Browse Source

Reverse Sitemap Version

Branche10.4
fredtempez 7 months ago
parent
commit
61a3dc6093
  1. 6
      CHANGES.md
  2. 2
      README.md
  3. 540
      core/class/SitemapGenerator.class.php
  4. 4
      core/class/autoload.php
  5. 9
      core/class/helper.class.php
  6. 36
      core/class/sitemap/FileSystem.class.php
  7. 36
      core/class/sitemap/Runtime.class.php
  8. 705
      core/class/sitemap/SitemapGenerator.class.php
  9. 36
      core/core.php

6
CHANGES.md

@ -1,5 +1,11 @@
# Changelog
## version 10.4.06
- Mise à jour :
- Annulation de la mise à jour SiteMapGenerator 4.3.1 et réinstallation de la version initiale.
- Modification :
- Méthode Curl pour la lecture de données par Url.
## version 10.4.05
- Mise à jour :
- SiteMapGenerator 4.3.1

2
README.md

@ -1,5 +1,5 @@
# ZwiiCMS 10.4.05
# ZwiiCMS 10.4.06
Zwii est un CMS sans base de données (flat-file) qui permet de créer et gérer facilement un site web sans aucune connaissance en programmation.

540
core/class/SitemapGenerator.class.php

@ -0,0 +1,540 @@
<?php
namespace Icamys\SitemapGenerator;
class SitemapGenerator
{
const MAX_FILE_SIZE = 10485760;
const MAX_URLS_PER_SITEMAP = 50000;
const URL_PARAM_LOC = 0;
const URL_PARAM_LASTMOD = 1;
const URL_PARAM_CHANGEFREQ = 2;
const URL_PARAM_PRIORITY = 3;
/**
* Name of sitemap file
* @var string
* @access public
*/
public $sitemapFileName = "sitemap.xml";
/**
* Name of sitemap index file
* @var string
* @access public
*/
public $sitemapIndexFileName = "sitemap-index.xml";
/**
* Robots file name
* @var string
* @access public
*/
public $robotsFileName = "robots.txt";
/**
* Quantity of URLs per single sitemap file.
* According to specification max value is 50.000.
* If Your links are very long, sitemap file can be bigger than 10MB,
* in this case use smaller value.
* @var int
* @access public
*/
public $maxURLsPerSitemap = self::MAX_URLS_PER_SITEMAP;
/**
* Quantity of sitemaps per index file.
* According to specification max value is 50.000
* If Your index file is very long, index file can be bigger than 10MB,
* in this case use smaller value.
* @see http://www.sitemaps.org/protocol.html
* @var int
* @access public
*/
public $maxSitemaps = 50000;
/**
* If true, two sitemap files (.xml and .xml.gz) will be created and added to robots.txt.
* If true, .gz file will be submitted to search engines.
* If quantity of URLs will be bigger than 50.000, option will be ignored,
* all sitemap files except sitemap index will be compressed.
* @var bool
* @access public
*/
public $createGZipFile = false;
/**
* URL to Your site.
* Script will use it to send sitemaps to search engines.
* @var string
* @access private
*/
private $baseURL;
/**
* Base path. Relative to script location.
* Use this if Your sitemap and robots files should be stored in other
* directory then script.
* @var string
* @access private
*/
private $basePath;
/**
* Version of this class
* @var string
* @access private
*/
private $classVersion = "1.0.0";
/**
* Search engines URLs
* @var array of strings
* @access private
*/
private $searchEngines = array(
array(
"http://search.yahooapis.com/SiteExplorerService/V1/updateNotification?appid=USERID&url=",
"http://search.yahooapis.com/SiteExplorerService/V1/ping?sitemap="
),
"http://www.google.com/webmasters/tools/ping?sitemap=",
"http://submissions.ask.com/ping?sitemap=",
"http://www.bing.com/webmaster/ping.aspx?siteMap="
);
/**
* Array with urls
* @var \SplFixedArray of strings
* @access private
*/
private $urls;
/**
* Array with sitemap
* @var array of strings
* @access private
*/
private $sitemaps;
/**
* Array with sitemap index
* @var array of strings
* @access private
*/
private $sitemapIndex;
/**
* Current sitemap full URL
* @var string
* @access private
*/
private $sitemapFullURL;
/**
* @var \DOMDocument
*/
private $document;
/**
* Constructor.
* @param string $baseURL You site URL, with / at the end.
* @param string|null $basePath Relative path where sitemap and robots should be stored.
*/
public function __construct($baseURL, $basePath = "")
{
$this->urls = new \SplFixedArray();
$this->baseURL = $baseURL;
$this->basePath = $basePath;
$this->document = new \DOMDocument("1.0");
$this->document->preserveWhiteSpace = false;
$this->document->formatOutput = true;
}
/**
* Use this to add many URL at one time.
* Each inside array can have 1 to 4 fields.
* @param $urlsArray
* @throws \InvalidArgumentException
*/
public function addUrls($urlsArray)
{
if (!is_array($urlsArray)) {
throw new \InvalidArgumentException("Array as argument should be given.");
}
foreach ($urlsArray as $url) {
$this->addUrl(
isset($url[0]) ? $url[0] : null,
isset($url[1]) ? $url[1] : null,
isset($url[2]) ? $url[2] : null,
isset($url[3]) ? $url[3] : null
);
}
}
/**
* Use this to add single URL to sitemap.
* @param string $url URL
* @param \DateTime $lastModified When it was modified, use ISO 8601
* @param string $changeFrequency How often search engines should revisit this URL
* @param string $priority Priority of URL on You site
* @see http://en.wikipedia.org/wiki/ISO_8601
* @see http://php.net/manual/en/function.date.php
* @throws \InvalidArgumentException
*/
