Create and use de-identified research databases. Preprocess, extract text, anonymise/de-identify, link, apply natural language processing, query for research, manage consent for contact.
Doesn't always happen, but it looks like the global research_database_info = ResearchDatabaseInfo() in research_db_info.py is flawed because it's global:
2023-10-08 14:32:15.366 [p3176044.t140577329673792] crate_anon.crateweb.research.research_db_info:INFO: Fetching/caching database structure (for database '', schema 'anonymous_output')...
2023-10-08 14:32:15.377 [p3176044.t140577795391488] crate_anon.crateweb.research.research_db_info:INFO: Fetching/caching database structure (for database '', schema 'anonymous_output')...
Exception in thread django-main-thread:
Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/autoreload.py", line 64, in wrapper
fn(*args, **kwargs)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/core/management/commands/runserver.py", line 118, in inner_run
self.check(display_num_errors=True)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/core/management/base.py", line 419, in check
all_issues = checks.run_checks(
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/core/checks/registry.py", line 76, in run_checks
new_errors = check(app_configs=app_configs, databases=databases)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/core/checks/urls.py", line 40, in check_url_namespaces_unique
all_namespaces = _load_all_namespaces(resolver)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/core/checks/urls.py", line 57, in _load_all_namespaces
url_patterns = getattr(resolver, 'url_patterns', [])
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/functional.py", line 48, in __get__
res = instance.__dict__[self.name] = self.func(instance)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/urls/resolvers.py", line 602, in url_patterns
patterns = getattr(self.urlconf_module, "urlpatterns", self.urlconf_module)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/functional.py", line 48, in __get__
res = instance.__dict__[self.name] = self.func(instance)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/urls/resolvers.py", line 595, in urlconf_module
return import_module(self.urlconf_name)
File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 688, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 883, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "/home/rudolf/Documents/code/crate/crate_anon/crateweb/config/urls.py", line 87, in <module>
research_database_info.get_colinfolist()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/cardinal_pythonlib/django/function_cache.py", line 176, in wrapper
func_result = fn(*args, **kwargs)
File "/home/rudolf/Documents/code/crate/crate_anon/crateweb/research/research_db_info.py", line 1370, in get_colinfolist
colinfolist.extend(dbi.colinfolist)
File "/home/rudolf/Documents/code/crate/crate_anon/crateweb/research/research_db_info.py", line 419, in colinfolist
ColumnInfo(**d) for d in self.schema_infodictlist
File "/home/rudolf/Documents/code/crate/crate_anon/crateweb/research/research_db_info.py", line 406, in schema_infodictlist
self._schema_infodictlist = self.get_schema_infodictlist(
File "/home/rudolf/Documents/code/crate/crate_anon/crateweb/research/research_db_info.py", line 918, in get_schema_infodictlist
cursor = connection.cursor()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/asyncio.py", line 33, in inner
return func(*args, **kwargs)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 259, in cursor
return self._cursor()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 235, in _cursor
self.ensure_connection()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/asyncio.py", line 33, in inner
return func(*args, **kwargs)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 219, in ensure_connection
self.connect()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/asyncio.py", line 33, in inner
return func(*args, **kwargs)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 202, in connect
self.init_connection_state()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/mysql/base.py", line 245, in init_connection_state
if self.features.is_sql_auto_is_null_enabled:
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/functional.py", line 48, in __get__
res = instance.__dict__[self.name] = self.func(instance)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/mysql/features.py", line 163, in is_sql_auto_is_null_enabled
return self.connection.mysql_server_data['sql_auto_is_null']
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/functional.py", line 48, in __get__
res = instance.__dict__[self.name] = self.func(instance)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/mysql/base.py", line 366, in mysql_server_data
with self.temporary_connection() as cursor:
File "/usr/lib/python3.10/contextlib.py", line 135, in __enter__
return next(self.gen)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 603, in temporary_connection
with self.cursor() as cursor:
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/utils/asyncio.py", line 33, in inner
return func(*args, **kwargs)
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 259, in cursor
return self._cursor()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 237, in _cursor
return self._prepare_cursor(self.create_cursor(name))
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 227, in _prepare_cursor
self.validate_thread_sharing()
File "/home/rudolf/dev/venvs/crate/lib/python3.10/site-packages/django/db/backends/base/base.py", line 552, in validate_thread_sharing
raise DatabaseError(
django.db.utils.DatabaseError: DatabaseWrapper objects created in a thread can only be used in that same thread. The object with alias 'research' was created in thread id 140577795391488 and this is thread id 140577329673792.
Doesn't always happen, but it looks like the global
research_database_info = ResearchDatabaseInfo()inresearch_db_info.pyis flawed because it's global: