feat(backend): hash uploaded files and store hash on documents and annotations

- Flyway V13: add file_hash column to documents and document_annotations
- FileService.uploadFile() now returns UploadResult(s3Key, fileHash) with SHA-256 hash computed from raw bytes
- Document and DocumentAnnotation models gain a fileHash field
- DocumentService propagates the hash at all three upload sites (storeDocument, createDocument, updateDocument)
- AnnotationService.createAnnotation() accepts and persists a fileHash
- AnnotationController resolves the document's hash and passes it through

Closes #55

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/src/main/java/org/raddatz/familienarchiv/controller/AnnotationController.java

@@ -4,10 +4,12 @@ import lombok.RequiredArgsConstructor;
 import lombok.extern.slf4j.Slf4j;
 import org.raddatz.familienarchiv.dto.CreateAnnotationDTO;
 import org.raddatz.familienarchiv.model.AppUser;
+import org.raddatz.familienarchiv.model.Document;
 import org.raddatz.familienarchiv.model.DocumentAnnotation;
 import org.raddatz.familienarchiv.security.Permission;
 import org.raddatz.familienarchiv.security.RequirePermission;
 import org.raddatz.familienarchiv.service.AnnotationService;
+import org.raddatz.familienarchiv.service.DocumentService;
 import org.raddatz.familienarchiv.service.UserService;
 import org.springframework.http.HttpStatus;
 import org.springframework.security.core.Authentication;
@@ -23,6 +25,7 @@ import java.util.UUID;
 public class AnnotationController {
 
     private final AnnotationService annotationService;
+    private final DocumentService documentService;
     private final UserService userService;
 
     @GetMapping
@@ -38,7 +41,8 @@ public class AnnotationController {
             @RequestBody CreateAnnotationDTO dto,
             Authentication authentication) {
         UUID userId = resolveUserId(authentication);
-        return annotationService.createAnnotation(documentId, dto, userId);
+        Document doc = documentService.getDocumentById(documentId);
+        return annotationService.createAnnotation(documentId, dto, userId, doc.getFileHash());
     }
 
     @DeleteMapping("/{annotationId}")

backend/src/main/java/org/raddatz/familienarchiv/model/Document.java

@@ -39,6 +39,10 @@ public class Document {
     @Column(name = "content_type")
     private String contentType;
 
+    // SHA-256 hash of the uploaded file — used to link annotations to a file version
+    @Column(name = "file_hash", length = 64)
+    private String fileHash;
+
     // Originaler Dateiname beim Upload (z.B. "Brief_Oma_1940.pdf")
     @Column(name = "original_filename", nullable = false)
     @Schema(requiredMode = Schema.RequiredMode.REQUIRED)

backend/src/main/java/org/raddatz/familienarchiv/model/DocumentAnnotation.java

@@ -49,6 +49,9 @@ public class DocumentAnnotation {
     @Schema(requiredMode = Schema.RequiredMode.REQUIRED)
     private String color;
 
+    @Column(name = "file_hash", length = 64)
+    private String fileHash;
+
     @Column(name = "created_by")
     private UUID createdBy;
 

backend/src/main/java/org/raddatz/familienarchiv/service/AnnotationService.java

@@ -23,7 +23,7 @@ public class AnnotationService {
     }
 
     @Transactional
-    public DocumentAnnotation createAnnotation(UUID documentId, CreateAnnotationDTO dto, UUID userId) {
+    public DocumentAnnotation createAnnotation(UUID documentId, CreateAnnotationDTO dto, UUID userId, String fileHash) {
         List<DocumentAnnotation> existing =
                 annotationRepository.findByDocumentIdAndPageNumber(documentId, dto.getPageNumber());
 
