feat(i18n): add gettext zh_CN runtime POC #1775
+574
−29
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,63 @@ | ||
| import gettext | ||
| import os | ||
| from functools import lru_cache | ||
| from pathlib import Path | ||
|
|
||
| DOMAIN = "hyde" | ||
|
|
||
|
|
||
| def _normalize_locale(lang: str | None) -> str: | ||
| lang = (lang or "en").split(":", 1)[0].split(".", 1)[0].split("@", 1)[0] | ||
| lang = lang.replace("-", "_") | ||
| lowered = lang.lower() | ||
|
|
||
| if lowered in {"", "c", "posix"}: | ||
| return "en" | ||
| if lowered in {"zh", "zh_cn", "zh_sg"}: | ||
| return "zh_CN" | ||
| return lang | ||
|
|
||
|
|
||
| def _language() -> str: | ||
| return _normalize_locale( | ||
| os.getenv("HYDE_LANG") | ||
| or os.getenv("I18N_LANGUAGE") | ||
| or os.getenv("LC_MESSAGES") | ||
| or os.getenv("LANG") | ||
| or "en" | ||
| ) | ||
|
|
||
|
|
||
| def _locale_dir() -> Path: | ||
| share_dir = os.getenv("SHARE_DIR") | ||
| if share_dir: | ||
| return Path(share_dir) / "hyde" / "locale" | ||
|
|
||
| return Path(os.getenv("XDG_DATA_HOME", Path.home() / ".local/share")) / "hyde" / "locale" | ||
|
|
||
|
|
||
| @lru_cache(maxsize=None) | ||
| def _translation(lang: str) -> gettext.NullTranslations: | ||
| try: | ||
| return gettext.translation( | ||
| DOMAIN, | ||
| localedir=str(_locale_dir()), | ||
| languages=[lang], | ||
| fallback=True, | ||
| ) | ||
| except Exception: | ||
| return gettext.NullTranslations() | ||
|
|
||
|
|
||
| def t(message: str, default: str | None = None, *args: object) -> str: | ||
| translated = _translation(_language()).gettext(message) | ||
| if translated == message and default is not None: | ||
| translated = default | ||
|
|
||
| if not args: | ||
| return translated | ||
|
|
||
| try: | ||
| return translated % args | ||
| except (TypeError, ValueError): | ||
| return translated | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,18 @@ | ||
| #!/usr/bin/env bash | ||
| # Generated by Source/locale/build.py; do not edit manually. | ||
| # shellcheck shell=bash disable=SC2034 | ||
| declare -gA _T 2>/dev/null || declare -A _T 2>/dev/null || : | ||
| _T[$'Description']=$'说明' | ||
| _T[$'Initialization failed.']=$'初始化失败。' | ||
| _T[$'Keybind Hint']=$'快捷键提示' | ||
| _T[$'Keybind cache updated']=$'快捷键缓存已更新' | ||
| _T[$'Keybindings']=$'快捷键' | ||
| _T[$'Keybinds']=$'快捷键' | ||
| _T[$'Notifications']=$'通知' | ||
| _T[$'Repeat']=$'重复执行' | ||
| _T[$'[Enter] repeat; [ESC] exit']=$'[Enter] 重复；[ESC] 退出' | ||
| _T[$'click-left: Enable & Disable DND']=$'左键：启用/关闭免打扰' | ||
| _T[$'click-middle: clear history']=$'中键：清空历史记录' | ||
| _T[$'click-right: close all']=$'右键：关闭全部通知' | ||
| _T[$'rofi not detected. Displaying on terminal instead']=$'未检测到 rofi，改为在终端中显示' | ||
| _T[$'scroll-down: history pop']=$'向下滚动：弹出历史通知' |
Binary file not shown.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| # HyDE Runtime Localization | ||
|
|
||
| HyDE uses gettext `.po` files as the editable source for runtime translations. | ||
| Generated `.mo` files are used by Python and other gettext consumers, while Bash | ||
| loads a small generated associative-array map from the same `.po` file. | ||
|
|
||
| ## Language selection | ||
|
|
||
| Force Simplified Chinese: | ||
|
|
||
| ```sh | ||
| HYDE_LANG=zh_CN hyde-shell keybinds_hint | ||
| ``` | ||
|
|
||
| Force English: | ||
|
|
||
| ```sh | ||
| HYDE_LANG=en hyde-shell keybinds_hint | ||
| ``` | ||
|
|
||
| Language resolution checks `HYDE_LANG`, `I18N_LANGUAGE`, `LC_MESSAGES`, and | ||
| `LANG`, then falls back to English/original strings. | ||
|
|
||
| ## Regenerating files | ||
|
|
||
| After editing `Source/locale/zh_CN/LC_MESSAGES/hyde.po`, regenerate runtime | ||
| translation files: | ||
|
|
||
| ```sh | ||
| python3 Source/locale/build.py | ||
| ``` | ||
|
|
||
| The script uses standard gettext tools when available: | ||
|
|
||
| - `xgettext` updates `Source/locale/hyde.pot` | ||
| - `msgmerge` updates `.po` files from the template | ||
| - `msgfmt` compiles `.po` files into `.mo` | ||
|
|
||
| It also generates Bash maps such as | ||
| `Configs/.local/share/hyde/locale/zh_CN.sh`. | ||
|
|
||
| Missing translation files or missing keys safely fall back to the original | ||
| English strings. |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Locale normalization doesn't standardize case for non-special-cased locales.
The function preserves the original casing after basic transformations (strip modifiers, replace hyphens) for all locales except the hardcoded special cases. Standard locale identifiers use lowercase language codes and uppercase territory codes (e.g.,
fr_FR,de_DE). If a user setsLANG=FR_FRorLANG=fr-fr, the normalization will produceFR_FRorfr_frrespectively, but gettext will look for directories with those exact names. If future locale directories follow the standardfr_FRpattern, lookups will fail for non-canonical casings.Currently this only affects hypothetical future locales, since
zh_CNis explicitly normalized. Consider normalizing all locales to lowercase language + uppercase territory to handle arbitraryLANGvalues robustly.Suggested fix to normalize case consistently
def _normalize_locale(lang: str | None) -> str: lang = (lang or "en").split(":", 1)[0].split(".", 1)[0].split("@", 1)[0] lang = lang.replace("-", "_") - lowered = lang.lower() + parts = lang.split("_", 1) + normalized = parts[0].lower() + ("_" + parts[1].upper() if len(parts) > 1 else "") - if lowered in {"", "c", "posix"}: + if normalized in {"", "c", "posix"}: return "en" - if lowered in {"zh", "zh_cn", "zh_sg"}: + if normalized in {"zh", "zh_CN", "zh_SG"}: return "zh_CN" - return lang + return normalized🤖 Prompt for AI Agents