Skip to content

armgit / memos

Public Imported from GitHub
0

Memos is an open-source, self-hosted note-taking app that brings your everyday thoughts together in a personal timeline. Your data stays yours, and you choose what to keep private or share.

feat: update Chinese translations in zh.json and zh-Hant.json using locale_updater.py (#1506)

Peng Ding0020498c101b
diff --git a/web/src/locales/locale_updater.py b/web/src/locales/locale_updater.py
new file mode 100644
index 000000000..8ce91aa22
--- /dev/null
+++ b/web/src/locales/locale_updater.py
@@ -0,0 +1,202 @@
+# Author: Oaklight
+# GitHub profile: https://github.com/Oaklight
+# Date: April 9, 2023
+# Description: This script is used to patch missing translations in a locale file.
+
+# The script uses 'en.json' as the reference file to find missing keys in other locale files.
+# It iterates through each field and their entries in 'en.json' and checks if the same field/entry exists in other files.
+# If a field/entry is missing, the script prompts the source string, reference Google translation, and asks for confirmation or correction.
+# The resulting file is saved as './*.proposed.json', and you should review it before merging and uploading.
+
+# usage: locale_updater.py [-h] ref_locale tgt_locale
+
+#TODO: add other NMT system for different preference and accuracy
+
+import json
+import requests
+
+
+def flatten_json(nested_json, parent_key="", sep=":"):
+ flattened_dict = {}
+ for key, value in nested_json.items():
+ new_key = parent_key + sep + key if parent_key else key
+ if isinstance(value, dict):
+ flattened_dict.update(flatten_json(value, new_key, sep))
+ else:
+ flattened_dict[new_key] = value
+ return flattened_dict
+
+
+def unflatten_json(flattened_dict, sep=":"):
+ nested_json = {}
+ for key, value in flattened_dict.items():
+ parts = key.split(sep)
+ current = nested_json
+ for part in parts[:-1]:
+ if part not in current:
+ current[part] = {}
+ current = current[part]
+ current[parts[-1]] = value
+ return nested_json
+
+
+def sort_nested_json(nested_json):
+ if isinstance(nested_json, dict):
+ sorted_dict = {}
+ for key in sorted(nested_json.keys()):
+ sorted_dict[key] = sort_nested_json(nested_json[key])
+ return sorted_dict
+ elif isinstance(nested_json, list):
+ sorted_list = []
+ for item in nested_json:
+ sorted_list.append(sort_nested_json(item))
+ return sorted_list
+ else:
+ return nested_json
+
+
+def google_translate(
+ source_text, source_language="en", target_language="zh-CN"
+):
+ # Create post content
+ new_line = "\r\n"
+ post_content = "q=" + source_text.replace(new_line, " ")
+
+ # Send post request and get JSON response, using source_language and target_language
+ # url = "https://translate.googleapis.com/translate_a/single?client=gtx&sl=en&tl=zh-CN&dt=t"
+ url = f"https://translate.googleapis.com/translate_a/single?client=gtx&sl={source_language}&tl={target_language}&dt=t"
+ headers = {"Content-type": "application/x-www-form-urlencoded"}
+ response = requests.post(url, headers=headers, data=post_content.encode("utf-8"))
+ json_value = response.json()
+
+ # Extract translations from JSON
+ translations = [item[0] for item in json_value[0]]
