Add option to print log in JSON format

pyega3/libs/pretty_printing.py

@@ -1,16 +1,20 @@
 import logging
+import json
 
 from .utils import status_ok
 
 
-def pretty_print_authorized_datasets(datasets):
-    logging.info("Dataset ID")
-    logging.info("-----------------")
-    for dataset in datasets:
-        logging.info(dataset.id)
+def pretty_print_authorized_datasets(datasets, as_json):
+    if as_json:
+        logging.info(json.dumps([{"id": dataset.id for dataset in datasets}]))
+    else:
+        logging.info("Dataset ID")
+        logging.info("-----------------")
+        for dataset in datasets:
+            logging.info(dataset.id)
 
 
-def pretty_print_files_in_dataset(files):
+def pretty_print_files_in_dataset(files, as_json):
     """
     Print a table of files in authorized dataset from api call api_list_files_in_dataset
 
@@ -26,12 +30,22 @@ def pretty_print_files_in_dataset(files):
         }
 
     """
-    format_string = "{:15} {:6} {:12} {:36} {}"
 
-    logging.info(format_string.format("File ID", "Status", "Bytes", "Check sum", "File name"))
-    for file in files:
-        logging.info(format_string.format(file.id, status_ok(file.status), str(file.size),
-                                          file.unencrypted_checksum, file.display_name))
-
-    logging.info('-' * 80)
-    logging.info("Total dataset size = %.2f GB " % (sum(file.size for file in files) / (1024 * 1024 * 1024.0)))
+    if as_json:
+        logging.info(json.dumps([{
+            "id": file.id,
+            "status": file.status,
+            "bytes": file.size,
+            "checksum": file.unencrypted_checksum,
+            "name": file.display_name
+        } for file in files]))
+    else:
+        format_string = "{:15} {:6} {:12} {:36} {}"
+
+        logging.info(format_string.format("File ID", "Status", "Bytes", "Check sum", "File name"))
+        for file in files:
+            logging.info(format_string.format(file.id, status_ok(file.status), str(file.size),
+                                              file.unencrypted_checksum, file.display_name))
+
+        logging.info('-' * 80)
+        logging.info("Total dataset size = %.2f GB " % (sum(file.size for file in files) / (1024 * 1024 * 1024.0)))

pyega3/pyega3.py

@@ -36,6 +36,7 @@ def main():
     parser.add_argument("-t", "--test", action="store_true", help="Test user activated")
     parser.add_argument("-ms", "--max-slice-size", type=int, default=DataFile.DEFAULT_SLICE_SIZE,
                         help="Set maximum size for each slice in bytes (default: 100 MB)")
+    parser.add_argument("-j", "--json", action="store_true", help="Output data in JSON format instead of tables")
 
     subparsers = parser.add_subparsers(dest="subcommand", help="subcommands")
 
@@ -137,15 +138,15 @@ def main():
 
     if args.subcommand == "datasets":
         datasets = DataSet.list_authorized_datasets(data_client)
-        pretty_print_authorized_datasets(datasets)
+        pretty_print_authorized_datasets(datasets, args.json)
 
     if args.subcommand == "files":
         if args.identifier[3] != 'D':
             logging.error("Unrecognized identifier - please use EGAD accession for dataset requests")
             sys.exit()
         dataset = DataSet(data_client, args.identifier)
         files = dataset.list_files()
-        pretty_print_files_in_dataset(files)
+        pretty_print_files_in_dataset(files, args.json)
 
     elif args.subcommand == "fetch":
         genomic_range_args = (args.reference_name, args.reference_md5, args.start, args.end, args.format)

test/test_pretty_printing.py

@@ -1,10 +1,19 @@
+import json
+
 from pyega3.libs.data_file import DataFile
 from pyega3.libs.data_set import DataSet
 from pyega3.libs.pretty_printing import *
 
 
 def test_pretty_print_authorized_datasets(mock_data_client):
-    pretty_print_authorized_datasets([DataSet(mock_data_client, 'EGAD0123')])
+    pretty_print_authorized_datasets([DataSet(mock_data_client, 'EGAD0123')], False)
+
+
+def test_pretty_print_authorized_datasets_in_json(mock_data_client, caplog):
+    caplog.set_level(logging.INFO)
+    pretty_print_authorized_datasets([DataSet(mock_data_client, 'EGAD0123')], True)
+    assert len(caplog.messages) == 1
+    assert json.loads(caplog.messages[0]) == [{"id": "EGAD0123"}]
 
 
 def test_pretty_print_files_in_dataset(mock_data_client):
@@ -14,4 +23,25 @@ def test_pretty_print_files_in_dataset(mock_data_client):
                            size=0,
                            unencrypted_checksum="MD5SUM678901234567890123456789012",
                            status="available")]
-    pretty_print_files_in_dataset(test_reply)
+    pretty_print_files_in_dataset(test_reply, False)
+
+
+def test_pretty_print_files_in_dataset_in_json(mock_data_client, caplog):
+    caplog.set_level(logging.INFO)
+    test_reply = [DataFile(mock_data_client, "EGAF00001753747",
+                           display_file_name="EGAZ00001314035.bam.bai.cip",
+                           file_name="EGAZ00001314035.bam.bai.cip",
+                           size=0,
+                           unencrypted_checksum="MD5SUM678901234567890123456789012",
+                           status="available")]
+    pretty_print_files_in_dataset(test_reply, True)
+
+    assert len(caplog.messages) == 1
+
+    output_object = json.loads(caplog.messages[0])
+    assert len(output_object) == 1
+    assert output_object[0]["id"] == test_reply[0].id
+    assert output_object[0]["name"] == test_reply[0].display_name
+    assert output_object[0]["bytes"] == test_reply[0].size
+    assert output_object[0]["checksum"] == test_reply[0].unencrypted_checksum
+    assert output_object[0]["status"] == test_reply[0].status