package main.java;

import java.io.*;
public class ReadWrite {

      static String readFileName;
      static String writeFileName;


      public static void main(String args[]){
           readFileName = args[0];
           writeFileName = args[1];
          try {
             // readInput();
            readFileByLines(readFileName);
          }catch(Exception e){
          }
      }

    public static void readFileByLines(String fileName) {
        FileInputStream fis = null;
        InputStreamReader isr = null;
        BufferedReader br = null;
        String tempString = null;
        try {
            System.out.println("以行为单位读取文件内容，一次读一整行：");
            fis = new FileInputStream(fileName);// FileInputStream
            // 从文件系统中的某个文件中获取字节
            isr = new InputStreamReader(fis,"GBK");
            br = new BufferedReader(isr);
            int count=0;
            while ((tempString = br.readLine()) != null) {
                count++;
                // 显示行号
                Thread.sleep(300);
                String str = new String(tempString.getBytes("UTF8"),"GBK");
                System.out.println("row:"+count+">>>>>>>>"+tempString);
                method1(writeFileName,tempString);
                //appendMethodA(writeFileName,tempString);
            }
            isr.close();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        } finally {
            if (isr != null) {
                try {
                    isr.close();
                } catch (IOException e1) {
                }
            }
        }
    }

//    public static void appendMethodA(String fileName, String content) {
//        try {
//            // 打开一个随机访问文件流，按读写方式
//            //logger.info("file line >>>>>>>>>>>>>>>>>>>>>>>>>:"+content);
//            RandomAccessFile randomFile = new RandomAccessFile(fileName, "rw");
//
//            // 文件长度，字节数
//            long fileLength = randomFile.length();
//            //将写文件指针移到文件尾。
//            randomFile.seek(fileLength);
//            //randomFile.writeUTF(content);
//            randomFile.writeUTF(content);
//            randomFile.writeUTF("\n");
//           // randomFile.wri;
//
//            randomFile.close();
//        } catch (IOException e) {
//            e.printStackTrace();
//        }
//    }

    public static void method1(String file, String conent) {
        BufferedWriter out = null;
        try {
            out = new BufferedWriter(new OutputStreamWriter(
                    new FileOutputStream(file, true)));
            out.write("\n");
            out.write(conent);
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                out.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }




}

bin/kafka-topics.sh --zookeeper bigdata-pro01.kfk.com:2181,bigdata-pro02.kfk.com:2181,bigdata-pro03.kfk.com:2181 --create --topic weblogs --replication-factor 1 --partitions 1

# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
# 
#    http://www.apache.org/licenses/LICENSE-2.0
# 
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# see kafka.server.KafkaConfig for additional details and defaults

############################# Server Basics #############################

# The id of the broker. This must be set to a unique integer for each broker.
broker.id=1

############################# Socket Server Settings #############################

listeners=PLAINTEXT://bigdata-pro01.kfk.com：9092

# The port the socket server listens on
port=9092

# Hostname the broker will bind to. If not set, the server will bind to all interfaces
host.name=bigdata-pro01.kfk.com

# Hostname the broker will advertise to producers and consumers. If not set, it uses the
# value for "host.name" if configured.  Otherwise, it will use the value returned from
# java.net.InetAddress.getCanonicalHostName().
#advertised.host.name=<hostname routable by clients>

# The port to publish to ZooKeeper for clients to use. If this is not set,
# it will publish the same port that the broker binds to.
#advertised.port=<port accessible by clients>

# The number of threads handling network requests
num.network.threads=3
 
# The number of threads doing disk I/O
num.io.threads=8

# The send buffer (SO_SNDBUF) used by the socket server
socket.send.buffer.bytes=102400

# The receive buffer (SO_RCVBUF) used by the socket server
socket.receive.buffer.bytes=102400

# The maximum size of a request that the socket server will accept (protection against OOM)
socket.request.max.bytes=104857600


############################# Log Basics #############################

# A comma seperated list of directories under which to store log files
log.dirs=/opt/modules/kafka_2.11-0.9.0.0/kafka-logs

# The default number of log partitions per topic. More partitions allow greater
# parallelism for consumption, but this will also result in more files across
# the brokers.
num.partitions=1

# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
# This value is recommended to be increased for installations with data dirs located in RAID array.
num.recovery.threads.per.data.dir=1

############################# Log Flush Policy #############################

# Messages are immediately written to the filesystem but by default we only fsync() to sync
# the OS cache lazily. The following configurations control the flush of data to disk. 
# There are a few important trade-offs here:
#    1. Durability: Unflushed data may be lost if you are not using replication.
#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks. 
# The settings below allow one to configure the flush policy to flush data after a period of time or
# every N messages (or both). This can be done globally and overridden on a per-topic basis.

# The number of messages to accept before forcing a flush of data to disk
#log.flush.interval.messages=10000

# The maximum amount of time a message can sit in a log before we force a flush
#log.flush.interval.ms=1000

############################# Log Retention Policy #############################

# The following configurations control the disposal of log segments. The policy can
# be set to delete segments after a period of time, or after a given size has accumulated.
# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
# from the end of the log.

# The minimum age of a log file to be eligible for deletion
log.retention.hours=168

# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
# segments don\'t drop below log.retention.bytes.
#log.retention.bytes=1073741824

# The maximum size of a log segment file. When this size is reached a new log segment will be created.
log.segment.bytes=1073741824

# The interval at which log segments are checked to see if they can be deleted according 
# to the retention policies
log.retention.check.interval.ms=300000

# By default the log cleaner is disabled and the log retention policy will default to just delete segments after their retention expires.
# If log.cleaner.enable=true is set the cleaner will be enabled and individual logs can then be marked for log compaction.
log.cleaner.enable=false

############################# Zookeeper #############################

# Zookeeper connection string (see zookeeper docs for details).
# This is a comma separated host:port pairs, each corresponding to a zk
# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
# You can also append an optional chroot string to the urls to specify the
# root directory for all kafka znodes.
zookeeper.connect=bigdata-pro01.kfk.com:2181,bigdata-pro02.kfk.com:2181,bigdata-pro03.kfk.com:2181

# Timeout in ms for connecting to zookeeper
zookeeper.connection.timeout.ms=60000

bin/kafka-topics.sh --zookeeper bigdata-pro01.kfk.com:2181,bigdata-pro02.kfk.com:2181,bigdata-pro03.kfk.com:2181 --create --topic weblogs --replication-factor 3 --partitions 1