URL parts, or FALSE if the URL is
+ * 	too malformed to recognize any parts.
+ */
+function split_url( $url, $decode=FALSE)
+{
+	// Character sets from RFC3986.
+	$xunressub     = 'a-zA-Z\d\-._~\!$&\'()*+,;=';
+	$xpchar        = $xunressub . ':@% ';
+
+	// Scheme from RFC3986.
+	$xscheme        = '([a-zA-Z][a-zA-Z\d+-.]*)';
+
+	// User info (user + password) from RFC3986.
+	$xuserinfo     = '((['  . $xunressub . '%]*)' .
+	                 '(:([' . $xunressub . ':%]*))?)';
+
+	// IPv4 from RFC3986 (without digit constraints).
+	$xipv4         = '(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})';
+
+	// IPv6 from RFC2732 (without digit and grouping constraints).
+	$xipv6         = '(\[([a-fA-F\d.:]+)\])';
+
+	// Host name from RFC1035.  Technically, must start with a letter.
+	// Relax that restriction to better parse URL structure, then
+	// leave host name validation to application.
+	$xhost_name    = '([a-zA-Z\d\-.%]+)';
+
+	// Authority from RFC3986.  Skip IP future.
+	$xhost         = '(' . $xhost_name . '|' . $xipv4 . '|' . $xipv6 . ')';
+	$xport         = '(\d*)';
+	$xauthority    = '((' . $xuserinfo . '@)?' . $xhost .
+		         '?(:' . $xport . ')?)';
+
+	// Path from RFC3986.  Blend absolute & relative for efficiency.
+	$xslash_seg    = '(/[' . $xpchar . ']*)';
+	$xpath_authabs = '((//' . $xauthority . ')((/[' . $xpchar . ']*)*))';
+	$xpath_rel     = '([' . $xpchar . ']+' . $xslash_seg . '*)';
+	$xpath_abs     = '(/(' . $xpath_rel . ')?)';
+	$xapath        = '(' . $xpath_authabs . '|' . $xpath_abs .
+			 '|' . $xpath_rel . ')';
+
+	// Query and fragment from RFC3986.
+	$xqueryfrag    = '([' . $xpchar . '/?' . ']*)';
+
+	// URL.
+	$xurl          = '^(' . $xscheme . ':)?' .  $xapath . '?' .
+	                 '(\?' . $xqueryfrag . ')?(#' . $xqueryfrag . ')?$';
+
+
+	// Split the URL into components.
+	if ( !preg_match( '!' . $xurl . '!', $url, $m ) )
+		return FALSE;
+
+	if ( !empty($m[2]) )		$parts['scheme']  = strtolower($m[2]);
+
+	if ( !empty($m[7]) ) {
+		if ( isset( $m[9] ) )	$parts['user']    = $m[9];
+		else			$parts['user']    = '';
+	}
+	if ( !empty($m[10]) )		$parts['pass']    = $m[11];
+
+	if ( !empty($m[13]) )		$h=$parts['host'] = $m[13];
+	else if ( !empty($m[14]) )	$parts['host']    = $m[14];
+	else if ( !empty($m[16]) )	$parts['host']    = $m[16];
+	else if ( !empty( $m[5] ) )	$parts['host']    = '';
+	if ( !empty($m[17]) )		$parts['port']    = $m[18];
+
+	if ( !empty($m[19]) )		$parts['path']    = $m[19];
+	else if ( !empty($m[21]) )	$parts['path']    = $m[21];
+	else if ( !empty($m[25]) )	$parts['path']    = $m[25];
+
+	if ( !empty($m[27]) )		$parts['query']   = $m[28];
+	if ( !empty($m[29]) )		$parts['fragment']= $m[30];
+
+	if ( !$decode )
+		return $parts;
+	if ( !empty($parts['user']) )
+		$parts['user']     = rawurldecode( $parts['user'] );
+	if ( !empty($parts['pass']) )
+		$parts['pass']     = rawurldecode( $parts['pass'] );
+	if ( !empty($parts['path']) )
+		$parts['path']     = rawurldecode( $parts['path'] );
+	if ( isset($h) )
+		$parts['host']     = rawurldecode( $parts['host'] );
+	if ( !empty($parts['query']) )
+		$parts['query']    = rawurldecode( $parts['query'] );
+	if ( !empty($parts['fragment']) )
+		$parts['fragment'] = rawurldecode( $parts['fragment'] );
+	return $parts;
+}
+
+/**
+ * This function joins together URL components to form a complete URL.
