Dispositif / Wikibot

src/Infrastructure/Monitor/ConsoleLogger.php

Spacing +10 added lines, -10 removed lines

@@ -20,7 +20,7 @@ 
 {
     //    use LoggerTrait;
 
-    protected const CRITICAL_LOG_PATH = __DIR__ . '/../../../log/critical.log';
+    protected const CRITICAL_LOG_PATH = __DIR__.'/../../../log/critical.log';
     public bool $verbose = false;
     public bool $debug = false;
     public bool $colorMode = false;
@@ -36,7 +36,7 @@ 
 
     public function __call(string $method, array $args): void
     {
-        $this->notice('Call to undefined method ConsoleLogger:' . $method . '()');
+        $this->notice('Call to undefined method ConsoleLogger:'.$method.'()');
     }
 
     /**
@@ -62,7 +62,7 @@ 
             case 'emergency':
             case 'alert':
             case 'critical':
-                $this->echoColor("[$level] " . $date . ' : ' . $message . "\n", Color::BG_RED . Color::WHITE);
+                $this->echoColor("[$level] ".$date.' : '.$message."\n", Color::BG_RED.Color::WHITE);
                 if ($context !== []) {
                     dump($context);
                 }
@@ -70,20 +70,20 @@ 
                 break;
             case 'error':
             case 'warning':
-                $this->echoColor("[$level] " . $date . ' : ' . $message . "\n", Color::BG_YELLOW . Color::BLACK);
+                $this->echoColor("[$level] ".$date.' : '.$message."\n", Color::BG_YELLOW.Color::BLACK);
                 if ($context !== []) {
                     dump($context);
                 }
                 break;
             case 'notice':
-                $this->echoColor("[$level] " . $message . "\n");
+                $this->echoColor("[$level] ".$message."\n");
                 if ($context !== []) {
                     dump($context);
                 }
                 break;
             case 'info':
                 if ($this->verbose || $this->debug) {
-                    $this->echoColor("[$level] " . $message . "\n", Color::GRAY);
+                    $this->echoColor("[$level] ".$message."\n", Color::GRAY);
                     if ($context !== []) {
                         dump($context);
                     }
@@ -91,14 +91,14 @@ 
                 break;
             case 'debug':
                 if ($this->debug) {
-                    $this->echoColor("[$level] " . $message . "\n", Color::GRAY);
+                    $this->echoColor("[$level] ".$message."\n", Color::GRAY);
                     if ($context !== []) {
                         dump($context);
                     }
                 }
                 break;
             case 'echo':
-                $this->echoColor($message . "\n");
+                $this->echoColor($message."\n");
                 break;
         }
     }
@@ -121,7 +121,7 @@ 
     private function echoColor(string $text, ?string $color = null): void
     {
         if ($this->colorMode && !empty($color)) {
-            echo $color . $text . Color::NORMAL;
+            echo $color.$text.Color::NORMAL;
 
             return;
         }
@@ -132,7 +132,7 @@ 
     {
         file_put_contents(
             self::CRITICAL_LOG_PATH,
-            date('d-m-Y H:i:s') . " : $level : " . $message . PHP_EOL,
+            date('d-m-Y H:i:s')." : $level : ".$message.PHP_EOL,
             FILE_APPEND
         );
     }

src/Domain/ExternLink/CheckURL.php

Spacing +4 added lines, -4 removed lines

@@ -49,12 +49,12 @@ 
         $this->url = $url;
         $this->registrableDomain = null;
         if (!HttpUtil::isHttpURL($url)) {
-            $this->log->debug('Skip : not Http URL : ' . $url, ['stats' => 'externref.skip.notRawURL']);
+            $this->log->debug('Skip : not Http URL : '.$url, ['stats' => 'externref.skip.notRawURL']);
             return false;
         }
 
         if ($this->hasForbiddenFilenameExtension()) {
-            $this->log->debug('Skip : ForbiddenFilenameExtension : ' . $url, ['stats' => 'externref.skip.forbiddenFilenameExtension']);
+            $this->log->debug('Skip : ForbiddenFilenameExtension : '.$url, ['stats' => 'externref.skip.forbiddenFilenameExtension']);
             return false;
         }
 