+ translations = [t.replace(new_line, "") for t in translations]
+ target_text = translations[0]
+
+ return target_text
+
+
+def get_code_name(json_filename):
+ # Remove extension and split language and country codes
+ file_parts = json_filename.split(".")[0].split("_")
+ lang_code = file_parts[0]
+ country_code = file_parts[1] if len(file_parts) > 1 else ""
+
+ # Map language code to code name
+ lang_map = {
+ "de": "de",
+ "en": "en",
+ "es": "es",
+ "fr": "fr",
+ "it": "it",
+ "ko": "ko",
+ "nl": "nl",
+ "pl": "pl",
+ "pt": "pt-BR",
+ "ru": "ru",
+ "sl": "sl",
+ "sv": "sv",
+ "tr": "tr",
+ "uk": "uk",
+ "vi": "vi",
+ "zh-Hant": "zh-TW",
+ "zh": "zh-CN",
+ }
+ code_name = lang_map.get(lang_code, "")
+
+ # Add country code if available
+ if country_code:
+ code_name += "-" + country_code.upper()
+
+ return code_name
+
+
+if __name__ == "__main__":
+ # ref_locale = "./en.json"
+ # tgt_locale = "./zh.json"
+ # receive the reference locale and target locale from the command line using argparse
+ import argparse
+
+ parser = argparse.ArgumentParser()
+ parser.add_argument("ref_locale", help="reference locale file")
+ parser.add_argument("tgt_locale", help="target locale file")
+ args = parser.parse_args()
+ ref_locale = args.ref_locale
+ tgt_locale = args.tgt_locale
+
+ ref_codename = get_code_name(ref_locale)
+ tgt_codename = get_code_name(tgt_locale)
+
+ with open(ref_locale, "r") as f:
+ ref = json.load(f)
+
+ with open(tgt_locale, "r") as f:
+ tgt = json.load(f)
+
+ # using the flatten_json function, produce a temp json for each locale and save to the disk
+ ref_flat = flatten_json(ref)
+ tgt_flat = flatten_json(tgt)
+
+ # # save the flattened json to the disk
+ # with open("ref_flat.json", "w") as f:
+ # json.dump(ref_flat, f, indent=2, ensure_ascii=False)
+ # with open("tgt_flat.json", "w") as f:
+ # json.dump(tgt_flat, f, indent=2, ensure_ascii=False)
+
+ # first diff the keys to inform the user of the missing keys
+ missing_keys = set(ref_flat.keys()) - set(tgt_flat.keys())
+ # print total number of missing keys, in red color, number as default
+ if len(missing_keys) == 0:
+ print("\033[92m All keys are present in the target locale \033[0m")
+ exit()
+ else:
+ print(f"\033[91m Total missing keys: \033[0m {len(missing_keys)}")
+
+
+ # formatted print line by line, wrap the missing key in red color, and the English translation in green color
+ for key in missing_keys:
+ # print(f"Missing key: {key} | English: {ref_flat[key]}")
+ print(
+ "\033[91m"
+ + f"Missing key: {key}"
+ + "\033[0m"
+ + " | "
+ + "\033[92m"
+ + f"English: {ref_flat[key]}"
+ + "\033[0m"
+ )
+ print("=============================================")
+ print(f"\033[91m Total missing keys: \033[0m {len(missing_keys)}")
+
+
+ # now compare the tgt_flat with ref_flat to find all missing keys and prompt to terminal for translation. Then save back to the tgt_flat
+
+ # iterate over the missing key and their corresponding values in ref_flat, to get reference google translation using google_translate_to_chinese function
+ # then present the reference translation to the user in the terminal
+ # then present the user with a prompt to ask for translation
+ for i, key in enumerate(missing_keys):
+ print(