+ *
+ * RFC3986 specifies the components of a Uniform Resource Identifier (URI).
+ * This function implements the specification's "component recomposition"
+ * algorithm for combining URI components into a full URI string.
+ *
+ * The $parts argument is an associative array containing zero or
+ * more of the following:
+ *
+ *	"scheme"	The scheme, such as "http".
+ *	"host"		The host name, IPv4, or IPv6 address.
+ *	"port"		The port number.
+ *	"user"		The user name.
+ *	"pass"		The user password.
+ *	"path"		The path, such as a file path for "http".
+ *	"query"		The query.
+ *	"fragment"	The fragment.
+ *
+ * The "port", "user", and "pass" values are only used when a "host"
+ * is present.
+ *
+ * The optional $encode argument indicates if appropriate URL components
+ * should be percent-encoded as they are assembled into the URL.  Encoding
+ * is only applied to the "user", "pass", "host" (if a host name, not an
+ * IP address), "path", "query", and "fragment" components.  The "scheme"
+ * and "port" are never encoded.  When a "scheme" and "host" are both
+ * present, the "path" is presumed to be hierarchical and encoding
+ * processes each segment of the hierarchy separately (i.e., the slashes
+ * are left alone).
+ *
+ * The assembled URL string is returned.
+ *
+ * Parameters:
+ * 	parts		an associative array of strings containing the
+ * 			individual parts of a URL.
+ *
+ * 	encode		an optional boolean flag selecting whether
+ * 			to do percent encoding or not.  Default = true.
+ *
+ * Return values:
+ * 	Returns the assembled URL string.  The string is an absolute
+ * 	URL if a scheme is supplied, and a relative URL if not.  An
+ * 	empty string is returned if the $parts array does not contain
+ * 	any of the needed values.
+ */
+function join_url( $parts, $encode=FALSE)
+{
+	if ( $encode )
+	{
+		if ( isset( $parts['user'] ) )
+			$parts['user']     = rawurlencode( $parts['user'] );
+		if ( isset( $parts['pass'] ) )
+			$parts['pass']     = rawurlencode( $parts['pass'] );
+		if ( isset( $parts['host'] ) &&
+			!preg_match( '!^(\[[\da-f.:]+\]])|([\da-f.:]+)$!ui', $parts['host'] ) )
+			$parts['host']     = rawurlencode( $parts['host'] );
+		if ( !empty( $parts['path'] ) )
+			$parts['path']     = preg_replace( '!%2F!ui', '/',
+				rawurlencode( $parts['path'] ) );
+		if ( isset( $parts['query'] ) )
+			$parts['query']    = rawurlencode( $parts['query'] );
+		if ( isset( $parts['fragment'] ) )
+			$parts['fragment'] = rawurlencode( $parts['fragment'] );
+	}
+
+	$url = '';
+	if ( !empty( $parts['scheme'] ) )
+		$url .= $parts['scheme'] . ':';
+	if ( isset( $parts['host'] ) )
+	{
+		$url .= '//';
+		if ( isset( $parts['user'] ) )
+		{
+			$url .= $parts['user'];
+			if ( isset( $parts['pass'] ) )
+				$url .= ':' . $parts['pass'];
+			$url .= '@';
+		}
+		if ( preg_match( '!^[\da-f]*:[\da-f.:]+$!ui', $parts['host'] ) )
+			$url .= '[' . $parts['host'] . ']';	// IPv6
+		else
+			$url .= $parts['host'];			// IPv4 or name
+		if ( isset( $parts['port'] ) )
+			$url .= ':' . $parts['port'];
+		if ( !empty( $parts['path'] ) && $parts['path'][0] != '/' )
+			$url .= '/';
+	}
+	if ( !empty( $parts['path'] ) )
+		$url .= $parts['path'];
+	if ( isset( $parts['query'] ) )
+		$url .= '?' . $parts['query'];
+	if ( isset( $parts['fragment'] ) )
+		$url .= '#' . $parts['fragment'];
+	return $url;
+}
+
+/**
+ * This function encodes URL to form a URL which is properly
+ * percent encoded to replace disallowed characters.
+ *
+ * RFC3986 specifies the allowed characters in the URL as well as
+ * reserved characters in the URL. This function replaces all the
+ * disallowed characters in the URL with their repective percent
+ * encodings. Already encoded characters are not encoded again,
+ * such as '%20' is not encoded to '%2520'.
