YDA-5600 create group lifecycle management report

README.md

@@ -328,6 +328,23 @@ List of columns if --by-extension is enabled:
 4. Extension
 5. Name of collection
 
+### yreport\_grouplifecycle
+
+```
+usage: yreport_grouplifecycle [-h] [-q] [-y {1.7,1.8,1.9}]
+
+Generates a list of groups, along with their creation date, expiration date
+(if available), as well as whether the research and vault compartment contain
+any collections or data objects .
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -q, --quasi-xml       Enable Quasi-XML parser in order to be able to parse
+                        characters not supported by regular XML parser
+  -y {1.7,1.8,1.9}, --yoda-version {1.7,1.8,1.9}
+                        Override Yoda version on the server
+```
+
 ### yreport\_intake
 
 Prints an intake collection report. This report is only relevant for environments

setup.py

@@ -20,6 +20,7 @@
         'console_scripts': [
             'yreport_dataobjectspercollection= yclienttools.reportdoc:entry',
             'yreport_collectionsize= yclienttools.reportsize:entry',
+            'yreport_grouplifecycle= yclienttools.reportgrouplifecycle:entry',
             'yreport_intake= yclienttools.reportintake:entry',
             'yreport_linecount= yclienttools.reportlinecount:entry',
             'ycleanup_files= yclienttools.cleanupfiles:entry',

yclienttools/reportgrouplifecycle.py

@@ -0,0 +1,129 @@
+'''Generates a list of groups, along with their creation date, expiration date (if available),
+   as well as whether the research and vault compartment contain any collections or data objects .'''
+
+import argparse
+import csv
+import itertools
+import sys
+
+from irods.column import Like
+from irods.message import (XML_Parser_Type, ET)
+from irods.models import Collection, DataObject, User
+from yclienttools import common_args, common_config
+from yclienttools import session as s
+
+
+def entry():
+    '''Entry point'''
+    try:
+        args = _get_args()
+        yoda_version = args.yoda_version if args.yoda_version is not None else common_config.get_default_yoda_version()
+        session = s.setup_session(yoda_version)
+        if args.quasi_xml:
+            ET(XML_Parser_Type.QUASI_XML, session.server_version)
+        report_groups_lifecycle(args, session)
+        session.cleanup()
+
+    except KeyboardInterrupt:
+        print("Script interrupted by user.\n", file=sys.stderr)
+
+
+def _get_args():
+    '''Parse command line arguments'''
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("-q", "--quasi-xml", default=False, action='store_true',
+                        help='Enable Quasi-XML parser in order to be able to parse characters not supported by regular XML parser')
+    common_args.add_default_args(parser)
+    return parser.parse_args()
+
+
+def _get_group_attributes(session, group_name):
+    """Retrieves a dictionary of attribute-values of group metadata.
+       This assumes attribute names are unique.
+    """
+    relevant_attributes = {"category", "subcategory", "expiration_date"}
+    result = dict()
+    group_objects = list(session.query(User).filter(
+        User.name == group_name).filter(
+        User.type == "rodsgroup").get_results())
+
+    if len(group_objects) > 0:
+        for group_object in group_objects:
+            obj = session.users.get(group_object[User.name])
+            avus = obj.metadata.items()
+            for avu in avus:
+                if avu.name in relevant_attributes:
+                    result[avu.name] = avu.value
+
+    return result
+
+
+def _group_research_has_data(session, group_name):
+    """Returns boolean that indicates whether the research compartment of
+       the group has any data (i.e. data objects or subcollections).
+       if the group has no research department, None is returned.
+    """
+    research_collection = f"/{session.zone}/home/{group_name}"
+    return _collection_has_data(session, research_collection)
+
+
+def _group_vault_has_data(session, group_name):
+    """Returns boolean that indicates whether the vault compartment of
+       the group has any data (i.e. data objects or subcollections).
+       If the group has no vault compartment, None is returned.
+    """
+    vault_collection = f"/{session.zone}/home/{group_name}".replace(
+        "research-", "vault-", 1)
+    return _collection_has_data(session, vault_collection)
+
+
+def _collection_has_data(session, coll_name):
+    root_data_objects = session.query(Collection.name, DataObject.name).filter(
+        Collection.name == coll_name).get_results()
+    sub_data_objects = session.query(Collection.name, DataObject.name).filter(
+        Like(Collection.name, coll_name + "/%")).get_results()
+    sub_data_collections = session.query(Collection.name).filter(
+        Like(Collection.name, coll_name + "/%")).get_results()
+    return len(list(itertools.chain(root_data_objects,
+                                    sub_data_objects,
+                                    sub_data_collections)))
+
+
+def _get_group_creation_date(session, group_name):
+    create_times = list(session.query(
+        User.create_time).filter(
+        User.name == group_name).get_results())
+    return create_times[0][User.create_time] if len(create_times) else None
+
+
+def _get_research_groups_list(session):
+    groups = session.query(User).filter(User.type == 'rodsgroup').get_results()
+    return [x[User.name]
+            for x in groups if x[User.name].startswith("research-")]
+
+
+def report_groups_lifecycle(args, session):
+    output = csv.writer(sys.stdout, delimiter=',')
+    output.writerow(["Group name", "Category", "Subcategory", "Creation date", "Expiration date",
+                     "Has research data", "Has vault data"])
+
+    def _has_data_to_string(value):
+        if value is None:
+            return "N/A"
+        else:
+            return "yes" if value else "no"
+
+    for group in sorted(_get_research_groups_list(session)):
+        attributes = _get_group_attributes(session, group)
+        category = attributes.get("category", "no category")
+        subcategory = attributes.get("subcategory", "no subcategory")
+        creation_date = _get_group_creation_date(session, group)
+        creation_date_str = creation_date.strftime(
+            "%Y-%m-%d") if creation_date is not None else "N/A"
+        expiration_date = attributes.get("expiration_date", "N/A")
+        research_has_data = _has_data_to_string(
+            _group_research_has_data(session, group))
+        vault_has_data = _has_data_to_string(
+            _group_vault_has_data(session, group))
+        output.writerow([group, category, subcategory, creation_date_str, expiration_date,
+                         research_has_data, vault_has_data])