Skip to content

A
Amazon-Selection-Data
Commit 17c74913 by hejiangming
Options

no message

parent d6c5d1af
Showing with 72 additions and 56 deletions
Pyspark_job/sqoop_export/dim_st_detail_week.py
......@@ -27,14 +27,17 @@ if __name__ == '__main__':
week = int(week_str)
export_master_tb = f"{site_name}_aba_report_week_{year}"
# 用上一年母表 like 出当年母表(including all 带那4个分区索引)、按 week 分区；已存在则 if not exists 跳过。
export_master_tb_before = f"{site_name}_aba_report_week_{year - 1}"
export_tb = f"{export_master_tb}_{week}"
next_week = week + 1
engine = DBUtil.get_db_engine(db_type, site_name)
with engine.connect() as connection:
sql = f"""
create table if not exists {export_master_tb} (like {export_master_tb_before} including all) partition by range (week);
drop table if exists {export_tb};
create table if not exists {export_tb}
create table if not exists {export_tb}
(
like {export_master_tb} including defaults including comments
);
......@@ -132,61 +135,63 @@ if __name__ == '__main__':
cp_index_flag=True,
)
# 第2步：Spark SQL 从 dim_st_detail_week 写入 dwt_st_base_report
print("================================写入周趋势数据到Hive================================")
spark = SparkUtil.get_spark_session(f"export_dim_st_detail_week_trend:{site_name} {date_type} {date_info}")
dwt_hive_tb = "dwt_st_base_report"
dwt_hdfs_path = f"/home/big_data_selection/dwt/{dwt_hive_tb}/site_name={site_name}/date_type=week/date_info={date_info}"
print(f"清除hdfs目录中数据:{dwt_hdfs_path}")
HdfsUtils.delete_hdfs_file(dwt_hdfs_path)
spark.sql(f"""
INSERT INTO TABLE {dwt_hive_tb} PARTITION(site_name='{site_name}', date_type='week', date_info='{date_info}')
SELECT
st_key,
search_term,
search_volume as st_volume,
orders as st_orders,
{year} as years,
current_timestamp() as created_time,
current_timestamp() as updated_time,
`rank` as st_rank
FROM dim_st_detail_week
WHERE site_name='{site_name}' AND date_type='week' AND date_info='{date_info}'
""")
spark.stop()
print("================================写入周趋势数据完成================================")
# 第3步：Sqoop 导出 dwt_st_base_report 到 PG 趋势表
print("================================导出周趋势图到PG集群================================")
trend_master_tb = f"{site_name}_aba_last_total_week"
trend_year_next = str(year + 1)
trend_export_tb = f"{trend_master_tb}_{year_str}"
trend_sql = f"""
create table if not exists {trend_export_tb} partition of {trend_master_tb} for values from ('{year_str}') to ('{trend_year_next}');
create index if not exists {trend_export_tb}_st_key_idx on {trend_export_tb} using btree (st_key);
delete from {trend_export_tb} where date_info = '{date_info}';
"""
DBUtil.engine_exec_sql(engine, trend_sql)
trend_columns = ["st_key", "search_term", "st_volume", "st_rank", "st_orders", "years",
"created_time", "updated_time", "date_type", "date_info"]
trend_sh = CommonUtil.build_export_sh(
site_name=site_name,
db_type=db_type,
hive_tb=dwt_hive_tb,
export_tb=trend_export_tb,
col=trend_columns,
partition_dict={
"site_name": site_name,
"date_type": "week",
"date_info": date_info
}
)
trend_client = SSHUtil.get_ssh_client()
SSHUtil.exec_command_async(trend_client, trend_sh, ignore_err=False)
trend_client.close()
print("================================周趋势图导出完成================================")