public function addUrl($url, \DateTime $lastModified = null, $changeFrequency = null, $priority = null)
{
if ($url == null) {
throw new \InvalidArgumentException("URL is mandatory. At least one argument should be given.");
}
$urlLength = extension_loaded('mbstring') ? mb_strlen($url) : strlen($url);
if ($urlLength > 2048) {
throw new \InvalidArgumentException(
"URL length can't be bigger than 2048 characters.
Note, that precise url length check is guaranteed only using mb_string extension.
Make sure Your server allow to use mbstring extension."
);
}
$tmp = new \SplFixedArray(1);
$tmp[self::URL_PARAM_LOC] = $url;
if (isset($lastModified)) {
$tmp->setSize(2);
$tmp[self::URL_PARAM_LASTMOD] = $lastModified->format(\DateTime::ATOM);
}
if (isset($changeFrequency)) {
$tmp->setSize(3);
$tmp[self::URL_PARAM_CHANGEFREQ] = $changeFrequency;
}
if (isset($priority)) {
$tmp->setSize(4);
$tmp[self::URL_PARAM_PRIORITY] = $priority;
}
if ($this->urls->getSize() === 0) {
$this->urls->setSize(1);
} else {
if ($this->urls->getSize() === $this->urls->key()) {
$this->urls->setSize($this->urls->getSize() * 2);
}
}
$this->urls[$this->urls->key()] = $tmp;
$this->urls->next();
}
/**
* @throws \BadMethodCallException
* @throws \InvalidArgumentException
* @throws \LengthException
*/
public function createSitemap()
{
if (!isset($this->urls)) {
throw new \BadMethodCallException("To create sitemap, call addUrl or addUrls function first.");
}
if ($this->maxURLsPerSitemap > self::MAX_URLS_PER_SITEMAP) {
throw new \InvalidArgumentException(
"More than " . self::MAX_URLS_PER_SITEMAP . " URLs per single sitemap is not allowed."
);
}
$generatorInfo = '<!-- generated-on="' . date('c') . '" -->';
$sitemapHeader = '<?xml version="1.0" encoding="UTF-8"?>' . $generatorInfo . '
<urlset
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"' . "\r\n" . '
xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9' . "\n" . '
http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd"' . "\n" . '
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
</urlset>';
$sitemapIndexHeader = '<?xml version="1.0" encoding="UTF-8"?>' . $generatorInfo . '
<sitemapindex
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9
http://www.sitemaps.org/schemas/sitemap/0.9/siteindex.xsd"
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
</sitemapindex>';
$nullUrls = 0;
foreach ($this->urls as $url) {
if (is_null($url)) {
$nullUrls++;
}
}
$nonEmptyUrls = $this->urls->getSize() - $nullUrls;
$chunks = ceil($nonEmptyUrls / $this->maxURLsPerSitemap);
for ($chunkCounter = 0; $chunkCounter < $chunks; $chunkCounter++) {
$xml = new \SimpleXMLElement($sitemapHeader);
for ($urlCounter = $chunkCounter * $this->maxURLsPerSitemap;
$urlCounter < ($chunkCounter + 1) * $this->maxURLsPerSitemap && $urlCounter < $nonEmptyUrls;
$urlCounter++
) {
$row = $xml->addChild('url');
$row->addChild(
'loc',
htmlspecialchars($this->baseURL . $this->urls[$urlCounter][self::URL_PARAM_LOC], ENT_QUOTES, 'UTF-8')
);
if ($this->urls[$urlCounter]->getSize() > 1) {
$row->addChild('lastmod', $this->urls[$urlCounter][self::URL_PARAM_LASTMOD]);
}
if ($this->urls[$urlCounter]->getSize() > 2) {
$row->addChild('changefreq', $this->urls[$urlCounter][self::URL_PARAM_CHANGEFREQ]);
}
if ($this->urls[$urlCounter]->getSize() > 3) {
$row->addChild('priority', $this->urls[$urlCounter][self::URL_PARAM_PRIORITY]);
}
}
if (strlen($xml->asXML()) > self::MAX_FILE_SIZE) {
throw new \LengthException(
"Sitemap size equals to " . strlen($xml->asXML())
. " bytes is more than 10MB (" . self::MAX_FILE_SIZE . " bytes),
please decrease maxURLsPerSitemap variable."
);
}
$this->sitemaps[] = $xml->asXML();
}
if (count($this->sitemaps) > $this->maxSitemaps) {
throw new \LengthException(
"Sitemap index can contain {$this->maxSitemaps} sitemaps.
Perhaps You trying to submit too many maps."
);
}
if (count($this->sitemaps) > 1) {
for ($i = 0; $i < count($this->sitemaps); $i++) {
$this->sitemaps[$i] = array(
str_replace(".xml", ($i + 1) . ".xml", $this->sitemapFileName),
$this->sitemaps[$i]
);
}
$xml = new \SimpleXMLElement($sitemapIndexHeader);
foreach ($this->sitemaps as $sitemap) {
$row = $xml->addChild('sitemap');
$row->addChild('loc', $this->baseURL . "/" . $this->getSitemapFileName(htmlentities($sitemap[0])));
$row->addChild('lastmod', date('c'));
}
$this->sitemapFullURL = $this->baseURL . "/" . $this->sitemapIndexFileName;
$this->sitemapIndex = array(
$this->sitemapIndexFileName,
$xml->asXML()
);
} else {
$this->sitemapFullURL = $this->baseURL . "/" . $this->getSitemapFileName();
$this->sitemaps[0] = array(
$this->sitemapFileName,
$this->sitemaps[0]
);
}
}
/**
* Returns created sitemaps as array of strings.
* Use it You want to work with sitemap without saving it as files.
* @return array of strings
* @access public
*/
public function toArray()
{
if (isset($this->sitemapIndex)) {
return array_merge(array($this->sitemapIndex), $this->sitemaps);
} else {
return $this->sitemaps;
}
}
/**
* Will write sitemaps as files.
* @access public
* @throws \BadMethodCallException
*/
public function writeSitemap()
{
if (!isset($this->sitemaps)) {
throw new \BadMethodCallException("To write sitemap, call createSitemap function first.");
}