+ f"============================================= {i + 1}/{len(missing_keys)}"
+ )
+ # print wrap the missing key in red color, and the English translation in green color
+ print("\033[91m" + "Missing key: " + "\033[0m" + key)
+ print("\033[92m" + f"{ref_codename}: " + "\033[0m" + ref_flat[key])
+ # get reference translation from google translate, print in blue
+ proposal_google = google_translate(ref_flat[key], ref_codename, tgt_codename)
+ print("\033[94m" + f"Reference {tgt_codename} translation: " + "\033[0m" + proposal_google)
+ # prompt user for translation, or enter to use the reference translation, in green color
+ proposal = input("\033[92m" + "Enter translation: " + "\033[0m")
+ if proposal == "":
+ proposal = proposal_google
+ # save the translation to the tgt_flat
+ tgt_flat[key] = proposal
+
+ # unflatten the ref_flat.json and tgt_flat.json back to the original format. save to another file
+ ref_unflat = unflatten_json(ref_flat)
+ tgt_unflat = unflatten_json(tgt_flat)
+ # save the unflattened json to the disk, with original tgt file name with ".proposed" appended before .json
+ # by getting the file name from from the tgt_locale path
+ tgt_locale_name = tgt_locale.split("/")[-1].split(".")[0]
+ with open(f"{tgt_locale_name}.proposed.json", "w") as f:
+ json.dump(tgt_unflat, f, indent=2, ensure_ascii=False)
diff --git a/web/src/locales/zh-Hant.json b/web/src/locales/zh-Hant.json
index c791dae58..5ec9b58ba 100644
--- a/web/src/locales/zh-Hant.json
+++ b/web/src/locales/zh-Hant.json
@@ -52,12 +52,20 @@
"vacuum": "清理",
"select": "選擇",
"database": "資料庫",
- "avatar": "頭像"
+ "avatar": "頭像",
+ "upload": "上傳",
+ "rename": "改名",
+ "name": "姓名",
+ "visibility": "能見度",
+ "clear": "清除",
+ "preview": "預覽"
},
"auth": {
"signup-as-host": "註冊為管理員",
"host-tip": "你正在註冊為管理員帳號。",
- "not-host-tip": "如果你沒有帳號,請聯絡網站管理員。"
+ "not-host-tip": "如果你沒有帳號,請聯絡網站管理員。",
+ "new-password": "新密碼",
+ "repeat-new-password": "重複新密碼"
},
"resource": {
"description": "查看在 Memo 中的靜態資源。例如:圖片",
@@ -78,7 +86,24 @@
"no-files-selected": "沒有文件被選中❗",
"upload-successfully": "上傳成功",
"file-drag-drop-prompt": "將您的文件拖放到此處以上傳文件",
- "select": "選擇"
+ "select": "選擇",
+ "create-dialog": {
+ "upload-method": "上傳方式",
+ "local-file": {
+ "choose": "選擇一個文件...",
+ "option": "本地文件"
+ },
+ "external-link": {
+ "file-name-placeholder": "文件名",
+ "option": "外部鏈接",
+ "type-placeholder": "文件類型",
+ "link": "鏈接",
+ "type": "類型",
+ "file-name": "文件名"
+ },
+ "title": "創建資源"
+ },
+ "search-bar-placeholder": "搜索資源"
},
"archived": {
"archived-memos": "已封存的 Memo",
@@ -104,7 +129,14 @@
"protected": "登入使用者可見",
"public": "所有人可見",
"disabled": "公共memos已禁用"
- }
+ },
+ "fetching-data": "正在獲取數據...",
+ "archived-memos": "歸檔備忘錄",
+ "archived-at": "存檔於",
+ "fetch-more": "點擊此處獲取更多",
+ "embed": "嵌入",
+ "no-archived-memos": "沒有存檔的備忘錄。",
+ "search-placeholder": "搜索備忘錄"
},
"memo-list": {
"fetching-data": "讀取資料中...",
@@ -144,7 +176,10 @@
"text-placeholder": "以 ^ 開頭使用正則表達式"
},
"tag-list": {
- "tip-text": "輸入`#tag `來新增標籤"
+ "tip-text": "輸入`#tag `來新增標籤",
+ "create-tag": "創建標籤",
+ "tag-name": "標籤名",
+ "all-tags": "所有標籤"
},
"search": {
"quickly-filter": "快速過濾"
@@ -170,7 +205,9 @@
"mobile-editor-style": "手機版編輯器樣式",
"default-memo-sort-option": "Memo 顯示時間",
