From 61f24ee9b299941f0490e2d0d0e06aa3c4a55fb6 Mon Sep 17 00:00:00 2001
From: Pingu Carsti <ehbrecht@dkrz.de>
Date: Thu, 12 Oct 2023 16:37:15 +0200
Subject: [PATCH] use intake to get era5 catalog

---
 environment.yml                     |  5 +++++
 shearwater/processes/wps_cyclone.py | 24 +++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/environment.yml b/environment.yml
index dd8d389..c8189f8 100644
--- a/environment.yml
+++ b/environment.yml
@@ -9,5 +9,10 @@ dependencies:
 - jinja2
 - click
 - psutil
+- intake
+- intake-esm
+- pydantic<2
+- requests
+- aiohttp
 # tests
 - pytest
diff --git a/shearwater/processes/wps_cyclone.py b/shearwater/processes/wps_cyclone.py
index 59f6312..3a0e3f3 100644
--- a/shearwater/processes/wps_cyclone.py
+++ b/shearwater/processes/wps_cyclone.py
@@ -2,6 +2,8 @@
 from pywps.app.Common import Metadata
 from datetime import datetime
 
+import intake
+
 import logging
 LOGGER = logging.getLogger("PYWPS")
 
@@ -52,6 +54,26 @@ def __init__(self):
     @staticmethod
     def _handler(request, response):
         LOGGER.info("running cyclone ...")
-        response.outputs['output'].data = 'netcdf ' + request.inputs['model'][0].data
+
+        master_catalog=intake.open_catalog(["https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_catalog.yaml"])
+        # master_catalog = intake.open_catalog('/pool/data/Catalogs/dkrz_catalog.yaml')
+        era5_catalog = master_catalog['dkrz_era5_disk']
+
+        query = {
+            'era_id': 'ET',
+            'level_type':'surface',
+            'table_id': 128,
+            #'frequency':'hourly',
+            'code':34,
+            'dataType': 'an',
+            'validation_date': '2023-06-27',
+        }
+
+        my_catalog = era5_catalog.search(**query)
+        # my_catalog.df
+
+        era_path = my_catalog.df['uri'].iloc[0]
+        
+        response.outputs['output'].data = f'netcdf {era_path}'
         response.outputs['output_csv'].data = 'csv ' + request.inputs['model'][0].data
         return response