flume 使用 spool source的时候字符集出错

1. 错误所在

-- ::, (pool--thread-) [ERROR - org.apache.flume.source.SpoolDirectorySource$SpoolDirectoryRunnable.run(SpoolDirectorySource.java:)] FATAL: Spool Directory source source1: { spoolDir: /home/hadoop_admin/movielog/ }: Uncaught exception in SpoolDirectorySource thread. Restart or reconfigure Flume to continue processing.
java.nio.charset.MalformedInputException: Input length =
        at java.nio.charset.CoderResult.throwException(CoderResult.java:)
        at org.apache.flume.serialization.ResettableFileInputStream.readChar(ResettableFileInputStream.java:)
        at org.apache.flume.serialization.LineDeserializer.readLine(LineDeserializer.java:)
        at org.apache.flume.serialization.LineDeserializer.readEvent(LineDeserializer.java:)
        at org.apache.flume.serialization.LineDeserializer.readEvents(LineDeserializer.java:)
        at org.apache.flume.client.avro.ReliableSpoolingFileEventReader.readEvents(ReliableSpoolingFileEventReader.java:)
        at org.apache.flume.source.SpoolDirectorySource$SpoolDirectoryRunnable.run(SpoolDirectorySource.java:)
        at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:)
        at java.util.concurrent.FutureTask.runAndReset(FutureTask.java:)
        at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$(ScheduledThreadPoolExecutor.java:)
        at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:)
        at java.lang.Thread.run(Thread.java:)

2. 解决方法

　　原因的inputCharset属性的默认值UTF-8,但是所读取的日志文件的字符集却是GBK,所以更改一下这个属性值就可以了

agent1.sources = source1
agent1.channels = channel1
agent1.sinks = sink1

# For each one of the sources, the type is defined
agent1.sources.source1.type = spooldir
agent1.sources.source1.spoolDir =/home/hadoop_admin/movielog/
agent1.sources.source1.inputCharset = GBK
agent1.sources.source1.fileHeader = true
agent1.sources.source1.deletePolicy = immediate
agent1.sources.source1.batchSize =
agent1.sources.source1.channels = channel1

# Each sink's type must be defined
agent1.sinks.sink1.type = hdfs
agent1.sinks.sink1.hdfs.path = hdfs://master:9000/flumeTest
agent1.sinks.sink1.hdfs.filePrefix = master-
agent1.sinks.sink1.hdfs.writeFormat = Text
agent1.sinks.sink1.hdfs.fileType = DataStream
agent1.sinks.sink1.hdfs.rollInterval =
agent1.sinks.sink1.hdfs.rollSize =
agent1.sinks.sink1.hdfs.batchSize =
agent1.sinks.sink1.hdfs.callTimeout =
agent1.sinks.sink1.channel = channel1

# Each channel's type is defined.
agent1.channels.channel1.type = memory
agent1.channels.channel1.capacity =
agent1.channels.channel1.transactionCapacity =
agent1.channels.channel1.keep-alive =