@@ -41,6 +41,7 @@ public class AnnotationService {
                 .width(dto.getWidth())
                 .height(dto.getHeight())
                 .color(dto.getColor())
+                .fileHash(fileHash)
                 .createdBy(userId)
                 .build();
 

backend/src/main/java/org/raddatz/familienarchiv/service/DocumentService.java

@@ -64,10 +64,11 @@ public class DocumentService {
         }
 
         // 2. Delegate Storage to FileService
-        String s3Key = fileService.uploadFile(file, originalFilename);
+        FileService.UploadResult upload = fileService.uploadFile(file, originalFilename);
 
         // 3. Update Database
-        document.setFilePath(s3Key);
+        document.setFilePath(upload.s3Key());
+        document.setFileHash(upload.fileHash());
         document.setContentType(file.getContentType());
         if (document.getStatus() == DocumentStatus.PLACEHOLDER) {
             document.setStatus(DocumentStatus.UPLOADED);
@@ -120,8 +121,9 @@ public class DocumentService {
 
         // Datei
         if (file != null && !file.isEmpty()) {
-            String s3Key = fileService.uploadFile(file, file.getOriginalFilename());
+            FileService.UploadResult upload = fileService.uploadFile(file, file.getOriginalFilename());
-            doc.setFilePath(s3Key);
+            doc.setFilePath(upload.s3Key());
+            doc.setFileHash(upload.fileHash());
             doc.setContentType(file.getContentType());
             doc.setStatus(DocumentStatus.UPLOADED);
         }
@@ -170,12 +172,9 @@ public class DocumentService {
 
         // 4. Datei austauschen (nur wenn eine neue ausgewählt wurde)
         if (newFile != null && !newFile.isEmpty()) {
-            // Alte Datei könnte man hier theoretisch löschen (optional)
+            FileService.UploadResult upload = fileService.uploadFile(newFile, newFile.getOriginalFilename());
-
+            doc.setFilePath(upload.s3Key());
-            // Neue Datei hochladen
+            doc.setFileHash(upload.fileHash());
-            String s3Key = fileService.uploadFile(newFile, newFile.getOriginalFilename());
-
-            doc.setFilePath(s3Key);
             doc.setOriginalFilename(newFile.getOriginalFilename());
             doc.setContentType(newFile.getContentType());
             doc.setStatus(DocumentStatus.UPLOADED);

backend/src/main/java/org/raddatz/familienarchiv/service/FileService.java

@@ -13,6 +13,8 @@ import org.springframework.web.multipart.MultipartFile;
 import org.springframework.core.io.InputStreamResource;
 
 import java.io.IOException;
+import java.security.MessageDigest;
+import java.security.NoSuchAlgorithmException;
 import java.util.UUID;
 
 @Service
@@ -29,10 +31,14 @@ public class FileService {
     }
 
     /**
-     * Uploads a file to S3/MinIO and returns the generated object key.
+     * Uploads a file to S3/MinIO.
+     * Returns an {@link UploadResult} containing the S3 key and the SHA-256
+     * hash of the file content.  The hash is used to link annotations to the
+     * specific file version they were created against.
      */
-    public String uploadFile(MultipartFile file, String originalFilename) throws IOException {
+    public UploadResult uploadFile(MultipartFile file, String originalFilename) throws IOException {
-        // Generate secure unique path: "documents/UUID_filename"
+        byte[] bytes = file.getBytes();
+        String fileHash = sha256Hex(bytes);
         String s3Key = "documents/" + UUID.randomUUID() + "_" + originalFilename;
 
         try {
@@ -42,11 +48,10 @@ public class FileService {
                     .contentType(file.getContentType())
                     .build();
 
-            s3Client.putObject(putObjectRequest,
+            s3Client.putObject(putObjectRequest, RequestBody.fromBytes(bytes));
-                    RequestBody.fromInputStream(file.getInputStream(), file.getSize()));
 
