AllForCompany/BLD_sync
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor logging functions to enhance clarity and consistency in log messages

Browse Source
This commit is contained in:
Misaka_Company
2026-01-07 15:17:20 +08:00
parent a1c8a572bd
commit 5defe7b80d
2 changed files with 180 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
init_full_sync.py
View File

@@ -29,9 +29,54 @@ def setup_logger():
)
logger = logging.getLogger(__name__)
logger.info(f"日志文件: {log_file}")
logger.info(f"📝 日志文件: {log_file}")
return logger
# ================= 日志辅助函数 =================
def log_success(logger, message):
"""成功消息"""
logger.info(f"✅ [成功] {message}")
def log_error(logger, message, exc_info=False):
"""错误消息"""
logger.error(f"❌ [错误] {message}", exc_info=exc_info)
def log_warning(logger, message):
"""警告消息"""
logger.warning(f"⚠️ [警告] {message}")
def log_info(logger, message):
"""信息消息"""
logger.info(f"ℹ️ {message}")
def log_processing(logger, message):
"""处理中消息"""
logger.info(f"🔄 [处理] {message}")
def log_skip(logger, message):
"""跳过消息"""
logger.info(f"⏭️ [跳过] {message}")
def log_start(logger, message):
"""启动消息"""
logger.info(f"🚀 [启动] {message}")
def log_file(logger, message):
"""文件操作消息"""
logger.info(f"📂 [文件] {message}")
def log_database(logger, message):
"""数据库操作消息"""
logger.info(f"💾 [数据库] {message}")
def log_sync(logger, message):
"""同步操作消息"""
logger.info(f"🔃 [同步] {message}")
def log_complete(logger, message):
"""完成消息"""
logger.info(f"🎯 [完成] {message}")
def format_duration(seconds):
"""格式化时长显示"""
if seconds < 60:
@@ -56,8 +101,11 @@ def has_identity_column(sql_cursor, schema, table):
def run_full_sync():
logger = setup_logger()
logger.info("=== 开始全量初始化同步 ===")
logger.info("注意:将基于 config.SYNC_MAPPING 中的文件路径进行处理")
logger.info("=" * 70)
log_start(logger, "全量初始化同步")
log_info(logger, f"配置文件数: {len(config.SYNC_MAPPING)} 个")
log_info(logger, f"批次大小: {config.BATCH_SIZE} 行")
logger.info("=" * 70)
sync_start_time = time.time()
total_tables = 0
@@ -69,23 +117,27 @@ def run_full_sync():
sql_conn = db_utils.get_sql_conn()
sql_cursor = sql_conn.cursor()
sql_cursor.fast_executemany = True
logger.info("✓ SQL Server 连接成功")
log_database(logger, "SQL Server 连接成功")
except Exception as e:
logger.error(f"❌ SQL Server 连接失败: {e}")
log_error(logger, f"SQL Server 连接失败: {e}")
return
# 第一层循环:遍历配置文件中的所有文件路径
for acc_path, tables_map in config.SYNC_MAPPING.items():
if not os.path.exists(acc_path):
logger.warning(f"⚠️ [跳过] 文件不存在: {acc_path}")
log_skip(logger, f"文件不存在: {acc_path}")
continue
logger.info(f"\n📂 正在处理文件: {acc_path}")
log_file(logger, f"开始处理: {os.path.basename(acc_path)}")
file_start_time = time.time()
file_success = 0
file_failed = 0
file_rows = 0
try:
acc_conn = db_utils.get_access_conn(acc_path)
acc_cursor = acc_conn.cursor()
logger.info(f" ✓ Access 文件连接成功")
log_database(logger, f"Access 文件连接成功: {os.path.basename(acc_path)}")
