{"id":36930,"date":"2023-02-27T17:59:41","date_gmt":"2022-08-12T23:46:15","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/"},"modified":"2024-01-15T09:13:33","modified_gmt":"2024-01-15T01:13:33","slug":"%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/","title":{"rendered":"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell"},"content":{"rendered":"<h1>\u603b\u7ed3<\/h1>\n<p>\u8fd9\u662fScala Advent Calendar 2014\u7684\u7b2c18\u5929\u3002\u5f88\u62b1\u6b49\u803d\u8bef\u4e86\u3002<\/p>\n<p>\u6211\u6b63\u5728\u8bbe\u8ba1\u4e00\u4e2a\u7cfb\u7edf\uff0c\u53ef\u4ee5\u89e3\u6790\u5e94\u7528\u7a0b\u5e8f\u65e5\u5fd7\u5e76\u5c06\u5176\u6ce8\u518c\u5230 Elasticsearch\uff0c\u5728 Kibana \u4e2d\u8fdb\u884c\u53ef\u89c6\u5316\u3002\u7531\u4e8e\u9700\u8981\u5b9e\u65f6\u9ad8\u901f\u5730\u89e3\u6790\u5927\u91cf\u65e5\u5fd7\uff0c\u6211\u51b3\u5b9a\u5c1d\u8bd5\u4f7f\u7528 Spark\uff0c\u5e76\u603b\u7ed3\u4e86\u6211\u7684\u7814\u7a76\u7ed3\u679c\u3002<\/p>\n<h1>\u6e2c\u8a66\u74b0\u5883<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Ubuntu 14.04.1 LTS<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Java 1.8.0_20<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Scala 2.10.4<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">Spark 1.1.1<\/ul>\n<p>\u8bf7\u53c2\u8003\u5b98\u65b9\u6587\u6863\u4ee5\u83b7\u53d6\u6709\u5173Spark\u7684\u5b89\u88c5\u65b9\u6cd5\u7b49\u4fe1\u606f\u3002<\/p>\n<h1>\u5c1d\u8bd5\u89e3\u6790Apache\u7684\u8bbf\u95ee\u65e5\u5fd7<\/h1>\n<p>\u5047\u8bbeLogFormat\u662f\u4ee5\u4e0b\u683c\u5f0f\u3002<\/p>\n<pre class=\"post-pre\"><code>LogFormat \"%h %l %u %t %&gt;s %X %T %B \\\"%r\\\" \\\"%{Referer}i\\\" \\\"%{User-Agent}i\\\"\"\r\n<\/code><\/pre>\n<p>\u5177\u4f53\u6765\u8bf4\uff0c\u5c31\u662f\u8fd9\u6837\u7684\u3002<\/p>\n<pre class=\"post-pre\"><code>192.168.1.10 - - [20\/Oct\/2014:09:00:03 +0900] 200 + 0 1194 \"POST \/hoge\/hoge HTTP\/1.1\" \"http:\/\/hoge.co.jp\/hoge\/view?aaa=1234\" \"Mozilla\/5.0 (Windows NT 5.1) AppleWebKit\/535.1 (KHTML, like Gecko) Chrome\/14.0.835.202 Safari\/535.1\"\r\n<\/code><\/pre>\n<h2>\u7f16\u5199\u89e3\u6790\u5668<\/h2>\n<p>\u4ee5\u4e0b\u662f Parser\uff1a<br \/>\n\u5728\u4ee5\u4e0b\u72b6\u6001\u4e0b\u8fd0\u884c sbt package \u547d\u4ee4\uff0c\u751f\u6210\u4e00\u4e2a jar \u6587\u4ef6\u3002<\/p>\n<pre class=\"post-pre\"><code>\r\n<span class=\"k\">package<\/span> <span class=\"nn\">parser<\/span>\r\n\r\n<span class=\"k\">import<\/span> <span class=\"nn\">model.AccessLog<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">util.parsing.combinator._<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">java.text.<\/span><span class=\"o\">{<\/span><span class=\"nc\">SimpleDateFormat<\/span><span class=\"o\">}<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">java.util.<\/span><span class=\"o\">{<\/span><span class=\"nc\">Locale<\/span><span class=\"o\">,<\/span> <span class=\"nc\">TimeZone<\/span><span class=\"o\">}<\/span>\r\n\r\n<span class=\"k\">object<\/span> <span class=\"nc\">AccessLogParser<\/span> <span class=\"k\">extends<\/span> <span class=\"nc\">RegexParsers<\/span> <span class=\"o\">{<\/span>\r\n\r\n  <span class=\"k\">override<\/span> <span class=\"k\">val<\/span> <span class=\"nv\">whiteSpace<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[ \\t]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">eol<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">Any<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"\\r?\\n\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">^^<\/span> <span class=\"o\">{<\/span> <span class=\"n\">s<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"s\">\"\"<\/span> <span class=\"o\">}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">line<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">AccessLog<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span>\r\n    <span class=\"n\">ipAddress<\/span> <span class=\"o\">~<\/span> <span class=\"n\">ident<\/span> <span class=\"o\">~<\/span> <span class=\"n\">user<\/span> <span class=\"o\">~<\/span> <span class=\"n\">time<\/span> <span class=\"o\">~<\/span> <span class=\"n\">status<\/span> <span class=\"o\">~<\/span> <span class=\"n\">connStatus<\/span> <span class=\"o\">~<\/span> <span class=\"n\">elapsedTime<\/span> <span class=\"o\">~<\/span> <span class=\"n\">bytes<\/span> <span class=\"o\">~<\/span> <span class=\"n\">method<\/span> <span class=\"o\">~<\/span> <span class=\"n\">uri<\/span> <span class=\"o\">~<\/span> <span class=\"n\">version<\/span> <span class=\"o\">~<\/span> <span class=\"n\">referrer<\/span> <span class=\"o\">~<\/span> <span class=\"n\">userAgent<\/span> <span class=\"o\">&lt;~<\/span> <span class=\"n\">rest<\/span> <span class=\"o\">^^<\/span> <span class=\"o\">{<\/span>\r\n      <span class=\"k\">case<\/span> <span class=\"n\">ipAddress<\/span> <span class=\"o\">~<\/span> <span class=\"n\">ident<\/span> <span class=\"o\">~<\/span> <span class=\"n\">user<\/span> <span class=\"o\">~<\/span> <span class=\"n\">time<\/span> <span class=\"o\">~<\/span> <span class=\"n\">status<\/span> <span class=\"o\">~<\/span> <span class=\"n\">connStatus<\/span> <span class=\"o\">~<\/span> <span class=\"n\">elapsedTime<\/span> <span class=\"o\">~<\/span> <span class=\"n\">bytes<\/span> <span class=\"o\">~<\/span> <span class=\"n\">method<\/span> <span class=\"o\">~<\/span> <span class=\"n\">uri<\/span> <span class=\"o\">~<\/span> <span class=\"n\">version<\/span> <span class=\"o\">~<\/span> <span class=\"n\">referrer<\/span> <span class=\"o\">~<\/span> <span class=\"n\">userAgent<\/span> <span class=\"k\">=&gt;<\/span>\r\n        <span class=\"nc\">AccessLog<\/span><span class=\"o\">(<\/span><span class=\"n\">ipAddress<\/span><span class=\"o\">,<\/span> <span class=\"n\">ident<\/span><span class=\"o\">,<\/span> <span class=\"n\">user<\/span><span class=\"o\">,<\/span> <span class=\"n\">time<\/span><span class=\"o\">,<\/span> <span class=\"n\">status<\/span><span class=\"o\">,<\/span> <span class=\"n\">bytes<\/span><span class=\"o\">,<\/span> <span class=\"n\">elapsedTime<\/span><span class=\"o\">,<\/span> <span class=\"n\">method<\/span><span class=\"o\">,<\/span> <span class=\"n\">uri<\/span><span class=\"o\">,<\/span> <span class=\"n\">version<\/span><span class=\"o\">,<\/span> <span class=\"n\">referrer<\/span><span class=\"o\">,<\/span> <span class=\"n\">userAgent<\/span><span class=\"o\">)<\/span>\r\n    <span class=\"o\">}<\/span>\r\n\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">ipAddress<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[^ ]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">ident<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[(?:\\w+)-]\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">user<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[(?:\\w+)-]\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">time<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"[\"<\/span> <span class=\"o\">~&gt;<\/span> <span class=\"s\">\"\"\"\\S+ [^ \\]]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">&lt;~<\/span> <span class=\"s\">\"]\"<\/span> <span class=\"o\">^^<\/span> <span class=\"o\">{<\/span> <span class=\"nf\">convertToIso8601<\/span><span class=\"o\">(<\/span><span class=\"k\">_<\/span><span class=\"o\">)<\/span> <span class=\"o\">}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">status<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">Int<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"\\d+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">^^<\/span> <span class=\"o\">{<\/span> <span class=\"nv\">_<\/span><span class=\"o\">.<\/span><span class=\"py\">toInt<\/span> <span class=\"o\">}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">connStatus<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"\\S+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">elapsedTime<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">Int<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"\\d+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">^^<\/span> <span class=\"o\">{<\/span> <span class=\"nv\">_<\/span><span class=\"o\">.<\/span><span class=\"py\">toInt<\/span> <span class=\"o\">}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">bytes<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">Int<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[^ ]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">^^<\/span> <span class=\"o\">{<\/span> <span class=\"k\">case<\/span> <span class=\"s\">\"-\"<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"mi\">0<\/span><span class=\"o\">;<\/span> <span class=\"k\">case<\/span> <span class=\"n\">s<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nv\">s<\/span><span class=\"o\">.