linux|常用的脚本：

1.查找某个类在哪个jar包中：

#!/bin/bash
ls *.jar | while read jarfile;do echo "$jarfile";jar -tf $jarfile | grep " "; done

#优化后的
ls *.jar | while read jarfile;do jar -tf $jarfile | grep " "; if [$? -eq 0]; then echo "find class in jar:"$jarfile;fi; done

2.hdfs自动清理目录下过期的文件：

#!/bin/bash
# 将需要监控的目录放至数组中
yarn_log_dir=/app-logs/spark/logs
spark_log_dir=/spark-history
spark2_log_dir=/spark2-history
mr_log_dir=/mr-history/done/$(date +"%Y/%m" -d "-1 days")

array_check=($yarn_log_dir $mr_log_dir)

# 过期天数
expire_days=14

# 当前时间戳
today_timestamp=$(date -d "$(date +"%Y-%m-%d %H:%M")" +%s)

#Func: 删除指定时间之前的过期数据
removeOutDate(){
hadoop fs -ls $1 > temp_list.txt
cat temp_list.txt | while read quanxian temp user group size day hour filepath
do
current_file_time="$day $hour"
current_file_timestamp=$(date -d "$current_file_time" +%s)
if [ $(($today_timestamp-$current_file_timestamp)) -ge $(($expire_days*24*60*60)) ];then
echo "$day $hour $size $filepath"
hadoop fs -rm -r -skipTrash $filepath > /dev/null 2>&1
fi
done
}

#Func: 执行删除
execute(){
echo -e "\n\n"
echo "$(date +'%Y-%m-%d %H:%M:%S') start to remove outdate files in hdfs"
echo "$(date +'%Y-%m-%d %H:%M:%S') today is: $(date +"%Y-%m-%d %H:%M:%S")"

for i in ${array_check[@]}
do
echo "$(date +'%Y-%m-%d %H:%M:%S') processing filepath: $i"
removeOutDate $i
echo -e "\n"
done

echo "$(date +'%Y-%m-%d %H:%M:%S') remove outdate files in hdfs finished"
echo -e "\n\n"

rm -f temp_list.txt
}

# 开始执行
execute