# 第二层循环:遍历该文件下的所有表映射
for acc_table, target_config in tables_map.items():
@@ -94,22 +146,21 @@ def run_full_sync():
target_table = target_config['target_table']
full_target_name = db_utils.fmt_table(target_schema, target_table)
logger.info(f" 👉 开始同步表: [{acc_table}] -> {full_target_name}")
log_processing(logger, f"表 [{acc_table}] → [{target_table}]")
table_start_time = time.time()
try:
# 1. 检查 Access 表是否存在
acc_cursor.execute(f"SELECT TOP 1 * FROM [{acc_table}]")
logger.info(f" ✓ Access 表 [{acc_table}] 存在")
# 2. 获取列结构
columns = [col[0] for col in acc_cursor.description]
logger.info(f" ✓ 获取到 {len(columns)} 个列: {', '.join(columns)}")
log_info(logger, f" 检测到 {len(columns)} 个列")
insert_sql = db_utils.generate_insert_sql(target_schema, target_table, columns)
# 3. TRUNCATE 目标表
sql_cursor.execute(f"TRUNCATE TABLE {full_target_name}")
logger.info(f" ✓ 已清空目标表")
log_info(logger, f" 已清空目标表")
# 4. 检查并启用 IDENTITY_INSERT
has_identity = has_identity_column(sql_cursor, target_schema, target_table)
@@ -119,17 +170,18 @@ def run_full_sync():
try:
sql_cursor.execute(f"SET IDENTITY_INSERT {full_target_name} ON")
identity_enabled = True
logger.info(f" ✓ 已启用 IDENTITY_INSERT")
log_info(logger, f" 已启用 IDENTITY_INSERT")
except Exception as id_err:
logger.error(f" ⚠️ 无法启用 IDENTITY_INSERT: {id_err}")
log_error(logger, f" 无法启用 IDENTITY_INSERT: {id_err}")
raise
# 5. 传输数据
logger.info(f" 正在读取并写入数据...")
log_info(logger, f" 开始数据传输...")
acc_cursor.execute(f"SELECT * FROM [{acc_table}]")
table_rows = 0
start_time = time.time()
last_log_time = start_time
while True:
rows = acc_cursor.fetchmany(config.BATCH_SIZE)
@@ -138,33 +190,38 @@ def run_full_sync():
sql_cursor.executemany(insert_sql, rows)
table_rows += len(rows)
# 定期记录进度到日志
if table_rows % (config.BATCH_SIZE * 10) == 0:
elapsed = time.time() - start_time
# 每5秒或每10000行记录一次进度
current_time = time.time()
if (current_time - last_log_time >= 5) or (table_rows % 10000 == 0):
elapsed = current_time - start_time
rate = table_rows / elapsed if elapsed > 0 else 0
logger.info(f" 进度: 已写入 {table_rows:,} 行 | 速率: {rate:,.0f} 行/秒")
log_info(logger, f" 进度: {table_rows:,} 行 | 速率: {rate:,.0f} 行/秒")
last_log_time = current_time
# 6. 关闭 IDENTITY_INSERT
if identity_enabled:
try:
sql_cursor.execute(f"SET IDENTITY_INSERT {full_target_name} OFF")
logger.info(f" ✓ 已关闭 IDENTITY_INSERT")
log_info(logger, f" 已关闭 IDENTITY_INSERT")
except Exception as id_err:
logger.warning(f" ⚠️ 关闭 IDENTITY_INSERT 时警告: {id_err}")
log_warning(logger, f" 关闭 IDENTITY_INSERT 时警告: {id_err}")
sql_conn.commit()
# 显示最终统计
table_time = time.time() - table_start_time
final_rate = table_rows / table_time if table_time > 0 else 0
logger.info(f" ✅ 完成。共 {table_rows:,} 行 | 平均速率: {final_rate:,.0f} 行/秒 | 总用时: {format_duration(table_time)}")
log_success(logger, f"表 [{target_table}] 完成: {table_rows:,} 行 | 速率: {final_rate:,.0f} 行/秒 | 用时: {format_duration(table_time)}")
success_tables += 1
file_success += 1