-            log.info("Uploaded file to S3: {}", s3Key);
+            log.info("Uploaded file to S3: {} (hash={})", s3Key, fileHash);
-            return s3Key;
+            return new UploadResult(s3Key, fileHash);
         } catch (S3Exception e) {
             log.error("S3 Upload Error", e);
             throw new IOException("Failed to upload file to storage", e);
@@ -58,32 +63,52 @@ public class FileService {
      * Returns a wrapper containing the stream and content type.
      */
     public S3FileDownload downloadFile(String s3Key) {
-    try {
+        try {
-        GetObjectRequest getObjectRequest = GetObjectRequest.builder()
+            GetObjectRequest getObjectRequest = GetObjectRequest.builder()
-                .bucket(bucketName)
+                    .bucket(bucketName)
-                .key(s3Key)
+                    .key(s3Key)
-                .build();
+                    .build();
 
-        ResponseInputStream<GetObjectResponse> s3Object = s3Client.getObject(getObjectRequest);
+            ResponseInputStream<GetObjectResponse> s3Object = s3Client.getObject(getObjectRequest);
 
-        // Use whatever content type S3 has stored (set at upload time)
+            String contentType = s3Object.response().contentType();
-        String contentType = s3Object.response().contentType();
+            if (contentType == null || contentType.isBlank()) {
-        if (contentType == null || contentType.isBlank()) {
+                contentType = "application/octet-stream";
-            contentType = "application/octet-stream";
+            }
+
+            return new S3FileDownload(new InputStreamResource(s3Object), contentType);
+
+        } catch (NoSuchKeyException e) {
+            throw new StorageFileNotFoundException("File not found in storage: " + s3Key);
+        } catch (S3Exception e) {
+            throw new RuntimeException("Storage Error: " + e.getMessage());
         }
-
-        return new S3FileDownload(new InputStreamResource(s3Object), contentType);
-
-    } catch (NoSuchKeyException e) {
-        throw new StorageFileNotFoundException("File not found in storage: " + s3Key);
-    } catch (S3Exception e) {
-        throw new RuntimeException("Storage Error: " + e.getMessage());
     }
-}
+
-    // Helper Record to carry the stream and metadata back to the controller
+    // ─── private helpers ──────────────────────────────────────────────────────
+
+    private static String sha256Hex(byte[] bytes) {
+        try {
+            MessageDigest digest = MessageDigest.getInstance("SHA-256");
+            byte[] hash = digest.digest(bytes);
+            StringBuilder sb = new StringBuilder(64);
+            for (byte b : hash) {
+                sb.append(String.format("%02x", b));
+            }
+            return sb.toString();
+        } catch (NoSuchAlgorithmException e) {
+            throw new IllegalStateException("SHA-256 not available", e);
+        }
+    }
+
+    // ─── result types ─────────────────────────────────────────────────────────
+
+    /** Carries the S3 object key and the content hash back to the caller. */
+    public record UploadResult(String s3Key, String fileHash) {}
+
+    /** Carries the download stream and content type. */
     public record S3FileDownload(InputStreamResource resource, String contentType) {}
 
-    // Custom Exception
     public static class StorageFileNotFoundException extends RuntimeException {
         public StorageFileNotFoundException(String message) { super(message); }
     }

backend/src/main/resources/db/migration/V13__add_file_hash.sql

@@ -0,0 +1,7 @@
+-- Add content-based file hash to documents for annotation versioning
+ALTER TABLE documents
+    ADD COLUMN file_hash VARCHAR(64);
+
+-- Each annotation remembers which file version it was created against
+ALTER TABLE document_annotations
+    ADD COLUMN file_hash VARCHAR(64);

backend/src/test/java/org/raddatz/familienarchiv/controller/AnnotationControllerTest.java

