Pin to python 3.9

Since our execution environment requires this

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

.python-version

@@ -0,0 +1 @@
+3.9

pyproject.toml

@@ -3,7 +3,7 @@ name = "mediawiki-dump-tools"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
-requires-python = ">=3.11"
+requires-python = "~=3.9"
 dependencies = [
     "deltas>=0.7.0",
     "mediawiki-utilities>=0.4.18",
@@ -12,7 +12,7 @@ dependencies = [
     "mwtypes>=0.4.0",
     "mwxml>=0.3.6",
     "pyarrow>=20.0.0",
-    "yamlconf",
+    "yamlconf>=0.2.6",
 ]
 
 [tool.uv.sources]

tables.py

@@ -2,7 +2,7 @@ import sys
 from abc import abstractmethod, ABC
 from datetime import datetime, timezone
 from hashlib import sha1
-from typing import Generic, TypeVar
+from typing import Generic, TypeVar, Union
 
 import mwreverts
 import mwtypes
@@ -89,10 +89,10 @@ class RevisionArticleId(RevisionField[int]):
         return page.id
 
 
-class RevisionEditorId(RevisionField[int | None]):
+class RevisionEditorId(RevisionField[Union[int, None]]):
     field = pa.field("editorid", pa.int64(), nullable=True)
 
-    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> int | None:
+    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> Union[int, None]:
         revision = revisions[-1]
         if revision.deleted.user:
             return None
@@ -100,10 +100,10 @@ class RevisionEditorId(RevisionField[int | None]):
         return revision.user.id
 
 
-class RevisionIsAnon(RevisionField[bool | None]):
+class RevisionIsAnon(RevisionField[Union[bool, None]]):
     field = pa.field("anon", pa.bool_(), nullable=True)
 
-    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> bool | None:
+    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> Union[bool, None]:
         revision = revisions[-1]
         if revision.deleted.user:
             return None
@@ -111,10 +111,10 @@ class RevisionIsAnon(RevisionField[bool | None]):
         return revision.user.id is None
 
 
-class RevisionEditorText(RevisionField[str | None]):
+class RevisionEditorText(RevisionField[Union[str, None]]):
     field = pa.field("editor", pa.string(), nullable=True)
 
-    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> str | None:
+    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> Union[str, None]:
         revision = revisions[-1]
         if revision.deleted.user:
             return None
@@ -152,10 +152,10 @@ class RevisionSha1(RevisionField[str]):
         return revision.sha1
 
 
-class RevisionTextChars(RevisionField[int | None]):
+class RevisionTextChars(RevisionField[Union[int, None]]):
     field = pa.field("text_chars", pa.int32(), nullable=True)
 
-    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> int | None:
+    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> Union[int, None]:
         revision = revisions[-1]
         if not revision.deleted.text:
             return len(revision.text)
@@ -179,14 +179,14 @@ class RevisionIsMinor(RevisionField[bool]):
         return revision.minor
 
 
-class RevisionReverts(RevisionField[str | None]):
+class RevisionReverts(RevisionField[Union[str, None]]):
     def __init__(self):
         super().__init__()
-        self.rev_detector: mwreverts.Detector | None = None
+        self.rev_detector: Union[mwreverts.Detector, None] = None
 
     field = pa.field("reverteds", pa.string(), nullable=True)
 
-    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> str | None:
+    def extract(self, page: mwtypes.Page, revisions: list[mwxml.Revision]) -> Union[str, None]:
         if self.rev_detector is None:
             return None
 

wikiq

@@ -14,7 +14,7 @@ from itertools import groupby
 from subprocess import Popen, PIPE
 from collections import deque
 from hashlib import sha1
-from typing import Any, IO, TextIO, Generator
+from typing import Any, IO, TextIO, Generator, Union
 
 import mwxml
 from mwxml import Dump
@@ -100,7 +100,7 @@ class WikiqPage:
         self.__revisions: Generator[list[mwxml.Revision]] = self.rev_list()
 
     @staticmethod
-    def user_text(rev) -> str | None:
+    def user_text(rev) -> Union[str, None]:
         return None if rev.deleted.user else rev.user.text
 
     def rev_list(self):
@@ -203,15 +203,15 @@ class RegexPair(object):
 
 class WikiqParser:
     def __init__(self,
-                 input_file: TextIOWrapper | IO[Any] | IO[bytes],
-                 output_file: TextIO | str,
+                 input_file: Union[TextIOWrapper, IO[Any], IO[bytes]],
+                 output_file: Union[TextIO, str],
                  regex_match_revision: list[str],
                  regex_match_comment: list[str],
                  regex_revision_label: list[str],
                  regex_comment_label: list[str],
                  collapse_user: bool = False,
                  persist: int = None,
-                 namespaces: list[int] | None = None,
+                 namespaces: Union[list[int], None] = None,
                  revert_radius: int = 15,
                  output_parquet: bool = True,
                  parquet_buffer_size: int = 2000):
@@ -410,7 +410,7 @@ class WikiqParser:
             # Collect the set of pages currently buffered in the table so we can run multi-page functions on them.
             row_buffer = table.pop()
 
-            is_revert_column: list[bool | None] = []
+            is_revert_column: list[Union[bool, None]] = []
             for r, d in zip(row_buffer['reverteds'], row_buffer['deleted']):
                 if self.revert_radius == 0 or d:
                     is_revert_column.append(None)