total_rows += table_rows
file_rows += table_rows
except Exception as tbl_err:
failed_tables += 1
logger.error(f" ❌ 表级错误: {tbl_err}", exc_info=True)
file_failed += 1
log_error(logger, f"表 [{acc_table}] 同步失败: {tbl_err}", exc_info=True)
sql_conn.rollback()
# 确保清理 IDENTITY_INSERT 状态
@@ -174,23 +231,32 @@ def run_full_sync():
pass
acc_conn.close()
logger.info(f" ✓ Access 文件处理完成")
# 文件级别汇总
file_time = time.time() - file_start_time
summary = f"文件 [{os.path.basename(acc_path)}] 完成: "
summary += f"成功 {file_success} 张表"
if file_failed > 0:
summary += f" | 失败 {file_failed} 张表"
summary += f" | 共 {file_rows:,} 行 | 用时: {format_duration(file_time)}"
log_sync(logger, summary)
except Exception as file_err:
logger.error(f" ❌ 文件级错误: {file_err}", exc_info=True)
log_error(logger, f"文件 [{os.path.basename(acc_path)}] 处理失败: {file_err}", exc_info=True)
sql_conn.close()
# 总结统计
sync_time = time.time() - sync_start_time
logger.info("\n" + "="*60)
logger.info("=== 全量同步结束 ===")
logger.info(f"总表数: {total_tables} | 成功: {success_tables} | 失败: {failed_tables}")
logger.info(f"总行数: {total_rows:,} 行")
logger.info(f"总用时: {format_duration(sync_time)}")
logger.info("\n" + "=" * 70)
log_complete(logger, "全量同步任务结束")
logger.info("-" * 70)
log_info(logger, f"总表数: {total_tables} 张 | 成功: {success_tables} 张 | 失败: {failed_tables} 张")
log_info(logger, f"总行数: {total_rows:,} 行")
log_info(logger, f"总用时: {format_duration(sync_time)}")
if total_rows > 0 and sync_time > 0:
logger.info(f"整体平均速率: {total_rows/sync_time:,.0f} 行/秒")
logger.info("="*60)
log_info(logger, f"整体平均速率: {total_rows/sync_time:,.0f} 行/秒")
logger.info("=" * 70)
if __name__ == "__main__":
run_full_sync()

92
run_incremental_sync.py
View File

@@ -35,6 +35,55 @@ def setup_logger():
logger = setup_logger()
# ================= 日志辅助函数 =================
def log_success(message):
"""成功消息 - 绿色感觉"""
logger.info(f"✅ [成功] {message}")
def log_error(message):
"""错误消息 - 红色感觉"""
logger.error(f"❌ [错误] {message}")
def log_warning(message):
"""警告消息 - 黄色感觉"""
logger.warning(f"⚠️ [警告] {message}")
def log_info(message):
"""信息消息"""
logger.info(f"ℹ️ {message}")
def log_processing(message):
"""处理中消息"""
logger.info(f"🔄 [处理] {message}")
def log_skip(message):
"""跳过消息"""
logger.info(f"⏭️ [跳过] {message}")
def log_critical(message):
"""严重错误"""
logger.critical(f"🔥 [严重] {message}")
def log_start(message):
"""启动消息"""
logger.info(f"🚀 [启动] {message}")
def log_stop(message):
"""停止消息"""
logger.info(f"🛑 [停止] {message}")
def log_file(message):
"""文件操作消息"""
logger.info(f"📂 [文件] {message}")
def log_database(message):
"""数据库操作消息"""
logger.info(f"💾 [数据库] {message}")
def log_sync(message):
"""同步操作消息"""
logger.info(f"🔃 [同步] {message}")
# ================= 主逻辑 =================
def process_sync_task():
@@ -102,7 +151,7 @@ def process_sync_task():
continue # 这个文件没有需要同步的记录，检查下一个文件
work_done = True # 标记有工作
logger.info(f"📂 文件 {os.path.basename(clean_path)} 发现 {len(logs)} 条变更...")
