diff --git a/src/wikiq/__init__.py b/src/wikiq/__init__.py index 27a2735..8a02c0c 100755 --- a/src/wikiq/__init__.py +++ b/src/wikiq/__init__.py @@ -32,19 +32,24 @@ from collections import deque, defaultdict from hashlib import sha1 from io import TextIOWrapper from itertools import groupby +from pathlib import Path from subprocess import PIPE, Popen from typing import IO, Any, Generator, TextIO, Union import mwpersistence import mwreverts import mwxml +import pyarrow as pa +import pyarrow.csv as pacsv +from deltas import SegmentMatcher, SequenceMatcher from deltas.tokenizers import wikitext_split from more_itertools import peekable from mwxml import Dump + import wikiq.tables as tables +from wikiq.resume import get_resume_point from wikiq.tables import RevisionTable from wikiq.wikitext_parser import WikitextParser -from wikiq.resume import get_resume_point try: from importlib.metadata import PackageNotFoundError @@ -56,11 +61,6 @@ except PackageNotFoundError: TO_ENCODE = ("title", "editor") PERSISTENCE_RADIUS = 7 DIFF_TIMEOUT_MS = 60000 -from pathlib import Path - -import pyarrow as pa -import pyarrow.csv as pacsv -from deltas import SegmentMatcher, SequenceMatcher # Some dependencies serve a single feature and are awkward enough to install