diff --git a/tools/i18n/scan_i18n.py b/tools/i18n/scan_i18n.py index b542c102..1091f95b 100644 --- a/tools/i18n/scan_i18n.py +++ b/tools/i18n/scan_i18n.py @@ -1,9 +1,14 @@ import ast +import code import glob import json import os from collections import OrderedDict +I18N_JSON_DIR = os.path.join(os.path.dirname(os.path.relpath(__file__)), 'locale') +DEFAULT_LANGUAGE = "zh_CN" +TITLE_LEN = 100 +SHOW_KEYS = False # 是否显示键信息 def extract_i18n_strings(node): i18n_strings = [] @@ -22,93 +27,80 @@ def extract_i18n_strings(node): return i18n_strings - # scan the directory for all .py files (recursively) # for each file, parse the code into an AST # for each AST, extract the i18n strings -strings = [] -for filename in glob.iglob("**/*.py", recursive=True): - with open(filename, "r", encoding="utf-8") as f: - code = f.read() - if "I18nAuto" in code: - tree = ast.parse(code) - i18n_strings = extract_i18n_strings(tree) - print(filename, len(i18n_strings)) - strings.extend(i18n_strings) -code_keys = set(strings) -""" -n_i18n.py -gui_v1.py 26 -app.py 16 -infer-web.py 147 -scan_i18n.py 0 -i18n.py 0 -lib/train/process_ckpt.py 1 -""" -print("Total unique:", len(code_keys)) +def scan_i18n_strings(): + strings = [] + print(" Scanning Files and Extracting i18n Strings ".center(TITLE_LEN, "=")) + for filename in glob.iglob("**/*.py", recursive=True): + with open(filename, "r", encoding="utf-8") as f: + code = f.read() + if "I18nAuto" in code: + tree = ast.parse(code) + i18n_strings = extract_i18n_strings(tree) + print(f"{filename.ljust(30)}: {len(i18n_strings)}") + strings.extend(i18n_strings) -I18N_FILE_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'locale') -# "i18n/locale" -DEFAULT_LANGUAGE = "zh_CN" + code_keys = set(strings) + print(f"{'Total Unique'.ljust(30)}: {len(code_keys)}") + return code_keys -standard_file = os.path.join(I18N_FILE_PATH, DEFAULT_LANGUAGE + ".json") -with open(standard_file, "r", encoding="utf-8") as f: - standard_data = json.load(f, object_pairs_hook=OrderedDict) -standard_keys = set(standard_data.keys()) - -# Define the standard file name -unused_keys = standard_keys - code_keys -print("Unused keys:", len(unused_keys)) -for unused_key in unused_keys: - print("\t", unused_key) - -missing_keys = code_keys - standard_keys -print("Missing keys:", len(missing_keys)) -for missing_key in missing_keys: - print("\t", missing_key) - -code_keys_dict = OrderedDict() -for s in strings: - code_keys_dict[s] = s - -# write back -with open(standard_file, "w", encoding="utf-8") as f: - json.dump(code_keys_dict, f, ensure_ascii=False, indent=4, sort_keys=True) - f.write("\n") - -languages_files = [os.path.join(I18N_FILE_PATH, f) for f in os.listdir(I18N_FILE_PATH) if f.endswith(r".json") and f != DEFAULT_LANGUAGE + ".json"] - -# print(os.listdir(I18N_FILE_PATH)) -# print(languages_files) -for language_file in languages_files: - print(f"Processing {language_file}".center(100, "=")) - with open(language_file, "r", encoding="utf-8") as f: - language_data = json.load(f, object_pairs_hook=OrderedDict) - - diff = set(standard_data.keys()) - set(language_data.keys()) - miss = set(language_data.keys()) - set(standard_data.keys()) - - for key in diff: - language_data[key] = "#!" + key - print(f"Added missing key {key} to {language_file}") - - for key in miss: - del language_data[key] - print(f"Removed unused key {key} from {language_file}") - - language_data = OrderedDict( - sorted(language_data.items(), - key=lambda x: list(standard_data.keys()).index(x[0]))) - - for key, value in language_data.items(): +def update_i18n_json(json_file, standard_keys): + print(f" Process {json_file} ".center(TITLE_LEN, "=")) + # 读取 JSON 文件 + with open(json_file, "r", encoding="utf-8") as f: + json_data = json.load(f, object_pairs_hook=OrderedDict) + # 打印处理前的 JSON 条目数 + print(f"{'Total Keys (Before)'.ljust(20)}: {len(json_data)}") + # 识别缺失的键并补全 + miss_keys = set(standard_keys) - set(json_data.keys()) + if len(miss_keys) > 0: + print(f"{'Missing Keys (+)'.ljust(20)}: {len(miss_keys)}") + for key in miss_keys: + if DEFAULT_LANGUAGE in json_file: + # 默认语言的键值相同. + json_data[key] = key + else: + # 其他语言的值设置为 #! + 键名以标注未被翻译. + json_data[key] = "#!" + key + if SHOW_KEYS: + print(f"{'Added Missing Key'.ljust(20)}: {key}") + # 识别多余的键并删除 + diff_keys = set(json_data.keys()) - set(standard_keys) + if len(diff_keys) > 0: + print(f"{'Unused Keys (-)'.ljust(20)}: {len(diff_keys)}") + for key in diff_keys: + del json_data[key] + if SHOW_KEYS: + print(f"{'Removed Unused Key'.ljust(20)}: {key}") + # 按键顺序排序 + json_data = OrderedDict( + sorted(json_data.items(), + key=lambda x: list(standard_keys).index(x[0]))) + # 打印处理后的 JSON 条目数 + print(f"{'Total Keys (After)'.ljust(20)}: {len(json_data)}") + # 识别有待翻译的键 + num_miss_translation = 0 + for key, value in json_data.items(): if value.startswith("#!"): - print(f"Missing translation for {key} in {language_file}") - - with open(language_file, "w", encoding="utf-8") as f: - json.dump(language_data, f, ensure_ascii=False, indent=4, sort_keys=True) + num_miss_translation += 1 + if SHOW_KEYS: + print(f"{'Missing Translation'.ljust(20)}: {key}") + if num_miss_translation > 0: + print(f"{'Missing Translation'.ljust(20)}: {num_miss_translation}") + # 将处理后的结果写入 JSON 文件 + with open(json_file, "w", encoding="utf-8") as f: + json.dump(json_data, f, ensure_ascii=False, indent=4, sort_keys=True) f.write("\n") - - print(f"Updated {language_file}".center(100, "=") + '\n') + print(f" Updated {json_file} ".center(TITLE_LEN, "=") + '\n') -print("Finished") \ No newline at end of file +if __name__ == "__main__": + code_keys = scan_i18n_strings() + for json_file in os.listdir(I18N_JSON_DIR): + if json_file.endswith(r".json"): + json_file = os.path.join(I18N_JSON_DIR, json_file) + update_i18n_json(json_file, code_keys) + else: + pass \ No newline at end of file