"created_ts": "建立時間",
- "updated_ts": "更新時間"
+ "updated_ts": "更新時間",
+ "daily-review-time-offset": "每日回顧時間偏移",
+ "default-resource-visibility": "默認資源可見性"
},
"storage-section": {
"storage-services-list": "存儲服務列表",
@@ -252,7 +289,8 @@
"succeed-update-additional-script": "更新附加腳本成功",
"update-succeed": "更新成功",
"page-not-found": "404 - 未找到網頁 😥",
- "succeed-vacuum-database": "清理資料庫成功"
+ "succeed-vacuum-database": "清理資料庫成功",
+ "resource-ready": "所有資源都準備好了"
},
"days": {
"monday": "星期一",
@@ -269,5 +307,23 @@
"sat": "六",
"sunday": "星期天",
"sun": "日"
+ },
+ "router": {
+ "back-to-home": "回到首頁"
+ },
+ "ask-ai": {
+ "not-enabled": "您尚未設置 OpenAI API 密鑰。",
+ "title": "問AI",
+ "placeholder": "隨便問",
+ "go-to-settings": "前往設置"
+ },
+ "embed-memo": {
+ "only-public-supported": "* 僅公開備忘錄支持。",
+ "title": "嵌入備忘錄",
+ "copy": "複製",
+ "text": "將以下代碼複製並粘貼到您的博客或網站中。"
+ },
+ "daily-review": {
+ "title": "每日回顧"
}
-}
+}
\ No newline at end of file
diff --git a/web/src/locales/zh.json b/web/src/locales/zh.json
index aba4d6ce6..22ddee566 100644
--- a/web/src/locales/zh.json
+++ b/web/src/locales/zh.json
@@ -52,12 +52,20 @@
"vacuum": "清理",
"select": "选择",
"database": "数据库",
- "avatar": "头像"
+ "avatar": "头像",
+ "rename": "改名",
+ "upload": "上传",
+ "visibility": "能见度",
+ "preview": "预览",
+ "name": "姓名",
+ "clear": "清除"
},
"auth": {
"signup-as-host": "注册为 Host",
"host-tip": "你正在注册为 Host 用户账号。",
- "not-host-tip": "如果你没有账号,请联系站点 Host"
+ "not-host-tip": "如果你没有账号,请联系站点 Host",
+ "new-password": "新密码",
+ "repeat-new-password": "重复新密码"
},
"resource": {
"description": "查看在 Memo 中的静态资源。例如:图片",
@@ -78,7 +86,24 @@
"no-files-selected": "没有文件被选中❗",
"upload-successfully": "上传成功",
"file-drag-drop-prompt": "将您的文件拖放到此处以上传文件",
- "select": "选择"
+ "select": "选择",
+ "create-dialog": {
+ "external-link": {
+ "type-placeholder": "文件类型",
+ "link": "链接",
+ "file-name": "文件名",
+ "type": "类型",
+ "file-name-placeholder": "文件名",
+ "option": "外部链接"
+ },
+ "local-file": {
+ "choose": "选择一个文件...",
+ "option": "本地文件"
+ },
+ "upload-method": "上传方式",
+ "title": "创建资源"
+ },
+ "search-bar-placeholder": "搜索资源"
},
"archived": {
"archived-memos": "已归档的 Memo",
@@ -104,7 +129,14 @@
"protected": "登录用户可见",
"public": "所有人可见",
"disabled": "公共memos已禁用"
- }
+ },
+ "embed": "嵌入",
+ "search-placeholder": "搜索备忘录",
+ "archived-at": "存档于",
+ "no-archived-memos": "没有存档的备忘录。",
+ "fetching-data": "正在获取数据...",
+ "archived-memos": "归档备忘录",
+ "fetch-more": "点击此处获取更多"
},
"memo-list": {
"fetching-data": "请求数据中...",
@@ -173,7 +205,9 @@
"mobile-editor-style": "移动端编辑器样式",
"default-memo-sort-option": "Memo 显示时间",
"created_ts": "创建时间",
- "updated_ts": "更新时间"
+ "updated_ts": "更新时间",
+ "daily-review-time-offset": "每日回顾时间偏移",
+ "default-resource-visibility": "默认资源可见性"
},
"storage-section": {
"storage-services-list": "存储服务列表",
@@ -272,5 +306,23 @@
"sat": "六",
"sunday": "星期天",
"sun": "日"
+ },
+ "embed-memo": {
+ "title": "嵌入备忘录",
+ "copy": "复制",
+ "only-public-supported": "* 仅支持公开备忘录。",
+ "text": "将以下代码复制并粘贴到您的博客或网站中。"
+ },
+ "ask-ai": {
+ "placeholder": "随便问",
+ "title": "问AI",
+ "not-enabled": "您尚未设置 OpenAI API 密钥。",
+ "go-to-settings": "前往设置"
+ },
+ "daily-review": {
+ "title": "每日回顾"
+ },
+ "router": {
+ "back-to-home": "回到首页"
}
-}
+}
\ No newline at end of file