@@ -49,7 +49,7 @@ discard block |
||
| 49 | 49 | { |
| 50 | 50 | $data = $this->getFileData(); |
| 51 | 51 | $this->lastDate = new DateTime($data['date'], new DateTimeZone(static::REBOOT_TIMEZONE)); |
| 52 | - $this->count = (int)$data['count']; |
|
| 52 | + $this->count = (int) $data['count']; |
|
| 53 | 53 | |
| 54 | 54 | // Today reboot date/time of the quota |
| 55 | 55 | $todayBoot = new DateTime(); |
@@ -70,7 +70,7 @@ discard block |
||
| 70 | 70 | |
| 71 | 71 | try { |
| 72 | 72 | $json = file_get_contents(static::JSON_FILENAME); |
| 73 | - $array = (array)json_decode($json, true, 512, JSON_THROW_ON_ERROR); |
|
| 73 | + $array = (array) json_decode($json, true, 512, JSON_THROW_ON_ERROR); |
|
| 74 | 74 | } catch (Throwable) { |
| 75 | 75 | throw new ConfigException('Error on Google Quota file : reading or JSON malformed.'); |
| 76 | 76 | } |
@@ -21,7 +21,7 @@ discard block |
||
| 21 | 21 | */ |
| 22 | 22 | class InternetDomainParser implements InternetDomainParserInterface |
| 23 | 23 | { |
| 24 | - private const PATH_CACHE_PUBLIC_SUFFIX_LIST = __DIR__ . '/resources/public_suffix_list.dat'; |
|
| 24 | + private const PATH_CACHE_PUBLIC_SUFFIX_LIST = __DIR__.'/resources/public_suffix_list.dat'; |
|
| 25 | 25 | |
| 26 | 26 | private readonly Rules $rules; |
| 27 | 27 | |
@@ -55,7 +55,7 @@ discard block |
||
| 55 | 55 | public static function extractSubdomainString(string $httpURL): string |
| 56 | 56 | { |
| 57 | 57 | if (!ExternHttpClient::isHttpURL($httpURL)) { |
| 58 | - throw new Exception('string is not an URL ' . $httpURL); |
|
| 58 | + throw new Exception('string is not an URL '.$httpURL); |
|
| 59 | 59 | } |
| 60 | 60 | |
| 61 | 61 | return parse_url($httpURL, PHP_URL_HOST); |
@@ -48,7 +48,7 @@ |
||
| 48 | 48 | /** |
| 49 | 49 | * @throws Exception |
| 50 | 50 | */ |
| 51 | - public function insertPageOuvrages(array $datas): bool|array |
|
| 51 | + public function insertPageOuvrages(array $datas): bool | array |
|
| 52 | 52 | { |
| 53 | 53 | // check if article already in db |
| 54 | 54 | $page = $datas[0]['page']; |
@@ -14,7 +14,7 @@ discard block |
||
| 14 | 14 | |
| 15 | 15 | class ExternHttpErrorLogic |
| 16 | 16 | { |
| 17 | - public const LOG_REQUEST_ERROR = __DIR__ . '/../../Application/resources/external_request_error.log'; |
|
| 17 | + public const LOG_REQUEST_ERROR = __DIR__.'/../../Application/resources/external_request_error.log'; |
|
| 18 | 18 | |
| 19 | 19 | public function __construct(private readonly LoggerInterface $log = new NullLogger()) |
| 20 | 20 | { |
@@ -40,12 +40,12 @@ discard block |
||
| 40 | 40 | } |
| 41 | 41 | return $url; |
| 42 | 42 | } elseif (preg_match('#401 Unauthorized#i', $errorMessage)) { |
| 43 | - $this->log->notice('401 Unauthorized : skip ' . $url); |
|
| 43 | + $this->log->notice('401 Unauthorized : skip '.$url); |
