sws-api-client 2.7.2__tar.gz → 2.7.3__tar.gz

{sws_api_client-2.7.2 → sws_api_client-2.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sws_api_client
-Version: 2.7.2
+Version: 2.7.3
 Summary: 
 License-File: LICENSE
 Author: Matteo

{sws_api_client-2.7.2 → sws_api_client-2.7.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sws_api_client"
-version = "2.7.2"
+version = "2.7.3"
 description = ""
 authors = ["Matteo <matteo.terrinoni@fao.org>", "Daniele <daniele.mansillo@fao.org>"]
 readme = "README.md"

{sws_api_client-2.7.2 → sws_api_client-2.7.3}/sws_api_client/data_retrieval.py

@@ -1,6 +1,6 @@
 import logging
 from time import time
-from typing import Callable, Dict, Any
+from typing import Callable, Dict, Any, Optional, TypedDict
 
 import pandas as pd
 import requests
@@ -12,6 +12,20 @@ from sws_api_client.tasks import TaskManager, PluginPayload
 logger = logging.getLogger(__name__)
 
 
+class GetDataMetadata(TypedDict):
+    retrieval_method: Optional[str]
+    task_id: Optional[str]
+    url: Optional[str]
+    execution_time_seconds: Optional[float]
+    error: Optional[str]
+
+
+class GetDataResult(TypedDict):
+    data: Optional[pd.DataFrame]
+    metadata: GetDataMetadata
+    success: bool
+
+
 class DataRetrieval:
     """Generic utility for data retrieval with fallback strategy.
 
@@ -36,11 +50,11 @@ class DataRetrieval:
         plugin_params: Dict[str, Any],
         s3_export: bool = False,
         cache_time: int = 0,
-    ) -> Dict[str, Any]:
+    ) -> GetDataResult:
         start_time = time()
         logger.debug("Starting generic data retrieval for %s %s", entity_type, entity_id)
 
-        metadata_info: Dict[str, Any] = {
+        metadata_info: GetDataMetadata = {
             "retrieval_method": None,
             "task_id": None,
             "url": None,
@@ -344,10 +358,46 @@ class DataRetrieval:
                             except Exception as e:
                                 logger.warning("Failed to parse CSV after plugin execution: %s", str(e))
 
-                    logger.info("Plugin task created successfully for %s %s", entity_type, entity_id)
-                    metadata_info["retrieval_method"] = "plugin_task"
+                    # Fallback: Check for task artifact
+                    output = task_response.info.output
+                    output_type = None
+                    if hasattr(output, 'type'):
+                        output_type = output.type
+                    elif isinstance(output, dict):
+                        output_type = output.get('type')
+
+                    if output_type == 'file':
+                        logger.debug("Checking task artifact for data...")
+                        try:
+                            artifact_url = tasks.get_task_artifact_url(task_id)
+                            resp = requests.get(artifact_url)
+                            if resp.status_code == 200:
+                                from io import StringIO
+                                df = pd.read_csv(StringIO(resp.text), dtype=str)
+                                for col in ['Value', 'value']:
+                                    if col in df.columns:
+                                        df[col] = pd.to_numeric(df[col], errors='coerce')
+                                
+                                logger.info(
+                                    "Retrieved data from task artifact (%s rows)",
+                                    len(df),
+                                )
+                                metadata_info["retrieval_method"] = "plugin_task_artifact"
+                                metadata_info["url"] = artifact_url
+                                metadata_info["execution_time_seconds"] = time() - start_time
+                                return {
+                                    "data": df,
+                                    "metadata": metadata_info,
+                                    "success": True,
+                                    "source": "task_artifact"
+                                }
+                        except Exception as e:
+                            logger.warning("Failed to retrieve/parse task artifact: %s", str(e))
+
+                    logger.error("Plugin task succeeded but no data could be retrieved for %s %s", entity_type, entity_id)
+                    metadata_info["error"] = "Task succeeded but data retrieval failed"
                     metadata_info["execution_time_seconds"] = time() - start_time
-                    return {"data": plugin_resp, "metadata": metadata_info, "success": True}
+                    return {"data": None, "metadata": metadata_info, "success": False}
 
                 logger.error(
                     "Plugin task failed for %s %s: %s",

{sws_api_client-2.7.2 → sws_api_client-2.7.3}/sws_api_client/datasets.py

@@ -12,7 +12,7 @@ from sws_api_client.flaglist import Flaglists
 from sws_api_client.generic_models import Code, Multilanguage
 from sws_api_client.sws_api_client import SwsApiClient
 from sws_api_client.s3 import S3
-from sws_api_client.data_retrieval import DataRetrieval
+from sws_api_client.data_retrieval import DataRetrieval, GetDataResult
 import pandas as pd
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
@@ -859,7 +859,7 @@ class Datasets:
         metadata_as_array: bool = False,
         cache_time: int = 0,
         plugin_name: str = "get_data",
-    ) -> Dict[str, Any]:
+    ) -> GetDataResult:
         """Retrieve dataset data using the shared DataRetrieval fallback strategy.
 
         Args:
@@ -884,7 +884,7 @@ class Datasets:
             plugin_name (str): Name of the plugin invoking this method. Defaults to "get_data".
 
         Returns:
-            Dict[str, Any]: The dataset data.
+            GetDataResult: The dataset data.
         """
 
         def sql_query_fn(force_s3: bool = False) -> Dict:

{sws_api_client-2.7.2 → sws_api_client-2.7.3}/sws_api_client/datatable.py

@@ -12,7 +12,7 @@ from typing import Literal
 from datetime import datetime
 from time import sleep
 from sws_api_client.s3 import S3
-from sws_api_client.data_retrieval import DataRetrieval
+from sws_api_client.data_retrieval import DataRetrieval, GetDataResult
 import json
 import pandas as pd
 import tempfile
@@ -382,7 +382,7 @@ class Datatables:
         s3_export: bool = False,
         cache_time: int = 0,
         plugin_name: str = "get_datatable_data",
-    ) -> Dict[str, Any]:
+    ) -> GetDataResult:
         """Retrieve datatable data using the shared DataRetrieval fallback strategy.
 
         Args:
@@ -398,7 +398,7 @@ class Datatables:
             plugin_name (str): Name of the plugin invoking this method. Defaults to "get_datatable_data".
 
         Returns:
-            Dict[str, Any]: The datatable data.
+            GetDataResult: The datatable data.
         """
 
         def sql_query_fn(force_s3: bool = False) -> Dict:

{sws_api_client-2.7.2 → sws_api_client-2.7.3}/sws_api_client/sessions.py

@@ -5,7 +5,7 @@ import pandas as pd
 from pydantic import BaseModel
 from sws_api_client.datasets import Datasets, ValueFilter, MetadataFilter, FlagsFilter, DimensionsProps
 from sws_api_client.sws_api_client import SwsApiClient
-from sws_api_client.data_retrieval import DataRetrieval
+from sws_api_client.data_retrieval import DataRetrieval, GetDataResult
 
 import logging
 
@@ -272,7 +272,7 @@ class Sessions:
         limit: Optional[int] = None,
         metadata_as_array: bool = False,
         cache_time: int = 0,
-    ) -> Dict:
+    ) -> GetDataResult:
         """Retrieve session data using the shared DataRetrieval fallback strategy.
         
         Args:
@@ -291,7 +291,7 @@ class Sessions:
             cache_time (int): Cache time in seconds. Defaults to 0.
 
         Returns:
-            Dict: The session data.
+            GetDataResult: The session data.
         """
         
         def sql_query_fn(force_s3: bool = False) -> Dict: