extract_tasks_i18n.py 5.3 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169
  1. #!/usr/bin/env python3
  2. """
  3. 提取 tasks 目录下子任务名称的翻译
  4. 从两个源文件提取:
  5. 1. module/config/i18n/zh_CN.xml (本仓库)
  6. 2. https://raw.githubusercontent.com/runhey/OASX/master/lib/config/translation/i18n_cn.dart (外部仓库)
  7. 输出到 .github/workflows/assets/tasks-i18n-{YYYY-MM-DD}.md
  8. """
  9. import os
  10. import re
  11. import urllib.request
  12. from pathlib import Path
  13. import datetime
  14. date = datetime.datetime.now().strftime("%Y-%m-%d")
  15. # paths
  16. SCRIPT_DIR = Path(__file__).parent.resolve()
  17. REPO_ROOT = SCRIPT_DIR.parent.parent.parent
  18. TASKS_DIR = REPO_ROOT / "tasks"
  19. ZH_CN_XML = REPO_ROOT / "module/config/i18n/zh_CN.xml"
  20. OASX_I18N_URL = "https://raw.githubusercontent.com/runhey/OASX/master/lib/config/translation/i18n_cn.dart"
  21. OUTPUT_FILE = SCRIPT_DIR.parent / "assets" / f"tasks-i18n-{date}.md"
  22. def get_tasks_directories():
  23. """获取 tasks 目录下的所有子目录名"""
  24. if not TASKS_DIR.exists():
  25. print(f"Warning: {TASKS_DIR} not found")
  26. return []
  27. dirs = [d.name for d in TASKS_DIR.iterdir() if d.is_dir()]
  28. return sorted(dirs)
  29. def extract_from_zh_cn_xml():
  30. """从 zh_CN.xml 提取翻译"""
  31. translations = {}
  32. if not ZH_CN_XML.exists():
  33. print(f"Warning: {ZH_CN_XML} not found")
  34. return translations
  35. content = ZH_CN_XML.read_text(encoding="utf-8")
  36. # 从 TaskList 和 FluTreeView 上下文中提取
  37. # 格式: <message><source>DailyTrifles</source><translation>每日琐事</translation></message>
  38. pattern = r'<source>([A-Za-z]+)</source>\s*<translation>([^<]+)</translation>'
  39. for match in re.finditer(pattern, content):
  40. key, value = match.groups()
  41. translations[key] = value.strip()
  42. return translations
  43. def extract_from_oasx():
  44. """从 OASX 的 i18n_cn.dart 提取翻译"""
  45. translations = {}
  46. try:
  47. print(f"Fetching {OASX_I18N_URL}...")
  48. with urllib.request.urlopen(OASX_I18N_URL, timeout=30) as response:
  49. content = response.read().decode("utf-8")
  50. except Exception as e:
  51. print(f"Warning: Failed to fetch OASX i18n: {e}")
  52. return translations
  53. # 格式1: I18n.daily_trifles: '每日琐事', (snake_case key -> PascalCase)
  54. pattern1 = r"I18n\.([a-z_]+):\s*'([^']+)'"
  55. for match in re.finditer(pattern1, content):
  56. key, value = match.groups()
  57. dir_name = "".join(word.capitalize() for word in key.split("_"))
  58. translations[dir_name] = value.strip()
  59. # 格式2: 'AbyssShadows': '狭间暗域', (PascalCase key,直接)
  60. pattern2 = r"'([A-Z][a-zA-Z]+)':\s*'([^']+)'"
  61. for match in re.finditer(pattern2, content):
  62. key, value = match.groups()
  63. # 只保留看起来像目录名的 key(PascalCase,多个单词)
  64. if len(key) > 3 and key[0].isupper():
  65. translations[key] = value.strip()
  66. return translations
  67. def merge_translations(tasks_dirs, zh_cn_translations, oasx_translations):
  68. """合并翻译结果"""
  69. result = {}
  70. for dir_name in tasks_dirs:
  71. # 优先级:zh_CN.xml > OASX > 未知
  72. if dir_name in zh_cn_translations:
  73. result[dir_name] = zh_cn_translations[dir_name]
  74. elif dir_name in oasx_translations:
  75. result[dir_name] = oasx_translations[dir_name]
  76. else:
  77. result[dir_name] = "" # 未找到翻译
  78. return result
  79. def generate_markdown(translations):
  80. """生成 Markdown 格式输出"""
  81. lines = [
  82. "# Tasks 子目录翻译",
  83. "",
  84. "自动生成文件 - 请勿手动修改",
  85. "",
  86. "| 目录 | 中文 |",
  87. "|------|------|",
  88. ]
  89. for dir_name in sorted(translations.keys()):
  90. chinese = translations[dir_name] or "(未找到翻译)"
  91. lines.append(f"| {dir_name} | {chinese} |")
  92. lines.append("")
  93. lines.append("## 来源说明")
  94. lines.append(f"- `{ZH_CN_XML.relative_to(REPO_ROOT)}` - 本仓库")
  95. lines.append(f"- {OASX_I18N_URL} - 外部仓库 (OASX)")
  96. return "\n".join(lines)
  97. def main():
  98. print("=== Tasks 翻译提取工具 ===\n")
  99. print(f"Repo root: {REPO_ROOT}")
  100. # 1. 获取 tasks 子目录
  101. print("1. 获取 tasks 子目录...")
  102. tasks_dirs = get_tasks_directories()
  103. print(f" 找到 {len(tasks_dirs)} 个子目录")
  104. # 2. 从 zh_CN.xml 提取
  105. print("2. 从 zh_CN.xml 提取翻译...")
  106. zh_cn_translations = extract_from_zh_cn_xml()
  107. print(f" 找到 {len(zh_cn_translations)} 条翻译")
  108. # 3. 从 OASX 提取
  109. print("3. 从 OASX i18n_cn.dart 提取翻译...")
  110. oasx_translations = extract_from_oasx()
  111. print(f" 找到 {len(oasx_translations)} 条翻译")
  112. # 4. 合并结果
  113. print("4. 合并翻译结果...")
  114. merged = merge_translations(tasks_dirs, zh_cn_translations, oasx_translations)
  115. # 5. 生成输出
  116. OUTPUT_FILE.parent.mkdir(parents=True, exist_ok=True)
  117. print(f"5. 生成输出到 {OUTPUT_FILE}...")
  118. output_content = generate_markdown(merged)
  119. OUTPUT_FILE.write_text(output_content, encoding="utf-8")
  120. # 6. 统计
  121. found = sum(1 for v in merged.values() if v)
  122. print(f"\n完成!找到翻译: {found}/{len(merged)}")
  123. # 打印未找到翻译的目录
  124. missing = [k for k, v in merged.items() if not v]
  125. if missing:
  126. print(f"\n未找到翻译的目录: {', '.join(missing)}")
  127. if __name__ == "__main__":
  128. main()