if (isset($this->sitemapIndex)) {
$this->document->loadXML($this->sitemapIndex[1]);
$this->writeFile($this->document->saveXML(), $this->basePath, $this->sitemapIndex[0], true);
foreach ($this->sitemaps as $sitemap) {
$this->writeFile($sitemap[1], $this->basePath, $sitemap[0]);
}
} else {
$this->document->loadXML($this->sitemaps[0][1]);
$this->writeFile($this->document->saveXML(), $this->basePath, $this->sitemaps[0][0], true);
$this->writeFile($this->sitemaps[0][1], $this->basePath, $this->sitemaps[0][0]);
}
}
private function getSitemapFileName($name = null)
{
if (!$name) {
$name = $this->sitemapFileName;
}
if ($this->createGZipFile) {
$name .= ".gz";
}
return $name;
}
/**
* Save file.
* @param string $content
* @param string $filePath
* @param string $fileName
* @param bool $noGzip
* @return bool
* @access private
*/
private function writeFile($content, $filePath, $fileName, $noGzip = false)
{
if (!$noGzip && $this->createGZipFile) {
return $this->writeGZipFile($content, $filePath, $fileName);
}
$file = fopen($filePath . $fileName, 'w');
fwrite($file, $content);
return fclose($file);
}
/**
* Save GZipped file.
* @param string $content
* @param string $filePath
* @param string $fileName
* @return bool
* @access private
*/
private function writeGZipFile($content, $filePath, $fileName)
{
$fileName .= '.gz';
$file = gzopen($filePath . $fileName, 'w');
gzwrite($file, $content);
return gzclose($file);
}
/**
* If robots.txt file exist, will update information about newly created sitemaps.
* If there is no robots.txt will, create one and put into it information about sitemaps.
* @access public
* @throws \BadMethodCallException
*/
public function updateRobots()
{
if (!isset($this->sitemaps)) {
throw new \BadMethodCallException("To update robots.txt, call createSitemap function first.");
}
$sampleRobotsFile = "User-agent: *\nAllow: /";
if (file_exists($this->basePath . $this->robotsFileName)) {
$robotsFile = explode("\n", file_get_contents($this->basePath . $this->robotsFileName));
$robotsFileContent = "";
foreach ($robotsFile as $key => $value) {
if (substr($value, 0, 8) == 'Sitemap:') {
unset($robotsFile[$key]);
} else {
$robotsFileContent .= $value . "\n";
}
}
$robotsFileContent .= "Sitemap: $this->sitemapFullURL";
if (!isset($this->sitemapIndex)) {
$robotsFileContent .= "\nSitemap: " . $this->getSitemapFileName($this->sitemapFullURL);
}
file_put_contents($this->basePath . $this->robotsFileName, $robotsFileContent);
} else {
$sampleRobotsFile = $sampleRobotsFile . "\n\nSitemap: " . $this->sitemapFullURL;
if (!isset($this->sitemapIndex)) {
$sampleRobotsFile .= "\nSitemap: " . $this->getSitemapFileName($this->sitemapFullURL);
}
file_put_contents($this->basePath . $this->robotsFileName, $sampleRobotsFile);
}
}
/**
* Will inform search engines about newly created sitemaps.
* Google, Ask, Bing and Yahoo will be noticed.
* If You don't pass yahooAppId, Yahoo still will be informed,
* but this method can be used once per day. If You will do this often,
* message that limit was exceeded will be returned from Yahoo.
* @param string $yahooAppId Your site Yahoo appid.
* @return array of messages and http codes from each search engine
* @access public
* @throws \BadMethodCallException
*/
public function submitSitemap($yahooAppId = null)
{
if (!isset($this->sitemaps)) {
throw new \BadMethodCallException("To submit sitemap, call createSitemap function first.");
}
if (!extension_loaded('curl')) {
throw new \BadMethodCallException("cURL library is needed to do submission.");
}
$searchEngines = $this->searchEngines;
$searchEngines[0] = isset($yahooAppId) ?
str_replace("USERID", $yahooAppId, $searchEngines[0][0]) :
$searchEngines[0][1];
$result = array();
for ($i = 0; $i < count($searchEngines); $i++) {
$submitSite = curl_init($searchEngines[$i] . htmlspecialchars($this->sitemapFullURL, ENT_QUOTES, 'UTF-8'));
curl_setopt($submitSite, CURLOPT_RETURNTRANSFER, true);
$responseContent = curl_exec($submitSite);
$response = curl_getinfo($submitSite);
$submitSiteShort = array_reverse(explode(".", parse_url($searchEngines[$i], PHP_URL_HOST)));
$result[] = array(
"site" => $submitSiteShort[1] . "." . $submitSiteShort[0],
"fullsite" => $searchEngines[$i] . htmlspecialchars($this->sitemapFullURL, ENT_QUOTES, 'UTF-8'),
"http_code" => $response['http_code'],
"message" => str_replace("\n", " ", strip_tags($responseContent))
);
}
return $result;
}
/**
* Returns array of URLs
*
* Converts internal SplFixedArray to array
* @return array
*/
public function getUrls()
{
$urls = $this->urls->toArray();
/**
* @var int $key
* @var \SplFixedArray $urlSplArr
*/
foreach ($urls as $key => $urlSplArr) {
if (!is_null($urlSplArr)) {
$urlArr = $urlSplArr->toArray();
$url = [];
foreach ($urlArr as $paramIndex => $paramValue) {
switch ($paramIndex) {
case static::URL_PARAM_LOC:
$url['loc'] = $paramValue;
break;
case static::URL_PARAM_CHANGEFREQ:
$url['changefreq'] = $paramValue;
break;
case static::URL_PARAM_LASTMOD:
$url['lastmod'] = $paramValue;
break;
case static::URL_PARAM_PRIORITY:
$url['priority'] = $paramValue;
break;
default:
break;
}
}
$urls[$key] = $url;
}
}
return $urls;
}
public function countUrls()
{
return $this->urls->getSize();
}
}