|
| 44 | 44 | |
| 45 | 45 | return $url; |
| 46 | 46 | } else { |
| 47 | 47 | // autre : ne pas générer de {lien brisé}, car peut-être 404 temporaire |
| 48 | - $this->log->warning('erreur sur extractWebData ' . $errorMessage); |
|
| 48 | + $this->log->warning('erreur sur extractWebData '.$errorMessage); |
|
| 49 | 49 | |
| 50 | 50 | //file_put_contents(self::LOG_REQUEST_ERROR, $this->domain."\n", FILE_APPEND); |
| 51 | 51 | |
@@ -72,7 +72,7 @@ discard block |
||
| 72 | 72 | { |
| 73 | 73 | $text = str_replace(['https://', 'http://', 'www.'], '', $url); |
| 74 | 74 | if (strlen($text) > 30) { |
| 75 | - $text = substr($text, 0, 30) . '…'; |
|
| 75 | + $text = substr($text, 0, 30).'…'; |
|
| 76 | 76 | } |
| 77 | 77 | |
| 78 | 78 | return $text; |
@@ -80,7 +80,7 @@ discard block |
||
| 80 | 80 | |
| 81 | 81 | protected function log403(string $url): void |
| 82 | 82 | { |
| 83 | - $this->log->warning('403 Forbidden : ' . $url); |
|
| 84 | - file_put_contents(self::LOG_REQUEST_ERROR, '403 Forbidden : ' . $url . "\n", FILE_APPEND); |
|
| 83 | + $this->log->warning('403 Forbidden : '.$url); |
|
| 84 | + file_put_contents(self::LOG_REQUEST_ERROR, '403 Forbidden : '.$url."\n", FILE_APPEND); |
|
| 85 | 85 | } |
| 86 | 86 | } |
| 87 | 87 | \ No newline at end of file |
@@ -32,7 +32,7 @@ |
||
| 32 | 32 | $this->summary->memo['sites'][] = $this->externalPage->getPrettyDomainName(); // ??? |
| 33 | 33 | } |
| 34 | 34 | if (isset($mapData['accès url'])) { |
| 35 | - $this->log->debug('accès |
|
@@ -54,7 +54,7 @@ discard block |
||
| 54 | 54 | ) |
| 55 | 55 | { |
| 56 | 56 | if (!ExternHttpClient::isHttpURL($url)) { |
| 57 | - throw new Exception('string is not an URL ' . $url); |
|
| 57 | + throw new Exception('string is not an URL '.$url); |
|
| 58 | 58 | } |
| 59 | 59 | $this->url = $url; |
| 60 | 60 | } |
@@ -170,7 +170,7 @@ discard block |
||
| 170 | 170 | { |
| 171 | 171 | try { |
| 172 | 172 | if (!ExternHttpClient::isHttpURL($this->url)) { |
| 173 | - throw new Exception('string is not an URL ' . $this->url); |
|
| 173 | + throw new Exception('string is not an URL '.$this->url); |
|
| 174 | 174 | } |
| 175 | 175 | if (!$this->domainParser instanceof InternetDomainParserInterface) { |
| 176 | 176 | $this->log->notice('InternetDomainParser is not set'); |
@@ -181,7 +181,7 @@ discard block |
||
| 181 | 181 | return $this->domainParser->getRegistrableDomainFromURL($this->url); |
| 182 | 182 | } catch (Exception $e) { |
| 183 | 183 | if ($this->log !== null) { |
| 184 | - $this->log->warning('InternetDomainParser->getRegistrableDomainFromURL NULL ' . $this->url); |
|
| 184 | + $this->log->warning('InternetDomainParser->getRegistrableDomainFromURL NULL '.$this->url); |
|
| 185 | 185 | } |
