From 44ff1efb1850ee5c903c44629d2d87e026b659c5 Mon Sep 17 00:00:00 2001
From: Kris Stanton <ksnimpact@gmail.com>
Date: Wed, 4 Dec 2024 11:23:28 -0600
Subject: [PATCH] WIP commit on the util for generating ORCA Input JSON #387

---
 utils/orca_input_generator/.python-version    |  1 +
 utils/orca_input_generator/config.json        | 38 +++++++++
 .../generate_orca_input.py                    | 77 +++++++++++++++++++
 3 files changed, 116 insertions(+)
 create mode 100644 utils/orca_input_generator/.python-version
 create mode 100644 utils/orca_input_generator/config.json
 create mode 100644 utils/orca_input_generator/generate_orca_input.py

diff --git a/utils/orca_input_generator/.python-version b/utils/orca_input_generator/.python-version
new file mode 100644
index 0000000..c6fa069
--- /dev/null
+++ b/utils/orca_input_generator/.python-version
@@ -0,0 +1 @@
+venv.3_10_8_validate_orca_backups
diff --git a/utils/orca_input_generator/config.json b/utils/orca_input_generator/config.json
new file mode 100644
index 0000000..df61eb9
--- /dev/null
+++ b/utils/orca_input_generator/config.json
@@ -0,0 +1,38 @@
+{
+	"restore_to__bucket_name":"csda-cumulus-kris-sbx7894-protected-7894",
+
+	"config": {
+		"buckets": {
+		  "protected": {
+		    "name": "csda-cumulus-kris-sbx7894-protected-7894",
+		    "type": "protected"
+		  },
+		  "internal": {
+		    "name": "csda-cumulus-kris-sbx7894-internal-7894",
+		    "type": "internal"
+		  },
+		  "private": {
+		    "name": "csda-cumulus-kris-sbx7894-private-7894",
+		    "type": "private"
+		  },
+		  "public": {
+		    "name": "csda-cumulus-kris-sbx7894-public-7894",
+		    "type": "public"
+		  },
+		  "orca_default": {
+		    "name": "csda-cumulus-cba-uat-orca-archive",
+		    "type": "orca"
+		  }
+		},
+		"fileBucketMaps": [
+		  {
+		    "regex": "^(\\d{8}_\\d{6}_.+)(?:_\\dB_.+|_thumb.*|_cmr[.]json|_metadata[.]json)$",
+		    "sampleFileName": "20160628_204526_1_0c74_3B_Analytic_DN_metadata.xml",
+		    "bucket": "protected"
+		  }
+		],
+		"s3MultipartChunksizeMb": 200,
+		"excludedFileExtensions": [],
+		"asyncOperationId": "e3d8b981-0da4-4cad-84c5-c12d2f1094bc"
+		}
+}
\ No newline at end of file
diff --git a/utils/orca_input_generator/generate_orca_input.py b/utils/orca_input_generator/generate_orca_input.py
new file mode 100644
index 0000000..4499d3a
--- /dev/null
+++ b/utils/orca_input_generator/generate_orca_input.py
@@ -0,0 +1,77 @@
+import sys
+import json
+from pprint import pprint
+
+# Resources:
+# https://github.com/NASA-IMPACT/csdap-cumulus/issues/387
+# https://github.com/NASA-IMPACT/csdap-cumulus/issues/279#issuecomment-1800344062
+
+# Settings
+SETTINGS__default_config_json = "config.json"
+
+print(f'generate_orca_input.py: STARTED')
+
+# JSON Loader
+def load_json_to_dict(file_path):
+    """
+    Loads a JSON file at the given path into a Python dictionary.
+    
+    Args:
+        file_path (str): The path to the JSON file. 
+    
+    Returns:
+        dict: The loaded data as a dictionary.
+    """
+    with open(file_path, 'r') as f:
+        data = json.load(f) 
+    return data 
+
+
+
+# Code to Actually Generate JSON Input for recovery Granules
+def generate_orca_recovery_json__v1(config_dict={}):
+    print(f'  generate_orca_recovery_json__v1: Started')
+    ret_dict = {}
+
+    ret_dict['payload'] = "TODO: Make an Object that goes here, it is a list of granules - May have to make this specific to the dataset or collection type"
+    ret_dict['config'] = config_dict['config']
+
+    print(f'  generate_orca_recovery_json__v1: Reached the End')
+    return ret_dict
+
+
+
+# Main Entry Point
+def main():
+    
+    if len(sys.argv) > 1:
+        input_config_json_file = sys.argv[1]
+    else:
+        input_config_json_file = SETTINGS__default_config_json
+
+    print(f'')
+    print(f'input_config_json_file: {input_config_json_file}')
+    print(f'')
+    #
+    # Load the Config Dictionary
+    print(f'Loading the Config Dictionary')
+    config_dict = load_json_to_dict(input_config_json_file)
+    print(f'config_dict: {config_dict}')
+    print(f'')
+
+    # Generate ORCA Recovery Input JSON from Config Dictonary
+    print(f'Generating the ORCA Recovery JSON')
+    orca_recoveery_json__v1 = generate_orca_recovery_json__v1(config_dict=config_dict)
+    print(f'orca_recoveery_json__v1: (Next Lines)')
+    pprint(orca_recoveery_json__v1)
+    print(f'')
+
+
+
+main()
+
+# Example usage:
+#data = load_json_to_dict("config.json") 
+#print(data) 
+
+print(f'generate_orca_input.py: Reached the End!')
\ No newline at end of file