4
core/class/autoload.php

@ -4,9 +4,7 @@ class autoload {
public static function autoloader () {
require_once 'core/class/helper.class.php';
require_once 'core/class/template.class.php';
require_once 'core/class/sitemap/Runtime.class.php';
require_once 'core/class/sitemap/FileSystem.class.php';
require_once 'core/class/sitemap/SitemapGenerator.class.php';
require_once 'core/class/SitemapGenerator.class.php';
require_once 'core/class/phpmailer/PHPMailer.class.php';
require_once 'core/class/phpmailer/Exception.class.php';
require_once 'core/class/phpmailer/SMTP.class.php';

9
core/class/helper.class.php

@ -19,7 +19,7 @@ class helper {
/**
/**
* Récupérer l'adresse IP sans tenit compte du proxy
* @return string IP adress
* Cette focntion est utilisé par user
@ -57,6 +57,13 @@ class helper {
ini_get('allow_url_fopen')){
$handle = fopen ($url, "r");
$url_get_contents_data = stream_get_contents($handle);
}elseif(function_exists('curl_version')){
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_URL, $url);
$url_get_contents_data = curl_exec($ch);
curl_close($ch);
}else{
$url_get_contents_data = false;
}

36
core/class/sitemap/FileSystem.class.php

@ -1,36 +0,0 @@
<?php
namespace Icamys\SitemapGenerator;
class FileSystem
{
public function file_get_contents($filepath)
{
return file_get_contents($filepath);
}
public function file_put_contents($filepath, $content, $flags = 0)
{
return file_put_contents($filepath, $content, $flags);
}
public function file_exists($filepath)
{
return file_exists($filepath);
}
public function rename($oldname, $newname)
{
return rename($oldname, $newname);
}
public function copy($source, $destination)
{
return copy($source, $destination);
}
public function unlink($filepath)
{
return unlink($filepath);
}
}

36
core/class/sitemap/Runtime.class.php

@ -1,36 +0,0 @@
<?php
namespace Icamys\SitemapGenerator;
class Runtime
{
public function extension_loaded($extname)
{
return extension_loaded($extname);
}
public function is_writable($filepath)
{
return is_writable($filepath);
}
public function curl_init($url)
{
return curl_init($url);
}
public function curl_setopt($handle, $option, $value)
{
return curl_setopt($handle, $option, $value);
}
public function curl_exec($handle)
{
return curl_exec($handle);
}
public function curl_getinfo($handle, $option = null)
{
return curl_getinfo($handle, $option);
}
}