@@ -70,7 +70,7 @@ 
      */
     protected function hasForbiddenFilenameExtension(): bool
     {
-        return (bool)preg_match(
+        return (bool) preg_match(
             '#\.(pdf|jpg|jpeg|gif|png|webp|xls|xlsx|xlr|xml|xlt|txt|csv|js|docx|exe|gz|zip|ini|movie|mp3|mp4|ogg|raw|rss|tar|tgz|wma)$#i',
             $this->url
         );
@@ -81,7 +81,7 @@ 
         try {
             $this->registrableDomain = $this->internetDomainParser->getRegistrableDomainFromURL($this->url);
         } catch (Exception) {
-            $this->log->warning('Skip : registrableDomain not a valid URL : ' . $this->url,
+            $this->log->warning('Skip : registrableDomain not a valid URL : '.$this->url,
                 ['stats' => 'externref.skip.URLAuthorized.exception2']
             );
             return null;

src/Domain/ExternLink/ExternRefTransformer.php

Spacing +16 added lines, -16 removed lines

@@ -35,13 +35,13 @@ 
     use SummaryExternTrait, PublisherLogicTrait;
 
     final public const HTTP_REQUEST_LOOP_DELAY = 10;
-    final public const SKIP_DOMAIN_FILENAME = __DIR__ . '/../resources/config_skip_domain.txt';
+    final public const SKIP_DOMAIN_FILENAME = __DIR__.'/../resources/config_skip_domain.txt';
     final public const REPLACE_404 = true;
     final public const REPLACE_410 = true;
-    final public const CONFIG_PRESSE = __DIR__ . '/../resources/config_presse.yaml';
-    final public const CONFIG_NEWSPAPER_JSON = __DIR__ . '/../resources/data_newspapers.json';
-    final public const CONFIG_SCIENTIFIC_JSON = __DIR__ . '/../resources/data_scientific_domain.json';
-    final public const CONFIG_SCIENTIFIC_WIKI_JSON = __DIR__ . '/../resources/data_scientific_wiki.json';
+    final public const CONFIG_PRESSE = __DIR__.'/../resources/config_presse.yaml';
+    final public const CONFIG_NEWSPAPER_JSON = __DIR__.'/../resources/data_newspapers.json';
+    final public const CONFIG_SCIENTIFIC_JSON = __DIR__.'/../resources/data_scientific_domain.json';
+    final public const CONFIG_SCIENTIFIC_WIKI_JSON = __DIR__.'/../resources/data_scientific_wiki.json';
 
     public bool $skipSiteBlacklisted = true;
     public bool $skipRobotNoIndex = true;
@@ -96,13 +96,13 @@ 
         }
         $this->registrableDomain = $this->urlChecker->getRegistrableDomain($url); // hack
         if ($this->isSiteBlackListed()) {
-            $this->log->debug('Site blacklisted : ' . $this->registrableDomain, ['stats' => 'externref.skip.blacklisted']);
+            $this->log->debug('Site blacklisted : '.$this->registrableDomain, ['stats' => 'externref.skip.blacklisted']);
             return $url;
         }
 
         if ($this->registrableDomain && !$this->validateConfigWebDomain($this->registrableDomain)) {
             $this->log->debug(
-                'Domain blocked by config : ' . $this->registrableDomain,
+                'Domain blocked by config : '.$this->registrableDomain,
                 ['stats' => 'externref.skip.domainDisabledByConfig']
             );
             return $url;
@@ -159,7 +159,7 @@ 
     protected function isSiteBlackListed(): bool
     {
         if ($this->registrableDomain && $this->skipSiteBlacklisted && in_array($this->registrableDomain, $this->skip_domain)) {
-            $this->log->notice("Skip web site " . $this->registrableDomain);
+            $this->log->notice("Skip web site ".$this->registrableDomain);
             return true;
         }
         return false;
@@ -177,7 +177,7 @@ 
         $this->config[$domain] = is_array($this->config[$domain]) ? $this->config[$domain] : [];
 
         if ($this->config[$domain] === 'deactivated' || isset($this->config[$domain]['deactivated'])) {
-            $this->log->info("Domain " . $domain . " disabled\n");
+            $this->log->info("Domain ".$domain." disabled\n");
 
             return false;
         }
@@ -188,9 +188,9 @@ 
     protected function logDebugConfigWebDomain(string $domain): void
     {
         if (!isset($this->config[$domain])) {
-            $this->log->debug("Domain " . $domain . " non configuré");
+            $this->log->debug("Domain ".$domain." non configuré");
         } else {
-            $this->log->debug("Domain " . $domain . " configuré");
+            $this->log->debug("Domain ".$domain." configuré");
         }
     }
 
