Add typing to preprocess.py script that I'm not using

ChatGPT did most of this for me. I just said "Please add type annotations to this code. Surround the code in a Markdown code block."
and then fixed the Generator and the lambda.
This commit is contained in:
Isaiah Odhner 2023-04-22 21:52:31 -04:00
parent 5d778c1879
commit 505605c660

View File

@ -2,52 +2,52 @@ import os
import re
import glob
import json
from typing import Generator, List, Dict, Any
from parse_rc_file import parse_rc_file
base_lang = "en"
available_langs = [dir for dir in os.listdir(os.path.dirname(__file__)) if re.match(r"^\w+(-\w+)?$", dir)]
target_langs = [lang for lang in available_langs if lang != base_lang]
base_lang: str = "en"
available_langs: List[str] = [dir for dir in os.listdir(os.path.dirname(__file__)) if re.match(r"^\w+(-\w+)?$", dir)]
target_langs: List[str] = [lang for lang in available_langs if lang != base_lang]
print("Target languages:", target_langs)
# & defines accelerators (hotkeys) in menus and buttons and things, which get underlined in the UI.
# & can be escaped by doubling it, e.g. "&Taskbar && Start Menu"
def index_of_hotkey(text):
def index_of_hotkey(text: str) -> int:
# Returns the index of the ampersand that defines a hotkey, or -1 if not present.
# The space here handles beginning-of-string matching and counteracts the offset for the [^&] so it acts like a negative lookbehind
m = re.search(r"[^&]&[^&\s]", f" {text}")
return m.start() if m else -1
def has_hotkey(text):
def has_hotkey(text: str) -> bool:
return index_of_hotkey(text) != -1
def remove_hotkey(text):
def remove_hotkey(text: str) -> str:
text = re.sub(r"\s?\(&.\)", "", text)
text = re.sub(r"([^&]|^)&([^&\s])", r"\1\2", text)
return text
def remove_ellipsis(string):
def remove_ellipsis(string: str) -> str:
return string.replace("...", "")
def get_strings(lang):
rc_files = glob.glob(f"{os.path.dirname(__file__)}/{lang}/**/*.rc", recursive=True)
def get_strings(lang: str) -> Generator[str, None, None]:
rc_files: List[str] = glob.glob(f"{os.path.dirname(__file__)}/{lang}/**/*.rc", recursive=True)
for rc_file in rc_files:
with open(rc_file, "r", encoding="utf16") as f:
yield from parse_rc_file(f.read().replace("\ufeff", ""))
base_strings = list(get_strings(base_lang))
base_strings: List[str] = list(get_strings(base_lang))
for target_lang in target_langs:
target_strings = list(get_strings(target_lang))
localizations = {}
target_strings: List[str] = list(get_strings(target_lang))
localizations: Dict[str, Any] = {}
def add_localization(base_string, target_string, fudgedness):
def add_localization(base_string: str, target_string: str, fudgedness: int) -> None:
localizations[base_string] = localizations.get(base_string, [])
localizations[base_string].append({"target_string": target_string, "fudgedness": fudgedness})
def add_localizations(base_strings, target_strings):
def add_localizations(base_strings: List[str], target_strings: List[str]) -> None:
for i, target_string in enumerate(target_strings):
if len(base_strings) <= i:
break
@ -66,7 +66,9 @@ for target_lang in target_langs:
add_localizations(base_strings, target_strings)
for base_string, options in localizations.items():
options.sort(key=lambda x: x["fudgedness"])
def get_fudgedness(translation_option: Dict[str, Any]) -> int:
return translation_option["fudgedness"]
# options.sort(key=lambda x: x["fudgedness"])
unique_strings = list(set(option["target_string"] for option in options))
if len(unique_strings) > 1:
unique_strings_json = json.dumps(unique_strings, ensure_ascii=False, indent="\t")