{"id":36786,"date":"2023-11-16T04:40:11","date_gmt":"2023-08-18T23:26:53","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/"},"modified":"2024-05-04T09:16:54","modified_gmt":"2024-05-04T01:16:54","slug":"%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/","title":{"rendered":"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount"},"content":{"rendered":"

\u6839\u636e\u8fd9\u4e2a\u53c2\u8003\uff0c\u6211\u5c1d\u8bd5\u5728Apache Spark Scala\u4e2d\u6267\u884c\u4e86WordCount\u3002\u73af\u5883\u5982\u4e0b\u6240\u793a\u3002<\/p>\n

\u30fbCentOS 7.5 (Linux \u64cd\u4f5c\u7cfb\u7edf\u7248\u672c\u4e3a CentOS 7.5)
\n\u30fbApache Spark 2.3.1 (\u4f7f\u7528 Apache Spark \u7248\u672c\u4e3a 2.3.1)
\n\u30fbScala 2.12.6 (\u4f7f\u7528 Scala \u7248\u672c\u4e3a 2.12.6)
\n\u30fbsbt 1.1.6 (\u4f7f\u7528 sbt \u7248\u672c\u4e3a 1.1.6)<\/p>\n

\u5b89\u88c5Spark\u3001Scala\u548csbt\u3002<\/h1>\n

\u6267\u884cApache Spark\u5b89\u88c5\u548c\u73af\u5883\u53d8\u91cf\u8bbe\u7f6e\u3002<\/p>\n

\u5b89\u88c5Scala\u548c\u8bbe\u7f6e\u73af\u5883\u53d8\u91cf\u3002<\/p>\n

# wget https:\/\/downloads.lightbend.com\/scala\/2.12.6\/scala-2.12.6.tgz\r\n# tar xvzf scala-2.12.6.tgz\r\n# mv scala-2.12.6 \/usr\/local\/scala\r\n\r\n# vi \/etc\/profile\r\n# export SCALA_HOME=\/usr\/local\/scala\r\n# export PATH=$PATH:$SCALA_HOME\/bin\r\n\r\nsource \/etc\/profile\r\n<\/code><\/pre>\n
\u5b89\u88c5 Scala sbt\uff0c\u786e\u8ba4\u7248\u672c<\/p>\n
# curl https:\/\/bintray.com\/sbt\/rpm\/rpm | sudo tee \/etc\/yum.repos.d\/bintray-sbt-rpm.repo\r\n# sudo yum install sbt\r\n\r\n# sbt sbtVersion\r\n<\/code><\/pre>\n
\u51c6\u5907sbt\u6784\u5efa\u73af\u5883\u3002<\/h1>\n
\u4e8b\u524d\u306b\u6e96\u5099\u3059\u308b\u305f\u3081\u306b\u3001\u4ee5\u4e0b\u306e\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\uff08output\u3092\u542b\u307e\u306a\u3044\uff09\u304a\u3088\u3073\u30d5\u30a1\u30a4\u30eb\u3092\u7528\u610f\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n
\u30fb\u76ee\u5f55<\/p>\n
WordCount\/\r\n\u251c\u2500\u2500 build.sbt\u3000(\u30d3\u30eb\u30c9\u65b9\u6cd5\u3092\u5b9a\u7fa9)\r\n\u251c\u2500\u2500 input.txt\u3000(\u30ef\u30fc\u30c9\u30ab\u30a6\u30f3\u30c8\u5bfe\u8c61\u306e\u30d5\u30a1\u30a4\u30eb)\r\n\u251c\u2500\u2500 output\/\u3000 (\u30ef\u30fc\u30c9\u30ab\u30a6\u30f3\u30c8\u306e\u7d50\u679c\uff1asbt run\u306b\u3066\u4f5c\u6210\u3055\u308c\u308b)\r\n\u2502\r\n\u251c\u2500\u2500 project\/ (sbt\u306e\u8ffd\u52a0\u8a2d\u5b9a)\r\n\u2502   \u2514\u2500\u2500 assembly.sbt (sbt\u306e\u30d7\u30e9\u30b0\u30a4\u30f3)\r\n\u2514\u2500\u2500 src\/\r\n \u3000 \u2514\u2500\u2500main\/\r\n \u3000\u3000 \u3000\u2514\u2500\u2500 scala\/\r\n\u3000\u3000\u3000 \u3000\u2514\u2500\u2500 jp\/\r\n \u3000\u3000\u3000\u3000\u3000 \u2514\u2500\u2500 hoge\/\r\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000\u3000\u2514\u2500\u2500 news\/\r\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000\u3000\u3000\u3000\u2514\u2500\u2500 WordCountApp.scala\r\n<\/code><\/pre>\n
