energy-data-trans/etl/common/SaveToDb.py

import multiprocessing
import os.path
import traceback

from etl.common.PathsAndTable import PathsAndTable
from service.trans_conf_service import update_trans_transfer_progress
from service.trans_service import save_partation_file_to_db, save_file_to_db
from utils.file.trans_methods import split_array
from utils.log.trans_log import trans_print
from utils.systeminfo.sysinfo import get_available_cpu_count_with_percent


class SaveToDb(object):

    def __init__(self, pathsAndTable: PathsAndTable, update_files, batch_count=100000):
        self.pathsAndTable = pathsAndTable
        self.batch_count = batch_count
        self.update_files = update_files

    def mutiprocessing_to_save_db(self):
        # 开始保存到SQL文件
        all_saved_files = self.update_files

        # 映射到的文件保存到数据库
        all_saved_files = [i for i in all_saved_files if
                           os.path.basename(i).split(".")[0] in self.pathsAndTable.wind_col_trans.keys()]

        self.pathsAndTable.create_wind_farm_db()

        split_count = get_available_cpu_count_with_percent(percent=2 / 3)
        split_count = split_count if split_count <= len(all_saved_files) else len(all_saved_files)
        all_arrays = split_array(all_saved_files, split_count)
        try:
            for index, arr in enumerate(all_arrays):
                with multiprocessing.Pool(split_count) as pool:
                    if self.pathsAndTable.read_type in ['minute', 'second']:
                        pool.starmap(save_partation_file_to_db,
                                     [(self.pathsAndTable.get_table_name(), file,
                                       self.pathsAndTable.wind_col_trans[os.path.basename(file).split(".")[0]],
                                       os.path.basename(os.path.dirname(file)),
                                       self.batch_count) for file in arr])
                    else:
                        pool.starmap(save_file_to_db,
                                     [(self.pathsAndTable.get_table_name(), file, self.batch_count) for file in arr])

                update_trans_transfer_progress(self.pathsAndTable.id,
                                               round(70 + 29 * (index + 1) / len(all_arrays), 2),
                                               self.pathsAndTable.save_db)
        except Exception as e:
            trans_print(traceback.format_exc())
            message = "保存到数据库错误,系统返回错误:" + str(e)
            raise ValueError(message)

    def run(self):
        if self.pathsAndTable.save_db:
            self.mutiprocessing_to_save_db()
            update_trans_transfer_progress(self.pathsAndTable.id,  99,
                                           self.pathsAndTable.save_db)