| 186 | 186 | throw new Exception('InternetDomainParser->getRegistrableDomainFromURL NULL', $e->getCode(), $e); |
| 187 | 187 | } |
@@ -27,7 +27,7 @@ discard block |
||
| 27 | 27 | || stripos((string) $robots, 'none') !== false |
| 28 | 28 | ) |
| 29 | 29 | ) { |
| 30 | - $this->log->notice('robots NOINDEX : ' . $url); |
|
| 30 | + $this->log->notice('robots NOINDEX : '.$url); |
|
| 31 | 31 | |
| 32 | 32 | return !$this->isNoIndexDomainWhitelisted($pageData['meta']['prettyDomainName']); |
| 33 | 33 | } |
@@ -38,7 +38,7 @@ discard block |
||
| 38 | 38 | protected function isNoIndexDomainWhitelisted(?string $prettyDomain): bool |
| 39 | 39 | { |
| 40 | 40 | if (in_array($prettyDomain ?? '', $this->noindexWhitelist)) { |
| 41 | - $this->log->notice('ROBOT_NOINDEX_WHITELIST ' . $prettyDomain); |
|
| 41 | + $this->log->notice('ROBOT_NOINDEX_WHITELIST '.$prettyDomain); |
|
| 42 | 42 | |
| 43 | 43 | return true; |
| 44 | 44 | } |
@@ -49,7 +49,7 @@ discard block |
||
| 49 | 49 | $this->url = $url; |
| 50 | 50 | $this->registrableDomain = null; |
| 51 | 51 | if (!ExternHttpClient::isHttpURL($url)) { |
| 52 | - $this->log->debug('Skip : not a valid URL : ' . $url); |
|
| 52 | + $this->log->debug('Skip : not a valid URL : '.$url); |
|
| 53 | 53 | return false; |
| 54 | 54 | } |
| 55 | 55 | |
@@ -57,7 +57,7 @@ discard block |
||
| 57 | 57 | return false; |
| 58 | 58 | } |
| 59 | 59 | if (!ExternHttpClient::isHttpURL($url)) { |
| 60 | - throw new Exception('string is not an URL ' . $url); |
|
| 60 | + throw new Exception('string is not an URL '.$url); |
|
| 61 | 61 | } |
| 62 | 62 | |
| 63 | 63 | $this->findRegistrableDomain(); |
@@ -79,7 +79,7 @@ discard block |
||
| 79 | 79 | try { |
| 80 | 80 | $this->registrableDomain = $this->internetDomainParser->getRegistrableDomainFromURL($this->url); |
| 81 | 81 | } catch (Exception) { |
| 82 | - $this->log->warning('Skip : not a valid URL : ' . $this->url); |
|
| 82 | + $this->log->warning('Skip : not a valid URL : '.$this->url); |
|
| 83 | 83 | return null; |
| 84 | 84 | } |
| 85 | 85 | return $this->registrableDomain; |
@@ -92,7 +92,7 @@ discard block |
||
| 92 | 92 | */ |
| 93 | 93 | protected function hasForbiddenFilenameExtension(): bool |
| 94 | 94 | { |
| 95 | - return (bool)preg_match( |
|
| 95 | + return (bool) preg_match( |
|
| 96 | 96 | '#\.(pdf|jpg|jpeg|gif|png|xls|xlsx|xlr|xml|xlt|txt|csv|js|docx|exe|gz|zip|ini|movie|mp3|mp4|ogg|raw|rss|tar|tgz|wma)$#i', |
| 97 | 97 | $this->url |
| 98 | 98 | ); |
@@ -49,7 +49,7 @@ discard block |
||
| 49 | 49 | // PUNCTUATION conversion |
| 50 | 50 | $punctuationColl = array_filter( |
| 51 | 51 | TextUtil::ALL_PUNCTUATION, |
| 52 | - function ($value) { |
|
| 52 | + function($value) { |
|
| 53 | 53 | // skip punctuation chars from mixed names (example : "Pierre-Marie L'Anglois") |
| 54 | 54 | return !in_array($value, ["'", '-', '-']); |
