From 98f9a3e5cbe43a15dd857c5fe88daf07a1e8e933 Mon Sep 17 00:00:00 2001
From: Simon Grasse <s.grasse@fz-juelich.de>
Date: Wed, 10 Jan 2024 14:42:06 +0100
Subject: [PATCH] add: Subclass for archiving query results as zipfiles
---
toargridding/toar_rest_client.py | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/toargridding/toar_rest_client.py b/toargridding/toar_rest_client.py
index 28fb9fc..ec51f85 100644
--- a/toargridding/toar_rest_client.py
+++ b/toargridding/toar_rest_client.py
@@ -4,6 +4,7 @@ from zipfile import ZipFile
from dataclasses import dataclass, asdict
from contextlib import contextmanager
import json
+from pathlib import Path
import requests
import pandas as pd
@@ -180,3 +181,32 @@ class AnalysisService:
with zip_file.open(f"{data_file}.csv") as f:
s_stream = io.StringIO(f.read().decode("utf-8"))
return pd.read_csv(s_stream, comment="#", index_col=0)
+
+
+class AnalysisServiceDownload(AnalysisService):
+ def __init__(
+ self, status_endpoint, cache_dir, sample_dir: Path, use_downloaded=True
+ ):
+ super().__init__(status_endpoint, cache_dir)
+ self.sample_dir = sample_dir
+ self.use_downloaded = use_downloaded
+
+ def get_timeseries_and_metadata(self, metadata: Metadata):
+ filename = self.sample_dir / self.get_sample_file_name(metadata)
+ query_options = QueryOptions.from_metadata(metadata)
+ needs_fresh_download = (not self.use_downloaded) or (not filename.is_file())
+
+ if needs_fresh_download:
+ content = self.connection.get(query_options)
+ with open(filename, "w+b") as downloaded_file:
+ downloaded_file.write()
+
+ with open(filename, "r+b") as data_file:
+ content = data_file.read()
+
+ timeseries, timeseries_metadata = self.load_data(content, metadata)
+ return timeseries, timeseries_metadata
+
+ @staticmethod
+ def get_sample_file_name(metadata: Metadata):
+ return f"data/{metadata.statistic}_{metadata.time.sampling}_{metadata.time.start.date()}_{metadata.time.end.date()}.zip"
--
GitLab