<\/span><span class=\"py\">toInt<\/span> <span class=\"o\">}<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">method<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\\\"\"<\/span> <span class=\"o\">~&gt;<\/span> <span class=\"s\">\"\"\"[A-Z]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">uri<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"\\S+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">version<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[^ \"]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">&lt;~<\/span> <span class=\"s\">\"\\\"\"<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">referrer<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\\\"\"<\/span> <span class=\"o\">~&gt;<\/span> <span class=\"s\">\"\"\"[^\"]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">&lt;~<\/span> <span class=\"s\">\"\\\"\"<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">userAgent<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\\\"\"<\/span> <span class=\"o\">~&gt;<\/span> <span class=\"s\">\"\"\"[^\"]+\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span> <span class=\"o\">&lt;~<\/span> <span class=\"s\">\"\\\"\"<\/span>\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">rest<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Parser<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\"\"[^$]*\"\"\"<\/span><span class=\"o\">.<\/span><span class=\"py\">r<\/span>\r\n\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">parse<\/span><span class=\"o\">(<\/span><span class=\"n\">log<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">ParseResult<\/span><span class=\"o\">[<\/span><span class=\"kt\">AccessLog<\/span><span class=\"o\">]<\/span>  <span class=\"k\">=<\/span> <span class=\"nf\">parseAll<\/span><span class=\"o\">(<\/span><span class=\"n\">line<\/span><span class=\"o\">,<\/span> <span class=\"n\">log<\/span><span class=\"o\">)<\/span>\r\n\r\n  <span class=\"k\">def<\/span> <span class=\"nf\">convertToIso8601<\/span><span class=\"o\">(<\/span><span class=\"n\">strDate<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span><span class=\"o\">)<\/span> <span class=\"k\">=<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"k\">val<\/span> <span class=\"nv\">df<\/span> <span class=\"k\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">SimpleDateFormat<\/span><span class=\"o\">(<\/span><span class=\"s\">\"dd\/MMM\/yyyy:HH:mm:ss Z\"<\/span><span class=\"o\">,<\/span> <span class=\"nv\">Locale<\/span><span class=\"o\">.<\/span><span class=\"py\">ENGLISH<\/span><span class=\"o\">)<\/span>\r\n    <span class=\"nv\">df<\/span><span class=\"o\">.<\/span><span class=\"py\">setTimeZone<\/span><span class=\"o\">(<\/span><span class=\"nv\">TimeZone<\/span><span class=\"o\">.<\/span><span class=\"py\">getTimeZone<\/span><span class=\"o\">(<\/span><span class=\"s\">\"UTC\"<\/span><span class=\"o\">))<\/span>\r\n    <span class=\"k\">val<\/span> <span class=\"nv\">date<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">df<\/span><span class=\"o\">.<\/span><span class=\"py\">parse<\/span><span class=\"o\">(<\/span><span class=\"n\">strDate<\/span><span class=\"o\">)<\/span>\r\n    <span class=\"nv\">df<\/span><span class=\"o\">.<\/span><span class=\"py\">applyPattern<\/span><span class=\"o\">(<\/span><span class=\"s\">\"YYYY-MM-dd'T'hh:mm:ss Z\"<\/span><span class=\"o\">)<\/span>\r\n    <span class=\"nv\">df<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(<\/span><span class=\"n\">date<\/span><span class=\"o\">).