general: migrate modules to use 3.9 features

my/google/takeout/html.py

@@ -2,18 +2,22 @@
 Google Takeout exports: browsing history, search/youtube/google play activity
 '''
 
-from enum import Enum
+from __future__ import annotations
+
+from my.core import __NOT_HPI_MODULE__  # isort: skip
+
 import re
-from pathlib import Path
+from collections.abc import Iterable
 from datetime import datetime
+from enum import Enum
 from html.parser import HTMLParser
-from typing import List, Optional, Any, Callable, Iterable, Tuple
+from pathlib import Path
+from typing import Any, Callable
 from urllib.parse import unquote
 
 import pytz
 
-from ...core.time import abbr_to_timezone
-
+from my.core.time import abbr_to_timezone
 
 # NOTE: https://bugs.python.org/issue22377 %Z doesn't work properly
 _TIME_FORMATS = [
@@ -36,7 +40,7 @@ def parse_dt(s: str) -> datetime:
         s, tzabbr = s.rsplit(maxsplit=1)
         tz = abbr_to_timezone(tzabbr)
 
-    dt: Optional[datetime] = None
+    dt: datetime | None = None
     for fmt in _TIME_FORMATS:
         try:
             dt = datetime.strptime(s, fmt)
@@ -73,7 +77,7 @@ class State(Enum):
 
 Url = str
 Title = str
-Parsed = Tuple[datetime, Url, Title]
+Parsed = tuple[datetime, Url, Title]
 Callback = Callable[[datetime, Url, Title], None]
 
 
@@ -83,9 +87,9 @@ class TakeoutHTMLParser(HTMLParser):
         super().__init__()
         self.state: State = State.OUTSIDE
 
-        self.title_parts: List[str] = []
-        self.title: Optional[str] = None
-        self.url: Optional[str] = None
+        self.title_parts: list[str] = []
+        self.title: str | None = None
+        self.url: str | None = None
 
         self.callback = callback
 
@@ -148,7 +152,7 @@ class TakeoutHTMLParser(HTMLParser):
 
 
 def read_html(tpath: Path, file: str) -> Iterable[Parsed]:
-    results: List[Parsed] = []
+    results: list[Parsed] = []
     def cb(dt: datetime, url: Url, title: Title) -> None:
         results.append((dt, url, title))
     parser = TakeoutHTMLParser(callback=cb)
@@ -156,5 +160,3 @@ def read_html(tpath: Path, file: str) -> Iterable[Parsed]:
         data = fo.read()
         parser.feed(data)
     return results
-
-from ...core import __NOT_HPI_MODULE__

my/google/takeout/parser.py

@@ -14,24 +14,27 @@ the cachew cache
 
 REQUIRES = ["git+https://github.com/seanbreckenridge/google_takeout_parser"]
 
+import os
+from collections.abc import Sequence
 from contextlib import ExitStack
 from dataclasses import dataclass
-import os
-from typing import List, Sequence, cast
 from pathlib import Path
-from my.core import make_config, stat, Stats, get_files, Paths, make_logger
+from typing import cast
+
+from google_takeout_parser.parse_html.html_time_utils import ABBR_TIMEZONES
+
+from my.core import Paths, Stats, get_files, make_config, make_logger, stat
 from my.core.cachew import mcachew
 from my.core.error import ErrorPolicy
 from my.core.structure import match_structure
-
 from my.core.time import user_forced
-from google_takeout_parser.parse_html.html_time_utils import ABBR_TIMEZONES
+
 ABBR_TIMEZONES.extend(user_forced())
 
 import google_takeout_parser
-from google_takeout_parser.path_dispatch import TakeoutParser
-from google_takeout_parser.merge import GoogleEventSet, CacheResults
+from google_takeout_parser.merge import CacheResults, GoogleEventSet
 from google_takeout_parser.models import BaseEvent
+from google_takeout_parser.path_dispatch import TakeoutParser
 
 # see https://github.com/seanbreckenridge/dotfiles/blob/master/.config/my/my/config/__init__.py for an example
 from my.config import google as user_config
@@ -56,6 +59,7 @@ logger = make_logger(__name__, level="warning")
 
 # patch the takeout parser logger to match the computed loglevel
 from google_takeout_parser.log import setup as setup_takeout_logger
+
 setup_takeout_logger(logger.level)
 
 
@@ -83,7 +87,7 @@ except ImportError:
 
 google_takeout_version = str(getattr(google_takeout_parser, '__version__', 'unknown'))
 
-def _cachew_depends_on() -> List[str]:
+def _cachew_depends_on() -> list[str]:
     exports = sorted([str(p) for p in inputs()])
     # add google takeout parser pip version to hash, so this re-creates on breaking changes
     exports.insert(0, f"google_takeout_version: {google_takeout_version}")

my/google/takeout/paths.py

@@ -2,13 +2,17 @@
 Module for locating and accessing [[https://takeout.google.com][Google Takeout]] data
 '''
 
+from __future__ import annotations
+
+from my.core import __NOT_HPI_MODULE__  # isort: skip
+
 from abc import abstractmethod
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional, Protocol
 
 from more_itertools import last
 
-from my.core import __NOT_HPI_MODULE__, Paths, get_files
+from my.core import Paths, get_files
 
 
 class config:
@@ -33,7 +37,7 @@ def make_config() -> config:
     return combined_config()
 
 
-def get_takeouts(*, path: Optional[str] = None) -> Iterable[Path]:
+def get_takeouts(*, path: str | None = None) -> Iterable[Path]:
     """
     Sometimes google splits takeout into multiple archives, so we need to detect the ones that contain the path we need
     """
@@ -45,7 +49,7 @@ def get_takeouts(*, path: Optional[str] = None) -> Iterable[Path]:
             yield takeout
 
 
-def get_last_takeout(*, path: Optional[str] = None) -> Optional[Path]:
+def get_last_takeout(*, path: str | None = None) -> Path | None:
     return last(get_takeouts(path=path), default=None)