feat!: upgrade pymongo

requirements/constraints.txt

@@ -34,7 +34,7 @@ django-simple-history==3.4.0
 
 # constrained in opaque_keys. migration guide here: https://pymongo.readthedocs.io/en/4.0/migrate-to-pymongo4.html
 # Major upgrade will be done in separate ticket.
-pymongo<4.0.0
+pymongo<4.4.1
 
 # greater version has breaking changes and requires some migration steps.
 django-webpack-loader==0.7.0

requirements/edx/base.txt

@@ -81,7 +81,7 @@ bridgekeeper==0.9
     # via -r requirements/edx/kernel.in
 camel-converter[pydantic]==3.1.2
     # via meilisearch
-celery==5.4.0
+celery==5.3.6
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/kernel.in
@@ -374,6 +374,10 @@ djangorestframework==3.14.0
     #   super-csv
 djangorestframework-xml==2.0.0
     # via edx-enterprise
+dnspython==2.6.1
+    # via
+    #   -r requirements/edx/paver.txt
+    #   pymongo
 done-xblock==2.3.0
     # via -r requirements/edx/bundled.in
 drf-jwt==1.19.2
@@ -534,7 +538,7 @@ enmerkar==0.7.1
     # via enmerkar-underscore
 enmerkar-underscore==2.3.0
     # via -r requirements/edx/kernel.in
-event-tracking==2.4.0
+event-tracking==2.4.1
     # via
     #   -r requirements/edx/kernel.in
     #   edx-completion
@@ -862,7 +866,7 @@ pylti1p3==2.0.0
     # via -r requirements/edx/kernel.in
 pymemcache==4.0.0
     # via -r requirements/edx/paver.txt
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/kernel.in

requirements/edx/development.txt

@@ -166,7 +166,7 @@ camel-converter[pydantic]==3.1.2
     #   -r requirements/edx/doc.txt
     #   -r requirements/edx/testing.txt
     #   meilisearch
-celery==5.4.0
+celery==5.3.6
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/doc.txt
@@ -612,8 +612,10 @@ djangorestframework-xml==2.0.0
     #   edx-enterprise
 dnspython==2.6.1
     # via
+    #   -r requirements/edx/doc.txt
     #   -r requirements/edx/testing.txt
     #   email-validator
+    #   pymongo
 docutils==0.21.2
     # via
     #   -r requirements/edx/doc.txt
@@ -851,7 +853,7 @@ enmerkar-underscore==2.3.0
     # via
     #   -r requirements/edx/doc.txt
     #   -r requirements/edx/testing.txt
-event-tracking==2.4.0
+event-tracking==2.4.1
     # via
     #   -r requirements/edx/doc.txt
     #   -r requirements/edx/testing.txt
@@ -1532,7 +1534,7 @@ pymemcache==4.0.0
     # via
     #   -r requirements/edx/doc.txt
     #   -r requirements/edx/testing.txt
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/doc.txt

requirements/edx/doc.txt

@@ -113,7 +113,7 @@ camel-converter[pydantic]==3.1.2
     # via
     #   -r requirements/edx/base.txt
     #   meilisearch
-celery==5.4.0
+celery==5.3.6
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/base.txt
@@ -438,6 +438,10 @@ djangorestframework-xml==2.0.0
     # via
     #   -r requirements/edx/base.txt
     #   edx-enterprise
+dnspython==2.6.1
+    # via
+    #   -r requirements/edx/base.txt
+    #   pymongo
 docutils==0.21.2
     # via
     #   pydata-sphinx-theme
@@ -612,7 +616,7 @@ enmerkar==0.7.1
     #   enmerkar-underscore
 enmerkar-underscore==2.3.0
     # via -r requirements/edx/base.txt
-event-tracking==2.4.0
+event-tracking==2.4.1
     # via
     #   -r requirements/edx/base.txt
     #   edx-completion
@@ -1023,7 +1027,7 @@ pylti1p3==2.0.0
     # via -r requirements/edx/base.txt
 pymemcache==4.0.0
     # via -r requirements/edx/base.txt
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/base.txt

requirements/edx/paver.txt

@@ -10,6 +10,8 @@ charset-normalizer==2.0.12
     # via
     #   -c requirements/edx/../constraints.txt
     #   requests
+dnspython==2.6.1
+    # via pymongo
 edx-opaque-keys==2.10.0
     # via -r requirements/edx/paver.in
 idna==3.7
@@ -36,7 +38,7 @@ psutil==6.0.0
     # via -r requirements/edx/paver.in
 pymemcache==4.0.0
     # via -r requirements/edx/paver.in
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/paver.in