705
core/class/sitemap/SitemapGenerator.class.php

@ -1,705 +0,0 @@
<?php
namespace Icamys\SitemapGenerator;
use BadMethodCallException;
use DateTime;
use Icamys\SitemapGenerator\Extensions\GoogleVideoExtension;
use InvalidArgumentException;
use OutOfRangeException;
use RuntimeException;
use XMLWriter;
/**
* Class SitemapGenerator
* @package Icamys\SitemapGenerator
*/
class SitemapGenerator
{
/**
* Max size of a sitemap according to spec.
* @see https://www.sitemaps.org/protocol.html
*/
private const MAX_FILE_SIZE = 52428800;
/**
* Max number of urls per sitemap according to spec.
* @see https://www.sitemaps.org/protocol.html
*/
private const MAX_URLS_PER_SITEMAP = 50000;
/**
* Max number of sitemaps per index file according to spec.
* @see http://www.sitemaps.org/protocol.html
*/
private const MAX_SITEMAPS_PER_INDEX = 50000;
/**
* Total max number of URLs.
*/
private const TOTAL_MAX_URLS = self::MAX_URLS_PER_SITEMAP * self::MAX_SITEMAPS_PER_INDEX;
/**
* Max url length according to spec.
* @see https://www.sitemaps.org/protocol.html#xmlTagDefinitions
*/
private const MAX_URL_LEN = 2048;
/**
* Robots file name
* @var string
* @access public
*/
private $robotsFileName = "robots.txt";
/**
* Name of sitemap file
* @var string
* @access public
*/
private $sitemapFileName = "sitemap.xml";
/**
* Name of sitemap index file
* @var string
* @access public
*/
private $sitemapIndexFileName = "sitemap-index.xml";
/**
* Quantity of URLs per single sitemap file.
* If Your links are very long, sitemap file can be bigger than 10MB,
* in this case use smaller value.
* @var int
* @access public
*/
private $maxUrlsPerSitemap = self::MAX_URLS_PER_SITEMAP;
/**
* If true, two sitemap files (.xml and .xml.gz) will be created and added to robots.txt.
* If true, .gz file will be submitted to search engines.
* If quantity of URLs will be bigger than 50.000, option will be ignored,
* all sitemap files except sitemap index will be compressed.
* @var bool
* @access public
*/
private $isCompressionEnabled = false;
/**
* URL to Your site.
* Script will use it to send sitemaps to search engines.
* @var string
* @access private
*/
private $baseURL;
/**
* Base path. Relative to script location.
* Use this if Your sitemap and robots files should be stored in other
* directory then script.
* @var string
* @access private
*/
private $basePath;
/**
* Version of this class
* @var string
* @access private
*/
private $classVersion = "4.3.2";
/**
* Search engines URLs
* @var array of strings
* @access private
*/
private $searchEngines = [
[
"http://search.yahooapis.com/SiteExplorerService/V1/updateNotification?appid=USERID&url=",
"http://search.yahooapis.com/SiteExplorerService/V1/ping?sitemap=",
],
"http://www.google.com/ping?sitemap=",
"http://submissions.ask.com/ping?sitemap=",
"http://www.bing.com/ping?sitemap=",
"http://www.webmaster.yandex.ru/ping?sitemap=",
];
/**
* Array with urls
* @var array
* @access private
*/
private $urls;
/**
* Lines for robots.txt file that are written if file does not exist
* @var array
*/
private $sampleRobotsLines = [
"User-agent: *",
"Allow: /",
];
/**
* @var array list of valid changefreq values according to the spec
*/
private $validChangefreqValues = [
'always',
'hourly',
'daily',
'weekly',
'monthly',
'yearly',
'never',
];
/**
* @var float[] list of valid priority values according to the spec
*/
private $validPriorities = [
0.0,
0.1,
0.2,
0.3,
0.4,
0.5,
0.6,
0.7,
0.8,
0.9,
1.0,
];
/**
* @var FileSystem object used to communicate with file system
*/
private $fs;
/**
* @var Runtime object used to communicate with runtime
*/
private $runtime;
/**
* @var XMLWriter Used for writing xml to files
*/
private $xmlWriter;
/**
* @var string
*/
private $flushedSitemapFilenameFormat;
/**
* @var int
*/
private $flushedSitemapSize = 0;
/**
* @var int
*/
private $flushedSitemapCounter = 0;
/**
* @var array
*/
private $flushedSitemaps = [];
/**
* @var bool
*/
private $isSitemapStarted = false;
/**
* @var int
*/
private $totalUrlCount = 0;
/**
* @var int
*/
private $urlsetClosingTagLen = 10; // strlen("</urlset>\n")
private $sitemapUrlCount = 0;
private $generatedFiles = [];
/**
* @param string $baseURL You site URL
* @param string $basePath Relative path where sitemap and robots should be stored.
* @param FileSystem|null $fs
* @param Runtime|null $runtime
*/
public function __construct(string $baseURL, string $basePath = "", FileSystem $fs = null, Runtime $runtime = null)
{
$this->urls = [];
$this->baseURL = rtrim($baseURL, '/');
if ($fs === null) {
$this->fs = new FileSystem();
} else {
$this->fs = $fs;
}
if ($runtime === null) {
$this->runtime = new Runtime();
} else {
$this->runtime = $runtime;
}
if ($this->runtime->is_writable($basePath) === false) {
throw new InvalidArgumentException(
sprintf('the provided basePath (%s) should be a writable directory,', $basePath) .
' please check its existence and permissions'
);
}
if (strlen($basePath) > 0 && substr($basePath, -1) != DIRECTORY_SEPARATOR) {
$basePath = $basePath . DIRECTORY_SEPARATOR;
}
$this->basePath = $basePath;
$this->xmlWriter = $this->createXmlWriter();
$this->flushedSitemapFilenameFormat = sprintf("sm-%%d-%d.xml", time());
}
private function createXmlWriter(): XMLWriter
{
$w = new XMLWriter();
$w->openMemory();
$w->setIndent(true);
return $w;
}
/**
* @param string $filename
* @return SitemapGenerator
*/
public function setSitemapFilename(string $filename = ''): SitemapGenerator
{
if (strlen($filename) === 0) {
throw new InvalidArgumentException('sitemap filename should not be empty');
}
if (pathinfo($filename, PATHINFO_EXTENSION) !== 'xml') {
throw new InvalidArgumentException('sitemap filename should have *.xml extension');
}
$this->sitemapFileName = $filename;
return $this;
}
/**
* @param string $filename
* @return $this
*/
public function setSitemapIndexFilename(string $filename = ''): SitemapGenerator
{
if (strlen($filename) === 0) {
throw new InvalidArgumentException('filename should not be empty');
}
$this->sitemapIndexFileName = $filename;
return $this;
}
/**
* @param string $filename
* @return $this
*/
public function setRobotsFileName(string $filename): SitemapGenerator
{
if (strlen($filename) === 0) {
throw new InvalidArgumentException('filename should not be empty');
}
$this->robotsFileName = $filename;
return $this;
}
/**
* @param int $value
* @return $this
*/
public function setMaxUrlsPerSitemap(int $value): SitemapGenerator
{
if ($value < 1 || self::MAX_URLS_PER_SITEMAP < $value) {
throw new OutOfRangeException(
sprintf('value %d is out of range 1-%d', $value, self::MAX_URLS_PER_SITEMAP)
);
}
$this->maxUrlsPerSitemap = $value;
return $this;
}
public function enableCompression(): SitemapGenerator
{
$this->isCompressionEnabled = true;
return $this;
}
public function disableCompression(): SitemapGenerator
{
$this->isCompressionEnabled = false;
return $this;
}
public function isCompressionEnabled(): bool
{
return $this->isCompressionEnabled;
}
public function validate(
string $path,
DateTime $lastModified = null,
string $changeFrequency = null,
float $priority = null,
array $alternates = null,
array $extensions = [])
{
if (!(1 <= mb_strlen($path) && mb_strlen($path) <= self::MAX_URL_LEN)) {
throw new InvalidArgumentException(
sprintf("The urlPath argument length must be between 1 and %d.", self::MAX_URL_LEN)
);
}
if ($changeFrequency !== null && !in_array($changeFrequency, $this->validChangefreqValues)) {
throw new InvalidArgumentException(
'The change frequency argument should be one of: %s' . implode(',', $this->validChangefreqValues)
);
}
if ($priority !== null && !in_array($priority, $this->validPriorities)) {
throw new InvalidArgumentException("Priority argument should be a float number in the range [0.0..1.0]");
}
if ($extensions !== null && isset($extensions['google_video'])) {
GoogleVideoExtension::validate($this->baseURL . $path, $extensions['google_video']);
}
}
/**
* Add url components.
* Instead of storing all urls in the memory, the generator will flush sets of added urls
* to the temporary files created on your disk.
* The file format is 'sm-{index}-{timestamp}.xml'
* @param string $path
* @param DateTime|null $lastModified
* @param string|null $changeFrequency
* @param float|null $priority
* @param array|null $alternates
* @param array $extensions
* @return $this
*/
public function addURL(
string $path,
DateTime $lastModified = null,
string $changeFrequency = null,
float $priority = null,
array $alternates = null,
array $extensions = []
): SitemapGenerator
{
$this->validate($path, $lastModified, $changeFrequency, $priority, $alternates, $extensions);
if ($this->totalUrlCount >= self::TOTAL_MAX_URLS) {
throw new OutOfRangeException(
sprintf("Max url limit reached (%d)", self::TOTAL_MAX_URLS)
);
}
if ($this->isSitemapStarted === false) {
$this->writeSitemapStart();
}
$this->writeSitemapUrl($this->baseURL . $path, $lastModified, $changeFrequency, $priority, $alternates, $extensions);
if ($this->totalUrlCount % 1000 === 0 || $this->sitemapUrlCount >= $this->maxUrlsPerSitemap) {
$this->flushWriter();
}
if ($this->sitemapUrlCount === $this->maxUrlsPerSitemap) {
$this->writeSitemapEnd();
}
return $this;
}
private function writeSitemapStart()
{
$this->xmlWriter->startDocument("1.0", "UTF-8");
$this->xmlWriter->writeComment(sprintf('generator-class="%s"', get_class($this)));
$this->xmlWriter->writeComment(sprintf('generator-version="%s"', $this->classVersion));
$this->xmlWriter->writeComment(sprintf('generated-on="%s"', date('c')));
$this->xmlWriter->startElement('urlset');
$this->xmlWriter->writeAttribute('xmlns', 'http://www.sitemaps.org/schemas/sitemap/0.9');
$this->xmlWriter->writeAttribute('xmlns:xhtml', 'http://www.w3.org/1999/xhtml');
$this->xmlWriter->writeAttribute('xmlns:video', 'http://www.google.com/schemas/sitemap-video/1.1');
$this->xmlWriter->writeAttribute('xmlns:xsi', 'http://www.w3.org/2001/XMLSchema-instance');
$this->xmlWriter->writeAttribute('xsi:schemaLocation', 'http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd');
$this->isSitemapStarted = true;
}
private function writeSitemapUrl($loc, $lastModified, $changeFrequency, $priority, $alternates, $extensions)
{
$this->xmlWriter->startElement('url');
$this->xmlWriter->writeElement('loc', htmlspecialchars($loc, ENT_QUOTES));
if ($lastModified !== null) {
$this->xmlWriter->writeElement('lastmod', $lastModified->format(DateTime::ATOM));
}
if ($changeFrequency !== null) {
$this->xmlWriter->writeElement('changefreq', $changeFrequency);
}
if ($priority !== null) {
$this->xmlWriter->writeElement('priority', number_format($priority, 1, ".", ""));
}
if (is_array($alternates) && count($alternates) > 0) {
foreach ($alternates as $alternate) {
if (is_array($alternate) && isset($alternate['hreflang']) && isset($alternate['href'])) {
$this->xmlWriter->startElement('xhtml:link');
$this->xmlWriter->writeAttribute('rel', 'alternate');
$this->xmlWriter->writeAttribute('hreflang', $alternate['hreflang']);
$this->xmlWriter->writeAttribute('href', $alternate['href']);
$this->xmlWriter->endElement();
}
}
}
foreach ($extensions as $extName => $extFields) {
if ($extName === 'google_video') {
GoogleVideoExtension::writeVideoTag($this->xmlWriter, $loc, $extFields);
}
}
$this->xmlWriter->endElement(); // url
$this->sitemapUrlCount++;
$this->totalUrlCount++;
}
private function flushWriter()
{
$targetSitemapFilepath = $this->basePath . sprintf($this->flushedSitemapFilenameFormat, $this->flushedSitemapCounter);
$flushedString = $this->xmlWriter->outputMemory(true);
$flushedStringLen = mb_strlen($flushedString);
if ($flushedStringLen === 0) {
return;
}
$this->flushedSitemapSize += $flushedStringLen;
if ($this->flushedSitemapSize > self::MAX_FILE_SIZE - $this->urlsetClosingTagLen) {
$this->writeSitemapEnd();
$this->writeSitemapStart();
}
$this->fs->file_put_contents($targetSitemapFilepath, $flushedString, FILE_APPEND);
}
private function writeSitemapEnd()
{
$targetSitemapFilepath = $this->basePath . sprintf($this->flushedSitemapFilenameFormat, $this->flushedSitemapCounter);
$this->xmlWriter->endElement(); // urlset
$this->xmlWriter->endDocument();
$this->fs->file_put_contents($targetSitemapFilepath, $this->xmlWriter->flush(true), FILE_APPEND);
$this->isSitemapStarted = false;
$this->flushedSitemaps[] = $targetSitemapFilepath;
$this->flushedSitemapCounter++;
$this->sitemapUrlCount = 0;
}
/**
* Flush all stored urls from memory to the disk and close all necessary tags.
*/
public function flush()
{
$this->flushWriter();
if ($this->isSitemapStarted) {
$this->writeSitemapEnd();
}
}
/**
* Move flushed files to their final location. Compress if necessary.
*/
public function finalize()
{
$this->generatedFiles = [];
if (count($this->flushedSitemaps) === 1) {
$targetSitemapFilename = $this->sitemapFileName;
if ($this->isCompressionEnabled) {
$targetSitemapFilename .= '.gz';
}
$targetSitemapFilepath = $this->basePath . $targetSitemapFilename;
if ($this->isCompressionEnabled) {
