From 14f3dcbe9706dff7b8ae96eb45daf3c8f0845a21 Mon Sep 17 00:00:00 2001 From: tangwang Date: Thu, 16 Oct 2025 22:21:48 +0800 Subject: [PATCH] offline tasks --- offline_tasks/run.sh | 6 ++++-- offline_tasks/scripts/i2i_content_similar.py | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++---------- offline_tasks/scripts/i2i_deepwalk.py | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------------- offline_tasks/scripts/i2i_session_w2v.py | 116 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----------------------- offline_tasks/scripts/interest_aggregation.py | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++------- 5 files changed, 278 insertions(+), 59 deletions(-) diff --git a/offline_tasks/run.sh b/offline_tasks/run.sh index 38bd1e3..b794ce2 100755 --- a/offline_tasks/run.sh +++ b/offline_tasks/run.sh @@ -4,7 +4,7 @@ cd /home/tw/recommendation/offline_tasks # cat UPDATE_CONFIG_GUIDE.md # 2. 测试连接 -python3 test_connection.py +# python3 test_connection.py # 3. 调试模式运行（小数据量） python3 run_all.py --lookback_days 7 --top_n 10 --debug @@ -13,7 +13,9 @@ mv output output_debug mkdir output # # 4. 生产模式运行（大数据量） -python3 run_all.py --lookback_days 730 --top_n 50 +python3 run_all.py --lookback_days 730 --top_n 50 --debug # 5. 加载到Redis python3 scripts/load_index_to_redis.py --redis-host localhost + + diff --git a/offline_tasks/scripts/i2i_content_similar.py b/offline_tasks/scripts/i2i_content_similar.py index c4c2108..b58861d 100644 --- a/offline_tasks/scripts/i2i_content_similar.py +++ b/offline_tasks/scripts/i2i_content_similar.py @@ -17,6 +17,11 @@ from db_service import create_db_connection from offline_tasks.config.offline_config import ( DB_CONFIG, OUTPUT_DIR, DEFAULT_I2I_TOP_N ) +from offline_tasks.scripts.debug_utils import ( + setup_debug_logger, log_dataframe_info, log_dict_stats, + save_readable_index, fetch_name_mappings, log_algorithm_params, + log_processing_step +) def fetch_product_features(engine): @@ -221,8 +226,19 @@ def main(): args = parser.parse_args() + # 设置logger + logger = setup_debug_logger('i2i_content_similar', debug=args.debug) + + # 记录算法参数 + params = { + 'top_n': args.top_n, + 'method': args.method, + 'debug': args.debug + } + log_algorithm_params(logger, params) + # 创建数据库连接 - print("Connecting to database...") + logger.info("连接数据库...") engine = create_db_connection( DB_CONFIG['host'], DB_CONFIG['port'], @@ -232,34 +248,47 @@ def main(): ) # 获取商品特征 + log_processing_step(logger, "获取商品特征") df = fetch_product_features(engine) + logger.info(f"获取到 {len(df)} 个商品的特征数据") + log_dataframe_info(logger, df, "商品特征数据") # 计算相似度 + log_processing_step(logger, f"计算相似度 (方法: {args.method})") if args.method == 'tfidf': - print("\nUsing TF-IDF method...") + logger.info("使用 TF-IDF 方法...") result = calculate_content_similarity(df, args.top_n) elif args.method == 'category': - print("\nUsing category-based method...") + logger.info("使用基于分类的方法...") result = calculate_category_based_similarity(df) else: # hybrid - print("\nUsing hybrid method...") + logger.info("使用混合方法 (TF-IDF 70% + 分类 30%)...") tfidf_sim = calculate_content_similarity(df, args.top_n) category_sim = calculate_category_based_similarity(df) result = merge_similarities(tfidf_sim, category_sim, weight1=0.7, weight2=0.3) - # 创建item_id到name的映射 - item_name_map = dict(zip(df['item_id'], df['item_name'])) + logger.info(f"为 {len(result)} 个物品生成了相似度") # 输出结果 + log_processing_step(logger, "保存结果") output_file = args.output or