@@ -4,10 +4,12 @@ import org.junit.jupiter.api.Test;
 import org.raddatz.familienarchiv.config.SecurityConfig;
 import org.raddatz.familienarchiv.exception.DomainException;
 import org.raddatz.familienarchiv.exception.ErrorCode;
+import org.raddatz.familienarchiv.model.Document;
 import org.raddatz.familienarchiv.model.DocumentAnnotation;
 import org.raddatz.familienarchiv.security.PermissionAspect;
 import org.raddatz.familienarchiv.service.AnnotationService;
 import org.raddatz.familienarchiv.service.CustomUserDetailsService;
+import org.raddatz.familienarchiv.service.DocumentService;
 import org.raddatz.familienarchiv.service.UserService;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.boot.autoconfigure.aop.AopAutoConfiguration;
@@ -36,6 +38,7 @@ class AnnotationControllerTest {
     @Autowired MockMvc mockMvc;
 
     @MockitoBean AnnotationService annotationService;
+    @MockitoBean DocumentService documentService;
     @MockitoBean UserService userService;
     @MockitoBean CustomUserDetailsService customUserDetailsService;
 
@@ -85,7 +88,8 @@ class AnnotationControllerTest {
         DocumentAnnotation saved = DocumentAnnotation.builder()
                 .id(UUID.randomUUID()).documentId(docId).pageNumber(1)
                 .x(0.1).y(0.1).width(0.2).height(0.2).color("#ff0000").build();
-        when(annotationService.createAnnotation(any(), any(), any())).thenReturn(saved);
+        when(documentService.getDocumentById(any())).thenReturn(Document.builder().build());
+        when(annotationService.createAnnotation(any(), any(), any(), any())).thenReturn(saved);
 
         mockMvc.perform(post("/api/documents/" + docId + "/annotations")
                         .contentType(MediaType.APPLICATION_JSON)
@@ -97,7 +101,8 @@ class AnnotationControllerTest {
     @Test
     @WithMockUser(authorities = "ANNOTATE_ALL")
     void createAnnotation_returns409_whenOverlap() throws Exception {
-        when(annotationService.createAnnotation(any(), any(), any()))
+        when(documentService.getDocumentById(any())).thenReturn(Document.builder().build());
+        when(annotationService.createAnnotation(any(), any(), any(), any()))
                 .thenThrow(DomainException.conflict(ErrorCode.ANNOTATION_OVERLAP, "Overlap"));
 
         mockMvc.perform(post("/api/documents/" + UUID.randomUUID() + "/annotations")

backend/src/test/java/org/raddatz/familienarchiv/service/AnnotationServiceTest.java

@@ -44,7 +44,7 @@ class AnnotationServiceTest {
         when(annotationRepository.findByDocumentIdAndPageNumber(docId, 1))
                 .thenReturn(List.of(existing));
 
-        assertThatThrownBy(() -> annotationService.createAnnotation(docId, dto, userId))
+        assertThatThrownBy(() -> annotationService.createAnnotation(docId, dto, userId, null))
                 .isInstanceOf(DomainException.class)
                 .satisfies(e -> assertThat(((DomainException) e).getStatus()).isEqualTo(CONFLICT));
 
@@ -63,7 +63,7 @@ class AnnotationServiceTest {
                 .x(0.0).y(0.0).width(0.05).height(0.05).color("#ff0000").createdBy(userId).build();
         when(annotationRepository.save(any())).thenReturn(saved);
 
-        DocumentAnnotation result = annotationService.createAnnotation(docId, dto, userId);
+        DocumentAnnotation result = annotationService.createAnnotation(docId, dto, userId, null);
 
         assertThat(result).isEqualTo(saved);
         verify(annotationRepository).save(any());
@@ -117,6 +117,35 @@ class AnnotationServiceTest {
         verify(annotationRepository).delete(annotation);
     }
 
