datax同步脚本和hive ods的full和orc建表語句
gen_import_config.py
# coding=utf-8
import json
import getopt
import os
import sys
import MySQLdb
#MySQL相关配置,需根据实际情况作出修改
mysql_host = "*****"
mysql_port = "3306"
mysql_user = "*****"
mysql_passwd = "*****"
#HDFS NameNode相关配置,需根据实际情况作出修改
hdfs_nn_host = "hadoop104"
hdfs_nn_port = "8020"
#生成配置文件的目标路径,可根据实际情况作出修改
output_path = "/opt/module/datax/job/import"
def get_connection():
return MySQLdb.connect(host=mysql_host, port=int(mysql_port), user=mysql_user, passwd=mysql_passwd)
def get_mysql_meta(database, table):
connection = get_connection()
cursor = connection.cursor()
sql = "SELECT COLUMN_NAME,DATA_TYPE from information_schema.COLUMNS WHERE TABLE_SCHEMA=%s AND TABLE_NAME=%s ORDER BY ORDINAL_POSITION"
cursor.execute(sql, [database, table])
fetchall = cursor.fetchall()
cursor.close()
connection.close()
return fetchall
def get_mysql_columns(database, table):
return map(lambda x: x[0], get_mysql_meta(database, table))
def get_hive_columns(database, table):
def type_mapping(mysql_type):
mappings = {
"bigint": "bigint",
"int": "bigint",
"smallint": "bigint",
"tinyint": "bigint",
"mediumint": "bigint",
"decimal": "string",
"double": "double",
"float": "float",
"binary": "string",
"char": "string",
"varchar": "string",
"datetime": "string",
"time": "string",
"timestamp": "string",
"date": "string",
"text": "string"
}
return mappings[mysql_type]
meta = get_mysql_meta(database, table)
return map(lambda x: {"name": x[0], "type": type_mapping(x[1].lower())}, meta)
def generate_json(source_database, source_table):
job = {
"job": {
"setting": {
"speed": {
"channel": 3
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": mysql_user,
"password": mysql_passwd,
"column": get_mysql_columns(source_database, source_table),
"splitPk": "",
"connection": [{
"table": [source_table],
"jdbcUrl": ["jdbc:mysql://" + mysql_host + ":" + mysql_port + "/" + source_database]
}]
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"defaultFS": "hdfs://" + hdfs_nn_host + ":" + hdfs_nn_port,
"fileType": "text",
"path": "${targetdir}",
"fileName": source_table,
"column": get_hive_columns(source_database, source_table),
"writeMode": "append",
"fieldDelimiter": u'\u0001',
"compress": "gzip"
}
},
"transformer": [
{
"name": "dx_groovy",
"parameter": {
"code": "for(int i=0;i<record.getColumnNumber();i++){if(record.getColumn(i).getByteSize()!=0){Column column = record.getColumn(i); def str = column.asString(); def newStr=null; newStr=str.replaceAll(\"[\\r\\n]\",\"\"); record.setColumn(i, new StringColumn(newStr)); };};return record;",
"extraPackage":[]
}
}
]
}]
}
}
if not os.path.exists(output_path):
os.makedirs(output_path)
with open(os.path.join(output_path, ".".join([source_database, source_table, "json"])), "w") as f:
json.dump(job, f)
def main(args):
source_database = ""
source_table = ""
options, arguments = getopt.getopt(args, '-d:-t:', ['sourcedb=', 'sourcetbl='])
for opt_name, opt_value in options:
if opt_name in ('-d', '--sourcedb'):
source_database = opt_value
if opt_name in ('-t', '--sourcetbl'):
source_table = opt_value
generate_json(source_database, source_table)
if __name__ == '__main__':
main(sys.argv[1:])
gen_import_config.sh
python ~/bin/gen_import_config.py -d database -t table
python ~/bin/gen_import_config.py -d database -t table
python ~/bin/gen_import_config.py -d database -t table
python ~/bin/gen_import_config.py -d database -t table
#!/bin/bash
DATAX_HOME=/opt/module/datax
# 如果传入日期则do_date等于传入的日期,否则等于前一天日期
if [ -n "$2" ] ;then
do_date=$2
else
do_date=`date -d "-1 day" +%F`
fi
#处理目标路径,此处的处理逻辑是,如果目标路径不存在,则创建;若存在,则清空,目的是保证同步任务可重复执行
handle_targetdir() {
hadoop fs -test -e $1
if [[ $? -eq 1 ]]; then
echo "路径$1不存在,正在创建......"
hadoop fs -mkdir -p $1
else
echo "路径$1已经存在"
fs_count=$(hadoop fs -count $1)
content_size=$(echo $fs_count | awk '{print $3}')
if [[ $content_size -eq 0 ]]; then
echo "路径$1为空"
else
echo "路径$1不为空,正在清空......"
hadoop fs -rm -r -f $1/*
fi
fi
}
#数据同步
import_data() {
datax_config=$1
target_dir=$2
handle_targetdir $target_dir
python $DATAX_HOME/bin/datax.py -p"-Dtargetdir=$target_dir" $datax_config
}
case $1 in
"a")
import_data /opt/module/datax/job/import/database.table.json /origin_data/easypm/db/table/$do_date
"all")
import_data /opt/module/datax/job/import/database.table.json /origin_data/easypm/db/table/$do_date
;;
esac
hdfs ods層建表語句 -》 text格式
-- auto-generated definition
DROP TABLE IF EXISTS ods_full;
create external table ods_full
(
Id string
) COMMENT '信息表'
PARTITIONED BY (`dt` STRING)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\001'
lines terminated by '\n'
NULL DEFINED AS ''
LOCATION '/warehouse/poc/esay_pm/ods/table';
load data inpath '/origin_data/database/db/table/2023-03-08' into table table partition (dt = '2023-03-08');
hdfs ods層建表語句 -》 orc格式
drop table if exists ods__orc;
create external table ods__orc
(
Id string
) COMMENT '信息表'
PARTITIONED BY (`dt` STRING)
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\001'
lines terminated by '\n'
STORED AS ORC
LOCATION '/warehouse/poc/database/ods/table'
TBLPROPERTIES ('orc.compress' = 'snappy');
再使用select將數據導入進去
insert overwrite table ods_tb_todo_full_orc partition (dt = '2023-03-08')
select
Id,
from ods__full;