args参数解析

痛点

def main(args: Array[String]): Unit

一般情况下我们是通过 args（0），args（1）。。。取传入程序的参数，少的话还好，参数一旦很多的话 就会很乱，时间长了，我们就不知道传递的参数的含义了

类似效果

Usage: hadoop fs [generic options]
	[-appendToFile <localsrc> ... <dst>]
	[-cat [-ignoreCrc] <src> ...]
	[-checksum <src> ...]
	[-chgrp [-R] GROUP PATH...]
	[-chmod [-R] <MODE[,MODE]... | OCTALMODE> PATH...]
	[-chown [-R] [OWNER][:[GROUP]] PATH...]
	[-copyFromLocal [-f] [-p] [-l] [-d] [-t <thread count>] <localsrc> ... <dst>]
	[-copyToLocal [-f] [-p] [-ignoreCrc] [-crc] <src> ... <localdst>]
	[-count [-q] [-h] [-v] [-t [<storage type>]] [-u] [-x] [-e] <path> ...]
	[-cp [-f] [-p | -p[topax]] [-d] <src> ... <dst>]
	[-createSnapshot <snapshotDir> [<snapshotName>]]
	[-deleteSnapshot <snapshotDir> <snapshotName>]
	[-df [-h] [<path> ...]]
	[-du [-s] [-h] [-v] [-x] <path> ...]
	[-expunge]

实现-scala

 private val options: Options = new Options

  private val option_h_desc: String =
    """ |print help info |usage: | java -cp jarLocation fullClassName [-h] || [-t]&&[-g]&&[-maxR] 1> applicationName.log 2>&1 & | |data flow: | kafka => Spark Streaming | RedisStateStorePerDay | |programs: | SampleFirstScanStateLaunch => -t&&-g&&-i&&-maxR | SampleFirstScanSinkHbaseLaunch => -pn&&-pt&&-t&&-g&&-i&&-maxR | SampleFirstScanSinkHiveLaunch => -hd&&-ht&&-t&&-g&&-i&&-maxR |outer: | 1.maxRatePerPartition throughput default 1000. | 2.phoenix table name && namespace Capital | | |""".stripMargin

  options.addOption("h", "help", false, option_h_desc)
  options.addOption("t", "topic", true, "kafka topic")
  options.addOption("g", "group.id", true, "kafka consumer group id")
  options.addOption("maxR", "maxRatePerPartition", true, "kafka topic partition max Rate")
  options.addOption("i", "interval", true, "SparkStreaming direct Kafka Batch Interval [s]")
  //hive || phoenix
// options.addOption("hd", "hive.database", true, "FirstScanSinkHive hive database")
// options.addOption("ht", "hive.table", true, "FirstScanSinkHive hive table")
  options.addOption("pn", "phoenix.namespace", true, "FirstScanSinkPhoenix phoenix namespace")
  options.addOption("pt", "phoenix.table", true, "FirstSinkPhoenix phoenix table")
  options.addOption("hp", "hp", true, "写入hive还是hbase h=hive p=phoenix hp=hive和phoenix")
  options.addOption("local", "local", true, "是否启用loncal(*)")


  private val parser: PosixParser = new PosixParser

  def parseParam(args: Array[String], applicationName: String): ExecutorParam = {
    

    if (args == null) {
    
      logger.error("HR => param is NULL")
      System.exit(ERROR_EXIT_STATUS)
    }
    var line: CommandLine = null
    try {
    
      line = parser.parse(options, args)
    } catch {
    
      case e: Exception => logger.error("HR => args parse Exception. parse check param")
        println(e.getStackTrace.mkString("Array(", ", ", ")"))
        System.exit(ERROR_EXIT_STATUS)
    }
    if (line.hasOption("h")) {
    
      new HelpFormatter().printHelp("desc", options)
      System.exit(ERROR_EXIT_STATUS)
    }
    val topic: String = line.getOptionValue("topic")
    val groupId: String = line.getOptionValue("group.id")
    val maxRatePerPartition: String = line.getOptionValue("maxRatePerPartition", "1000")
    val interval: String = line.getOptionValue("interval")
    val hp: String = line.getOptionValue("hp")
    val local: String = line.getOptionValue("local")

    if (topic == null || groupId == null || interval == null || hp == null || local == null) {
    
      logger.error(s"HR => topic|groupId|interval Exception.parse check param")
      System.exit(ERROR_EXIT_STATUS)
    }
    logger.info(s"HR => paramList[topic : $topic \n groupId : $groupId \n maxRatePerPartition : $maxRatePerPartition \n interval : $interval]")
    val phoenixNameSpace: String = line.getOptionValue("phoenix.namespace")
    val phoenixTable: String = line.getOptionValue("phoenix.table")

    logger.info(s"HR => paramList[ phoenix.namespace : $phoenixNameSpace \n phoenix.table : $phoenixTable]")
// val hiveDatabase: String = line.getOptionValue("hive.database")
// val hiveTable: String = line.getOptionValue("hive.table")
// logger.info(s"HR => paramList[ hive.database : $hiveDatabase \n hive.table : $hiveTable]")

    ExecutorParam(topic, groupId, maxRatePerPartition.toInt, interval.toInt, applicationName + hp, phoenixNameSpace, phoenixTable, hp, local.toBoolean)
  }


}

case class ExecutorParam(
                          topic: String,
                          groupId: String,
                          maxRatePerPartition: Int,
                          interval: Int,
                          applicationName: String,
                          phoenixNameSpace: String,
                          phoenixTable: String,
                          hp: String,
                          local: Boolean)

如何传参 - 示例

	-maxR 500 \
	-t hr_task_scan \
	-i 3 \
	-g SplitTaskTypeUOFFICIAL \
	-pn OFFICIAL \
	-pt SAMPLE_U_SCAN,SAMPLE_U_SCAN_LATEST,SAMPLE_T_SCAN_LATEST \
	-local false

如何获取参数 - 示例

	//解析参数
    val param: ExecutorParam = Constant.parseParam(args, this.getClass.getSimpleName)
    
    //获取参数
    val applicationName: String = param.applicationName
    val maxRatePerPartition: Int = param.maxRatePerPartition
    val conf: SparkConf = new SparkConf()
    val topic: String = param.topic
    val groupId: String = param.groupId
    val local: Boolean = param.local