Store Transcriptions in local cache

Depends on !67 (merged)

Closes #43 (closed)

arkindex_worker/worker.py

@@ -512,20 +512,25 @@ class ElementsWorker(BaseWorker):
 
         self.report.add_transcription(element.id)
 
-        # Store transcription in local cache
-        try:
-            to_insert = [
-                CachedTranscription(
-                    id=convert_str_uuid_to_hex(created["id"]),
-                    element_id=convert_str_uuid_to_hex(element.id),
-                    text=created["text"],
-                    confidence=created["confidence"],
-                    worker_version_id=convert_str_uuid_to_hex(self.worker_version_id),
+        if self.cache:
+            # Store transcription in local cache
+            try:
+                to_insert = [
+                    CachedTranscription(
+                        id=convert_str_uuid_to_hex(created["id"]),
+                        element_id=convert_str_uuid_to_hex(element.id),
+                        text=created["text"],
+                        confidence=created["confidence"],
+                        worker_version_id=convert_str_uuid_to_hex(
+                            self.worker_version_id
+                        ),
+                    )
+                ]
+                self.cache.insert("transcriptions", to_insert)
+            except sqlite3.IntegrityError as e:
+                logger.warning(
+                    f"Couldn't save created transcription in local cache: {e}"
                 )
-            ]
-            self.cache.insert("transcriptions", to_insert)
-        except sqlite3.IntegrityError as e:
-            logger.warning(f"Couldn't save created transcription in local cache: {e}")
 
     def create_classification(
         self, element, ml_class, confidence, high_confidence=False
@@ -676,27 +681,30 @@ class ElementsWorker(BaseWorker):
             },
         )
 
-        created_ids = []
-        elements_to_insert = []
-        transcriptions_to_insert = []
-        parent_id_hex = convert_str_uuid_to_hex(element.id)
-        worker_version_id_hex = convert_str_uuid_to_hex(self.worker_version_id)
-        for index, annotation in enumerate(annotations):
-            transcription = transcriptions[index]
-            element_id_hex = convert_str_uuid_to_hex(annotation["id"])
+        for annotation in annotations:
             if annotation["created"]:
                 logger.debug(
                     f"A sub_element of {element.id} with type {sub_element_type} was created during transcriptions bulk creation"
                 )
                 self.report.add_element(element.id, sub_element_type)
+            self.report.add_transcription(annotation["id"])
 
-                if annotation["id"] not in created_ids:
+        if self.cache:
+            # Store transcriptions and their associated element (if created) in local cache
+            created_ids = []
+            elements_to_insert = []
+            transcriptions_to_insert = []
+            parent_id_hex = convert_str_uuid_to_hex(element.id)
+            worker_version_id_hex = convert_str_uuid_to_hex(self.worker_version_id)
+            for index, annotation in enumerate(annotations):
+                transcription = transcriptions[index]
+                element_id_hex = convert_str_uuid_to_hex(annotation["id"])
+                if annotation["created"] and annotation["id"] not in created_ids:
                     # TODO: Retrieve real element_name through API
                     elements_to_insert.append(
                         CachedElement(
                             id=element_id_hex,
                             parent_id=parent_id_hex,
-                            name="test",
                             type=sub_element_type,
                             polygon=json.dumps(transcription["polygon"]),
                             worker_version_id=worker_version_id_hex,
@@ -704,25 +712,24 @@ class ElementsWorker(BaseWorker):
                     )
                     created_ids.append(annotation["id"])
 
-            self.report.add_transcription(annotation["id"])
-
-            transcriptions_to_insert.append(
-                CachedTranscription(
-                    # TODO: Retrieve real transcription_id through API
-                    id=convert_str_uuid_to_hex(uuid.uuid4()),
-                    element_id=element_id_hex,
-                    text=transcription["text"],
-                    confidence=transcription["score"],
-                    worker_version_id=worker_version_id_hex,
+                transcriptions_to_insert.append(
+                    CachedTranscription(
+                        # TODO: Retrieve real transcription_id through API
+                        id=convert_str_uuid_to_hex(uuid.uuid4()),
+                        element_id=element_id_hex,
+                        text=transcription["text"],
+                        confidence=transcription["score"],
+                        worker_version_id=worker_version_id_hex,
+                    )
                 )
-            )
 
-        # Store transcriptions and their associated element (if created) in local cache
-        try:
-            self.cache.insert("elements", elements_to_insert)
-            self.cache.insert("transcriptions", transcriptions_to_insert)
-        except sqlite3.IntegrityError as e:
-            logger.warning(f"Couldn't save created transcriptions in local cache: {e}")
+            try:
+                self.cache.insert("elements", elements_to_insert)
+                self.cache.insert("transcriptions", transcriptions_to_insert)
+            except sqlite3.IntegrityError as e:
+                logger.warning(
+                    f"Couldn't save created transcriptions in local cache: {e}"
+                )
 
         return annotations