\u8fd9\u91cc\u53c2\u8003build.sbt\u6587\u6863\uff0c\u6307\u5b9ascalaVersion\u4e3a2.11.7\uff0cspark-core\u7248\u672c\u4e3a2.1.0\u3002
\n\u203b\u7531\u4e8eSpark 2.3.1\u662f\u4f7f\u7528Scala 2.11\u7f16\u8bd1\u7684\uff0c\u6240\u4ee5\u9700\u8981\u964d\u4f4eScala\u7684\u7248\u672c\u3002<\/p>\n
name<\/span> :=<\/span> \"WordCountApp\"<\/span>\r\nversion<\/span> :=<\/span> \"1.0.0\"<\/span>\r\nscalaVersion<\/span> :=<\/span> \"2.11.7\"<\/span>\r\nresolvers<\/span> +=<\/span> \"Atilika Open Source repository\"<\/span> at<\/span> \"http:\/\/www.atilika.org\/nexus\/content\/repositories\/atilika\"<\/span>\r\nlibraryDependencies<\/span> +=<\/span> \"org.apache.spark\"<\/span> %%<\/span> \"spark-core\"<\/span> %<\/span> \"2.1.0\"<\/span>\r\nlibraryDependencies<\/span> +=<\/span> \"org.atilika.kuromoji\"<\/span> %<\/span> \"kuromoji\"<\/span> %<\/span> \"0.7.7\"<\/span>\r\nassemblyMergeStrategy<\/span> in<\/span> assembly<\/span> :=<\/span> {<\/span>\r\n  case<\/span> PathList<\/span>(<\/span>\"javax\"<\/span>,<\/span> \"servlet\"<\/span>,<\/span> xs<\/span> @<\/span> _<\/span>*)<\/span>         =><\/span> MergeStrategy<\/span>.<\/span>first<\/span>\r\n  case<\/span> PathList<\/span>(<\/span>ps<\/span> @<\/span> _<\/span>*)<\/span> if<\/span> ps<\/span>.<\/span>last<\/span> endsWith<\/span> \".properties\"<\/span> =><\/span> MergeStrategy<\/span>.<\/span>first<\/span>\r\n  case<\/span> PathList<\/span>(<\/span>ps<\/span> @<\/span> _<\/span>*)<\/span> if<\/span> ps<\/span>.<\/span>last<\/span> endsWith<\/span> \".xml\"<\/span> =><\/span> MergeStrategy<\/span>.<\/span>first<\/span>\r\n  case<\/span> PathList<\/span>(<\/span>ps<\/span> @<\/span> _<\/span>*)<\/span> if<\/span> ps<\/span>.<\/span>last<\/span> endsWith<\/span> \".types\"<\/span> =><\/span> MergeStrategy<\/span>.<\/span>first<\/span>\r\n  case<\/span> PathList<\/span>(<\/span>ps<\/span> @<\/span> _<\/span>*)<\/span> if<\/span> ps<\/span>.<\/span>last<\/span> endsWith<\/span> \".class\"<\/span> =><\/span> MergeStrategy<\/span>.<\/span>first<\/span>\r\n  case<\/span> \"application.conf\"<\/span>                            =><\/span> MergeStrategy<\/span>.<\/span>concat<\/span>\r\n  case<\/span> \"unwanted.txt\"<\/span>                                =><\/span> MergeStrategy<\/span>.<\/span>discard<\/span>\r\n  case<\/span> x<\/span> =><\/span>\r\n    val<\/span> oldStrategy<\/span> =<\/span> (<\/span>assemblyMergeStrategy<\/span> in<\/span> assembly<\/span>).<\/span>value<\/span>\r\n    oldStrategy<\/span>(<\/span>x<\/span>)<\/span>\r\n}<\/span>\r\nmainClass<\/span> in<\/span> assembly<\/span> :=<\/span> Some<\/span>(<\/span>\"WordCountApp\"<\/span>)<\/span>\r\n<\/code><\/pre>\n
\u5728\u4ee5\u4e0b\u6307\u5b9a\u4e2d\u751f\u6210\u4e00\u4e2a\u5305\u542bScala JAR\u548clib\u76ee\u5f55\u4e0b\u6240\u6709JAR\u7684fat JAR\u6587\u4ef6\u3002