@@ -216,7 +216,7 @@ 
         if ($pageData === []
             || (empty($pageData['JSON-LD']) && empty($pageData['meta']))
         ) {
-            $this->log->notice('No metadata : ' . $url);
+            $this->log->notice('No metadata : '.$url);
 
             return true;
         }
@@ -231,7 +231,7 @@ 
     protected function emptyMapData(array $mapData, string $url): bool
     {
         if ($mapData === [] || empty($mapData['url']) || empty($mapData['titre'])) {
-            $this->log->info('Mapping incomplet : ' . $url);
+            $this->log->info('Mapping incomplet : '.$url);
 
             return true;
         }
@@ -322,7 +322,7 @@ 
     protected function correctSiteViaWebarchiver(array $mapData): array
     {
         if (!empty($this->options['originalRegistrableDomain']) && $mapData['site']) {
-            $mapData['site'] = $this->options['originalRegistrableDomain'] . ' via ' . $mapData['site'];
+            $mapData['site'] = $this->options['originalRegistrableDomain'].' via '.$mapData['site'];
         }
 
         return $mapData;
@@ -346,7 +346,7 @@ 
         $templateOptimized = $optimizer->getOptiTemplate();
 
         $serialized = $templateOptimized->serialize(true);
-        $this->log->info('Serialized 444: ' . $serialized . "\n");
+        $this->log->info('Serialized 444: '.$serialized."\n");
         return $serialized;
     }
 
@@ -354,7 +354,7 @@ 
     {
         $template = WikiTemplateFactory::create($templateName);
         $template->userSeparator = " |";
-        $this->summary->memo['count ' . $templateName] = 1 + ($this->summary->memo['count ' . $templateName] ?? 0);
+        $this->summary->memo['count '.$templateName] = 1 + ($this->summary->memo['count '.$templateName] ?? 0);
 
         return $template;
     }

src/Infrastructure/WikiBlameAdapter.php

Spacing +5 added lines, -5 removed lines

@@ -23,7 +23,7 @@ 
 {
     protected HttpClientInterface $client;
 
-    public function __construct(private readonly LoggerInterface|NullLogger $log = new NullLogger())
+    public function __construct(private readonly LoggerInterface | NullLogger $log = new NullLogger())
     {
         $this->client = ServiceFactory::getHttpClient();
     }
@@ -38,16 +38,16 @@ 
     {
         $url = 'http://wikipedia.ramselehof.de/wikiblame.php?project=wikipedia&article='
             . str_replace(' ', '+', $article)
-            . '&needle=' . urlencode($string)
+            . '&needle='.urlencode($string)
             . '&lang=fr&limit=2000&offjahr=2024&offmon=1&offtag=1&offhour=23&offmin=55'
             . '&searchmethod=int&order=desc'
-            . '&force_wikitags=' . ($hasWikicode ? 'on' : 'off')
+            . '&force_wikitags='.($hasWikicode ? 'on' : 'off')
             . '&user_lang=fr&ignorefirst=0';
 
         $response = $this->client->get($url);
 
         if ($response->getStatusCode() !== 200) {
-            $this->log->warning('WikiBlame: ' . $response->getStatusCode() . ' ' . $response->getReasonPhrase());
+            $this->log->warning('WikiBlame: '.$response->getStatusCode().' '.$response->getReasonPhrase());
             return null;
         }
 
@@ -68,7 +68,7 @@ 
         }
 
         return [
-            'versionid' => (int)$matches[1],
+            'versionid' => (int) $matches[1],
             'dateraw' => $matches[2],
             'datetime' => DateUtil::simpleFrench2object($matches[2]),
         ];

src/Domain/ExternLink/ExternPage.php

Spacing +4 added lines, -4 removed lines

@@ -54,7 +54,7 @@ 
     )
     {
         if (!HttpUtil::isHttpURL($url)) {
-            throw new Exception('string is not an URL ' . $url);
+            throw new Exception('string is not an URL '.$url);
         }
         $this->url = $url;
     }
@@ -94,7 +94,7 @@ 
                 '//script[@type="application/ld+json"]'
             );
         } catch (Exception $e) {
-            $this->log->warning('TagParser->xpathResults NULL ' . $this->url);
+            $this->log->warning('TagParser->xpathResults NULL '.$this->url);
 