+ *
+ * Parameters:
+ * 	url		the url to encode.
+ *
+ * Return values:
+ * 	Returns the encoded URL string.
+ */
+function encode_url($url) {
+  $reserved = array(
+    ":" => '!%3A!ui',
+    "/" => '!%2F!ui',
+    "?" => '!%3F!ui',
+    "#" => '!%23!ui',
+    "[" => '!%5B!ui',
+    "]" => '!%5D!ui',
+    "@" => '!%40!ui',
+    "!" => '!%21!ui',
+    "$" => '!%24!ui',
+    "&" => '!%26!ui',
+    "'" => '!%27!ui',
+    "(" => '!%28!ui',
+    ")" => '!%29!ui',
+    "*" => '!%2A!ui',
+    "+" => '!%2B!ui',
+    "," => '!%2C!ui',
+    ";" => '!%3B!ui',
+    "=" => '!%3D!ui',
+    "%" => '!%25!ui',
+  );
+
+  $url = rawurlencode($url);
+  $url = preg_replace(array_values($reserved), array_keys($reserved), $url);
+  return $url;
+}
+
+/**
+ * Extract URLs from a web page.
+ *
+ * URLs are extracted from a long list of tags and attributes as defined
+ * by the HTML 2.0, HTML 3.2, HTML 4.01, and draft HTML 5.0 specifications.
+ * URLs are also extracted from tags and attributes that are common
+ * extensions of HTML, from the draft Forms 2.0 specification, from XHTML,
+ * and from WML 1.3 and 2.0.
+ *
+ * The function returns an associative array of associative arrays of
+ * arrays of URLs.  The outermost array's keys are the tag (element) name,
+ * such as "a" for <a> or "img" for <img>.  The values for these entries
+ * are associative arrays where the keys are attribute names for those
+ * tags, such as "href" for <a href="...">.  Finally, the values for
+ * those arrays are URLs found in those tags and attributes throughout
+ * the text.
+ *
+ * Parameters:
+ * 	text		the UTF-8 text to scan
+ *
+ * Return values:
+ * 	an associative array where keys are tags and values are an
+ * 	associative array where keys are attributes and values are
+ * 	an array of URLs.
+ *
+ * See:
+ * 	http://nadeausoftware.com/articles/2008/01/php_tip_how_extract_urls_web_page
+ */
+function extract_html_urls( $text )
+{
+	$match_elements = array(
+		// HTML
+		array('element'=>'a',		'attribute'=>'href'),		// 2.0
+		array('element'=>'a',		'attribute'=>'urn'),		// 2.0
+		array('element'=>'base',	'attribute'=>'href'),		// 2.0
+		array('element'=>'form',	'attribute'=>'action'),		// 2.0
+		array('element'=>'img',		'attribute'=>'src'),		// 2.0
+		array('element'=>'link',	'attribute'=>'href'),		// 2.0
+
+		array('element'=>'applet',	'attribute'=>'code'),		// 3.2
+		array('element'=>'applet',	'attribute'=>'codebase'),	// 3.2
+		array('element'=>'area',	'attribute'=>'href'),		// 3.2
+		array('element'=>'body',	'attribute'=>'background'),	// 3.2
+		array('element'=>'img',		'attribute'=>'usemap'),		// 3.2
+		array('element'=>'input',	'attribute'=>'src'),		// 3.2
+
+		array('element'=>'applet',	'attribute'=>'archive'),	// 4.01
+		array('element'=>'applet',	'attribute'=>'object'),		// 4.01
+		array('element'=>'blockquote',	'attribute'=>'cite'),		// 4.01
+		array('element'=>'del',		'attribute'=>'cite'),		// 4.01
+		array('element'=>'frame',	'attribute'=>'longdesc'),	// 4.01
+		array('element'=>'frame',	'attribute'=>'src'),		// 4.01
+		array('element'=>'head',	'attribute'=>'profile'),	// 4.01
+		array('element'=>'iframe',	'attribute'=>'longdesc'),	// 4.01
+		array('element'=>'iframe',	'attribute'=>'src'),		// 4.01
+		array('element'=>'img',		'attribute'=>'longdesc'),	// 4.01
+		array('element'=>'input',	'attribute'=>'usemap'),		// 4.01
+		array('element'=>'ins',		'attribute'=>'cite'),		// 4.01
+		array('element'=>'object',	'attribute'=>'archive'),	// 4.01