+    @Test
+    void createAnnotation_setsFileHash_whenProvided() {
+        UUID docId = UUID.randomUUID();
+        UUID userId = UUID.randomUUID();
+        CreateAnnotationDTO dto = new CreateAnnotationDTO(1, 0.0, 0.0, 0.05, 0.05, "#ff0000");
+        String fileHash = "abc123";
+
+        when(annotationRepository.findByDocumentIdAndPageNumber(docId, 1)).thenReturn(List.of());
+        when(annotationRepository.save(any())).thenAnswer(inv -> inv.getArgument(0));
+
+        DocumentAnnotation result = annotationService.createAnnotation(docId, dto, userId, fileHash);
+
+        assertThat(result.getFileHash()).isEqualTo(fileHash);
+    }
+
+    @Test
+    void createAnnotation_setsNullFileHash_whenNoneProvided() {
+        UUID docId = UUID.randomUUID();
+        UUID userId = UUID.randomUUID();
+        CreateAnnotationDTO dto = new CreateAnnotationDTO(1, 0.0, 0.0, 0.05, 0.05, "#ff0000");
+
+        when(annotationRepository.findByDocumentIdAndPageNumber(docId, 1)).thenReturn(List.of());
+        when(annotationRepository.save(any())).thenAnswer(inv -> inv.getArgument(0));
+
+        DocumentAnnotation result = annotationService.createAnnotation(docId, dto, userId, null);
+
+        assertThat(result.getFileHash()).isNull();
+    }
+
     // ─── listAnnotations ──────────────────────────────────────────────────────
 
     @Test

backend/src/test/java/org/raddatz/familienarchiv/service/DocumentServiceTest.java

@@ -135,6 +135,48 @@ class DocumentServiceTest {
         assertThat(documentService.getDocumentsByReceiver(receiverId)).containsExactly(doc);
     }
 
+    // ─── file hash propagation ───────────────────────────────────────────────
+
+    @Test
+    void createDocument_setsFileHashFromUpload_whenFileProvided() throws Exception {
+        DocumentUpdateDTO dto = new DocumentUpdateDTO();
+        dto.setTitle("Doc");
+        org.springframework.mock.web.MockMultipartFile file =
+                new org.springframework.mock.web.MockMultipartFile("file", "scan.pdf", "application/pdf", new byte[]{1});
+        FileService.UploadResult uploadResult = new FileService.UploadResult("documents/uuid_scan.pdf", "deadbeef");
+
+        Document savedDoc = Document.builder().id(UUID.randomUUID()).title("Doc")
+                .originalFilename("scan.pdf").status(DocumentStatus.PLACEHOLDER).build();
+        when(documentRepository.save(any())).thenReturn(savedDoc);
+        when(documentRepository.findById(any())).thenReturn(Optional.of(savedDoc));
+        when(fileService.uploadFile(any(), any())).thenReturn(uploadResult);
+
+        documentService.createDocument(dto, file);
+
+        org.mockito.ArgumentCaptor<Document> captor = org.mockito.ArgumentCaptor.forClass(Document.class);
+        verify(documentRepository, atLeastOnce()).save(captor.capture());
+        assertThat(captor.getAllValues()).anySatisfy(d -> assertThat(d.getFileHash()).isEqualTo("deadbeef"));
+    }
+
+    @Test
+    void updateDocument_setsFileHashFromUpload_whenNewFileProvided() throws Exception {
+        UUID id = UUID.randomUUID();
+        Document existing = Document.builder()
+                .id(id).title("Alt").originalFilename("old.pdf")
+                .status(DocumentStatus.UPLOADED).build();
+        org.springframework.mock.web.MockMultipartFile newFile =
+                new org.springframework.mock.web.MockMultipartFile("file", "new.pdf", "application/pdf", new byte[]{2});
+        FileService.UploadResult uploadResult = new FileService.UploadResult("documents/uuid_new.pdf", "cafebabe");
+
+        when(documentRepository.findById(id)).thenReturn(Optional.of(existing));
+        when(fileService.uploadFile(any(), any())).thenReturn(uploadResult);
+        when(documentRepository.save(any())).thenReturn(existing);
+
+        documentService.updateDocument(id, new DocumentUpdateDTO(), newFile);
+
+        assertThat(existing.getFileHash()).isEqualTo("cafebabe");
+    }
+
     // ─── versioning ───────────────────────────────────────────────────────────
 