\n\u8bf7\u6ce8\u610f\uff0c\u4ece\u8fd9\u4e2a\u94fe\u63a5\u4e0b\u8f7d\u7684sbt\u7248\u672c1.x\u652f\u6301sbt-assembly 0.14.6\u3002<\/p>\n
addSbtPlugin(\"com.eed3si9n\" % \"sbt-assembly\" % \"0.14.6\")    \r\n<\/code><\/pre>\n
\u30fbWordCountApp.scala\u7684\u4e2d\u6587\u672c\u5730\u5316\u7248\u672c\u3002<\/p>\n
package<\/span> jp.hoge.news<\/span>\r\n\r\nimport<\/span> java.util.regex.<\/span>{<\/span>Matcher<\/span>,<\/span> Pattern<\/span>}<\/span>\r\nimport<\/span> scala.collection.convert.WrapAsScala._<\/span>\r\nimport<\/span> org.apache.spark.SparkConf<\/span>\r\nimport<\/span> org.apache.spark.SparkContext._<\/span>\r\nimport<\/span> org.apache.spark.SparkContext<\/span>\r\nimport<\/span> org.atilika.kuromoji.Tokenizer<\/span>\r\nimport<\/span> org.atilika.kuromoji.Token<\/span>\r\n\r\nobject<\/span> WordCountApp<\/span>{<\/span>\r\ndef<\/span> main<\/span>(<\/span>args<\/span>:<\/span> Array<\/span>[<\/span>String<\/span>])<\/span> {<\/span>\r\n    \/\/\u30b9\u30d1\u30fc\u30af\u306e\u74b0\u5883\u8a2d\u5b9a<\/span>\r\n    val<\/span> sparkConf<\/span> =<\/span> new<\/span> SparkConf<\/span>().<\/span>setMaster<\/span>(<\/span>\"local[4]\"<\/span>).<\/span>setAppName<\/span>(<\/span>\"WordCount App\"<\/span>)<\/span>\r\n    val<\/span> sc<\/span> =<\/span> new<\/span> SparkContext<\/span>(<\/span>sparkConf<\/span>)<\/span>\r\n    \/\/kuromoji\u306e\u30c8\u30fc\u30af\u30ca\u30a4\u30b6<\/span>\r\n    val<\/span> tokenizer<\/span> =<\/span> Tokenizer<\/span>.<\/span>builder<\/span>.<\/span>mode<\/span>(<\/span>Tokenizer<\/span>.<\/span>Mode<\/span>.<\/span>NORMAL<\/span>).<\/span>build<\/span>()<\/span>\r\n    \/\/\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u304b\u30891\u884c\u305a\u3064\u8aad\u307f\u8fbc\u307f\u3002\u540d\u8a5e\u3092\u914d\u5217\u306b\u5206\u89e3\u3059\u308b\u3002<\/span>\r\n    \/\/\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u304b\u3089RDD\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u3092\u53d6\u5f97\u3059\u308b\u3002<\/span>\r\n        val<\/span> input<\/span> =<\/span> sc<\/span>.<\/span>textFile<\/span>(<\/span>\"input.txt\"<\/span>).<\/span>flatMap<\/span>(<\/span>line<\/span> =><\/span> {<\/span>\r\n        val<\/span> tokens<\/span> :<\/span> java.util.List<\/span>[<\/span>Token<\/span>]<\/span> =<\/span> Tokenizer<\/span>.<\/span>builder<\/span>().<\/span>build<\/span>().<\/span>tokenize<\/span>(<\/span>line<\/span>)<\/span>\r\n        val<\/span> output<\/span> :<\/span> scala.collection.mutable.ArrayBuffer<\/span>[<\/span>String<\/span>]<\/span> =<\/span> new<\/span> collection<\/span>.<\/span>mutable<\/span>.<\/span>ArrayBuffer<\/span>[<\/span>String<\/span>]()<\/span>\r\n        tokens<\/span>.<\/span>foreach<\/span>(<\/span>token<\/span> =><\/span> {<\/span>\r\n            if<\/span>(<\/span>token<\/span>.