os.path.join( OUTPUT_DIR, f'i2i_content_{args.method}_{datetime.now().strftime("%Y%m%d")}.txt' ) - print(f"\nWriting results to {output_file}...") + # 获取name mappings + name_mappings = {} + if args.debug: + logger.info("获取物品名称映射...") + name_mappings = fetch_name_mappings(engine, debug=True) + + logger.info(f"写入结果到 {output_file}...") with open(output_file, 'w', encoding='utf-8') as f: for item_id, sims in result.items(): - item_name = item_name_map.get(item_id, 'Unknown') + # 使用name_mappings获取名称 + item_name = name_mappings.get(item_id, 'Unknown') + if item_name == 'Unknown' and 'item_name' in df.columns: + item_name = df[df['item_id'] == item_id]['item_name'].iloc[0] if len(df[df['item_id'] == item_id]) > 0 else 'Unknown' if not sims: continue @@ -268,8 +297,19 @@ def main(): sim_str = ','.join([f'{sim_id}:{score:.4f}' for sim_id, score in sims]) f.write(f'{item_id}\t{item_name}\t{sim_str}\n') - print(f"Done! Generated content-based similarities for {len(result)} items") - print(f"Output saved to: {output_file}") + logger.info(f"完成！为 {len(result)} 个物品生成了基于内容的相似度") + logger.info(f"输出保存到：{output_file}") + + # 如果启用debug模式，保存可读格式 + if args.debug: + log_processing_step(logger, "保存Debug可读格式") + save_readable_index( + output_file, + result, + name_mappings, + index_type=f'i2i:content:{args.method}', + logger=logger + ) if __name__ == '__main__': diff --git a/offline_tasks/scripts/i2i_deepwalk.py b/offline_tasks/scripts/i2i_deepwalk.py index 51ac7dd..955b9d6 100644 --- a/offline_tasks/scripts/i2i_deepwalk.py +++ b/offline_tasks/scripts/i2i_deepwalk.py @@ -17,6 +17,11 @@ from offline_tasks.config.offline_config import ( DB_CONFIG, OUTPUT_DIR, I2I_CONFIG, get_time_range, DEFAULT_LOOKBACK_DAYS, DEFAULT_I2I_TOP_N ) +from offline_tasks.scripts.debug_utils import ( + setup_debug_logger, log_dataframe_info, log_dict_stats, + save_readable_index, fetch_name_mappings, log_algorithm_params, + log_processing_step +) def build_item_graph(df, behavior_weights): @@ -223,8 +228,26 @@ def main(): args = parser.parse_args() + # 设置logger + logger = setup_debug_logger('i2i_deepwalk', debug=args.debug) + + # 记录算法参数 + params = { + 'num_walks': args.num_walks, + 'walk_length': args.walk_length, + 'window_size': args.window_size, + 'vector_size': args.vector_size, + 'min_count': args.min_count, + 'workers': args.workers, + 'epochs': args.epochs, + 'top_n': args.top_n, + 'lookback_days': args.lookback_days, + 'debug': args.debug + } + log_algorithm_params(logger, params) + # 创建数据库连接 - print("Connecting to database...") + logger.info("连接数据库...") engine = create_db_connection( DB_CONFIG['host'], DB_CONFIG['port'], @@ -235,7 +258,7 @@ def main(): # 获取时间范围 start_date, end_date = get_time_range(args.lookback_days) - print(f"Fetching data from {start_date} to {end_date}...") + logger.info(f"获取数据范围：{start_date} 到 {end_date}") # SQL查询 - 获取用户行为数据 sql_query = f""" @@ -255,9 +278,12 @@ def main(): AND se.anonymous_id IS NOT NULL """ - print("Executing SQL query...") + logger.info("执行SQL查询...") df = pd.read_sql(sql_query, engine) - print(f"Fetched {len(df)} records") + logger.info(f"获取到 {len(df)} 条记录") + + # 记录数据信息 + log_dataframe_info(logger, df, "用户行为数据") # 定义行为权重 behavior_weights = { @@ -267,23 +293,26 @@ def main(): 'addToCart': 3.0, 'purchase': 10.0 } + logger.debug(f"行为权重: {behavior_weights}") # 构建物品图 - print("Building item graph...") + log_processing_step(logger, "构建物品图") graph = build_item_graph(df, behavior_weights) - print(f"Graph built with {len(graph)} nodes") + logger.info(f"构建物品图完成，共 {len(graph)} 个节点") # 保存边文件（可选） if args.save_graph: edge_file = os.path.join(OUTPUT_DIR, f'item_graph_{datetime.now().strftime("%Y%m%d")}.txt') save_edge_file(graph, edge_file) + logger.info(f"图边文件已保存到 {edge_file}") # 生成随机游走 - print("Generating random walks...") + log_processing_step(logger, "生成随机游走") walks = generate_walks(graph, args.num_walks, args.walk_length) - print(f"Generated {len(walks)} walks") + logger.info(f"生成 {len(walks)} 条游走路径") # 训练Word2Vec模型 + log_processing_step(logger, "训练Word2Vec模型") w2v_config = { 'vector_size': args.vector_size, 'window_size': args.window_size, @@ -292,29 +321,39 @@ def main(): 'epochs': args.epochs, 'sg': 1 } + logger.debug(f"Word2Vec配置: {w2v_config}") model = train_word2vec(walks, w2v_config) + logger.info(f"训练完成。词汇表大小：{len(model.wv)}") # 保存模型（可选） if args.save_model: model_path = os.path.join(OUTPUT_DIR, f'deepwalk_model_{datetime.now().strftime("%Y%m%d")}.model') model.save(model_path) - print(f"Model saved to {model_path}") + logger.info(f"模型已保存到 {model_path}") # 生成相似度 - print("Generating similarities...") + log_processing_step(logger, "生成相似度") result = generate_similarities(model, top_n=args.top_n) - - # 创建item_id到name的映射 - item_name_map = dict(zip(df['item_id'].astype(str), df.groupby('item_id')['item_name'].first())) + logger.info(f"生成了 {len(result)} 个物品的相似度") # 输出结果 + log_processing_step(logger, "保存结果") output_file = args.output or os.path.join(OUTPUT_DIR, f'i2i_deepwalk_{datetime.now().strftime("%Y%m%d")}.txt') - print(f"Writing results to {output_file}...") + # 获取name mappings + name_mappings = {} + if args.debug: + logger.info("获取物品名称映射...") + name_mappings = fetch_name_mappings(engine, debug=True) + + logger.info(f"写入结果到 {output_file}...") with open(output_file, 'w', encoding='utf-8') as f: for item_id, sims in result.items(): - item_name = item_name_map.get(item_id, 'Unknown') + # 使用name_mappings获取名称 + item_name = name_mappings.get(int(item_id), 'Unknown') if item_id.isdigit() else 'Unknown' + if item_name == 'Unknown' and 'item_name' in df.columns: + item_name = df[df['item_id'].astype(str) == item_id]['item_name'].iloc[0] if len(df[df['item_id'].astype(str) == item_id]) > 0 else 'Unknown' if not sims: continue @@ -323,8 +362,19 @@ def main(): sim_str = ','.join([f'{sim_id}:{score:.4f}' for sim_id, score in sims]) f.write(f'{item_id}\t{item_name}\t{sim_str}\n') - print(f"Done! Generated i2i similarities for {len(result)} items") - print(f"Output saved to: {output_file}") + logger.info(f"完成！为 {len(result)} 个物品生成了相似度") + logger.info(f"输出保存到：{output_file}") + + # 如果启用debug模式，保存可读格式 + if args.debug: + log_processing_step(logger, "保存Debug可读格式") + save_readable_index( + output_file, + result, + name_mappings, + index_type='i2i:deepwalk', + logger=logger + ) if __name__ == '__main__': diff --git a/offline_tasks/scripts/i2i_session_w2v.py b/offline_tasks/scripts/i2i_session_w2v.py index ab74f77..3a71a4e 100644 --- a/offline_tasks/scripts/i2i_session_w2v.py +++ b/offline_tasks/scripts/i2i_session_w2v.py @@ -18,21 +18,30 @@ from offline_tasks.config.offline_config import ( DB_CONFIG, OUTPUT_DIR, I2I_CONFIG, get_time_range, DEFAULT_LOOKBACK_DAYS, DEFAULT_I2I_TOP_N ) +from offline_tasks.scripts.debug_utils import ( + setup_debug_logger, log_dataframe_info, log_dict_stats, + save_readable_index, fetch_name_mappings, log_algorithm_params, + log_processing_step +) -def prepare_session_data(df, session_gap_minutes=30): +def prepare_session_data(df, session_gap_minutes=30, logger=None): """ 准备会话数据 Args: df: DataFrame with columns: user_id, item_id, create_time session_gap_minutes: 会话间隔时间（分钟） + logger: Logger instance for debugging Returns: List of sessions, each session is a list of item_ids """ sessions = [] + if logger: + logger.debug(f"开始准备会话数据，会话间隔：{session_gap_minutes}分钟") + # 按用户和时间排序 df = df.sort_values(['user_id', 'create_time']) @@ -65,21 +74,33 @@ def prepare_session_data(df, session_gap_minutes=30): # 过滤掉长度小于2的会话 sessions = [s for s in sessions if len(s) >= 2] + if logger: + session_lengths = [len(s) for s in sessions] + logger.debug(f"生成 {len(sessions)} 个会话") + logger.debug(f"会话长度统计：最小={min(session_lengths)}, 最大={max(session_lengths)}, " + f"平均={sum(session_lengths)/len(session_lengths):.2f}") + return sessions -def train_word2vec(sessions, config): +def train_word2vec(sessions, config, logger=None): """ 训练Word2Vec模型 Args: sessions: List of sessions config: Word2Vec配置 + logger: Logger instance for debugging Returns: Word2Vec模型 """ - print(f"Training Word2Vec with {len(sessions)} sessions...") + if logger: + logger.info(f"训练Word2Vec模型，共 {len(sessions)} 个会话") + logger.debug(f"模型参数：vector_size={config['vector_size']}, window={config['window_size']}, " + f"min_count={config['min_count']}, epochs={config['epochs']}") + else: + print(f"Training Word2Vec with {len(sessions)} sessions...") model = Word2Vec( sentences=sessions, @@ -92,23 +113,30 @@ def train_word2vec(sessions, config): seed=42 ) - print(f"Training completed. Vocabulary size: {len(model.wv)}") + if logger: + logger.info(f"训练完成。词汇表大小：{len(model.wv)}") + else: + print(f"Training completed. Vocabulary size: {len(model.wv)}") return model -def generate_similarities(model, top_n=50): +def generate_similarities(model, top_n=50, logger=None): """ 生成物品相似度 Args: model: Word2Vec模型 top_n: Top N similar items + logger: Logger instance for debugging Returns: Dict[item_id, List[Tuple(similar_item_id, score)]] """ result = {} + if logger: + logger.info(f"生成Top {top_n} 相似物品") + for item_id in model.wv.index_to_key: try: similar_items = model.wv.most_similar(item_id, topn=top_n) @@ -116,6 +144,9 @@ def generate_similarities(model, top_n=50): except KeyError: continue + if logger: + logger.info(f"生成了 {len(result)} 个物品的相似度") + return result @@ -146,8 +177,25 @@ def main(): args = parser.parse_args() + # 设置logger + logger = setup_debug_logger('i2i_session_w2v', debug=args.debug) + + # 记录算法参数 + params = { + 'window_size': args.window_size, + 'vector_size': args.vector_size, + 'min_count': args.min_count, + 'workers': args.workers, + 'epochs': args.epochs, + 'top_n': args.top_n, + 'lookback_days': args.lookback_days, + 'session_gap_minutes': args.session_gap, + 'debug': args.debug + } + log_algorithm_params(logger, params) + # 创建数据库连接 - print("Connecting to database...") + logger.info("连接数据库...") engine = create_db_connection( DB_CONFIG['host'], DB_CONFIG['port'], @@ -158,7 +206,7 @@ def main(): # 获取时间范围 start_date, end_date = get_time_range(args.lookback_days) - print(f"Fetching data from {start_date} to {end_date}...") + logger.info(f"获取数据范围：{start_date} 到 {end_date}") # SQL查询 - 获取用户行为序列 sql_query = f""" @@ -181,19 +229,23 @@ def main(): se.create_time """ - print("Executing SQL query...") + logger.info("执行SQL查询...") df = pd.read_sql(sql_query, engine) - print(f"Fetched {len(df)} records") + logger.info(f"获取到 {len(df)} 条记录") + + # 记录数据信息 + log_dataframe_info(logger, df, "用户行为数据") # 转换create_time为datetime