             return [];
         }
@@ -176,7 +176,7 @@ 
     {
         try {
             if (!HttpUtil::isHttpURL($this->url)) {
-                throw new Exception('string is not an URL ' . $this->url);
+                throw new Exception('string is not an URL '.$this->url);
             }
             if (!$this->domainParser instanceof InternetDomainParserInterface) {
                 $this->log->notice('InternetDomainParser is not set');
@@ -187,7 +187,7 @@ 
             return $this->domainParser->getRegistrableDomainFromURL($this->url);
         } catch (Exception $e) {
             if ($this->log !== null) {
-                $this->log->warning('InternetDomainParser->getRegistrableDomainFromURL NULL ' . $this->url);
+                $this->log->warning('InternetDomainParser->getRegistrableDomainFromURL NULL '.$this->url);
             }
             throw new Exception('InternetDomainParser->getRegistrableDomainFromURL NULL', $e->getCode(), $e);
         }

src/Domain/Utils/TextUtil.php

Spacing +4 added lines, -4 removed lines

@@ -102,7 +102,7 @@ 
         $first = mb_strtoupper(mb_substr($str, 0, 1, $e), $e);
         $rest = mb_substr($str, 1, mb_strlen($str, $e), $e);
 
-        return $first . $rest;
+        return $first.$rest;
     }
 
     /**
@@ -115,7 +115,7 @@ 
         $first = mb_strtolower(mb_substr($str, 0, 1, $e), $e);
         $rest = mb_substr($str, 1, mb_strlen($str, $e), $e);
 
-        return $first . $rest;
+        return $first.$rest;
     }
 
     public static function replaceNonBreakingSpaces(string $text): string
@@ -128,7 +128,7 @@ 
      */
     public static function trim(string $string): string
     {
-        return trim($string, self::NO_BREAK_SPACE . self::NO_BREAK_THIN_SPACE . "\n\t\r");
+        return trim($string, self::NO_BREAK_SPACE.self::NO_BREAK_THIN_SPACE."\n\t\r");
     }
 
     /**
@@ -254,7 +254,7 @@ 
         if (mb_strlen($text) > $maxLength) {
             $spacePos = mb_strrpos(mb_substr($text, 0, $maxLength), ' ');
             $spacePos = ($spacePos > ($maxLength - 12)) ? $spacePos : $maxLength;
-            $text = trim(mb_substr($text, 0, $spacePos)) . self::SYMBOL_TEXT_CUT;
+            $text = trim(mb_substr($text, 0, $spacePos)).self::SYMBOL_TEXT_CUT;
         }
 
         return $text;

src/Domain/Transformers/GoogleTransformer.php

Spacing +16 added lines, -16 removed lines

@@ -60,13 +60,13 @@ 
         }
 
         $refsData = $this->extractAllGoogleRefs($text);
-        $this->logger->debug('GoogleTransformer: refs found: ' . count($refsData));
+        $this->logger->debug('GoogleTransformer: refs found: '.count($refsData));
         if ($refsData !== []) {
             $text = $this->processRef($text, $refsData);
         }
 
         $links = $this->extractGoogleExternalBullets($text);
-        $this->logger->debug('GoogleTransformer: links found: ' . count($links));
+        $this->logger->debug('GoogleTransformer: links found: '.count($links));
         if ($links !== []) {
             $text = $this->processExternLinks($text, $links);
         }
@@ -87,7 +87,7 @@ 
         // <ref>...</ref> or {{ref|...}}
         // GoogleLivresTemplate::GOOGLEBOOK_URL_PATTERN
         if (preg_match_all(
-            '#(?:<ref[^>]*>|{{ref\|) ?(' . GoogleBooksUtil::GOOGLEBOOKS_START_URL_PATTERN . '[^>\]} \n]+) ?(?:</ref>|}})#i',
+            '#(?:<ref[^>]*>|{{ref\|) ?('.GoogleBooksUtil::GOOGLEBOOKS_START_URL_PATTERN.'[^>\]} \n]+) ?(?:</ref>|}})#i',
             $text,
             $matches,
             PREG_SET_ORDER
@@ -102,7 +102,7 @@ 
     protected function processRef(string $text, array $refsData): string
     {
         foreach ($refsData as $ref) {
-            $this->logger->info('Process GoogleBooks ref: ' . $ref[1]);
+            $this->logger->info('Process GoogleBooks ref: '.$ref[1]);
             if ($this->quota->isQuotaReached()) {
                 $this->logger->debug('Quota Google atteint');
                 throw new DomainException('Quota Google atteint');
@@ -111,19 +111,19 @@ 
                 $citation = $this->convertGBurl2OuvrageCitation(WikiTextUtil::stripFinalPoint($ref[1]));
                 sleep(2);
             } catch (Throwable $e) {
-                $this->logger->debug("Exception " . $e->getMessage());
+                $this->logger->debug("Exception ".$e->getMessage());
                 continue;
             }
 
             // ajout point final pour référence
             $citation .= '.';
 
-            $newRef = str_replace($ref[1], $citation, (string)$ref[0]);
+            $newRef = str_replace($ref[1], $citation, (string) $ref[0]);
             $this->logger->info($newRef);
 
             $text = str_replace($ref[0], $newRef, $text);
 
-            $this->logger->notice("sleep " . self::SLEEP_GOOGLE_API_INTERVAL);
+            $this->logger->notice("sleep ".self::SLEEP_GOOGLE_API_INTERVAL);
             sleep(self::SLEEP_GOOGLE_API_INTERVAL);
         }
 
@@ -177,13 +177,13 @@ 
         // Google page => 'passage'
         if (!empty($gooDat['pg'])) {
             // Exclusion de page=1, page=2 (vue par défaut sur Google Book)
-            if (preg_match('#(?:PA|PT)(\d+)$#', (string)$gooDat['pg'], $matches) && (int)$matches[1] >= 3) {
+            if (preg_match('#(?:PA|PT)(\d+)$#', (string) $gooDat['pg'], $matches) && (int) $matches[1] >= 3) {
                 $page = $matches[1];
             }
             // conversion chiffres Romain pour PR
             // Exclusion de page=1, page=2 (vue par défaut sur Google Book)
-            if (preg_match('#PR(\d+)$#', (string)$gooDat['pg'], $matches) && (int)$matches[1] >= 3) {
-                $page = NumberUtil::arab2roman((int)$matches[1], true);
+            if (preg_match('#PR(\d+)$#', (string) $gooDat['pg'], $matches) && (int) $matches[1] >= 3) {
+                $page = NumberUtil::arab2roman((int) $matches[1], true);
             }
 
             if (!empty($page)) {
@@ -244,7 +244,7 @@ 
     {
         // match "* https://books.google.fr/..."
         if (preg_match_all(
-            '#^\* *(' . GoogleBooksUtil::GOOGLEBOOKS_START_URL_PATTERN . '[^ <{\]}\n\r]+) *$#im',
+            '#^\* *('.GoogleBooksUtil::GOOGLEBOOKS_START_URL_PATTERN.'[^ <{\]}\n\r]+) *$#im',
             $text,
             $matches,
             PREG_SET_ORDER
@@ -261,10 +261,10 @@ 
      * @return string|string[]
      * @throws Throwable
      */
-    protected function processExternLinks(string $text, array $links): string|array
+    protected function processExternLinks(string $text, array $links): string | array
     {
         foreach ($links as $pattern) {
-            $this->logger->info('Process links: ' . $pattern[1]);
+            $this->logger->info('Process links: '.$pattern[1]);
             if ($this->quota->isQuotaReached()) {
                 $this->logger->debug('Quota Google atteint');
                 throw new DomainException('Quota Google atteint');
@@ -272,19 +272,19 @@ 
             try {
                 $citation = $this->convertGBurl2OuvrageCitation(WikiTextUtil::stripFinalPoint($pattern[1]));
             } catch (Exception $e) {
-                $this->logger->debug("Exception " . $e->getMessage());
+                $this->logger->debug("Exception ".$e->getMessage());
                 continue;
             }
 
             // todo : ajout point final pour référence ???
             $citation .= '.';
 
-            $newRef = str_replace($pattern[1], $citation, (string)$pattern[0]);
+            $newRef = str_replace($pattern[1], $citation, (string) $pattern[0]);
             $this->logger->info($newRef);
 
             $text = str_replace($pattern[0], $newRef, $text);
 
-            $this->logger->info("Sleep " . self::SLEEP_GOOGLE_API_INTERVAL);
+            $this->logger->info("Sleep ".self::SLEEP_GOOGLE_API_INTERVAL);
             sleep(self::SLEEP_GOOGLE_API_INTERVAL);
         }
 

src/Infrastructure/CirrusSearch.php

Spacing +7 added lines, -7 removed lines

@@ -38,7 +38,7 @@ 
     public const SRQIPROFILE_DEFAULT = 'engine_autoselect';
 
     protected const BASE_URL = 'https://fr.wikipedia.org/w/api.php'; // todo move config
-    protected const CONTINUE_OFFSET_FILENAME = __DIR__ . '/../../resources/cirrusSearch-{HASH}.txt'; // todo move config
+    protected const CONTINUE_OFFSET_FILENAME = __DIR__.'/../../resources/cirrusSearch-{HASH}.txt'; // todo move config
 
     protected array $requestParams = [];
     protected array $defaultParams
@@ -72,7 +72,7 @@ 
         if ($this->options[self::OPTION_CONTINUE] ?? false) {
             $continueOffset = 0;
             if (!empty($arrayResp['continue']['sroffset'])) {
-                $continueOffset = (int)$arrayResp['continue']['sroffset'];
+                $continueOffset = (int) $arrayResp['continue']['sroffset'];
             }
             $this->saveOffsetInFile($continueOffset);
         }
@@ -85,7 +85,7 @@ 
         $titles = [];
         foreach ($results as $res) {
             if (!empty($res['title'])) {
-                $titles[] = trim((string)$res['title']); // trim utile ?
+                $titles[] = trim((string) $res['title']); // trim utile ?
             }
         }
 
@@ -115,7 +115,7 @@ 
          */
         if ($response->getStatusCode() !== 200) {
             throw new Exception(
-                'CirrusSearch error : ' . $response->getStatusCode() . ' ' . $response->getReasonPhrase()
+                'CirrusSearch error : '.$response->getStatusCode().' '.$response->getReasonPhrase()
             );
         }
         $json = $response->getBody()->getContents();
@@ -123,7 +123,7 @@ 
             return [];
         }
         try {
-            $array = json_decode((string)$json, true, 512, JSON_THROW_ON_ERROR);
+            $array = json_decode((string) $json, true, 512, JSON_THROW_ON_ERROR);
         } catch (Throwable $e) {
             throw new Exception($e->getMessage(), $e->getCode(), $e);
         }
@@ -145,7 +145,7 @@ 
         // RFC3986 : space => %20
         $query = http_build_query($this->requestParams, 'bla', '&', PHP_QUERY_RFC3986);
 
-        return self::BASE_URL . '?' . $query;
+        return self::BASE_URL.'?'.$query;
     }
 
     protected function getOffsetFromFile(array $allParams): int
@@ -156,7 +156,7 @@ 
             return 0;
         }
 
-        return (int)trim(file_get_contents($file));
+        return (int) trim(file_get_contents($file));
     }
 
     protected function hashSearchParams(array $params): string

src/Application/CLI/wikiwixListProcess.php

Spacing +5 added lines, -5 removed lines

@@ -25,7 +25,7 @@ 
  * Traitement synchrone des URL brutes http:// transformée en {lien web} ou {article}
  */
 
-include __DIR__ . '/../myBootstrap.php';
+include __DIR__.'/../myBootstrap.php';
 
 echo "WikiwixListProcess\n";
 
@@ -62,7 +62,7 @@ 
 $titles = [];
 foreach ($rawtitles as $rawtitle) {
     // $convTitle =  @iconv('UTF-8', 'latin1', $rawtitle);
-    $convTitle =  TextUtil::fixWrongUTF8Encoding($rawtitle);
+    $convTitle = TextUtil::fixWrongUTF8Encoding($rawtitle);
     if ($convTitle !== false && trim($convTitle) !== '') {
         $titles[] = $convTitle;
     }
@@ -71,14 +71,14 @@ 
 echo sprintf("> %d converted titles\n", count($titles));
 
 // filtering
-echo '> before filtering: ' . count($titles) . " articles.\n";
-$edited = file(__DIR__ . '/../resources/article_externRef_edited.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
+echo '> before filtering: '.count($titles)." articles.\n";
+$edited = file(__DIR__.'/../resources/article_externRef_edited.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
 $titles = array_diff($titles, $edited);
 $list = new PageList($titles);
 // end HACK list manuelle
 
 
-echo ">" . $list->count() . " dans liste\n";
+echo ">".$list->count()." dans liste\n";
 if ($list->count() === 0) {
     echo "END of process: EMPTY ARTICLE LIST\n";
     sleep(120);