requirements/edx/testing.txt

@@ -118,7 +118,7 @@ camel-converter[pydantic]==3.1.2
     # via
     #   -r requirements/edx/base.txt
     #   meilisearch
-celery==5.4.0
+celery==5.3.6
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/base.txt
@@ -474,7 +474,10 @@ djangorestframework-xml==2.0.0
     #   -r requirements/edx/base.txt
     #   edx-enterprise
 dnspython==2.6.1
-    # via email-validator
+    # via
+    #   -r requirements/edx/base.txt
+    #   email-validator
+    #   pymongo
 done-xblock==2.3.0
     # via -r requirements/edx/base.txt
 drf-jwt==1.19.2
@@ -648,7 +651,7 @@ enmerkar==0.7.1
     #   enmerkar-underscore
 enmerkar-underscore==2.3.0
     # via -r requirements/edx/base.txt
-event-tracking==2.4.0
+event-tracking==2.4.1
     # via
     #   -r requirements/edx/base.txt
     #   edx-completion
@@ -1138,7 +1141,7 @@ pylti1p3==2.0.0
     # via -r requirements/edx/base.txt
 pymemcache==4.0.0
     # via -r requirements/edx/base.txt
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -c requirements/edx/../constraints.txt
     #   -r requirements/edx/base.txt

scripts/structures_pruning/requirements/base.txt

@@ -11,11 +11,13 @@ click==8.1.6
     #   click-log
 click-log==0.4.0
     # via -r scripts/structures_pruning/requirements/base.in
+dnspython==2.6.1
+    # via pymongo
 edx-opaque-keys==2.10.0
     # via -r scripts/structures_pruning/requirements/base.in
 pbr==6.0.0
     # via stevedore
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -c scripts/structures_pruning/requirements/../../../requirements/constraints.txt
     #   -r scripts/structures_pruning/requirements/base.in

scripts/structures_pruning/requirements/testing.txt

@@ -12,6 +12,10 @@ click-log==0.4.0
     # via -r scripts/structures_pruning/requirements/base.txt
 ddt==1.7.2
     # via -r scripts/structures_pruning/requirements/testing.in
+dnspython==2.6.1
+    # via
+    #   -r scripts/structures_pruning/requirements/base.txt
+    #   pymongo
 edx-opaque-keys==2.10.0
     # via -r scripts/structures_pruning/requirements/base.txt
 iniconfig==2.0.0
@@ -24,7 +28,7 @@ pbr==6.0.0
     #   stevedore
 pluggy==1.5.0
     # via pytest
-pymongo==3.13.0
+pymongo==4.4.0
     # via
     #   -r scripts/structures_pruning/requirements/base.txt
     #   edx-opaque-keys

scripts/user_retirement/requirements/base.txt

@@ -83,7 +83,7 @@ lxml==4.9.4
     #   zeep
 more-itertools==10.3.0
     # via simple-salesforce
-newrelic==9.12.0
+
     # via edx-django-utils
 pbr==6.0.0
     # via stevedore

scripts/user_retirement/requirements/testing.txt

@@ -132,7 +132,7 @@ more-itertools==10.3.0
     #   simple-salesforce
 moto==4.2.14
     # via -r scripts/user_retirement/requirements/testing.in
-newrelic==9.12.0
+
     # via
     #   -r scripts/user_retirement/requirements/base.txt
     #   edx-django-utils

xmodule/contentstore/mongo.py

@@ -3,6 +3,7 @@
 """
 
 
+import hashlib
 import json
 import os
 
@@ -40,23 +41,55 @@ def __init__(
         # GridFS will throw an exception if the Database is wrapped in a MongoProxy. So don't wrap it.
         # The appropriate methods below are marked as autoretry_read - those methods will handle
         # the AutoReconnect errors.
-        proxy = False
-        mongo_db = connect_to_mongodb(
-            db, host,
-            port=port, tz_aware=tz_aware, user=user, password=password, proxy=proxy, **kwargs
-        )
+        self.connection_params = {
+            'db': db,
+            'host': host,
+            'port': port,
+            'tz_aware': tz_aware,
+            'user': user,
+            'password': password,
+            'proxy': False,
+            **kwargs
+        }
+        self.bucket = bucket
+        self.do_connection()
+
+    def do_connection(self):
+        """
+        Connects to mongodb.
+        """
+        mongo_db = connect_to_mongodb(**self.connection_params)
 
