详解如何使用Spark和Scala分析Apache访问日志

$ sbt/sbt assembly

$ ./bin/spark-shell

scala> val textFile = sc.textFile("README.md") // 创建一个指向 README.md 引用
scala> textFile.count // 对这个文件内容行数进行计数
scala> textFile.first // 打印出第一行

sbt compile
sbt test
sbt package

// this works
$ MASTER=local[4] SPARK_CLASSPATH=AlsApacheLogParser.jar ./bin/spark-shell

// does not work
$ MASTER=local[4] ADD_JARS=AlsApacheLogParser.jar ./bin/spark-shell
// does not work
spark> :cp AlsApacheLogParser.jar

import com.alvinalexander.accesslogparser._
val p = new AccessLogParser

scala> val log = sc.textFile("accesslog.small")
14/03/09 11:25:23 INFO MemoryStore: ensureFreeSpace(32856) called with curMem=0, maxMem=309225062
14/03/09 11:25:23 INFO MemoryStore: Block broadcast_0 stored as values to memory (estimated size 32.1 KB, free 294.9 MB)
log: org.apache.spark.rdd.RDD[String] = MappedRDD[1] at textFile at <console>:15
scala> log.count
(a lot of output here)
res0: Long = 100000

def getStatusCode(line: Option[AccessLogRecord]) = {
 line match {
  case Some(l) => l.httpStatusCode
  case None => "0"
 }
}

log.filter(line => getStatusCode(p.parseRecord(line)) == "404").count

// get the `request` field from an access log record
def getRequest(rawAccessLogString: String): Option[String] = {
 val accessLogRecordOption = p.parseRecord(rawAccessLogString)
 accessLogRecordOption match {
  case Some(rec) => Some(rec.request)
  case None => None
 }
}

log.filter(line => getStatusCode(p.parseRecord(line)) == "404").map(getRequest(_)).count
val recs = log.filter(line => getStatusCode(p.parseRecord(line)) == "404").map(getRequest(_))
val distinctRecs = log.filter(line => getStatusCode(p.parseRecord(line)) == "404").map(getRequest(_)).distinct
distinctRecs.foreach(println)