<\/span>getAllFeatures<\/span>().<\/span>indexOf<\/span>(<\/span>\"\u540d\u8a5e\"<\/span>)<\/span> !=<\/span> -<\/span>1<\/span>)<\/span> {<\/span>\r\n\u3000\u3000\u3000\u3000\u3000\u3000<\/span>output<\/span> +=<\/span> token<\/span>.<\/span>getSurfaceForm<\/span>()<\/span>\r\n        }})<\/span>\r\n        output<\/span>\/\/ return<\/span>\r\n\u3000\u3000\u3000\u3000<\/span>})<\/span>\r\n    \/\/\u30ef\u30fc\u30c9\u30ab\u30a6\u30f3\u30c8\u3092\u884c\u3046\u3002\u6570\u3048\u308b\u540d\u8a5e\u3092\u30ad\u30fc\u306b\u3057\u3001\u30ad\u30fc\u3092\u5143\u306b\u52a0\u7b97\u51e6\u7406\u3092\u884c\u3046\u3002<\/span>\r\n    val<\/span> wordCounts<\/span> =<\/span> input<\/span>.<\/span>map<\/span>(<\/span>x<\/span> =><\/span> (<\/span>x<\/span>,<\/span> 1L<\/span>)).<\/span>reduceByKey<\/span>((<\/span>x<\/span>,<\/span> y<\/span>)<\/span>=><\/span> x<\/span> +<\/span> y<\/span>)<\/span>\r\n    \/\/\u964d\u9806\u306b\u5358\u8a9e\u3092\u5217\u6319\u3057\u3066\u51fa\u529b\u3059\u308b\u3002<\/span>\r\n    val<\/span> output<\/span> =<\/span> wordCounts<\/span>.<\/span>map<\/span>(<\/span> x<\/span> =><\/span> (<\/span>x<\/span>.<\/span>_2<\/span>,<\/span> x<\/span>.<\/span>_1<\/span>)).<\/span>sortByKey<\/span>(<\/span>false<\/span>).<\/span>saveAsTextFile<\/span>(<\/span>\"output\"<\/span>)<\/span>\r\n    }<\/span>\r\n}<\/span>\r\n<\/code><\/pre>\n
\u30fb\u8f93\u5165\u6587\u4ef6.txt .txt)<\/p>\n
Apache Spark\u306f\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e\u30af\u30e9\u30b9\u30bf\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308b\u3002\u30ab\u30ea\u30d5\u30a9\u30eb\u30cb\u30a2\u5927\u5b66\u30d0\u30fc\u30af\u30ec\u30fc\u6821\u306eAMPLab\u3067\u958b\u767a\u3055\u308c\u305f\u30b3\u30fc\u30c9\u304c\u3001\u7ba1\u7406\u5143\u306eApache\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u8ca1\u56e3\u306b\u5bc4\u8d08\u3055\u308c\u305f\u3002Spark\u306e\u30a4\u30f3\u30bf\u30d5\u30a7\u30fc\u30b9\u3092\u4f7f\u3046\u3068\u3001\u6697\u9ed9\u306e\u30c7\u30fc\u30bf\u4e26\u5217\u6027\u3068\u8010\u6545\u969c\u6027\u3092\u5099\u3048\u305f\u30af\u30e9\u30b9\u30bf\u5168\u4f53\u3092\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u3067\u304d\u308b\u3002\u65e5\u7d4cBP\u793e\u304c\u767a\u8868\u3057\u305f\u300cIT\u30a4\u30f3\u30d5\u30e9\u30c6\u30af\u30ce\u30ed\u30b8\u30fcAWARD 2015\u300d\u306b\u304a\u3044\u3066\u3001Spark\u306fDocker\u306b\u6b21\u3050\u6e96\u30b0\u30e9\u30f3\u30d7\u30ea\u3068\u3055\u308c\u305f\u3002\r\n\u30d5\u30a9\u30fc\u30eb\u30c8\u30c8\u30ec\u30e9\u30f3\u30c8\u30b7\u30b9\u30c6\u30e0\u3067\u7ba1\u7406\u3055\u308c\u3001\u8907\u6570\u30de\u30b7\u30f3\u306e\u30af\u30e9\u30b9\u30bf\u306b\u5206\u6563\u3055\u308c\u305f\u30c7\u30fc\u30bf\u9805\u76ee\u306e\u8aad\u307f\u53d6\u308a\u5c02\u7528\u591a\u91cd\u96c6\u5408\u3067\u3042\u308bRDD\uff08resilient distributed