Added scanned PDF test resource for OCR integration (#15428)

Author: justanothercoder-hub

jablib/src/test/java/org/jabref/logic/search/indexing/DocumentReaderTest.java

@@ -1,12 +1,20 @@
 package org.jabref.logic.search.indexing;
 
+import java.nio.file.Path;
+import java.util.List;
 import java.util.stream.Stream;
 
+import org.jabref.model.search.LinkedFilesConstants;
+
+import org.apache.lucene.document.Document;
+import org.junit.jupiter.api.Test;
 import org.junit.jupiter.params.ParameterizedTest;
 import org.junit.jupiter.params.provider.Arguments;
 import org.junit.jupiter.params.provider.MethodSource;
 
 import static org.junit.jupiter.api.Assertions.assertEquals;
+import static org.junit.jupiter.api.Assertions.assertFalse;
+import static org.junit.jupiter.api.Assertions.assertNull;
 
 public class DocumentReaderTest {
 
@@ -25,4 +33,19 @@ public void mergeLinesTest(String expected, String linesToMerge) {
         String result = DocumentReader.mergeLines(linesToMerge);
         assertEquals(expected, result);
     }
+
+    @Test
+    void scannedPdfHasNoExtractableContent() {
+        DocumentReader reader = new DocumentReader();
+        List<Document> pages = reader.readPdfContents(
+                "scanned-image-only.pdf",
+                Path.of("src/test/resources/pdfs/scanned-image-only.pdf")
+        );
+
+        assertFalse(pages.isEmpty());
+
+        for (Document page : pages) {
+            assertNull(page.getField(LinkedFilesConstants.CONTENT.toString()));
+        }
+    }
 }