Add noargs test for ikwiki

This way we can ensure that the parquet code outputs equivalent output.

Signed-off-by: Will Beason <willbeason@gmail.com>

wikiq

@@ -14,7 +14,7 @@ from io import TextIOWrapper
 from subprocess import Popen, PIPE
 from collections import deque
 from hashlib import sha1
-from typing import Any, IO, TextIO, Iterable
+from typing import Any, IO, TextIO
 
 from mwxml import Dump
 
@@ -387,7 +387,7 @@ class WikiqParser:
                  namespaces: list[int] | None = None,
                  revert_radius: int = 15,
                  output_parquet: bool = True,
-                 parquet_buffer_size: int=2000):
+                 parquet_buffer_size: int = 2000):
         """ 
         Parameters:
            persist : what persistence method to use. Takes a PersistMethod value
@@ -427,8 +427,8 @@ class WikiqParser:
         # make_dataclass is a function that defines a new dataclass type.
         # here we extend the type we have already chosen and add the regular expression types 
         self.revdata_type: type = dc.make_dataclass('RevData_Parser',
-                                              fields=regex_fields,
-                                              bases=(revdata_type,))
+                                                    fields=regex_fields,
+                                                    bases=(revdata_type,))
 
         # we also need to make sure that we have the right pyarrow schema
         self.revdata_type.pa_schema_fields = revdata_type.pa_schema_fields + self.regex_schemas
@@ -544,11 +544,12 @@ class WikiqParser:
             # Iterate through a page's revisions
             for rev in page:
 
-                # create a new data object instead of a dictionary. 
+                editorid = None if rev.deleted.user or rev.user.id is None else rev.user.id
+                # create a new data object instead of a dictionary.
                 rev_data = self.revdata_type(revid=rev.id,
                                              date_time=datetime.fromtimestamp(rev.timestamp.unix(), tz=timezone.utc),
                                              articleid=page.id,
-                                             editorid=None if rev.deleted.user == True or rev.user.id is None else rev.user.id,
+                                             editorid=editorid,
                                              title=page.title,
                                              deleted=rev.deleted.text,
                                              namespace=namespace