+		array('element'=>'object',	'attribute'=>'classid'),	// 4.01
+		array('element'=>'object',	'attribute'=>'codebase'),	// 4.01
+		array('element'=>'object',	'attribute'=>'data'),		// 4.01
+		array('element'=>'object',	'attribute'=>'usemap'),		// 4.01
+		array('element'=>'q',		'attribute'=>'cite'),		// 4.01
+		array('element'=>'script',	'attribute'=>'src'),		// 4.01
+
+		array('element'=>'audio',	'attribute'=>'src'),		// 5.0
+		array('element'=>'command',	'attribute'=>'icon'),		// 5.0
+		array('element'=>'embed',	'attribute'=>'src'),		// 5.0
+		array('element'=>'event-source','attribute'=>'src'),		// 5.0
+		array('element'=>'html',	'attribute'=>'manifest'),	// 5.0
+		array('element'=>'source',	'attribute'=>'src'),		// 5.0
+		array('element'=>'video',	'attribute'=>'src'),		// 5.0
+		array('element'=>'video',	'attribute'=>'poster'),		// 5.0
+
+		array('element'=>'bgsound',	'attribute'=>'src'),		// Extension
+		array('element'=>'body',	'attribute'=>'credits'),	// Extension
+		array('element'=>'body',	'attribute'=>'instructions'),	// Extension
+		array('element'=>'body',	'attribute'=>'logo'),		// Extension
+		array('element'=>'div',		'attribute'=>'href'),		// Extension
+		array('element'=>'div',		'attribute'=>'src'),		// Extension
+		array('element'=>'embed',	'attribute'=>'code'),		// Extension
+		array('element'=>'embed',	'attribute'=>'pluginspage'),	// Extension
+		array('element'=>'html',	'attribute'=>'background'),	// Extension
+		array('element'=>'ilayer',	'attribute'=>'src'),		// Extension
+		array('element'=>'img',		'attribute'=>'dynsrc'),		// Extension
+		array('element'=>'img',		'attribute'=>'lowsrc'),		// Extension
+		array('element'=>'input',	'attribute'=>'dynsrc'),		// Extension
+		array('element'=>'input',	'attribute'=>'lowsrc'),		// Extension
+		array('element'=>'table',	'attribute'=>'background'),	// Extension
+		array('element'=>'td',		'attribute'=>'background'),	// Extension
+		array('element'=>'th',		'attribute'=>'background'),	// Extension
+		array('element'=>'layer',	'attribute'=>'src'),		// Extension
+		array('element'=>'xml',		'attribute'=>'src'),		// Extension
+
+		array('element'=>'button',	'attribute'=>'action'),		// Forms 2.0
+		array('element'=>'datalist',	'attribute'=>'data'),		// Forms 2.0
+		array('element'=>'form',	'attribute'=>'data'),		// Forms 2.0
+		array('element'=>'input',	'attribute'=>'action'),		// Forms 2.0
+		array('element'=>'select',	'attribute'=>'data'),		// Forms 2.0
+
+		// XHTML
+		array('element'=>'html',	'attribute'=>'xmlns'),
+
+		// WML
+		array('element'=>'access',	'attribute'=>'path'),		// 1.3
+		array('element'=>'card',	'attribute'=>'onenterforward'),	// 1.3
+		array('element'=>'card',	'attribute'=>'onenterbackward'),// 1.3
+		array('element'=>'card',	'attribute'=>'ontimer'),	// 1.3
+		array('element'=>'go',		'attribute'=>'href'),		// 1.3
+		array('element'=>'option',	'attribute'=>'onpick'),		// 1.3
+		array('element'=>'template',	'attribute'=>'onenterforward'),	// 1.3
+		array('element'=>'template',	'attribute'=>'onenterbackward'),// 1.3
+		array('element'=>'template',	'attribute'=>'ontimer'),	// 1.3
+		array('element'=>'wml',		'attribute'=>'xmlns'),		// 2.0
+	);
+
+	$match_metas = array(
+		'content-base',
+		'content-location',
+		'referer',
+		'location',
+		'refresh',
+	);
+
+	// Extract all elements
+	if ( !preg_match_all( '/<([a-z][^>]*)>/iu', $text, $matches ) )
+		return array( );
+	$elements = $matches[1];
+	$value_pattern = '=(("([^"]*)")|([^\s]*))';
+
+	// Match elements and attributes
+	foreach ( $match_elements as $match_element )
+	{
+		$name = $match_element['element'];
+		$attr = $match_element['attribute'];
+		$pattern = '/^' . $name . '\s.*' . $attr . $value_pattern . '/iu';
+		if ( $name == 'object' )
+			$split_pattern = '/\s*/u';	// Space-separated URL list
+		else if ( $name == 'archive' )
+			$split_pattern = '/,\s*/u';	// Comma-separated URL list
+		else
+			unset( $split_pattern );	// Single URL
+		foreach ( $elements as $element )
+		{
+			if ( !preg_match( $pattern, $element, $match ) )
+				continue;
+			$m = empty($match[3]) ? (!empty($match[4])?$match[4]:'') : $match[3];
+			if ( !isset( $split_pattern ) )
+				$urls[$name][$attr][] = $m;
+			else
+			{
+				$msplit = preg_split( $split_pattern, $m );
+				foreach ( $msplit as $ms )
+					$urls[$name][$attr][] = $ms;
+			}
+		}
+	}
+
+	// Match meta http-equiv elements
+	foreach ( $match_metas as $match_meta )
+	{
+		$attr_pattern    = '/http-equiv="?' . $match_meta . '"?/iu';
+		$content_pattern = '/content'  . $value_pattern . '/iu';
+		$refresh_pattern = '/\d*;\s*(url=)?(.*)$/iu';
+		foreach ( $elements as $element )
+		{
+			if ( !preg_match( '/^meta/iu', $element ) ||
+				!preg_match( $attr_pattern, $element ) ||
+				!preg_match( $content_pattern, $element, $match ) )
+				continue;
+			$m = empty($match[3]) ? $match[4] : $match[3];
+			if ( $match_meta != 'refresh' )
+				$urls['meta']['http-equiv'][] = $m;
+			else if ( preg_match( $refresh_pattern, $m, $match ) )
+				$urls['meta']['http-equiv'][] = $match[2];
+		}
+	}
+
+	// Match style attributes
+	$urls['style'] = array( );
+	$style_pattern = '/style' . $value_pattern . '/iu';
+	foreach ( $elements as $element )
+	{
+		if ( !preg_match( $style_pattern, $element, $match ) )
+			continue;
+		$m = empty($match[3]) ? $match[4] : $match[3];
+		$style_urls = extract_css_urls( $m );
+		if ( !empty( $style_urls ) )
+			$urls['style'] = array_merge_recursive(
+				$urls['style'], $style_urls );
+	}
+
+	// Match style bodies
+	if ( preg_match_all( '/<style[^>]*>(.*?)<\/style>/siu', $text, $style_bodies ) )
+	{
+		foreach ( $style_bodies[1] as $style_body )
+		{
+			$style_urls = extract_css_urls( $style_body );
+			if ( !empty( $style_urls ) )
+				$urls['style'] = array_merge_recursive(
+					$urls['style'], $style_urls );
+		}
+	}
+	if ( empty($urls['style']) )
+		unset( $urls['style'] );
+
+	return $urls;
+}
+/**
+ * Extract URLs from UTF-8 CSS text.
+ *
+ * URLs within @import statements and url() property functions are extracted
+ * and returned in an associative array of arrays.  Array keys indicate
+ * the use context for the URL, including:
+ *
+ * 	"import"
+ * 	"property"
+ *
+ * Each value in the associative array is an array of URLs.
+ *
+ * Parameters:
+ * 	text		the UTF-8 text to scan
+ *
+ * Return values:
+ * 	an associative array of arrays of URLs.
+ *
+ * See:
+ * 	http://nadeausoftware.com/articles/2008/01/php_tip_how_extract_urls_css_file
+ */
+function extract_css_urls( $text )
+{
+	$urls = array( );
+
+	$url_pattern     = '(([^\\\\\'", \(\)]*(\\\\.)?)+)';
+	$urlfunc_pattern = 'url\(\s*[\'"]?' . $url_pattern . '[\'"]?\s*\)';
+	$pattern         = '/(' .
+		 '(@import\s*[\'"]' . $url_pattern     . '[\'"])' .
+		'|(@import\s*'      . $urlfunc_pattern . ')'      .
+		'|('                . $urlfunc_pattern . ')'      .  ')/iu';
+	if ( !preg_match_all( $pattern, $text, $matches ) )
+		return $urls;
+
+	// @import '...'
+	// @import "..."