$this->fs->copy($this->flushedSitemaps[0], 'compress.zlib://' . $targetSitemapFilepath);
$this->fs->unlink($this->flushedSitemaps[0]);
} else {
$this->fs->rename($this->flushedSitemaps[0], $targetSitemapFilepath);
}
$this->generatedFiles['sitemaps_location'] = [$targetSitemapFilepath];
$this->generatedFiles['sitemaps_index_url'] = $this->baseURL . '/' . $targetSitemapFilename;
} else if (count($this->flushedSitemaps) > 1) {
$ext = '.' . pathinfo($this->sitemapFileName, PATHINFO_EXTENSION);
$targetExt = $ext;
if ($this->isCompressionEnabled) {
$targetExt .= '.gz';
}
$sitemapsUrls = [];
$targetSitemapFilepaths = [];
foreach ($this->flushedSitemaps as $i => $flushedSitemap) {
$targetSitemapFilename = str_replace($ext, ($i + 1) . $targetExt, $this->sitemapFileName);
$targetSitemapFilepath = $this->basePath . $targetSitemapFilename;
if ($this->isCompressionEnabled) {
$this->fs->copy($flushedSitemap, 'compress.zlib://' . $targetSitemapFilepath);
$this->fs->unlink($flushedSitemap);
} else {
$this->fs->rename($flushedSitemap, $targetSitemapFilepath);
}
$sitemapsUrls[] = htmlspecialchars($this->baseURL . '/' . $targetSitemapFilename, ENT_QUOTES);
$targetSitemapFilepaths[] = $targetSitemapFilepath;
}
$targetSitemapIndexFilepath = $this->basePath . $this->sitemapIndexFileName;
$this->createSitemapIndex($sitemapsUrls, $targetSitemapIndexFilepath);
$this->generatedFiles['sitemaps_location'] = $targetSitemapFilepaths;
$this->generatedFiles['sitemaps_index_location'] = $targetSitemapIndexFilepath;
$this->generatedFiles['sitemaps_index_url'] = $this->baseURL . '/' . $this->sitemapIndexFileName;
} else {
throw new RuntimeException('failed to finalize, please add urls and flush first');
}
}
private function createSitemapIndex($sitemapsUrls, $sitemapIndexFileName)
{
$this->xmlWriter->flush(true);
$this->writeSitemapIndexStart();
foreach ($sitemapsUrls as $sitemapsUrl) {
$this->writeSitemapIndexUrl($sitemapsUrl);
}
$this->writeSitemapIndexEnd();
$this->fs->file_put_contents(
$sitemapIndexFileName,
$this->xmlWriter->flush(true),
FILE_APPEND
);
}
private function writeSitemapIndexStart()
{
$this->xmlWriter->startDocument("1.0", "UTF-8");
$this->xmlWriter->writeComment(sprintf('generator-class="%s"', get_class($this)));
$this->xmlWriter->writeComment(sprintf('generator-version="%s"', $this->classVersion));
$this->xmlWriter->writeComment(sprintf('generated-on="%s"', date('c')));
$this->xmlWriter->startElement('sitemapindex');
$this->xmlWriter->writeAttribute('xmlns', 'http://www.sitemaps.org/schemas/sitemap/0.9');
$this->xmlWriter->writeAttribute('xmlns:xsi', 'http://www.w3.org/2001/XMLSchema-instance');
$this->xmlWriter->writeAttribute('xsi:schemaLocation', 'http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd');
}
private function writeSitemapIndexUrl($url)
{
$this->xmlWriter->startElement('sitemap');
$this->xmlWriter->writeElement('loc', htmlspecialchars($url, ENT_QUOTES));
$this->xmlWriter->writeElement('lastmod', date('c'));
$this->xmlWriter->endElement(); // sitemap
}
private function writeSitemapIndexEnd()
{
$this->xmlWriter->endElement(); // sitemapindex
$this->xmlWriter->endDocument();
}
/**
* @return array Array of previously generated files
*/
public function getGeneratedFiles(): array
{
return $this->generatedFiles;
}
/**
* Will inform search engines about newly created sitemaps.
* Google, Ask, Bing and Yahoo will be noticed.
* If You don't pass yahooAppId, Yahoo still will be informed,
* but this method can be used once per day. If You will do this often,
* message that limit was exceeded will be returned from Yahoo.
* @param string $yahooAppId Your site Yahoo appid.
* @return array of messages and http codes from each search engine
* @access public
* @throws BadMethodCallException
*/
public function submitSitemap($yahooAppId = null): array
{
if (count($this->generatedFiles) === 0) {
throw new BadMethodCallException("To update robots.txt, call finalize() first.");
}
if (!$this->runtime->extension_loaded('curl')) {
throw new BadMethodCallException("cURL extension is needed to do submission.");
}
$searchEngines = $this->searchEngines;
$searchEngines[0] = isset($yahooAppId) ?
str_replace("USERID", $yahooAppId, $searchEngines[0][0]) :
$searchEngines[0][1];
$result = [];
for ($i = 0; $i < count($searchEngines); $i++) {
$submitUrl = $searchEngines[$i] . htmlspecialchars($this->generatedFiles['sitemaps_index_url'], ENT_QUOTES);
$submitSite = $this->runtime->curl_init($submitUrl);
$this->runtime->curl_setopt($submitSite, CURLOPT_RETURNTRANSFER, true);
$responseContent = $this->runtime->curl_exec($submitSite);
$response = $this->runtime->curl_getinfo($submitSite);
$submitSiteShort = array_reverse(explode(".", parse_url($searchEngines[$i], PHP_URL_HOST)));
$result[] = [
"site" => $submitSiteShort[1] . "." . $submitSiteShort[0],
"fullsite" => $submitUrl,
"http_code" => $response['http_code'],
"message" => str_replace("\n", " ", strip_tags($responseContent)),
];
}
return $result;
}
/**
* Adds sitemap url to robots.txt file located in basePath.
* If robots.txt file exists,
* the function will append sitemap url to file.
* If robots.txt does not exist,
* the function will create new robots.txt file with sample content and sitemap url.
* @access public
* @throws BadMethodCallException
* @throws RuntimeException
*/
public function updateRobots(): SitemapGenerator
{
if (count($this->generatedFiles) === 0) {
throw new BadMethodCallException("To update robots.txt, call finalize() first.");
}
$robotsFilePath = $this->basePath . $this->robotsFileName;
$robotsFileContent = $this->createNewRobotsContentFromFile($robotsFilePath);
$this->fs->file_put_contents($robotsFilePath, $robotsFileContent);
return $this;
}
/**
* @param $filepath
* @return string
*/
private function createNewRobotsContentFromFile($filepath): string
{
if ($this->fs->file_exists($filepath)) {
$robotsFileContent = "";
$robotsFile = explode(PHP_EOL, $this->fs->file_get_contents($filepath));
foreach ($robotsFile as $key => $value) {
if (substr($value, 0, 8) == 'Sitemap:') {
unset($robotsFile[$key]);
} else {
$robotsFileContent .= $value . PHP_EOL;
}
}
} else {
$robotsFileContent = $this->getSampleRobotsContent();
}
$robotsFileContent .= "Sitemap: {$this->generatedFiles['sitemaps_index_url']}";
return $robotsFileContent;
}
/**
* @return string
* @access private
*/
private function getSampleRobotsContent(): string
{
return implode(PHP_EOL, $this->sampleRobotsLines) . PHP_EOL;
}
}

