- Update dependencies.

- Code polishing.

pom.xml

@@ -61,7 +61,7 @@
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-surefire-plugin</artifactId>
-        <version>3.2.2</version>
+        <version>3.2.3</version>
         <configuration>
           <!--<excludes>
             <exclude>some test to exclude here</exclude>
@@ -85,7 +85,7 @@
     <dependency>
       <groupId>ch.qos.logback</groupId>
       <artifactId>logback-core</artifactId>
-      <version>1.2.12</version>
+      <version>1.2.13</version>
     </dependency>
 
     <!-- https://mvnrepository.com/artifact/org.slf4j/slf4j-api -->
@@ -99,14 +99,14 @@
     <dependency>
       <groupId>ch.qos.logback</groupId>
       <artifactId>logback-classic</artifactId>
-      <version>1.2.12</version>
+      <version>1.2.13</version>
     </dependency>
 
     <!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
     <dependency>
       <groupId>org.jsoup</groupId>
       <artifactId>jsoup</artifactId>
-      <version>1.16.2</version>
+      <version>1.17.1</version>
     </dependency>
 
     <!-- https://mvnrepository.com/artifact/com.google.guava/guava -->
@@ -141,7 +141,7 @@
     <dependency>
       <groupId>commons-io</groupId>
       <artifactId>commons-io</artifactId>
-      <version>2.15.0</version>
+      <version>2.15.1</version>
     </dependency>
 
     <!-- https://mvnrepository.com/artifact/org.json/json -->

src/main/java/eu/openaire/publications_retriever/exceptions/DomainWithUnsupportedHEADmethodException.java

@@ -3,9 +3,9 @@
 
 /**
  * This class implements the new custom exception: "DomainWithUnsupportedHEADmethodException".
- * This exception is designed to be thrown when the domain is caught to not support HTTP HEAD method and we don't want to continue connecting to it's internal links.
- * The possible-docInternalLinks will be connected with "GET" method by default, so the exclusion promoted by this exception is of low risk.
- * Note that when the exception is thrown, we just return from the "visitPage()"-method , we do not block the domain, since an inputUrl from this domain might be a docUrl which we don't want to miss.
+ * This exception is designed to be thrown when the domain is caught to not support HTTP HEAD method, and we don't want to continue connecting to its internal links.
+ * The possible document-related internalLinks will be connected with "GET" method by default, so this exception is thrown for the less-possibly docUrls, after all the possible ones have been checked.
+ * Note that when the exception is thrown, we just return from the "visitPage()"-method, we do not block the domain, since an inputUrl from this domain might be a docUrl which we don't want to miss.
  * ...
  * @author Lampros Smyrnaios
  */

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

@@ -67,7 +67,7 @@ public class HttpConnUtils
 	public static final Set<String> domainsWithSlashRedirect = Collections.newSetFromMap(new ConcurrentHashMap<String, Boolean>());
 
 
-	public static final Pattern ENDING_WITH_SLASH_OR_EXTENSION_FILTER = Pattern.compile(".*(?:(?:/|\\.[^.?&/_-]{1,7})(?:\\?.+)?|(?:\\?.+))$");
+	public static final Pattern ENDING_WITH_SLASH_OR_EXTENSION_FILTER = Pattern.compile(".*(?:(?:/|\\.[^.?&/_-]{1,7})(?:\\?.+)?|\\?.+)$");
 	// The above regex, assumes file-extensions up to 7-chars long. Rare file-extensions with app to 10 or more characters exist,
 	// but then the risk of identifying irrelevant dot-prepended strings as extensions, increases (some urls end with: "<other chars>.NOTEXTENSIONSTRING").