# 趋势改由独立脚本产：dwt/dwt_st_base_report_week.py(算)+sqoop_export/dwt_st_base_report_week.py(导)，
# 三站共用、口径逐字段一致。此处不再产趋势，避免与独立趋势任务并行写 {site}_aba_last_total_week
# # 第2步：Spark SQL 从 dim_st_detail_week 写入 dwt_st_base_report
# print("================================写入周趋势数据到Hive================================")
# spark = SparkUtil.get_spark_session(f"export_dim_st_detail_week_trend:{site_name} {date_type} {date_info}")
# dwt_hive_tb = "dwt_st_base_report"
# dwt_hdfs_path = f"/home/big_data_selection/dwt/{dwt_hive_tb}/site_name={site_name}/date_type=week/date_info={date_info}"
# print(f"清除hdfs目录中数据:{dwt_hdfs_path}")
# HdfsUtils.delete_hdfs_file(dwt_hdfs_path)
# spark.sql(f"""
# INSERT INTO TABLE {dwt_hive_tb} PARTITION(site_name='{site_name}', date_type='week', date_info='{date_info}')
# SELECT
# st_key,
# search_term,
# search_volume as st_volume,
# orders as st_orders,
# {year} as years,
# current_timestamp() as created_time,
# current_timestamp() as updated_time,
# `rank` as st_rank
# FROM dim_st_detail_week
# WHERE site_name='{site_name}' AND date_type='week' AND date_info='{date_info}'
# """)
# spark.stop()
# print("================================写入周趋势数据完成================================")
# # 第3步：Sqoop 导出 dwt_st_base_report 到 PG 趋势表
# print("================================导出周趋势图到PG集群================================")
# trend_master_tb = f"{site_name}_aba_last_total_week"
# trend_year_next = str(year + 1)
# trend_export_tb = f"{trend_master_tb}_{year_str}"
#
# trend_sql = f"""
# create table if not exists {trend_export_tb} partition of {trend_master_tb} for values from ('{year_str}') to ('{trend_year_next}');
# create index if not exists {trend_export_tb}_st_key_idx on {trend_export_tb} using btree (st_key);
# delete from {trend_export_tb} where date_info = '{date_info}';
# """
# DBUtil.engine_exec_sql(engine, trend_sql)
#
# trend_columns = ["st_key", "search_term", "st_volume", "st_rank", "st_orders", "years",
# "created_time", "updated_time", "date_type", "date_info"]
# trend_sh = CommonUtil.build_export_sh(
# site_name=site_name,
# db_type=db_type,
# hive_tb=dwt_hive_tb,
# export_tb=trend_export_tb,
# col=trend_columns,
# partition_dict={
# "site_name": site_name,
# "date_type": "week",
# "date_info": date_info
# }
# )
# trend_client = SSHUtil.get_ssh_client()
# SSHUtil.exec_command_async(trend_client, trend_sh, ignore_err=False)
# trend_client.close()
# print("================================周趋势图导出完成================================")
# 插入流程记录表
sql = f"""
......
Pyspark_job/sqoop_export/dwt_st_base_report_week.py
......@@ -14,6 +14,7 @@ sys.path.append(os.path.dirname(sys.path[0]))
from utils.ssh_util import SSHUtil
from utils.common_util import CommonUtil
from utils.db_util import DBUtil, DbTypes
from utils.hdfs_utils import HdfsUtils
if __name__ == '__main__':
site_name = CommonUtil.get_sys_arg(1, None) # 参数1：站点 us/uk/de
......@@ -40,6 +41,16 @@ if __name__ == '__main__':
engine = DBUtil.get_db_engine(db_type, site_name)
hive_path = CommonUtil.build_hdfs_path(
"dwt_st_base_report",
partition_dict={"site_name": site_name, "date_type": date_type, "date_info": date_info},
)
if not HdfsUtils.read_list(hive_path):
print(f"[ERROR] Hive 分区无数据文件：{hive_path}，跳过导出(不删PG)，请先检查趋势计算任务！")
engine.dispose()
sys.exit(1)
print(f"Hive 分区有数据：{hive_path}，继续导出")
# ============================================================
# 建当年分区子表 + st_key 索引 + 清本周
# 【为什么 create if not exists partition of】趋势表是「顶层母表 + 按年 RANGE 分区子表」，
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment