feat: 自动提取i18n文件

ChuanhuChatbot.py

@@ -467,7 +467,7 @@ with gr.Blocks(theme=small_and_beautiful_theme) as demo:
                     updatingMsg_i18n=i18n("正在尝试更新..."),
                     updateSuccess_i18n=i18n("更新成功，请重启本程序"),
                     updateFailure_i18n=i18n(
-                        '更新失败，请尝试<a href="https://github.com/GaiZhenbiao/ChuanhuChatGPT/wiki/使用教程#手动更新" target="_blank">手动更新</a>'),
+                        "更新失败，请尝试[手动更新](https://github.com/GaiZhenbiao/ChuanhuChatGPT/wiki/使用教程#手动更新)"),
                     regenerate_i18n=i18n("重新生成"),
                     deleteRound_i18n=i18n("删除这轮问答"),
                     renameChat_i18n=i18n("重命名该对话"),

locale/extract_locale.py

@@ -2,25 +2,83 @@ import os
 import json
 import re
 
-# Define regular expression patterns
-pattern = r'i18n\((\"{3}.*?\"{3}|\".*?\")\)'
+def get_current_strings():
+    pattern = r'i18n\s*\(\s*["\']([^"\']*(?:\)[^"\']*)?)["\']\s*\)'
 
-# Load the .py file
-with open('ChuanhuChatbot.py', 'r', encoding='utf-8') as f:
-    contents = f.read()
+    # Load the .py files
+    contents = ""
+    for dirpath, dirnames, filenames in os.walk("."):
+        for filename in filenames:
+            if filename.endswith(".py"):
+                filepath = os.path.join(dirpath, filename)
+                with open(filepath, 'r', encoding='utf-8') as f:
+                    contents += f.read()
+    # Matching with regular expressions
+    matches = re.findall(pattern, contents, re.DOTALL)
+    data = {match.strip('()"'): '' for match in matches}
+    fixed_data = {}     # fix some keys
+    for key, value in data.items():
+        if "](" in key and key.count("(") != key.count(")"):
+                fixed_data[key+")"] = value
+        else:
+            fixed_data[key] = value
 
-# Load the .py files in the modules folder
-for filename in os.listdir("modules"):
-    if filename.endswith(".py"):
-        with open(os.path.join("modules", filename), "r", encoding="utf-8") as f:
-            contents += f.read()
+    return fixed_data
 
-# Matching with regular expressions
-matches = re.findall(pattern, contents, re.DOTALL)
 
-# Convert to key/value pairs
-data = {match.strip('()"'): '' for match in matches}
+def get_locale_strings(filename):
+    try:
+        with open(filename, "r", encoding="utf-8") as f:
+            locale_strs = json.load(f)
+    except FileNotFoundError:
+        locale_strs = {}
+    return locale_strs
 
-# Save as a JSON file
-with open('labels.json', 'w', encoding='utf-8') as f:
-    json.dump(data, f, ensure_ascii=False, indent=4)
+
+def sort_strings(existing_translations):
+    # Sort the merged data
+    sorted_translations = {}
+    # Add entries with (NOT USED) in their values
+    for key, value in sorted(existing_translations.items(), key=lambda x: x[0]):
+        if "(NOT USED)" in value:
+            sorted_translations[key] = value
+    # Add entries with empty values
+    for key, value in sorted(existing_translations.items(), key=lambda x: x[0]):
+        if value == "":
+            sorted_translations[key] = value
+    # Add the rest of the entries
+    for key, value in sorted(existing_translations.items(), key=lambda x: x[0]):
+        if value != "" and "(NOT USED)" not in value:
+            sorted_translations[key] = value
+
+    return sorted_translations
+
+
+current_strs = get_current_strings()
+
+locale_files = []
+# 遍历locale目录下的所有json文件
+for dirpath, dirnames, filenames in os.walk("locale"):
+    for filename in filenames:
+        if filename.endswith(".json"):
+            locale_files.append(os.path.join(dirpath, filename))
+
+
+for locale_filename in locale_files:
+    if "zh_CN" in locale_filename:
+        continue
+    locale_strs = get_locale_strings(locale_filename)
+
+    # Add new keys
+    for key in current_strs:
+        if key not in locale_strs:
+            locale_strs[key] = ""
+    # Add (NOT USED) to invalid keys
+    for key in locale_strs:
+        if key not in current_strs:
+            locale_strs[key] = "(NOT USED)" + locale_strs[key]
+
+    locale_strs = sort_strings(locale_strs)
+
+    with open(locale_filename, 'w', encoding='utf-8') as f:
+        json.dump(locale_strs, f, ensure_ascii=False, indent=4)