- Optimize the "DOC_URL_FILTER"-regex.

- Update the user-agent.
- Update dependencies.

pom.xml

@@ -24,7 +24,7 @@
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-shade-plugin</artifactId>
-        <version>3.5.1</version>
+        <version>3.5.2</version>
         <executions>
           <execution>
             <phase>package</phase>
@@ -119,7 +119,7 @@
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-compress</artifactId>
-      <version>1.25.0</version>
+      <version>1.26.1</version>
     </dependency>
 
     <!-- https://mvnrepository.com/artifact/org.brotli/dec -->
@@ -147,14 +147,14 @@
     <dependency>
       <groupId>org.json</groupId>
       <artifactId>json</artifactId>
-      <version>20231013</version>
+      <version>20240303</version>
     </dependency>
 
     <!-- https://mvnrepository.com/artifact/io.minio/minio -->
     <dependency>
       <groupId>io.minio</groupId>
       <artifactId>minio</artifactId>
-      <version>8.5.7</version>
+      <version>8.5.9</version>
       <exclusions>
       <exclusion>
         <groupId>com.google.guava</groupId>

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

@@ -88,7 +88,7 @@ public class ConnSupportUtils
 
 	public static final ConcurrentHashMap<String, DomainConnectionData> domainsWithConnectionData = new ConcurrentHashMap<>();
 
-	public static String userAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/118.0";	// This should not be "final", another program, using this software as a library, should be able to set its own "UserAgent".
+	public static String userAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:123.0) Gecko/20100101 Firefox/123.0";	// This should not be "final", another program, using this software as a library, should be able to set its own "UserAgent".
 	public static String acceptLanguage = "en-US,en;q=0.5";
 
 

src/main/java/eu/openaire/publications_retriever/util/url/LoaderAndChecker.java

@@ -35,7 +35,7 @@ public class LoaderAndChecker
 
 	public static boolean useIdUrlPairs = true;
 
-	public static final Pattern DOC_URL_FILTER = Pattern.compile(".+(pdf|download|/doc|document|(?:/|[?]|&)file|/fulltext|attachment|/paper|viewfile|viewdoc|/get|cgi/viewcontent.cgi\\?|t[ée]l[ée]charger|descargar).*");
+	public static final Pattern DOC_URL_FILTER = Pattern.compile(".+(pdf|download|/doc|document|(?:/|[?]|&)file|/fulltext|attachment|/paper|view(?:file|doc)|/get|cgi/viewcontent.cgi\\?|t[ée]l[ée]charger|descargar).*");
 	// "DOC_URL_FILTER" works for lowerCase Strings (we make sure they are in lowerCase before we check).
 	// Note that we still need to check if it's an alive link and if it's actually a docUrl (though it's mimeType).