- Avoid double-logging in "PageCrawler.verifyDocLink()".

- Code polishing.

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

@@ -242,7 +242,7 @@ public static synchronized boolean shouldRunPrediction()
 	/**
 	 * This method tries to predict the docUrl of a page, if this page gives us the ID of the document, based on previous success cases.
 	 * The idea is that we might get a url which shows info about the publication and has the same ID with the wanted docUrl, but it just happens to be in a different directory (path).
-	 * So, before going and checking each and every one of the internal links, we should check if by using known docUrl-paths that gave docUrls before (for the current pageUrl-path), we are able to retrieve the docUrl immediately.
+	 * So, before going and checking each one of the internal links, we should check if by using known docUrl-paths that gave docUrls before (for the current pageUrl-path), we are able to retrieve the docUrl immediately.
 	 * @param urlId
 	 * @param sourceUrl
 	 * @param pageUrl

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

@@ -73,6 +73,8 @@ public class PageCrawler
 																		+ "|ープンアクセス方針|(?:刊行物|個人)単位登録).*");	// "Open access policy" in Japanese, "Publication unit registration"
 
 	// Example of docUrl having the "editorial" keyword: https://publikationen.ub.uni-frankfurt.de/opus4/frontdoor/deliver/index/docId/45461/file/daek_et_al_2017_editorial.pdf
+	// Example of docUrl having the "review" keyword: https://jag.journalagent.com/tkd/pdfs/TKDA-33903-INVITED_REVIEW-ASLAN.pdf
+
 
 	public static void visit(String urlId, String sourceUrl, String pageUrl, String pageContentType, HttpURLConnection conn, String firstHTMLlineFromDetectedContentType, BufferedReader bufferedReader)
 	{
@@ -602,10 +604,8 @@ public static boolean verifyDocLink(String urlId, String sourceUrl, String pageU
 				return false;
 			}
 			return true;
-		} catch (Exception e) {	// After connecting to the metaDocUrl.
-			logger.warn("The DocLink < " + docLink + " > was not reached!");
-			if (e instanceof RuntimeException)
-				ConnSupportUtils.printEmbeddedExceptionMessage(e, docLink);
+		} catch (Exception e) {	// After connecting to the possibleDocLink.
+			logger.warn("The DocLink < " + docLink + " > was not reached!");	// The specific error has already been written inside the called method.
 			UrlUtils.logOutputData(urlId, sourceUrl, null, UrlUtils.unreachableDocOrDatasetUrlIndicator, "Discarded in 'PageCrawler.visit()' method, as the retrieved DocLink: < " + docLink + " > had connectivity problems.", null, true, "true", "true", "false", "false", "false", null, "null");
 			return false;
 		}

src/main/java/eu/openaire/publications_retriever/util/http/ConnSupportUtils.java

@@ -186,8 +186,7 @@ public static String hasDocOrDatasetMimeType(String urlStr, String mimeType, Str
 						contentDisposition = contentDisposition.toLowerCase();
 						if ( !contentDisposition.equals("attachment") )
 							typeToReturn = contentDisposition.contains(".pdf") ? "document" : null;    // TODO - add more types as needed. Check: "http://www.esocialsciences.org/Download/repecDownload.aspx?qs=Uqn/rN48N8UOPcbSXUd2VFI+dpOD3MDPRfIL8B3DH+6L18eo/yEvpYEkgi9upp2t8kGzrjsWQHUl44vSn/l7Uc1SILR5pVtxv8VYECXSc8pKLF6QJn6MioA5dafPj/8GshHBvLyCex2df4aviMvImCZpwMHvKoPiO+4B7yHRb97u1IHg45E+Z6ai0Z/0vacWHoCsNT9O4FNZKMsSzen2Cw=="
-					}
-					else
+					} else
 						typeToReturn = urlStr.toLowerCase().contains("pdf") ? "document" : null;
 				}
 				return typeToReturn;	// It may be null.
@@ -1204,7 +1203,7 @@ public static long getRandomNumber(int min, int max) {
 	public static String getWasDirectLink(String sourceUrl, String pageUrl, boolean calledForPageUrl, String finalUrlStr) {
 		String wasDirectLink;
 		if ( calledForPageUrl ) {
-			boolean isSpecialUrl = HttpConnUtils.isSpecialUrl.get();	// It's more efficient to save it once in a temp-variable.
+			boolean isSpecialUrl = HttpConnUtils.isSpecialUrl.get();
 			if ( (!isSpecialUrl && ( pageUrl.equals(finalUrlStr) || ConnSupportUtils.haveOnlyProtocolDifference(pageUrl, finalUrlStr) ))
 					|| sourceUrl.equals(finalUrlStr) || ConnSupportUtils.haveOnlyProtocolDifference(sourceUrl, finalUrlStr))	// Or if it was not a "specialUrl" and the pageUrl is the same as the docUrl.
 				wasDirectLink = "true";