wip troubleshoot change to stdout, configurable log

groups_import.py

@@ -142,7 +142,7 @@ def parse_csv_file(ctx):
     # Start processing the actual group data rows
     for line in lines:
         row_number += 1
-        rowdata, error = process_csv_line(line)
+        rowdata, error = process_csv_line(ctx, line)
 
         if error is None:
             extracted_data.append(rowdata)

tools/arb-update-resources.py

@@ -53,7 +53,7 @@ def parse_args():
 
 def parse_cs_values(input):
     """Parses a comma-separated list of key:value pairs as a dict."""
-    result = dict()
+    result = {}
     for kv_pair in input.split(","):
         if kv_pair == "":
             continue
@@ -96,7 +96,7 @@ def setup_session(irods_environment_config, ca_file="/etc/pki/tls/certs/chain.cr
                     'encryption_num_hash_rounds': 16,
                     'encryption_salt_size': 8,
                     'ssl_context': ssl_context}
-    settings = dict()
+    settings = {}
     settings.update(irods_environment_config)
     settings.update(ssl_settings)
     settings["password"] = password
@@ -160,8 +160,8 @@ def call_rule(session, rulename, params, number_outputs, rule_engine='irods_rule
         output=output_params,
         **re_config)
 
-    outArray = myrule.execute()
-    buf = outArray.MsParam_PI[0].inOutStruct.stdoutBuf.buf.decode(
+    out_array = myrule.execute()
+    buf = out_array.MsParam_PI[0].inOutStruct.stdoutBuf.buf.decode(
         'utf-8').splitlines()
 
     return buf[:number_outputs]
@@ -208,7 +208,7 @@ def main():
                 print("Updating misc resources ...")
             call_rule_update_misc(session)
     except NetworkException:
-        print("Could not connect to iRODS sever ...")
+        print("Could not connect to iRODS server ...")
 
 
 if __name__ == '__main__':

tools/troubleshoot-published-data.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+"""This script collects all published packages and checks that they have all the required info.
+
+Example:
+To check all published packages:
+python3 troubleshoot-published-data.py
+
+To check one specific package by name:
+python3 troubleshoot-published-data.py -p research-initial[1725262507]
+
+To put results into a json lines log file:
+python3 troubleshoot-published-data.py -l /etc/irods/yoda-ruleset/troubleshoot-pub-log.jsonl
+"""
+import argparse
+import subprocess
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(
+        prog="troubleshoot-published-data.py",
+        description=__doc__,
+        formatter_class=argparse.RawTextHelpFormatter)
+    parser.add_argument("-l", "--log-file", type=str, required=False,
+                        help="If write to json lines log file, location to write to")
+    parser.add_argument("-p", "--package", type=str, required=False,
+                        help="Troubleshoot a specific data package by name (default: troubleshoot all packages)")
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    rule_name = "/etc/irods/yoda-ruleset/tools/troubleshoot_data.r"
+    # rule_name = "rule_batch_troubleshoot_published_data_packages"
+    # TODO handle packages with spaces in the name
+    data_package = f"*data_package={args.package}"
+    log_loc = f"*log_loc={args.log_file if args.log_file else ''}"
+    subprocess.call(['irule', '-r', 'irods_rule_engine_plugin-python-instance', '-F',
+                    rule_name, data_package, log_loc])
+
+
+if __name__ == '__main__':
+    main()

tools/troubleshoot_data.r

@@ -2,7 +2,8 @@
 
 def main(rule_args, callback, rei):
     data_package = global_vars["*data_package"].strip('"')
-    callback.rule_batch_troubleshoot_published_data_packages(data_package)
+    log_loc = global_vars["*log_loc"].strip('"')
+    callback.rule_batch_troubleshoot_published_data_packages(data_package, log_loc)
 
-INPUT *data_package=all_published_packages
+INPUT *data_package="", *log_loc=""
 OUTPUT ruleExecOut