Improve naming for "metadata" handler.

src/main/java/eu/openaire/publications_retriever/PublicationsRetriever.java

@@ -1,7 +1,7 @@
 package eu.openaire.publications_retriever;
 
 import eu.openaire.publications_retriever.crawler.MachineLearning;
-import eu.openaire.publications_retriever.crawler.MetaDocUrlsHandler;
+import eu.openaire.publications_retriever.crawler.MetadataHandler;
 import eu.openaire.publications_retriever.crawler.PageCrawler;
 import eu.openaire.publications_retriever.util.file.FileUtils;
 import eu.openaire.publications_retriever.util.http.ConnSupportUtils;
@@ -379,15 +379,15 @@ public static void showStatistics(Instant startTime)
 			logger.info("From which docUrls, we were able to retrieve: " + numOfStoredDocFiles + " distinct docFiles. That's about: " + df.format(numOfStoredDocFiles * 100.0 / UrlUtils.sumOfDocUrlsFound.get()) + "%."
 					+ " The un-retrieved docFiles were either belonging to already-found docUrls or they had connection-issues.");
 		}
-		logger.debug("The metaDocUrl-handler is responsible for the discovery of " + MetaDocUrlsHandler.numOfMetaDocUrlsFound + " docUrls (" + df.format(MetaDocUrlsHandler.numOfMetaDocUrlsFound.get() * 100.0 / UrlUtils.sumOfDocUrlsFound.get()) + "% of the found docUrls).");
+		logger.debug("The metaDocUrl-handler is responsible for the discovery of " + MetadataHandler.numOfMetaDocUrlsFound + " docUrls (" + df.format(MetadataHandler.numOfMetaDocUrlsFound.get() * 100.0 / UrlUtils.sumOfDocUrlsFound.get()) + "% of the found docUrls).");
 		logger.debug("The re-crossed docUrls (from all handlers) were " + ConnSupportUtils.reCrossedDocUrls.get() + ". That's about " + df.format(ConnSupportUtils.reCrossedDocUrls.get() * 100.0 / UrlUtils.sumOfDocUrlsFound.get()) + "% of the found docUrls.");
 		if ( MachineLearning.useMLA )
 			logger.debug("The M.L.A. is responsible for the discovery of " + MachineLearning.docUrlsFoundByMLA.get() + " of the docUrls (" + df.format(MachineLearning.docUrlsFoundByMLA.get() * 100.0 / UrlUtils.sumOfDocUrlsFound.get()) + "%). The M.L.A.'s average success-rate was: " + df.format(MachineLearning.getAverageSuccessRate()) + "%. Gathered data for " + MachineLearning.timesGatheredData.get() + " valid pageUrl-docUrl pairs.");
 		else
 			logger.debug("The M.L.A. was not enabled.");
 
 		logger.debug("About " + df.format(LoaderAndChecker.connProblematicUrls.get() * 100.0 / inputCheckedUrlNum) + "% (" + LoaderAndChecker.connProblematicUrls.get() + " urls) were pages which had connectivity problems.");
-		logger.debug("About " + df.format(MetaDocUrlsHandler.numOfProhibitedAccessPagesFound.get() * 100.0 / inputCheckedUrlNum) + "% (" + MetaDocUrlsHandler.numOfProhibitedAccessPagesFound.get() + " urls) were pages with prohibited access.");
+		logger.debug("About " + df.format(MetadataHandler.numOfProhibitedAccessPagesFound.get() * 100.0 / inputCheckedUrlNum) + "% (" + MetadataHandler.numOfProhibitedAccessPagesFound.get() + " urls) were pages with prohibited access.");
 		logger.debug("About " + df.format(UrlTypeChecker.pagesNotProvidingDocUrls.get() * 100.0 / inputCheckedUrlNum) + "% (" + UrlTypeChecker.pagesNotProvidingDocUrls.get() + " urls) were pages which did not provide docUrls.");
 		logger.debug("About " + df.format(UrlTypeChecker.longToRespondUrls.get() * 100.0 / inputCheckedUrlNum) + "% (" + UrlTypeChecker.longToRespondUrls.get() + " urls) were urls which belong to domains which take too long to respond.");
 		logger.debug("About " + df.format(PageCrawler.contentProblematicUrls.get() * 100.0 / inputCheckedUrlNum) + "% (" + PageCrawler.contentProblematicUrls.get() + " urls) were urls which had problematic content.");

src/main/java/eu/openaire/publications_retriever/crawler/MetaDocUrlsHandler.java → src/main/java/eu/openaire/publications_retriever/crawler/MetadataHandler.java

@@ -13,9 +13,9 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-public class MetaDocUrlsHandler {
+public class MetadataHandler {
 
-    private static final Logger logger = LoggerFactory.getLogger(MetaDocUrlsHandler.class);
+    private static final Logger logger = LoggerFactory.getLogger(MetadataHandler.class);
 
 
     // Order-independent META_RESTRICTED_ACCESS_RIGHTS-regex.
@@ -72,7 +72,7 @@ else if ( !LoaderAndChecker.retrieveDocuments )
      * @param pageHtml
      * @return
      */
-    public static boolean checkIfAndHandleMetaDocUrl(String urlId, String sourceUrl, String pageUrl, String pageDomain, String pageHtml)
+    public static boolean checkAndHandleMetadata(String urlId, String sourceUrl, String pageUrl, String pageDomain, String pageHtml)
     {
         // Before checking for the MetaDocUrl, check whether this publication is restricted or not. It may have a metaDocUrl, but it will redirect to the landing page.
         // e.g.: https://le.uwpress.org/content/78/2/260

src/main/java/eu/openaire/publications_retriever/crawler/PageCrawler.java

@@ -107,8 +107,8 @@ else if ( firstHTMLlineFromDetectedContentType != null ) {
 			return;
 		}
 
-		// Check if the docLink is provided in a metaTag and connect to it directly.
-		if ( MetaDocUrlsHandler.checkIfAndHandleMetaDocUrl(urlId, sourceUrl, pageUrl, pageDomain, pageHtml) )
+		// Check if this publication is (likely) open-access and then check the docLink is provided in a metaTag and connect to it directly.
+		if ( MetadataHandler.checkAndHandleMetadata(urlId, sourceUrl, pageUrl, pageDomain, pageHtml) )
 			return;	// The sourceUrl is already logged inside the called method.
 
 		HashSet<String> currentPageLinks = null;	// We use "HashSet" to avoid duplicates.