Merge pull request #150 from elfkuzco/simplify-types

simplify Optional and Union types

src/zimscraperlib/download.py

@@ -7,7 +7,7 @@
 import pathlib
 import subprocess
 from concurrent.futures import Future, ThreadPoolExecutor
-from typing import ClassVar, Optional, Union
+from typing import ClassVar
 
 import requests
 import yt_dlp as youtube_dl
@@ -21,7 +21,7 @@ class YoutubeDownloader:
     Shutdown method must be run explicitly to
     free any occupied resources"""
 
-    def __init__(self, threads: Optional[int] = 1) -> None:
+    def __init__(self, threads: int | None = 1) -> None:
         self.executor = ThreadPoolExecutor(max_workers=threads)
 
     def __enter__(self):
@@ -41,9 +41,9 @@ def _run_youtube_dl(self, url: str, options: dict) -> None:
     def download(
         self,
         url: str,
-        options: Optional[dict],
-        wait: Optional[bool] = True,  # noqa: FBT002
-    ) -> Union[bool, Future]:
+        options: dict | None,
+        wait: bool | None = True,  # noqa: FBT002
+    ) -> bool | Future:
         """Downloads video using initialized executor.
 
         url: URL or Video ID
@@ -65,8 +65,8 @@ def download(
 
 
 class YoutubeConfig(dict):
-    options: ClassVar[dict[str, Optional[Union[str, bool, int]]]] = {}
-    defaults: ClassVar[dict[str, Optional[Union[str, bool, int]]]] = {
+    options: ClassVar[dict[str, str | bool | int | None]] = {}
+    defaults: ClassVar[dict[str, str | bool | int | None]] = {
         "writethumbnail": True,
         "write_all_thumbnails": True,
         "writesubtitles": True,
@@ -88,8 +88,8 @@ def __init__(self, **kwargs):
     @classmethod
     def get_options(
         cls,
-        target_dir: Optional[pathlib.Path] = None,
-        filepath: Optional[pathlib.Path] = None,
+        target_dir: pathlib.Path | None = None,
+        filepath: pathlib.Path | None = None,
         **options,
     ):
         if "outtmpl" not in options:
@@ -109,14 +109,14 @@ def get_options(
 
 
 class BestWebm(YoutubeConfig):
-    options: ClassVar[dict[str, Optional[Union[str, bool, int]]]] = {
+    options: ClassVar[dict[str, str | bool | int | None]] = {
         "preferredcodec": "webm",
         "format": "best[ext=webm]/bestvideo[ext=webm]+bestaudio[ext=webm]/best",
     }
 
 
 class BestMp4(YoutubeConfig):
-    options: ClassVar[dict[str, Optional[Union[str, bool, int]]]] = {
+    options: ClassVar[dict[str, str | bool | int | None]] = {
         "preferredcodec": "mp4",
         "format": "best[ext=mp4]/bestvideo[ext=mp4]+bestaudio[ext=m4a]/best",
     }
@@ -142,7 +142,7 @@ def save_large_file(url: str, fpath: pathlib.Path) -> None:
 
 
 def _get_retry_adapter(
-    max_retries: Optional[int] = 5,
+    max_retries: int | None = 5,
 ) -> requests.adapters.BaseAdapter:  # pyright: ignore
     retries = requests.packages.urllib3.util.retry.Retry(  # pyright: ignore
         total=max_retries,  # total number of retries
@@ -164,7 +164,7 @@ def _get_retry_adapter(
     return requests.adapters.HTTPAdapter(max_retries=retries)  # pyright: ignore
 
 
-def get_session(max_retries: Optional[int] = 5) -> requests.Session:
+def get_session(max_retries: int | None = 5) -> requests.Session:
     """Session to hold cookies and connection pool together"""
     session = requests.Session()
     session.mount("http", _get_retry_adapter(max_retries))  # tied to http and https
@@ -173,14 +173,14 @@ def get_session(max_retries: Optional[int] = 5) -> requests.Session:
 
 def stream_file(
     url: str,
-    fpath: Optional[pathlib.Path] = None,
-    byte_stream: Optional[io.BytesIO] = None,
-    block_size: Optional[int] = 1024,
-    proxies: Optional[dict] = None,
-    only_first_block: Optional[bool] = False,  # noqa: FBT002
-    max_retries: Optional[int] = 5,
-    headers: Optional[dict[str, str]] = None,
-    session: Optional[requests.Session] = None,
+    fpath: pathlib.Path | None = None,
+    byte_stream: io.BytesIO | None = None,
+    block_size: int | None = 1024,
+    proxies: dict | None = None,
+    only_first_block: bool | None = False,  # noqa: FBT002
+    max_retries: int | None = 5,
+    headers: dict[str, str] | None = None,
+    session: requests.Session | None = None,
 ) -> tuple[int, requests.structures.CaseInsensitiveDict]:  # pyright: ignore
     """Stream data from a URL to either a BytesIO object or a file
     Arguments -

src/zimscraperlib/filesystem.py

@@ -5,10 +5,12 @@
 
     Shortcuts to retrieve mime type using magic"""
 
