package com.garret.chen;
import com.alibaba.fastjson.JSONObject;
import com.google.common.collect.Lists;
import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;
import java.io.UnsupportedEncodingException;
import java.util.HashMap;
import java.util.List;
/**
* 自定义拦截器
*/
public class LogInterceptor implements Interceptor {
private String keys[] = {"id","name","age"};
private String separator;
private HashMap<String,String> map = new HashMap<>();
private LogInterceptor(String separator){
this.separator = separator;
}
@Override
public void initialize() {
//no-op
}
@Override
public Event intercept(Event event) {
try {
final byte[] body = event.getBody();
final String msg = new String(body, "UTF-8");
final String[] strings = msg.split(separator);
if(strings.length!=keys.length){
return null;
}
for(int i= 0;i<strings.length;i++){
map.put(keys[i],strings[i]);
}
//将map转成json
final String jsonString = JSONObject.toJSONString(map);
event.setBody(jsonString.getBytes("UTF-8"));
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
}
return event;
}
@Override
public List<Event> intercept(List<Event> events) {
List<Event> out = Lists.newArrayList();
for (Event event : events) {
Event outEvent = intercept(event);
if (outEvent != null) {
out.add(outEvent);
}
}
return out;
}
@Override
public void close() {
//no-op
}
public static class Builder implements Interceptor.Builder {
private String separator;
@Override
public Interceptor build() {
return new LogInterceptor(separator);
}
/**
* 获取配置文件的属性
* @param context
*/
@Override
public void configure(Context context) {
separator = context.getString("separator"," ");
}
}
}
flum配置
#配置组件的别名
#a1 就是agent的别名
#给a1这个agent中的source取别名
a1.sources = r1
#给a1这个agent中的channel取别名
a1.channels = c1
#给a1这个agent中的sink取别名
a1.sinks = k1
#配置source
a1.sources.r1.type = netcat
a1.sources.r1.bind = plum01
a1.sources.r1.port = 6666
#配置channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 1000
#配置拦截器
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = com.garret.chen.LogInterceptor$Builder
a1.sources.r1.interceptors.i1.separator = ,
#配置sink
a1.sinks.k2.type = file_roll
a1.sinks.k2.sink.directory = /home/hadoop/logs
#绑定source channel sink
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1