dataset\uff09\u3068\u547c\u3070\u308c\u308b\u30c7\u30fc\u30bf\u69cb\u9020\u3092\u4e2d\u5fc3\u3068\u3059\u308b\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3092\u5099\u3048\u3066\u3044\u308b\u3002MapReduce\u306f\u3001\u5206\u6563\u30d7\u30ed\u30b0\u30e9\u30e0\u4e0a\u3067\u7279\u5b9a\u306e\u7dda\u5f62\u30c7\u30fc\u30bf\u30d5\u30ed\u30fc\u69cb\u9020\u3092\u5f37\u5236\u3059\u308b\u30af\u30e9\u30b9\u30bf\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30d1\u30e9\u30c0\u30a4\u30e0\u306e\u5236\u9650\u306b\u5bfe\u5fdc\u3057\u3066\u958b\u767a\u3055\u308c\u305f\u3002MapReduce\u306f\u3001\u30c7\u30a3\u30b9\u30af\u304b\u3089\u5165\u529b\u30c7\u30fc\u30bf\u3092\u8aad\u307f\u8fbc\u307f\u3001\u30c7\u30fc\u30bf\u5168\u4f53\u306b\u95a2\u6570\u3092\u30de\u30c3\u30d7\u3057\u3001\u524a\u6e1b\u7d50\u679c\u3092\u30c7\u30a3\u30b9\u30af\u306b\u683c\u7d0d\u3059\u308b\u3002Spark\u306eRDD\u306f\u3001 \u5206\u6563\u5171\u6709\u30e1\u30e2\u30ea\u306e \uff08\u610f\u56f3\u7684\u306b\uff09\u5236\u9650\u3055\u308c\u305f\u5f62\u5f0f\u3067\u63d0\u4f9b\u3059\u308b\u5206\u6563\u30d7\u30ed\u30b0\u30e9\u30e0\u306e\u30ef\u30fc\u30ad\u30f3\u30b0\u30bb\u30c3\u30c8\u3068\u3057\u3066\u6a5f\u80fd\u3059\u308b\u3002\r\n\r\nRDD\u306e\u53ef\u7528\u6027\u306f\u3001\u30eb\u30fc\u30d7\u5185\u3067\u8907\u6570\u56de\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u53c2\u7167\u3059\u308b\u53cd\u5fa9\u6cd5\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3001\u304a\u3088\u3073\u5bfe\u8a71\u578b\/\u63a2\u7d22\u578b\u30c7\u30fc\u30bf\u5206\u6790\u3001\u30c7\u30fc\u30bf\u53cd\u5fa9\u306e\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u30af\u30a8\u30ea\u306e\u4e21\u65b9\u306e\u5b9f\u88c5\u3092\u5bb9\u6613\u306b\u3059\u308b\u3002\u3053\u306e\u3088\u3046\u306a\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306e\u30ec\u30a4\u30c6\u30f3\u30b7\uff08Apache Hadoop\u30b9\u30bf\u30c3\u30af\u3067\u306f\u4e00\u822c\u7684\u3067\u3042\u3063\u305fMapReduce\u5b9f\u88c5\u3068\u6bd4\u8f03\u3057\u3066\uff09\u306f\u3001\u6841\u9055\u3044\u306b\u4f4e\u4e0b\u3059\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u3002\u53cd\u5fa9\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u30af\u30e9\u30b9\u306e\u4e2d\u306b\u306f\u3001 \u6a5f\u68b0\u5b66\u7fd2\u306e\u305f\u3081\u306e\u8a13\u7df4\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u304c\u3042\u308a\u3001Apache Spark\u3092\u958b\u767a\u306e\u521d\u671f\u306e\u523a\u6fc0\u3068\u306a\u3063\u305f\u3002\u30af\u30e9\u30b9\u30bf\u30de\u30cd\u30fc\u30b8\u30e3\u3068\u5206\u6563\u30b9\u30c8\u30ec\u30fc\u30b8\u30b7\u30b9\u30c6\u30e0\u304c\u5fc5\u8981\u3067\u3042\u308a\u3001\u30af\u30e9\u30b9\u30bf\u7ba1\u7406\u306e\u305f\u3081\u306b\u30b9\u30bf\u30f3\u30c9\u30a2\u30ed\u30f3\uff08\u30cd\u30a4\u30c6\u30a3\u30d6\u306eSpark\u30af\u30e9\u30b9\u30bf\uff09\u3001Hadoop YARN\u3001Apache