+from __future__ import annotations
+
 import os
 import pathlib
 from collections.abc import Callable
-from typing import Any, Optional, Union
+from typing import Any
 
 import magic
 
@@ -43,8 +45,8 @@ def get_content_mimetype(content: bytes) -> str:
 
 
 def delete_callback(
-    fpath: Union[str, pathlib.Path],
-    callback: Optional[Callable] = None,
+    fpath: str | pathlib.Path,
+    callback: Callable | None = None,
     *callback_args: Any,
 ):
     """helper deleting passed filepath, optionnaly calling an additional callback"""

src/zimscraperlib/fix_ogvjs_dist.py

@@ -9,13 +9,12 @@
 import logging
 import pathlib
 import sys
-from typing import Union
 
 logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.DEBUG)
 logger = logging.getLogger(__name__)
 
 
-def fix_source_dir(source_vendors_path: Union[pathlib.Path, str]):
+def fix_source_dir(source_vendors_path: pathlib.Path | str):
     """update ogvjs plugin to trigger on webm mimetype"""
     root = pathlib.Path(source_vendors_path)
     logger.info("fixing videosjs-ogvjs.js")

src/zimscraperlib/html.py

@@ -2,16 +2,17 @@
 # vim: ai ts=4 sts=4 et sw=4 nu
 
 """ Tools to work with HTML contents """
+from __future__ import annotations
 
 import pathlib
-from typing import BinaryIO, TextIO, Union
+from typing import BinaryIO, TextIO
 
 from bs4 import BeautifulSoup
 
 from zimscraperlib.types import ARTICLE_MIME
 
 
-def find_title_in(content: Union[str, BinaryIO, TextIO], mime_type: str) -> str:
+def find_title_in(content: str | BinaryIO | TextIO, mime_type: str) -> str:
     """Extracted title from HTML content
 
     blank on failure to extract and non-HTML files"""
@@ -32,7 +33,7 @@ def find_title_in_file(fpath: pathlib.Path, mime_type: str) -> str:
         return ""
 
 
-def find_language_in(content: Union[str, BinaryIO, TextIO], mime_type: str) -> str:
+def find_language_in(content: str | BinaryIO | TextIO, mime_type: str) -> str:
     """Extracted language from HTML content
 
     blank on failure to extract and non-HTML files"""

src/zimscraperlib/i18n.py

@@ -7,7 +7,6 @@
 import locale
 import pathlib
 import re
-from typing import Optional, Union
 
 import babel
 import iso639
@@ -60,7 +59,7 @@ def setlocale(root_dir: pathlib.Path, locale_name: str):
     return Locale.setup(root_dir / "locale", locale_name)
 
 
-def get_iso_lang_data(lang: str) -> tuple[dict, Union[dict, None]]:
+def get_iso_lang_data(lang: str) -> tuple[dict, dict | None]:
     """ISO-639-x languages details for lang. Raises NotFound
 
     Included keys: iso-639-1, iso-639-2b, iso-639-2t, iso-639-3, iso-639-5
@@ -113,9 +112,7 @@ def replace_types(new_type: str) -> str:
     return lang_data, None
 
 
-def find_language_names(
-    query: str, lang_data: Optional[dict] = None
-) -> tuple[str, str]:
+def find_language_names(query: str, lang_data: dict | None = None) -> tuple[str, str]:
     """(native, english) language names for lang with help from language_details dict
 
     Falls back to English name if available or query if not"""
@@ -152,7 +149,7 @@ def update_with_macro(lang_data: dict, macro_data: dict):
 
 
 def get_language_details(
-    query: str, failsafe: Optional[bool] = False  # noqa: FBT002
+    query: str, failsafe: bool | None = False  # noqa: FBT002
 ) -> dict:
     """language details dict from query.
 