df['create_time'] = pd.to_datetime(df['create_time']) # 准备会话数据 - print("Preparing session data...") - sessions = prepare_session_data(df, session_gap_minutes=args.session_gap) - print(f"Generated {len(sessions)} sessions") + log_processing_step(logger, "准备会话数据") + sessions = prepare_session_data(df, session_gap_minutes=args.session_gap, logger=logger) + logger.info(f"生成 {len(sessions)} 个会话") # 训练Word2Vec模型 + log_processing_step(logger, "训练Word2Vec模型") w2v_config = { 'vector_size': args.vector_size, 'window_size': args.window_size, @@ -203,28 +255,35 @@ def main(): 'sg': 1 } - model = train_word2vec(sessions, w2v_config) + model = train_word2vec(sessions, w2v_config, logger=logger) # 保存模型（可选） if args.save_model: model_path = os.path.join(OUTPUT_DIR, f'session_w2v_model_{datetime.now().strftime("%Y%m%d")}.model') model.save(model_path) - print(f"Model saved to {model_path}") + logger.info(f"模型已保存到 {model_path}") # 生成相似度 - print("Generating similarities...") - result = generate_similarities(model, top_n=args.top_n) - - # 创建item_id到name的映射 - item_name_map = dict(zip(df['item_id'].astype(str), df.groupby('item_id')['item_name'].first())) + log_processing_step(logger, "生成相似度") + result = generate_similarities(model, top_n=args.top_n, logger=logger) # 输出结果 + log_processing_step(logger, "保存结果") output_file = args.output or os.path.join(OUTPUT_DIR, f'i2i_session_w2v_{datetime.now().strftime("%Y%m%d")}.txt') - print(f"Writing results to {output_file}...") + # 获取name mappings用于标准输出格式 + name_mappings = {} + if args.debug: + logger.info("获取物品名称映射...") + name_mappings = fetch_name_mappings(engine, debug=True) + + logger.info(f"写入结果到 {output_file}...") with open(output_file, 'w', encoding='utf-8') as f: for item_id, sims in result.items(): - item_name = item_name_map.get(item_id, 'Unknown') + # 使用name_mappings获取名称，如果没有则从df中获取 + item_name = name_mappings.get(int(item_id), 'Unknown') if item_id.isdigit() else 'Unknown' + if item_name == 'Unknown' and 'item_name' in df.columns: + item_name = df[df['item_id'].astype(str) == item_id]['item_name'].iloc[0] if len(df[df['item_id'].astype(str) == item_id]) > 0 else 'Unknown' if not sims: continue @@ -233,8 +292,19 @@ def main(): sim_str = ','.join([f'{sim_id}:{score:.4f}' for sim_id, score in sims]) f.write(f'{item_id}\t{item_name}\t{sim_str}\n') - print(f"Done! Generated i2i similarities for {len(result)} items") - print(f"Output saved to: {output_file}") + logger.info(f"完成！为 {len(result)} 个物品生成了相似度") + logger.info(f"输出保存到：{output_file}") + + # 如果启用debug模式，保存可读格式 + if args.debug: + log_processing_step(logger, "保存Debug可读格式") + save_readable_index( + output_file, + result, + name_mappings, + index_type='i2i:session_w2v', + logger=logger + ) if __name__ == '__main__': diff --git a/offline_tasks/scripts/interest_aggregation.py b/offline_tasks/scripts/interest_aggregation.py index 622e623..bfc3abf 100644 --- a/offline_tasks/scripts/interest_aggregation.py +++ b/offline_tasks/scripts/interest_aggregation.py @@ -17,6 +17,11 @@ from offline_tasks.config.offline_config import ( DB_CONFIG, OUTPUT_DIR, INTEREST_AGGREGATION_CONFIG, get_time_range, DEFAULT_LOOKBACK_DAYS, DEFAULT_RECENT_DAYS, DEFAULT_INTEREST_TOP_N ) +from offline_tasks.scripts.debug_utils import ( + setup_debug_logger, log_dataframe_info, log_dict_stats, + save_readable_index, fetch_name_mappings, log_algorithm_params, + log_processing_step +) def calculate_time_weight(event_time, reference_time, decay_factor=0.95, days_unit=30): @@ -227,8 +232,22 @@ def main(): args = parser.parse_args() + # 设置logger + logger = setup_debug_logger('interest_aggregation', debug=args.debug) + + # 记录算法参数 + params = { + 'top_n': args.top_n, + 'lookback_days': args.lookback_days, + 'recent_days': args.recent_days, + 'new_days': args.new_days, + 'decay_factor': args.decay_factor, + 'debug': args.debug + } + log_algorithm_params(logger, params) + # 创建数据库连接 - print("Connecting to database...") + logger.info("连接数据库...") engine = create_db_connection( DB_CONFIG['host'], DB_CONFIG['port'], @@ -242,7 +261,9 @@ def main(): recent_start_date, _ = get_time_range(args.recent_days) new_start_date, _ = get_time_range(args.new_days) - print(f"Fetching data from {start_date} to {end_date}...") + logger.info(f"获取数据范围：{start_date} 到 {end_date}") + logger.debug(f"热门商品起始日期：{recent_start_date}") + logger.debug(f"新品起始日期：{new_start_date}") # SQL查询 - 获取用户行为数据（包含用户特征和商品分类） sql_query = f""" @@ -279,9 +300,12 @@ def main(): se.create_time """ - print("Executing SQL query...") + logger.info("执行SQL查询...") df = pd.read_sql(sql_query, engine) - print(f"Fetched {len(df)} records") + logger.info(f"获取到 {len(df)} 条记录") + + # 记录数据信息 + log_dataframe_info(logger, df, "用户行为数据") # 转换时间列 df['create_time'] = pd.to_datetime(df['create_time']) @@ -289,37 +313,70 @@ def main(): # 定义行为权重 behavior_weights = INTEREST_AGGREGATION_CONFIG['behavior_weights'] + logger.debug(f"行为权重: {behavior_weights}") # 准备不同类型的数据集 + log_processing_step(logger, "准备不同类型的数据集") # 1. 热门商品：最近N天的高交互商品 df_hot = df[df['create_time'] >= recent_start_date].copy() + logger.info(f"热门商品数据集：{len(df_hot)} 条记录") # 2. 加购商品：加购行为 df_cart = df[df['event_type'].isin(['addToCart', 'addToPool'])].copy() + logger.info(f"加购商品数据集：{len(df_cart)} 条记录") # 3. 新品：商品创建时间在最近N天内 df_new = df[df['item_create_time'] >= new_start_date].copy() + logger.info(f"新品数据集：{len(df_new)} 条记录") # 生成不同列表类型的索引 - print("\n=== Generating indices ===") + log_processing_step(logger, "生成不同列表类型的索引") list_type_indices = generate_list_type_indices( df_hot, df_cart, df_new, behavior_weights ) + logger.info(f"生成了 {len(list_type_indices)} 种列表类型的索引") + + # 获取name mappings用于debug输出 + name_mappings = {} + if args.debug: + logger.info("获取物品名称映射...") + name_mappings = fetch_name_mappings(engine, debug=True) # 输出索引 + log_processing_step(logger, "保存索引文件") for list_type, aggregations in list_type_indices.items(): output_prefix = f'{args.output_prefix}_{list_type}' + logger.info(f"保存 {list_type} 类型的索引...") output_indices(aggregations, output_prefix, top_n=args.top_n) + + # 如果启用debug模式，保存可读格式 + if args.debug and aggregations: + for dim_key, items in aggregations.items(): + if items: + # 为每个维度生成可读索引 + result_dict = {dim_key: items[:args.top_n]} + output_file = os.path.join(OUTPUT_DIR, f'{output_prefix}_{dim_key}_{datetime.now().strftime("%Y%m%d")}.txt') + if os.path.exists(output_file): + save_readable_index( + output_file, + result_dict, + name_mappings, + index_type=f'interest:{list_type}:{dim_key}', + logger=logger + ) # 生成全局索引（所有数据） - print("\nGenerating global indices...") + log_processing_step(logger, "生成全局索引") global_aggregations = aggregate_by_dimensions( df, behavior_weights, time_decay=True, decay_factor=args.decay_factor ) + logger.info("保存全局索引...") output_indices(global_aggregations, f'{args.output_prefix}_global', top_n=args.top_n) - print("\n=== All indices generated successfully! ===") + logger.info("="*80) + logger.info("所有索引生成完成！") + logger.info("="*80) if __name__ == '__main__': -- libgit2 0.21.2