Mesos\u306b\u5bfe\u5fdc\u3057\u3066\u3044\u308b\u3002\u5206\u6563\u30b9\u30c8\u30ec\u30fc\u30b8\u306e\u5834\u5408\u3001Hadoop\u5206\u6563\u30d5\u30a1\u30a4\u30eb\u30b7\u30b9\u30c6\u30e0\u3001MapR\u30d5\u30a1\u30a4\u30eb\u30b7\u30b9\u30c6\u30e0\uff08MapR-FS\uff09\u3001Apache Cassandra\u3001OpenStack Swift\u3001Amazon S3\u3001Kudu\u3001\u30ab\u30b9\u30bf\u30e0\u30bd\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u3092\u5b9f\u88c5\u3067\u304d\u308b\u3002\u64ec\u4f3c\u5206\u6563\u30ed\u30fc\u30ab\u30eb\u30e2\u30fc\u30c9\u3082\u5bfe\u5fdc\u3057\u3066\u304a\u308a\u901a\u5e38\u306f\u958b\u767a\u3084\u30c6\u30b9\u30c8\u76ee\u7684\u3067\u306e\u307f\u4f7f\u7528\u3055\u308c\u308b\u3002\u5206\u6563\u30b9\u30c8\u30ec\u30fc\u30b8\u306f\u4e0d\u8981\u3067\u30ed\u30fc\u30ab\u30eb\u30d5\u30a1\u30a4\u30eb\u30b7\u30b9\u30c6\u30e0\u3092\u4ee3\u308f\u308a\u306b\u4f7f\u7528\u3067\u304d\u3001CPU\u30de\u30eb\u30c1\u30b3\u30a2\u3054\u3068\u306b1\u53f0\u306e\u30de\u30b7\u30f3\u4e0a\u3067\u5b9f\u884c\u3055\u308c\u308b\u3002\r\n<\/code><\/pre>\n
\u8fd0\u884csbt\u3002<\/h1>\n
\u5728\u5305\u542bbulid.bat\u6587\u4ef6\u7684\u9879\u76ee\u6839\u76ee\u5f55\u4e0a\u6267\u884c\u4ee5\u4e0b\u64cd\u4f5c<\/p>\n
#<\/span> sbt<\/span> run<\/span>\r\n<\/code><\/pre>\n
\u6210\u529f\u8fd0\u884c\u5b8c\u6bd5\u540e\uff0c\u67e5\u770boutput\u6587\u4ef6\u5939\u4e0b\u7684part-00000x\uff0c\u786e\u8ba4WordCount\u5df2\u6267\u884c\u3002<\/p>\n
# vi output\/part-00000\r\n(9,\u5206\u6563)\r\n(8,\u30c7\u30fc\u30bf)\r\n(6,Apache)\r\n(6,Spark)\r\n(5,\u30af\u30e9\u30b9\u30bf)\r\n(5,\u30b7\u30b9\u30c6\u30e0)\r\n(4,\u958b\u767a)\r\n(3,\u53cd\u5fa9)\r\n(3,\u5b9f\u88c5)\r\n(3,MapReduce)\r\n(3,RDD)\r\n(3,\u5bfe\u5fdc)\r\n(3,\u30d5\u30a1\u30a4\u30eb)\r\n(3,\u30b9\u30c8\u30ec\u30fc\u30b8)\r\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
\u6839\u636e\u8fd9\u4e2a\u53c2\u8003\uff0c\u6211\u5c1d\u8bd5\u5728Apache Spark Scala\u4e2d\u6267\u884c\u4e86WordCount\u3002\u73af\u5883\u5982\u4e0b\u6240\u793a\u3002 \u30fbCen […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-36786","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"\n\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528apache-spark-2-3\u8fdb\u884cwordcount\u3002\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount\" \/>\n<meta property=\"og:description\" content=\"\u6839\u636e\u8fd9\u4e2a\u53c2\u8003\uff0c\u6211\u5c1d\u8bd5\u5728Apache Spark Scala\u4e2d\u6267\u884c\u4e86WordCount\u3002\u73af\u5883\u5982\u4e0b\u6240\u793a\u3002 \u30fbCen […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528apache-spark-2-3\u8fdb\u884cwordcount\u3002\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-08-18T23:26:53+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-04T01:16:54+00:00\" \/>\n<meta name=\"author\" content=\"\u97f5, \u79d1\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u97f5, \u79d1\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/\",\"name\":\"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-08-18T23:26:53+00:00\",\"dateModified\":\"2024-05-04T01:16:54+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/6530331a63adef3b3443a1fab53a0e6e\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/6530331a63adef3b3443a1fab53a0e6e\",\"name\":\"\u97f5, \u79d1\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/429ccb39b3fff5188bc17986222cfb0936cbadb8cc933cff04ab5ca01bd30a08?