log_file(f"{os.path.basename(clean_path)} 发现 {len(logs)} 条待同步变更")
# 3. 本地分组 (按表名)
# 结构: table_tasks[TableName] = { ids: {}, log_ids: [] }
@@ -116,16 +165,22 @@ def process_sync_task():
# 4. 执行同步 (连接一次 Access，处理多张表)
if not os.path.exists(clean_path):
logger.error(f"无法访问文件: {clean_path}")
log_error(f"无法访问文件: {clean_path}")
continue
try:
acc_conn = db_utils.get_access_conn(clean_path)
acc_cursor = acc_conn.cursor()
log_database(f"已连接 Access 文件: {os.path.basename(clean_path)}")
except Exception as conn_err:
logger.error(f"连接 Access 失败: {conn_err}")
log_error(f"连接 Access 失败 [{os.path.basename(clean_path)}]: {conn_err}")
continue
# 统计每个文件的同步情况
file_success_count = 0
file_error_count = 0
file_total_records = 0
for acc_table, data in table_tasks.items():
record_ids = list(data['record_ids'])
log_ids = data['log_ids']
@@ -137,6 +192,8 @@ def process_sync_task():
pk_col = target_conf['pk_col']
target_full_name = db_utils.fmt_table(target_schema, target_table)
log_processing(f"正在同步表 [{acc_table}] → [{target_table}] ({len(record_ids)} 条记录)")
try:
# --- A. Access 查新数据 ---
ids_placeholders = ','.join(['?'] * len(record_ids))
@@ -171,26 +228,40 @@ def process_sync_task():
sql_cursor.execute(update_log_sql, log_ids)
sql_conn.commit()
logger.info(f" -> {target_table} 同步成功: {len(record_ids)} 条")
log_success(f"表 [{target_table}] 同步完成: {len(record_ids)} 条记录")
file_success_count += 1
file_total_records += len(record_ids)
except Exception as tbl_err:
logger.error(f" -> 处理表 {acc_table} 异常: {tbl_err}")
log_error(f"表 [{acc_table}] 同步失败: {tbl_err}")
sql_conn.rollback()
file_error_count += 1
acc_conn.close() # 关闭 Access 连接
# 输出文件级别的汇总
if file_success_count > 0 or file_error_count > 0:
summary = f"文件 [{os.path.basename(clean_path)}] 同步汇总: "
summary += f"成功 {file_success_count} 张表 ({file_total_records} 条记录)"
if file_error_count > 0:
summary += f" | 失败 {file_error_count} 张表"
log_sync(summary)
return work_done
except Exception as e:
logger.critical(f"全局严重异常: {e}")
log_critical(f"全局异常: {e}")
return False
finally:
try: sql_conn.close()
except: pass
if __name__ == "__main__":
logger.info("=== 增量同步服务启动 (配置驱动模式) ===")
logger.info("正在按 config.SYNC_MAPPING 轮询...")
log_start("增量同步服务已启动 (配置驱动模式)")
log_info(f"轮询间隔: {config.POLL_INTERVAL} 秒")
log_info(f"监控配置: {len(config.SYNC_MAPPING)} 个文件")
logger.info("=" * 70)
while True:
try:
@@ -199,8 +270,9 @@ if __name__ == "__main__":
# 如果没工作，休息标准间隔(5s)
time.sleep(0.1 if has_work else config.POLL_INTERVAL)
except KeyboardInterrupt:
logger.info("服务停止")
logger.info("=" * 70)
log_stop("收到停止信号，服务正在关闭...")
break
except Exception as e:
logger.critical(f"主循环崩溃: {e}")
log_critical(f"主循环崩溃: {e}")
time.sleep(5)