src/zimscraperlib/image/convertion.py

@@ -1,9 +1,10 @@
 #!/usr/bin/env python3
 # vim: ai ts=4 sts=4 et sw=4 nu
 
+from __future__ import annotations
+
 import io
 import pathlib
-from typing import Union
 
 import PIL
 
@@ -14,8 +15,8 @@
 
 
 def convert_image(
-    src: Union[pathlib.Path, io.BytesIO],
-    dst: Union[pathlib.Path, io.BytesIO],
+    src: pathlib.Path | io.BytesIO,
+    dst: pathlib.Path | io.BytesIO,
     **params: str,
 ) -> None:
     """convert an image file from one format to another

src/zimscraperlib/image/optimization.py

@@ -28,7 +28,6 @@
 import os
 import pathlib
 import subprocess
-from typing import Optional, Union
 
 import piexif
 from optimize_images.img_aux_processing import do_reduce_colors, rebuild_palette
@@ -52,15 +51,15 @@ def ensure_matches(
 
 
 def optimize_png(
-    src: Union[pathlib.Path, io.BytesIO],
-    dst: Optional[pathlib.Path] = None,
-    reduce_colors: Optional[bool] = False,  # noqa: FBT002
-    max_colors: Optional[int] = 256,
-    fast_mode: Optional[bool] = True,  # noqa: FBT002
-    remove_transparency: Optional[bool] = False,  # noqa: FBT002
-    background_color: Optional[tuple[int, int, int]] = (255, 255, 255),
+    src: pathlib.Path | io.BytesIO,
+    dst: pathlib.Path | None = None,
+    reduce_colors: bool | None = False,  # noqa: FBT002
+    max_colors: int | None = 256,
+    fast_mode: bool | None = True,  # noqa: FBT002
+    remove_transparency: bool | None = False,  # noqa: FBT002
+    background_color: tuple[int, int, int] | None = (255, 255, 255),
     **options,  # noqa: ARG001
-) -> Union[pathlib.Path, io.BytesIO]:
+) -> pathlib.Path | io.BytesIO:
     """method to optimize PNG files using a pure python external optimizer
 
     Arguments:
@@ -99,13 +98,13 @@ def optimize_png(
 
 
 def optimize_jpeg(
-    src: Union[pathlib.Path, io.BytesIO],
-    dst: Optional[pathlib.Path] = None,
-    quality: Optional[int] = 85,
-    fast_mode: Optional[bool] = True,  # noqa: FBT002
-    keep_exif: Optional[bool] = True,  # noqa: FBT002
+    src: pathlib.Path | io.BytesIO,
+    dst: pathlib.Path | None = None,
+    quality: int | None = 85,
+    fast_mode: bool | None = True,  # noqa: FBT002
+    keep_exif: bool | None = True,  # noqa: FBT002
     **options,  # noqa: ARG001
-) -> Union[pathlib.Path, io.BytesIO]:
+) -> pathlib.Path | io.BytesIO:
     """method to optimize JPEG files using a pure python external optimizer
     quality: JPEG quality (integer between 1 and 100)
         values: 50 | 55 | 35 | 100 | XX
@@ -169,13 +168,13 @@ def optimize_jpeg(
 
 
 def optimize_webp(
-    src: Union[pathlib.Path, io.BytesIO],
-    dst: Optional[pathlib.Path] = None,
-    lossless: Optional[bool] = False,  # noqa: FBT002
-    quality: Optional[int] = 60,
-    method: Optional[int] = 6,
+    src: pathlib.Path | io.BytesIO,
+    dst: pathlib.Path | None = None,
+    lossless: bool | None = False,  # noqa: FBT002
+    quality: int | None = 60,
+    method: int | None = 6,
     **options,  # noqa: ARG001
-) -> Union[pathlib.Path, io.BytesIO]:
+) -> pathlib.Path | io.BytesIO:
     """method to optimize WebP using Pillow options
     lossless: Whether to use lossless compression (boolean)
         values: True | False
@@ -214,11 +213,11 @@ def optimize_webp(
 def optimize_gif(
     src: pathlib.Path,
     dst: pathlib.Path,
-    optimize_level: Optional[int] = 1,
-    lossiness: Optional[int] = None,
-    interlace: Optional[bool] = True,  # noqa: FBT002
-    no_extensions: Optional[bool] = True,  # noqa: FBT002
-    max_colors: Optional[int] = None,
+    optimize_level: int | None = 1,
+    lossiness: int | None = None,
+    interlace: bool | None = True,  # noqa: FBT002
+    no_extensions: bool | None = True,  # noqa: FBT002
+    max_colors: int | None = None,
     **options,  # noqa: ARG001
 ) -> pathlib.Path:
     """method to optimize GIFs using gifsicle >= 1.92
@@ -267,8 +266,8 @@ def optimize_gif(
 def optimize_image(
     src: pathlib.Path,
     dst: pathlib.Path,
-    delete_src: Optional[bool] = False,  # noqa: FBT002
-    convert: Optional[Union[bool, str]] = False,  # noqa: FBT002
+    delete_src: bool | None = False,  # noqa: FBT002
+    convert: bool | str | None = False,  # noqa: FBT002
     **options,
 ) -> bool:  # pyright: ignore
     """Optimize image, automatically selecting correct optimizer