-        self.fs = gridfs.GridFS(mongo_db, bucket)  # pylint: disable=invalid-name
+        self.fs = gridfs.GridFS(mongo_db, self.bucket)  # pylint: disable=invalid-name
 
-        self.fs_files = mongo_db[bucket + ".files"]  # the underlying collection GridFS uses
-        self.chunks = mongo_db[bucket + ".chunks"]
+        self.fs_files = mongo_db[self.bucket + ".files"]  # the underlying collection GridFS uses
+        self.chunks = mongo_db[self.bucket + ".chunks"]
 
     def close_connections(self):
         """
         Closes any open connections to the underlying databases
         """
         self.fs_files.database.client.close()
 
+    def ensure_connection(self):
+        """
+        Ensure that mongodb connection is open.
+        """
+        if self.check_connection():
+            return
+        self.do_connection()
+
+    def check_connection(self):
+        """
+        Check if mongodb connection is open or not.
+        """
+        connection = self.fs_files.database.client
+        try:
+            connection.admin.command('ping')
+            return True
+        except pymongo.errors.InvalidOperation:
+            return False
+
     def _drop_database(self, database=True, collections=True, connections=True):
         """
         A destructive operation to drop the underlying database and close all connections.
@@ -69,8 +102,8 @@ def _drop_database(self, database=True, collections=True, connections=True):
 
         If connections is True, then close the connection to the database as well.
         """
+        self.ensure_connection()
         connection = self.fs_files.database.client
-
         if database:
             connection.drop_database(self.fs_files.database.name)
         elif collections:
@@ -103,16 +136,22 @@ def save(self, content):
             # but many more objects have this in python3 and shouldn't be using the chunking logic. For string and
             # byte streams we write them directly to gridfs and convert them to byetarrys if necessary.
             if hasattr(content.data, '__iter__') and not isinstance(content.data, (bytes, (str,))):
+                custom_md5 = hashlib.md5()
                 for chunk in content.data:
                     fp.write(chunk)
+                    custom_md5.update(chunk)
+                fp.custom_md5 = custom_md5.hexdigest()
             else:
                 # Ideally we could just ensure that we don't get strings in here and only byte streams
                 # but being confident of that wolud be a lot more work than we have time for so we just
                 # handle both cases here.
                 if isinstance(content.data, str):
-                    fp.write(content.data.encode('utf-8'))
+                    encoded_data = content.data.encode('utf-8')
+                    fp.write(encoded_data)
+                    fp.custom_md5 = hashlib.md5(encoded_data).hexdigest()
                 else:
                     fp.write(content.data)
+                    fp.custom_md5 = hashlib.md5(content.data).hexdigest()
 
         return content
 
@@ -142,12 +181,13 @@ def find(self, location, throw_on_not_found=True, as_stream=False):  # lint-amne
                         'thumbnail',
                         thumbnail_location[4]
                     )
+
                 return StaticContentStream(
                     location, fp.displayname, fp.content_type, fp, last_modified_at=fp.uploadDate,
                     thumbnail_location=thumbnail_location,
                     import_path=getattr(fp, 'import_path', None),
                     length=fp.length, locked=getattr(fp, 'locked', False),
-                    content_digest=getattr(fp, 'md5', None),
+                    content_digest=getattr(fp, 'custom_md5', None),
                 )
             else:
                 with self.fs.get(content_id) as fp:
@@ -161,12 +201,13 @@ def find(self, location, throw_on_not_found=True, as_stream=False):  # lint-amne
                             'thumbnail',
                             thumbnail_location[4]
                         )
+
                     return StaticContent(
                         location, fp.displayname, fp.content_type, fp.read(), last_modified_at=fp.uploadDate,
                         thumbnail_location=thumbnail_location,
                         import_path=getattr(fp, 'import_path', None),
                         length=fp.length, locked=getattr(fp, 'locked', False),
-                        content_digest=getattr(fp, 'md5', None),
+                        content_digest=getattr(fp, 'custom_md5', None),
                     )
         except NoFile:
             if throw_on_not_found:  # lint-amnesty, pylint: disable=no-else-raise