     @Test

backend/src/test/java/org/raddatz/familienarchiv/service/FileServiceTest.java

@@ -0,0 +1,85 @@
+package org.raddatz.familienarchiv.service;
+
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Test;
+import org.mockito.ArgumentCaptor;
+import org.springframework.mock.web.MockMultipartFile;
+import software.amazon.awssdk.core.sync.RequestBody;
+import software.amazon.awssdk.services.s3.S3Client;
+import software.amazon.awssdk.services.s3.model.PutObjectRequest;
+
+import java.io.IOException;
+import java.security.MessageDigest;
+import java.security.NoSuchAlgorithmException;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import static org.mockito.ArgumentMatchers.any;
+import static org.mockito.Mockito.*;
+
+class FileServiceTest {
+
+    private S3Client s3Client;
+    private FileService fileService;
+
+    @BeforeEach
+    void setUp() {
+        s3Client = mock(S3Client.class);
+        fileService = new FileService(s3Client, "test-bucket");
+    }
+
+    @Test
+    void uploadFile_returnsS3Key() throws IOException {
+        MockMultipartFile file = new MockMultipartFile(
+                "file", "test.pdf", "application/pdf", new byte[]{1, 2, 3});
+
+        FileService.UploadResult result = fileService.uploadFile(file, "test.pdf");
+
+        assertThat(result.s3Key()).startsWith("documents/");
+        assertThat(result.s3Key()).endsWith("_test.pdf");
+        verify(s3Client).putObject(any(PutObjectRequest.class), any(RequestBody.class));
+    }
+
+    @Test
+    void uploadFile_returnsCorrectSha256FileHash() throws IOException, NoSuchAlgorithmException {
+        byte[] content = "hello pdf content".getBytes();
+        MockMultipartFile file = new MockMultipartFile(
+                "file", "doc.pdf", "application/pdf", content);
+
+        FileService.UploadResult result = fileService.uploadFile(file, "doc.pdf");
+
+        // Compute expected hash independently
+        MessageDigest digest = MessageDigest.getInstance("SHA-256");
+        byte[] hashBytes = digest.digest(content);
+        StringBuilder expected = new StringBuilder();
+        for (byte b : hashBytes) {
+            expected.append(String.format("%02x", b));
+        }
+
+        assertThat(result.fileHash()).isEqualTo(expected.toString());
+    }
+
+    @Test
+    void uploadFile_differentContents_produceDifferentHashes() throws IOException {
+        MockMultipartFile file1 = new MockMultipartFile(
+                "f", "a.pdf", "application/pdf", new byte[]{1, 2, 3});
+        MockMultipartFile file2 = new MockMultipartFile(
+                "f", "b.pdf", "application/pdf", new byte[]{4, 5, 6});
+
+        FileService.UploadResult r1 = fileService.uploadFile(file1, "a.pdf");
+        FileService.UploadResult r2 = fileService.uploadFile(file2, "b.pdf");
+
+        assertThat(r1.fileHash()).isNotEqualTo(r2.fileHash());
+    }
+
+    @Test
+    void uploadFile_sameContents_produceSameHash() throws IOException {
+        byte[] content = new byte[]{10, 20, 30};
+        MockMultipartFile file1 = new MockMultipartFile("f", "x.pdf", "application/pdf", content);
+        MockMultipartFile file2 = new MockMultipartFile("f", "y.pdf", "application/pdf", content);
+
+        FileService.UploadResult r1 = fileService.uploadFile(file1, "x.pdf");
+        FileService.UploadResult r2 = fileService.uploadFile(file2, "y.pdf");
+
+        assertThat(r1.fileHash()).isEqualTo(r2.fileHash());
+    }
+}