36
core/core.php

@ -740,26 +740,22 @@ class common {
$timezone = $this->getData(['config','timezone']);
$outputDir = getcwd();
$sitemap = new \Icamys\SitemapGenerator\SitemapGenerator(helper::baseurl(false),$outputDir);
$sitemap = new \Icamys\SitemapGenerator\SitemapGenerator(helper::baseurl());
// will create also compressed (gzipped) sitemap
$sitemap->enableCompression();
$sitemap->createGZipFile = true;
// determine how many urls should be put into one file
// according to standard protocol 50000 is maximum value (see http://www.sitemaps.org/protocol.html)
$sitemap->setMaxUrlsPerSitemap(50000);
$sitemap->maxURLsPerSitemap = 50000;
// sitemap file name
$sitemap->setSitemapFileName("sitemap.xml");
// Set the sitemap index file name
$sitemap->setSitemapIndexFileName("sitemap-index.xml");
$sitemap->sitemapFileName = "sitemap.xml";
$datetime = new DateTime(date('c'));
$datetime->format(DateTime::ATOM); // Updated ISO8601
// sitemap index file name
$sitemap->sitemapIndexFileName = "sitemap-index.xml";
foreach($this->getHierarchy(null, null, null) as $parentPageId => $childrenPageIds) {
// Exclure les barres et les pages non publiques et les pages masquées
if ($this->getData(['page',$parentPageId,'group']) !== 0 ||
@ -801,22 +797,17 @@ class common {
}
// Flush all stored urls from memory to the disk and close all necessary tags.
$sitemap->flush();
// Move flushed files to their final location. Compress if the option is enabled.
$sitemap->finalize();
// generating internally a sitemap
$sitemap->createSitemap();
// Update robots.txt file in output directory or create a new one
$sitemap->updateRobots();
// Submit your sitemaps to Google, Yahoo, Bing and Ask.com
$sitemap->submitSitemap();
// writing early generated sitemap to file
$sitemap->writeSitemap();
return(file_exists('sitemap.xml'));
}
/*
* Création d'une miniature
* Fonction utilisée lors de la mise à jour d'une version 9 à une version 10
@ -1578,6 +1569,11 @@ class common {
if ($this->getData(['core', 'dataVersion']) < 10405) {
$this->setData(['core', 'dataVersion', 10405]);
}
// Version 10.4.06
if ($this->getData(['core', 'dataVersion']) < 10406) {
$this->removeDir ('core/class/sitemap');
$this->setData(['core', 'dataVersion', 10406]);
}
}
}

Loading…
Cancel
Save