#!/bin/bash
#set java env
export JAVA_HOME=/home/hadoop/apps/jdk1.7.0_80
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
#set hadoop env
export HADOOP_HOME=/home/hadoop/apps/hadoop-2.6.4
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
date=`date -d "1 day ago" +"%Y%m%d"`
date2=`date +%Y_%m_%d_%H_%M_%S`
#日誌文件存放的目錄
log_src_dir=/hadoop/logs/log/
#待上傳文件存放的目錄
log_toupload_dir=/hadoop/logs/toupload/
if [ ! -d "$log_toupload_dir" ];then
mkdir -p $log_toupload_dir
else
echo "$log_toupload_dir文件夾已經存在"
fi
#日誌文件上傳到hdfs的根路徑
hdfs_root_dir=/data/clickLog/$date/ ##把上傳到hdfs的目錄改成根據當前時間動態獲取來設置,上傳昨日日誌
hadoop fs -test -e $hdfs_root_dir
if [ $? -eq 0 ] ;then
echo "$hdfs_root_dir文件夾已經存在"
else
hadoop fs -mkdir -p $hdfs_root_dir
fi
#讀取日誌文件的目錄,判斷是否有需要上傳的文件
echo "log_src_dir:"$log_src_dir
ls $log_src_dir | while read fileName
do
if [[ "$fileName" == access.log.* ]]; then
#將文件移動到待上傳目錄並重命名
echo "moving $log_src_dir$fileName to $log_toupload_dir"xxxxx_click_log_$fileName"_$date2"
mv $log_src_dir$fileName $log_toupload_dir"xxxxx_click_log_$fileName_"$date2
#將待上傳的文件path寫入一個列表文件willDoing
echo $log_toupload_dir"xxxxx_click_log_$fileName_"$date2 >> $log_toupload_dir"willDoing."$date2
fi
done
#找到列表文件willDoing
ls $log_toupload_dir | grep will |grep -v "_COPY_" | grep -v "_DONE_" | while read line
do
#打印信息
echo "toupload is in file:"$line
#將待上傳文件列表willDoing改名爲willDoing_COPY_
mv $log_toupload_dir$line $log_toupload_dir$line"_COPY_"
#讀列表文件willDoing_COPY_的內容(一個一個的待上傳文件名) ,此處的line 就是列表中的一個待上傳文件的path
cat $log_toupload_dir$line"_COPY_" |while read line
do
#打印信息
echo "puting...$line to hdfs path.....$hdfs_root_dir"
hadoop fs -put $line $hdfs_root_dir
done
mv $log_toupload_dir$line"_COPY_" $log_toupload_dir$line"_DONE_"
done
## 發現失敗,發郵件,發短信
## wget http://smssendplatform.com/sendsms?custom=cid&smscontent=xxxx&receiver=13838383338