| 55 | 55 | } |
@@ -68,7 +68,7 @@ discard block |
||
| 68 | 68 | } |
| 69 | 69 | if (preg_match('#^(PATTERNINITIAL|PATTERNURL|PATTERNAND|PATTERNCOMMA|PATTERNBIBABREV|PATTERNPUNCTUATION)$#', (string) $tok, $matches) > 0) { |
| 70 | 70 | |
| 71 | - $shortpattern = str_replace('PATTERN','', (string) $tok); |
|
| 71 | + $shortpattern = str_replace('PATTERN', '', (string) $tok); |
|
| 72 | 72 | $res['pattern'] .= ' '.$shortpattern; // PATTERNAND -> AND |
| 73 | 73 | if (in_array($matches[1], ['PATTERNCOMMA', 'PATTERNPUNCTUATION']) || empty($matches[1])) { |
| 74 | 74 | $res['value'][] = '*'; |
@@ -123,7 +123,7 @@ discard block |
||
| 123 | 123 | return preg_replace_callback_array( |
| 124 | 124 | [ |
| 125 | 125 | // URL |
| 126 | - '#\bhttps?://[^ \]]+#i' => function ($match): string { |
|
| 126 | + '#\bhttps?://[^ \]]+#i' => function($match): string { |
|
| 127 | 127 | // '#https?\:\/\/[\w\-_]+(\.[\w\-_]+)+([\w\-\.,@?^=%&:/~\+\#]*[\w\-\@?^=%&/~\+#])?#' |
| 128 | 128 | $this->tokenValue['URL'][] = $match[0]; |
| 129 | 129 | |
@@ -131,26 +131,26 @@ discard block |
||
| 131 | 131 | }, |
| 132 | 132 | // BIBABREV : "dir.", "trad.", "(dir.)", "[dir.]", etc. |
| 133 | 133 | // TODO: regex flaw : "(" not evaluated in BIBABREV. Example : "(dir.)" |
| 134 | - '#\b[(\[]?(collectif|coll\.|dir\.|trad\.|coord\.|ill\.)[)\]]?#i' => function ($match): string { |
|
| 134 | + '#\b[(\[]?(collectif|coll\.|dir\.|trad\.|coord\.|ill\.)[)\]]?#i' => function($match): string { |
|
| 135 | 135 | $this->tokenValue['BIBABREV'][] = $match[0]; // [1] = dir |
| 136 | 136 | |
| 137 | 137 | return ' PATTERNBIBABREV '; |
| 138 | 138 | }, |
| 139 | 139 | // AND |
| 140 | - '# (et|and|&|with|avec|e) #i' => function ($match): string { |
|
| 140 | + '# (et|and|&|with|avec|e) #i' => function($match): string { |
|
| 141 | 141 | $this->tokenValue['AND'][] = $match[0]; |
| 142 | 142 | |
| 143 | 143 | return ' PATTERNAND '; |
| 144 | 144 | }, |
| 145 | 145 | // COMMA |
| 146 | - '#,#' => function (): string { |
|
| 146 | + '#,#' => function(): string { |
|
| 147 | 147 | return ' PATTERNCOMMA '; |
| 148 | 148 | }, |
| 149 | 149 | // INITIAL : 2) convert letter ("A.") or junior ("Jr.") or senior ("Sr.") |
| 150 | 150 | // extract initial before "." converted in PUNCTUATION |
| 151 | 151 | // Note : \b word boundary match between "L" and "'Amour" in "L'Amour" (for [A-Z]\b) |
| 152 | 152 | // \b([A-Z]\. |[A-Z] |JR|Jr\.|Jr\b|Sr\.|Sr\b)+ for grouping "A. B." in same INITIAL ? |
| 153 | - "#\b([A-Z]\.|[A-Z] |JR|Jr\.|Jr\b|Sr\.|Sr\b)#" => function ($match): string { |
|
| 153 | + "#\b([A-Z]\.|[A-Z] |JR|Jr\.|Jr\b|Sr\.|Sr\b)#" => function($match): string { |
|
| 154 | 154 | $this->tokenValue['INITIAL'][] = $match[0]; |
| 155 | 155 | |
| 156 | 156 | return ' PATTERNINITIAL '; |