Do not extract file ending from Urls (JabRef#4547)

* Fixes JabRef#4544 Do not extract file ending from Urls

* Add tests

* file type for any resource type

* Keep simple file name extraction for files

* checkstyle

build.gradle

@@ -100,6 +100,8 @@ dependencies {
     compile 'org.apache.pdfbox:fontbox:2.0.13'
     compile 'org.apache.pdfbox:xmpbox:2.0.13'
 
+    compile group: 'org.apache.tika', name: 'tika-core', version: '1.20'
+
     // required for reading write-protected PDFs - see https://github.com/JabRef/jabref/pull/942#issuecomment-209252635
     compile 'org.bouncycastle:bcprov-jdk15on:1.60'
 

src/main/java/org/jabref/model/util/FileHelper.java

@@ -1,5 +1,9 @@
 package org.jabref.model.util;
 
+import java.io.BufferedInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.net.URL;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.nio.file.Paths;
@@ -12,6 +16,14 @@
 import org.jabref.model.database.BibDatabaseContext;
 import org.jabref.model.metadata.FilePreferences;
 
+import org.apache.tika.config.TikaConfig;
+import org.apache.tika.detect.Detector;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.mime.MediaType;
+import org.apache.tika.mime.MimeType;
+import org.apache.tika.mime.MimeTypeException;
+import org.apache.tika.parser.AutoDetectParser;
+
 public class FileHelper {
 
     /**
@@ -31,12 +43,37 @@ public static Optional<String> getFileExtension(Path file) {
      * @return The extension (without leading dot), trimmed and in lowercase.
      */
     public static Optional<String> getFileExtension(String fileName) {
+        Metadata metadata = new Metadata();
+        metadata.add(Metadata.RESOURCE_NAME_KEY, fileName);
+
+        if (isUrl(fileName)) {
+            try (InputStream is = new URL(fileName).openStream()) {
+                return detectExtension(is, metadata);
+            } catch (IOException | MimeTypeException e) {
+                return Optional.empty();
+            }
+        }
+
         int dotPosition = fileName.lastIndexOf('.');
         if ((dotPosition > 0) && (dotPosition < (fileName.length() - 1))) {
             return Optional.of(fileName.substring(dotPosition + 1).trim().toLowerCase(Locale.ROOT));
-        } else {
+        }
+        return Optional.empty();
+    }
+
+    private static Optional<String> detectExtension(InputStream is, Metadata metaData) throws IOException, MimeTypeException {
+        BufferedInputStream bis = new BufferedInputStream(is);
+        AutoDetectParser parser = new AutoDetectParser();
+        Detector detector = parser.getDetector();
+        MediaType mediaType = detector.detect(bis, metaData);
+        MimeType mimeType = TikaConfig.getDefaultConfig().getMimeRepository().forName(mediaType.toString());
+        String extension = mimeType.getExtension();
+
+        if (extension.isEmpty()) {
             return Optional.empty();
         }
+
+        return Optional.of(extension.substring(1, extension.length()));
     }
 
     /**
@@ -129,4 +166,13 @@ private static Optional<Path> expandFilename(String filename, Path directory) {
             return Optional.empty();
         }
     }
+
+    private static boolean isUrl(String url) {
+        try {
+            new URL(url);
+            return true;
+        } catch (Exception e) {
+            return false;
+        }
+    }
 }

src/test/java/org/jabref/model/util/FileHelperTest.java

@@ -0,0 +1,21 @@
+package org.jabref.model.util;
+
+import java.util.Optional;
+
+import org.junit.jupiter.api.Test;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+class FileHelperTest {
+    @Test
+    public void extractFileExtension() {
+        final String filePath = FileHelperTest.class.getResource("pdffile.pdf").getPath();
+        assertEquals(Optional.of("pdf"), FileHelper.getFileExtension(filePath));
+    }
+
+    @Test
+    public void fileExtensionFromUrl() {
+        final String filePath = "https://link.springer.com/content/pdf/10.1007%2Fs40955-018-0121-9.pdf";
+        assertEquals(Optional.of("pdf"), FileHelper.getFileExtension(filePath));
+    }
+}