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/429ccb39b3fff5188bc17986222cfb0936cbadb8cc933cff04ab5ca01bd30a08?s=96&d=mm&r=g\",\"caption\":\"\u97f5, \u79d1\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yunke\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528apache-spark-2-3\u8fdb\u884cwordcount\u3002\/","og_locale":"zh_CN","og_type":"article","og_title":"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount","og_description":"\u6839\u636e\u8fd9\u4e2a\u53c2\u8003\uff0c\u6211\u5c1d\u8bd5\u5728Apache Spark Scala\u4e2d\u6267\u884c\u4e86WordCount\u3002\u73af\u5883\u5982\u4e0b\u6240\u793a\u3002 \u30fbCen […]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528apache-spark-2-3\u8fdb\u884cwordcount\u3002\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-08-18T23:26:53+00:00","article_modified_time":"2024-05-04T01:16:54+00:00","author":"\u97f5, \u79d1","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u97f5, \u79d1","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"2 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/","name":"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-08-18T23:26:53+00:00","dateModified":"2024-05-04T01:16:54+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/6530331a63adef3b3443a1fab53a0e6e"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u4f7f\u7528Apache Spark 2.3\u8fdb\u884cWordCount"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/6530331a63adef3b3443a1fab53a0e6e","name":"\u97f5, \u79d1","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/429ccb39b3fff5188bc17986222cfb0936cbadb8cc933cff04ab5ca01bd30a08?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/429ccb39b3fff5188bc17986222cfb0936cbadb8cc933cff04ab5ca01bd30a08?s=96&d=mm&r=g","caption":"\u97f5, \u79d1"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yunke\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8apache-spark-2-3%e8%bf%9b%e8%a1%8cwordcount%e3%80%82\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36786","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=36786"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36786\/revisions"}],"predecessor-version":[{"id":97452,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36786\/revisions\/97452"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=36786"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=36786"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=36786"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}