Add export option to LDAP client

.gitignore

@@ -142,3 +142,4 @@ cython_debug/
 # Development IDE
 .vscode/launch.json
 .running
+LDAP_export.json

agent.py

@@ -16,6 +16,7 @@ import time
 import glob
 import codecs
 import zipfile
+import copy
 
 
 class TimedCompressedRotatingFileHandler(logging.handlers.TimedRotatingFileHandler):
@@ -615,6 +616,89 @@ class VRWLDAP():
                         # It looks like this is taken care by the LDAP server
                         self.connection.modify(researcher_dn, {'groupMembership': [(MODIFY_DELETE, [group])]})
 
+    def export_studies(self):
+        """This will export all the existing studies that are created in the LDAP server. The starting point is `self.__RESOURCE_GROUPS_BASE` setting
+
+        Returns:
+            dict: A python dictionary with all the studies with the study ID as key
+
+        """
+        studies = {}
+        logger.debug(f'Exporting all studies in DN "{self.__RESOURCE_GROUPS_BASE}"')
+        # We are missing Faculty information here....
+        if self.connection.search(self.__RESOURCE_GROUPS_BASE, f'(ou=*)', attributes=['ou', 'description', ]):
+            entries = copy.deepcopy(self.connection.entries)
+            for entry in entries:
+                # Skip starting point... not sure why it is found in the list...
+                if entry.entry_dn == self.__RESOURCE_GROUPS_BASE:
+                    continue
+
+                dn = entry.ou.value.strip()
+                # But when using the description field, we get a better study name (I think)
+                study_name = entry.description.value.strip().replace('Researchgroup', '').strip()
+                studies[dn] = {
+                    'dn': dn,
+                    'name': study_name,
+                    'description': None if not entry.description else entry.description.value.strip(),
+                    'contributors': {}
+                }
+
+        return studies
+
+    def export_researchers(self, studies):
+        """Export all the existing researchers. And will update the studies with the correct researchers with their role and workspace
+
+        Args:
+            studies (dict): A dict of all the studies generated by `export_studies`
+
+        Returns:
+            tuple: Returns a tuple with two values. First is a list with all the researchers, the second is a list with all the studies
+        """
+        researchers = []
+        logger.debug(f'Exporting all researchers in DN "{self.__RESOURCE_MEMBERS_BASE}"')
+        # We are missing Faculty information here....
+        if self.connection.search(self.__RESOURCE_MEMBERS_BASE, f'(uid=*)', attributes=['sn', 'givenName', 'uid', 'mobile', 'employeeNumber', 'groupMembership']):
+            for entry in self.connection.entries:
+                uid = entry.uid.value.strip()
+                researchers.append({
+                    'uid': uid,
+                    'first_name': None if not entry.givenName else entry.givenName.value.strip(),
+                    'last_name': None if not entry.sn else entry.sn.value.strip(),
+                    'email_address': None if not entry.uid else entry.uid.value.strip(),
+                    'mobile': None if not entry.mobile else entry.mobile.value.strip(),
+                    'pnumber': None if not entry.employeeNumber else entry.employeeNumber.value.strip()
+                })
+
+                # Loop over group member ships to construct the contributors data
+                for group in entry.groupMembership:
+                    group = group.replace('cn=', '').split(',')[0].split(':')
+                    if len(group) < 2:
+                        continue
+
+                    group_id = group[0]
+                    if uid not in studies[group_id]['contributors']:
+                        studies[group_id]['contributors'][uid] = {
+                            'uid': uid,
+                            'role': 'Contributor',
+                            'workspace': ''
+                        }
+
+                    if group[1].lower() == 'ws' and len(group) == 4:
+                        studies[group_id]['contributors'][uid]['workspace'] = 'Premium' if 'large' == group[3].lower() else 'Basic'
+
+                    elif group[1].lower() == 'role' and len(group) == 3:
+                        studies[group_id]['contributors'][uid]['role'] = 'Administrator' if 'datamanager' == group[2].lower() else 'Contributor'
+
+        # convert study dict to list. Is less data and easier for the import later on.
+        studies_list = []
+        for study_data in studies.values():
+            studies_list.append(study_data)
+
+        return (researchers, studies_list)
+
+    def export(self):
+        return self.export_researchers(self.export_studies())
+
 
 class VRE_API_CLient():
     """This is the VRE API client. With this client you can easily get the latest VRW actions from the VRE API.

export.py

@@ -0,0 +1,32 @@
+from agent import WORKINGDIR, logger, VRWLDAP
+from dotenv import dotenv_values
+import json
+from pathlib import Path
+
+if __name__ == "__main__":
+    config = dotenv_values(f'{WORKINGDIR}/.env')
+
+    print('Start exporting data')
+
+    # Load LDAP client
+    ldap_client = VRWLDAP(config['LDAP_HOST'], int(config['LDAP_PORT']), config['LDAP_USER'], config['LDAP_PASS'], config['LDAP_SSL'], not config['LDAP_MANUAL_GROUPS'])
+    if not ldap_client.check_connection():
+        logger.error(f'Could not login to the LDAP server. Check connection credentials.')
+        quit()
+
+    # Get the data from the LDAP server
+    (researchers, studies) = ldap_client.export()
+
+    # Make a nice dict for JSON export saving
+    data = {
+        'researchers': researchers,
+        'studies': studies,
+    }
+
+    json_data = json.dumps(data, indent=2)
+
+    # Write data to file
+    export_file = Path('LDAP_export.json')
+    export_file.write_text(json_data)
+
+    print('Data exported to: LDAP_export.json')