<\/span><span class=\"py\">replace<\/span><span class=\"o\">(<\/span><span class=\"s\">\" \"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">)<\/span>\r\n  <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n\r\n<span class=\"k\">case<\/span> <span class=\"k\">class<\/span> <span class=\"nc\">AccessLog<\/span><span class=\"o\">(<\/span>\r\n  <span class=\"n\">ipAddress<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">ident<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">user<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">time<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">status<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Int<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">0<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">bytes<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Int<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">0<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">elapsedTime<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Int<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">0<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">method<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">uri<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">version<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">referrer<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">,<\/span>\r\n  <span class=\"n\">userAgent<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>\r\n<span class=\"n\">name<\/span> <span class=\"o\">:=<\/span> <span class=\"s\">\"LogParser\"<\/span>\r\n\r\n<span class=\"n\">version<\/span> <span class=\"o\">:=<\/span> <span class=\"s\">\"1.0\"<\/span>\r\n\r\n<span class=\"n\">scalaVersion<\/span> <span class=\"o\">:=<\/span> <span class=\"s\">\"2.10.4\"<\/span>\r\n\r\n<\/code><\/pre>\n<h2>\u5c1d\u8bd5\u5728Spark\u7684REPL\u4e2d\u8fd0\u884c<\/h2>\n<p>\u5728\u8fd9\u91cc\u4f7f\u75284\u4e2a\u6838\u5fc3\u542f\u52a8Spark\u7684REPL\u3002<br \/>\n\u987a\u4fbf\u63d0\u4e00\u4e0b\uff0c\u5728\u4e4b\u524d\u7684\u6b65\u9aa4\u4e2d\uff0c\u6211\u4eec\u5c06\u521b\u5efa\u7684jar\u6587\u4ef6\u653e\u7f6e\u5728\/pathToSparkHome\/jar\u76ee\u5f55\u4e0b\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"nv\">$ <\/span><span class=\"nb\">cd<\/span> \/pathToSparkHome\/\r\n<span class=\"nv\">$ <\/span>.\/bin\/spark-shell <span class=\"nt\">--master<\/span> <span class=\"nb\">local<\/span><span class=\"o\">[<\/span>4] <span class=\"nt\">--jars<\/span> jar\/logparser_2.10-1.0.jar\r\n<\/code><\/pre>\n<p>\u5bf9\u5b58\u50a8\u5728\/pathToAccesslog\/accesslog\u4e2d\u7684\u5927\u7ea61GB\u5927\u5c0f\u7684\u65e5\u5fd7\u6587\u4ef6\u8fdb\u884c\u89e3\u6790\u3002<br \/>\n\u8ba1\u7b97\u6709\u6548\u8bb0\u5f55\u7684\u6570\u91cf\uff0c\u5e76\u8ba1\u7b97\u72b6\u6001\u7801\u4e3a400\u7684\u8bf7\u6c42\u7684\u6570\u91cf\u3002<\/p>\n<pre class=\"post-pre\"><code>scala&gt; import parser._\r\nimport parser._\r\n\r\nscala&gt; val file = sc.textFile(\"\/pathToAccesslog\/accesslog\")\r\n14\/12\/19 10:54:22 INFO MemoryStore: ensureFreeSpace(32728) called with curMem=0, maxMem=278019440\r\n14\/12\/19 10:54:22 INFO MemoryStore: Block broadcast_0 stored as values in memory (estimated size 32.0 KB, free 265.1 MB)\r\n14\/12\/19 10:54:22 INFO MemoryStore: ensureFreeSpace(4959) called with curMem=32728, maxMem=278019440\r\n14\/12\/19 10:54:22 INFO MemoryStore: Block broadcast_0_piece0 stored as bytes in memory (estimated size 4.8 KB, free 265.1 MB)\r\n14\/12\/19 10:54:22 INFO BlockManagerInfo: Added broadcast_0_piece0 in memory on localhost:35772 (size: 4.8 KB, free: 265.1 MB)\r\n14\/12\/19 10:54:22 INFO BlockManagerMaster: Updated info of block broadcast_0_piece0\r\n14\/12\/19 10:54:22 INFO SparkContext: Created broadcast 0 from textFile at &lt;console&gt;:15\r\nfile: org.apache.spark.rdd.RDD[String] = \/home\/ysksuzuki\/access.log MappedRDD[1] at textFile at &lt;console&gt;:15\r\n\r\nscala&gt; val records = file.map{ line =&gt;\r\n     | AccessLogParser.parse(line).getOrElse(AccessLog())\r\n     | }.filter(!_.ipAddress.isEmpty)\r\nrecords: org.apache.spark.rdd.RDD[parser.AccessLog] = FilteredRDD[3] at filter at &lt;console&gt;:19\r\n\r\nscala&gt; records.count\r\n\r\n(\u7701\u7565)\r\n\r\nres0: Long = 2767874\r\n\r\nscala&gt; records.filter(_.status == 400).count\r\n\r\n(\u7701\u7565)\r\n\r\nres1: Long = 93\r\n<\/code><\/pre>\n<h1>\u5c1d\u8bd5\u7684\u7ed3\u679c<\/h1>\n<p>\u6211\u7528\u5927\u7ea630\u79d2\u7684\u65f6\u95f4\u89e3\u6790\u4e861GB\u7684\u8bbf\u95ee\u65e5\u5fd7\u3002\u867d\u7136\u53ea\u662f\u5728\u672c\u5730\u73af\u5883\u7684\u5355\u53f0\u673a\u5668\u4e0a\u8fdb\u884c\u4e86\u6d4b\u8bd5\uff0c\u4f46\u6211\u89c9\u5f97\u80fd\u591f\u611f\u53d7\u5230Spark\u529f\u80fd\u7684\u4e00\u90e8\u5206\u3002<\/p>\n<p>\u6211\u539f\u672c\u60f3\u4f7f\u7528Spark-hadoop\u5c06\u6570\u636e\u6ce8\u518c\u5230elasticsearch\uff0c\u4f46\u5b83\u5e76\u4e0d\u50cf\u6211\u60f3\u8c61\u7684\u90a3\u6837\u5de5\u4f5c\uff0c\u6240\u4ee5\u6211\u653e\u5f03\u4e86\u3002\u6211\u60f3\u518d\u7ee7\u7eed\u7814\u7a76\u4e00\u4e0b\u8fd9\u4e2a\u95ee\u9898\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u603b\u7ed3 \u8fd9\u662fScala Advent Calendar 2014\u7684\u7b2c18\u5929\u3002\u5f88\u62b1\u6b49\u803d\u8bef\u4e86\u3002 \u6211\u6b63\u5728\u8bbe\u8ba1\u4e00\u4e2a\u7cfb\u7edf\uff0c [&hellip;]<\/p>\n","protected":false},"author":9,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-36930","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell - 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\/\u5c1d\u8bd5\u4f7f\u7528apache-spark\u7684scala-shell\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell\" \/>\n<meta property=\"og:description\" content=\"\u603b\u7ed3 \u8fd9\u662fScala Advent Calendar 2014\u7684\u7b2c18\u5929\u3002\u5f88\u62b1\u6b49\u803d\u8bef\u4e86\u3002 \u6211\u6b63\u5728\u8bbe\u8ba1\u4e00\u4e2a\u7cfb\u7edf\uff0c [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5c1d\u8bd5\u4f7f\u7528apache-spark\u7684scala-shell\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2022-08-12T23:46:15+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-01-15T01:13:33+00:00\" \/>\n<meta name=\"author\" content=\"\u6e05, \u626c\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6e05, \u626c\" \/>\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\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/\",\"name\":\"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2022-08-12T23:46:15+00:00\",\"dateModified\":\"2024-01-15T01:13:33+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell\"}]},{\"@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\/cb5556d2501da73d864cac945e8d9461\",\"name\":\"\u6e05, \u626c\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g\",\"caption\":\"\u6e05, \u626c\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell - 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\/\u5c1d\u8bd5\u4f7f\u7528apache-spark\u7684scala-shell\/","og_locale":"zh_CN","og_type":"article","og_title":"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell","og_description":"\u603b\u7ed3 \u8fd9\u662fScala Advent Calendar 2014\u7684\u7b2c18\u5929\u3002\u5f88\u62b1\u6b49\u803d\u8bef\u4e86\u3002 \u6211\u6b63\u5728\u8bbe\u8ba1\u4e00\u4e2a\u7cfb\u7edf\uff0c [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u5c1d\u8bd5\u4f7f\u7528apache-spark\u7684scala-shell\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2022-08-12T23:46:15+00:00","article_modified_time":"2024-01-15T01:13:33+00:00","author":"\u6e05, \u626c","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6e05, \u626c","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"2 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/","name":"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2022-08-12T23:46:15+00:00","dateModified":"2024-01-15T01:13:33+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/cb5556d2501da73d864cac945e8d9461"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u5c1d\u8bd5\u4f7f\u7528Apache Spark\u7684Scala shell"}]},{"@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\/cb5556d2501da73d864cac945e8d9461","name":"\u6e05, \u626c","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/32a4239de8ff29adace466261d309424a1e5fe9f7e3036bf89fe03f2e3dbe717?s=96&d=mm&r=g","caption":"\u6e05, \u626c"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyang\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%b0%9d%e8%af%95%e4%bd%bf%e7%94%a8apache-spark%e7%9a%84scala-shell\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36930","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\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=36930"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36930\/revisions"}],"predecessor-version":[{"id":58099,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36930\/revisions\/58099"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=36930"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=36930"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=36930"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}