+	foreach ( $matches[3] as $match )
+		if ( !empty($match) )
+			$urls['import'][] =
+				preg_replace( '/\\\\(.)/u', '\\1', $match );
+
+	// @import url(...)
+	// @import url('...')
+	// @import url("...")
+	foreach ( $matches[7] as $match )
+		if ( !empty($match) )
+			$urls['import'][] =
+				preg_replace( '/\\\\(.)/u', '\\1', $match );
+
+	// url(...)
+	// url('...')
+	// url("...")
+	foreach ( $matches[11] as $match )
+		if ( !empty($match) )
+			$urls['property'][] =
+				preg_replace( '/\\\\(.)/u', '\\1', $match );
+
+	return $urls;
+}

repository/url/tests/generator/lib.php

@@ -0,0 +1,35 @@
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * URL repository data generator
+ *
+ * @package    repository_url
+ * @category   test
+ * @copyright  2013 Frédéric Massart
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+/**
+ * URL repository data generator class
+ *
+ * @package    repository_url
+ * @category   test
+ * @copyright  2013 Frédéric Massart
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+class repository_url_generator extends testing_repository_generator {
+}

repository/url/tests/lib_test.php

@@ -0,0 +1,92 @@
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Unit tests for the URL repository.
+ *
+ * @package   repository_url
+ * @copyright 2014 John Okely
+ * @license   http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+namespace repository_url;
+
+defined('MOODLE_INTERNAL') || die;
+
+global $CFG;
+require_once($CFG->dirroot . '/repository/url/lib.php');
+
+
+/**
+ * URL repository test case.
+ *
+ * @copyright 2014 John Okely
+ * @license   http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+class lib_test extends \advanced_testcase {
+
+    /**
+     * Check that the url escaper performs as expected
+     */
+    public function test_escape_url(): void {
+        $this->resetAfterTest();
+
+        $repoid = $this->getDataGenerator()->create_repository('url')->id;
+
+        $conversions = array(
+                'http://example.com/test_file.png' => 'http://example.com/test_file.png',
+                'http://example.com/test%20file.png' => 'http://example.com/test%20file.png',
+                'http://example.com/test file.png' => 'http://example.com/test%20file.png',
+                'http://example.com/test file.png?query=string+test&more=string+tests' =>
+                    'http://example.com/test%20file.png?query=string+test&more=string+tests',
+                'http://example.com/?tag=<p>' => 'http://example.com/?tag=%3Cp%3E',
+                'http://example.com/"quoted".txt' => 'http://example.com/%22quoted%22.txt',
+                'http://example.com/\'quoted\'.txt' => 'http://example.com/%27quoted%27.txt',
+                '' => ''
+            );
+
+        foreach ($conversions as $input => $expected) {
+            // The constructor uses a optional_param, so we need to hack $_GET.
+            $_GET['file'] = $input;
+            $repository = new \repository_url($repoid);
+            $this->assertSame($expected, $repository->file_url);
+        }
+
+        $exceptions = array(
+                '%' => true,
+                '!' => true,
+                '!https://download.moodle.org/unittest/test.jpg' => true,
+                'https://download.moodle.org/unittest/test.jpg' => false
+            );
+
+        foreach ($exceptions as $input => $expected) {
+            $caughtexception = false;
+            try {
+                // The constructor uses a optional_param, so we need to hack $_GET.
+                $_GET['file'] = $input;
+                $repository = new \repository_url($repoid);
+                $repository->get_listing();
+            } catch (\repository_exception $e) {
+                if ($e->errorcode == 'validfiletype') {
+                    $caughtexception = true;
+                }
+            }
+            $this->assertSame($expected, $caughtexception);
+        }
+
+        unset($_GET['file']);
+    }
+
+}

repository/url/version.php

@@ -0,0 +1,31 @@
+<?php
+// This file is part of Moodle - http://moodle.org/
+//
+// Moodle is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// Moodle 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 General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
+
+/**
+ * Version details
+ *
+ * @package    repository
+ * @subpackage url
+ * @copyright  2009 Dongsheng Cai
+ * @author     Dongsheng Cai <dongsheng@moodle.com>
+ * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
+ */
+
+defined('MOODLE_INTERNAL') || die();
+
+$plugin->version   = 2024042200;        // The current plugin version (Date: YYYYMMDDXX).
+$plugin->requires  = 2024041600;        // Requires this Moodle version.
+$plugin->component = 'repository_url';  // Full name of the plugin (used for diagnostics)