Package Com.wangzs;
Import org.apache.spark.SparkConf;
Import Org.apache.spark.api.java.JavaRDD;
Import Org.apache.spark.api.java.JavaSparkContext;
Import org.apache.spark.api.java.function.Function; /** * @title: Counts the number of occurrences of keywords in a text file <br/> * @author: Wangzs <br/> * @date: April 26, 2018 * * public class Simpleapp Test {public static void main (string[] args) {sparkconf conf = new sparkconf (). Setmaster ("local"). Setappname ("Simplea
Pptest ");
Javasparkcontext sc = new Javasparkcontext (conf);
javardd<string> logdata = Sc.textfile ("e:\\pss_2018\\spark-2.5-learn\\src\\main\\resources\\readme.md"); javardd<string> Rdda = logdata.filter (New function<string, boolean> () {@Override public Boolean call (St
Ring s) throws Exception {return S.contains ("a");
}
});
Long CountA = Rdda.count (); javardd<string> rddb = logdata.filter (New function<string, boolean> () {@Override public Boolean call (St Ring s) throws Exception {reTurn S.contains ("B");
}
});
Long countb = Rddb.count ();
System.out.println ("CountA:" + CountA + "\TCOUNTB:" + countb);
}
}
<project xmlns= "http://maven.apache.org/POM/4.0.0" xmlns:xsi= "Http://www.w3.org/2001/XMLSchema-instance" xsi: schemalocation= "http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" > < Modelversion>4.0.0</modelversion> <groupId>com.pss</groupId> <artifactId> Spark-2.5-learn</artifactid> <version>0.0.1-SNAPSHOT</version> <packaging>jar</ Packaging> <name>spark-2.5-learn</name> <url>http://maven.apache.org</url> < Properties> <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> </properties > <dependencies> <dependency> <!--Spark dependency--> <groupid>org.apache.spark</gr oupid> <artifactId>spark-core_2.11</artifactId> <version>2.1.0</version> </dependen cy> </dependencies> <build> <pluginManagement> <plugins> <plugiN> <groupId>org.apache.maven.plugins</groupId> <artifactid>maven-compiler-plugin</artifa ctid> <configuration> <source>1.7</source> <target>1.7</target> ;/configuration> </plugin> < skip test--> <plugin> <groupid>org.apache.maven when packaging!-- .plugins</groupid> <artifactId>maven-surefire-plugin</artifactId> <version>2.18.1</ve rsion> <configuration> <skipTests>true</skipTests> </configuration> </pl
ugin> </plugins> </pluginManagement> </build> </project>
Statistical results:
counta:61 countb:30