finishing image pipeline

Author: AhmadHAW

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
     hooks:
       - id: pyright
         name: "Pyright"
-        entry: bash -c 'ENV_NAME=dats source backend/_activate_current_env.sh && pyright'
+        entry: bash -c 'PYRIGHT_PYTHON_PYLANCE_VERSION=2024.10.1 ENV_NAME=dats source backend/_activate_current_env.sh && pyright'
         language: system
   - repo: https://github.com/pre-commit/mirrors-eslint
     rev: v9.11.0

backend/.env.example

@@ -16,7 +16,7 @@ JWT_SECRET=
 
 # Where to store uploaded files.
 # <path_to_dats_repo>/docker/backend_repo
-REPO_ROOT=/insert_path_to_dats_repo/docker/backend_repo
+SHARED_REPO_ROOT=/insert_path_to_dats_repo/docker/backend_repo
 
 # The system user is automatically created and owns automatically generated data.
 SYSTEM_USER_EMAIL="[email protected]"

backend/src/api/endpoints/import_.py

@@ -53,7 +53,7 @@ def start_import_codes_job(
         )
     user_id = authz_user.user.id
     filename = f"import_user_code_{user_id}_{proj_id}.csv"
-    filepath = repo._get_dst_path_for_temp_file(filename)
+    filepath = repo.get_dst_path_for_temp_file(filename)
     filepath = repo.store_uploaded_file(
         uploaded_file=uploaded_file, filepath=filepath, fn=filename
     )
@@ -90,7 +90,7 @@ def start_import_tags_job(
         )
     user_id = authz_user.user.id
     filename = f"import_tags_{user_id}_{proj_id}.csv"
-    filepath = repo._get_dst_path_for_temp_file(filename)
+    filepath = repo.get_dst_path_for_temp_file(filename)
     filepath = repo.store_uploaded_file(
         uploaded_file=uploaded_file, filepath=filepath, fn=filename
     )
@@ -129,7 +129,7 @@ def start_import_project_project_metadata_job(
         )
     user_id = authz_user.user.id
     filename = f"import_project_project_metadata_{proj_id}.csv"
-    filepath = repo._get_dst_path_for_temp_file(filename)
+    filepath = repo.get_dst_path_for_temp_file(filename)
     filepath = repo.store_uploaded_file(
         uploaded_file=uploaded_file, filepath=filepath, fn=filename
     )
@@ -166,7 +166,7 @@ def start_import_project_metadata_job(
     user_id = current_user.id
     random_temp_project_name = str(uuid.uuid4())
     filename = f"import_project_{random_temp_project_name}_for_user_{user_id}.json"
-    filepath = repo._get_dst_path_for_temp_file(filename)
+    filepath = repo.get_dst_path_for_temp_file(filename)
     filepath = repo.store_uploaded_file(
         uploaded_file=uploaded_file, filepath=filepath, fn=filename
     )
@@ -206,7 +206,7 @@ def start_import_project_job(
     user_id = current_user.id
     random_temp_project_name = str(uuid.uuid4())
     filename = f"import_project_{random_temp_project_name}_for_user_{user_id}.zip"
-    filepath = repo._get_dst_path_for_temp_file(filename)
+    filepath = repo.get_dst_path_for_temp_file(filename)
     filepath = repo.store_uploaded_file(
         uploaded_file=uploaded_file, filepath=filepath, fn=filename
     )

backend/src/app/core/data/dto/code.py

@@ -41,3 +41,14 @@ class CodeRead(CodeBaseDTO):
     updated: datetime = Field(description="Updated timestamp of the Code")
     is_system: bool = Field(description="Is the Code a system code")
     model_config = ConfigDict(from_attributes=True)
+
+
+# Properties for importing Codes
+class CodeImport(BaseModel):
+    name: str = Field(description="Name of the Code")
+    color: str = Field(description="Color of the Code")
+    description: str = Field(description="Description of the Code")
+    parent_name: Optional[str] = Field(
+        description="Name of the Parent Code", default=None
+    )
+    created: datetime = Field(description="Created timestamp of the Code")

backend/src/app/core/data/export/export_service.py

@@ -201,18 +201,26 @@ def __get_sdocs_metadata_for_export(
         sdoc_ids: Optional[List[int]] = None,
         sdocs: Optional[List[SourceDocumentRead]] = None,
     ) -> List[Dict[str, Any]]:
-        # TODO Flo: paging for too many docs
-        if sdocs is None:
-            if sdoc_ids is None:
+        if sdoc_ids is None:
+            if sdocs is None:
                 raise ValueError("Either IDs or DTOs must be not None")
-            sdocs = [
-                SourceDocumentRead.model_validate(sdoc)
-                for sdoc in crud_sdoc.read_by_ids(db=db, ids=sdoc_ids)
-            ]
+            sdoc_ids = list(map(lambda sdoc: sdoc.id, sdocs))
+
+        sdoc_orms = crud_sdoc.read_by_ids(db=db, ids=sdoc_ids)
+
+        if sdocs is None:
+            sdocs = [SourceDocumentRead.model_validate(sdoc) for sdoc in sdoc_orms]
+
+        sdoc_tags: Dict[int, List[DocumentTagORM]] = {sdoc.id: [] for sdoc in sdocs}
+        for sdoc_orm in sdoc_orms:
+            for tag in sdoc_orm.document_tags:
+                sdoc_tags[sdoc_orm.id].append(tag)
+
         exported_sdocs_metadata = []
+
         for sdoc in sdocs:
             sdoc_metadatas = crud_sdoc_meta.read_by_sdoc(db=db, sdoc_id=sdoc.id)
-            sdoc_tags = crud_project.read(db=db, id=sdoc.project_id).document_tags
+            logger.info(f"export sdoc tags: {sdoc_tags[sdoc.id]} for {sdoc.filename}")
             sdoc_metadata_dtos = [
                 SourceDocumentMetadataReadResolved.model_validate(sdoc_metadata)
                 for sdoc_metadata in sdoc_metadatas
@@ -228,7 +236,7 @@ def __get_sdocs_metadata_for_export(
                     "filename": sdoc.filename,
                     "doctype": sdoc.doctype,
                     "metadata": metadata_dict,
-                    "tags": [tag.name for tag in sdoc_tags],
+                    "tags": [tag.name for tag in sdoc_tags[sdoc.id]],
                 }
             )