[PRMP-990] Add S3 version id support

Author: adamwhitingnhs

lambdas/models/document_reference.py

@@ -126,7 +126,7 @@ class DocumentReference(BaseModel):
     raw_request: str | None = None
     s3_bucket_name: str = Field(exclude=True, default=None)
     s3_file_key: str = Field(default=None)
-    s3_version_id: Optional[str] = Field(default=None, exclude=True)
+    s3_version_id: Optional[str] = Field(default=None, alias="S3VersionID")
     s3_upload_key: str = Field(default=None, exclude=True)
     status: Literal["current", "superseded", "entered-in-error"] = Field(
         default="current"

lambdas/repositories/bulk_upload/bulk_upload_s3_repository.py

@@ -68,8 +68,8 @@ def check_virus_result(
             f"Verified that all documents for patient {staging_metadata.nhs_number} are clean."
         )
 
-    def copy_to_lg_bucket(self, source_file_key: str, dest_file_key: str):
-        self.s3_repository.copy_across_bucket(
+    def copy_to_lg_bucket(self, source_file_key: str, dest_file_key: str): 
+        result = self.s3_repository.copy_across_bucket(
             source_bucket=self.staging_bucket_name,
             source_file_key=source_file_key,
             dest_bucket=self.lg_bucket_name,
@@ -78,6 +78,8 @@ def copy_to_lg_bucket(self, source_file_key: str, dest_file_key: str):
         self.source_bucket_files_in_transaction.append(source_file_key)
         self.dest_bucket_files_in_transaction.append(dest_file_key)
 
+        return result
+
     def remove_ingested_file_from_source_bucket(self):
         for source_file_key in self.source_bucket_files_in_transaction:
             self.s3_repository.delete_object(

lambdas/services/bulk_upload_service.py

@@ -363,11 +363,13 @@ def create_lg_records_and_copy_files(
             source_file_key = self.file_path_cache[file_metadata.file_path]
             dest_file_key = document_reference.s3_file_key
 
-            self.bulk_upload_s3_repository.copy_to_lg_bucket(
+            copy_result = self.bulk_upload_s3_repository.copy_to_lg_bucket(
                 source_file_key=source_file_key, dest_file_key=dest_file_key
             )
             s3_bucket_name = self.bulk_upload_s3_repository.lg_bucket_name
 
+            document_reference.s3_version_id = copy_result.get("VersionId")
+
             document_reference.file_size = (
                 self.bulk_upload_s3_repository.s3_repository.get_file_size(
                     s3_bucket_name=s3_bucket_name, object_key=dest_file_key

lambdas/services/pdf_stitching_service.py

@@ -101,6 +101,7 @@ def process_message(self, stitching_message: PdfStitchingSqsMessage):
                 stitch_file_size=sys.getsizeof(stitching_data_stream),
             )
             self.upload_stitched_file(stitching_data_stream=stitching_data_stream)
+            self.update_stitched_reference()
             self.migrate_multipart_references()
             self.write_stitching_reference()
             self.publish_nrl_message(
@@ -129,6 +130,12 @@ def create_stitched_reference(
             deep=True,
         )
 
+    def update_stitched_reference(self):
+        self.stitched_reference.s3_version_id = self.s3_service.get_head_object(
+            self.target_bucket, 
+            self.stitched_reference.s3_file_key
+        ).get("VersionId")
+
     def process_stitching(self, s3_object_keys: list[str]) -> BytesIO:
         pdf_writer = PdfWriter()
 

lambdas/services/upload_document_reference_service.py

@@ -229,6 +229,7 @@ def _finalize_and_supersede_with_transaction(self, new_document: DocumentReferen
                     "file_size",
                     "uploaded",
                     "uploading",
+                    "s3_version_id",
                 },
             )