feat:首次提交

This commit is contained in:
2026-09-16 11:25:50 +08:00
commit 705f7a08ee
9 changed files with 311 additions and 0 deletions
+39
View File
@@ -0,0 +1,39 @@
target/
!.mvn/wrapper/maven-wrapper.jar
!**/src/main/**/target/
!**/src/test/**/target/
.kotlin
### IntelliJ IDEA ###
.idea/modules.xml
.idea/jarRepositories.xml
.idea/compiler.xml
.idea/libraries/
*.iws
*.iml
*.ipr
### Eclipse ###
.apt_generated
.classpath
.factorypath
.project
.settings
.springBeans
.sts4-cache
### NetBeans ###
/nbproject/private/
/nbbuild/
/dist/
/nbdist/
/.nb-gradle/
build/
!**/src/main/**/build/
!**/src/test/**/build/
### VS Code ###
.vscode/
### Mac OS ###
.DS_Store
+10
View File
@@ -0,0 +1,10 @@
# 默认忽略的文件
/shelf/
/workspace.xml
# 基于编辑器的 HTTP 客户端请求
/httpRequests/
# 已忽略包含查询文件的默认文件夹
/queries/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml
+145
View File
@@ -0,0 +1,145 @@
<?xml version="1.0" encoding="UTF-8"?>
<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>org.example</groupId>
<artifactId>spark_project</artifactId>
<version>1.0-SNAPSHOT</version>
<packaging>jar</packaging>
<name>spark_project</name>
<url>http://maven.apache.org</url>
<properties>
<!-- Java -->
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
<!-- Scala -->
<scala.version>2.11.12</scala.version>
<!-- Spark -->
<spark.version>2.4.3</spark.version>
<!-- Hadoop -->
<hadoop.version>2.7.3</hadoop.version>
<!-- Encoding -->
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<dependencies>
<!-- Scala -->
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<!-- Spark Core -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- Spark SQL -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- Hadoop Client -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- MySQL -->
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>8.0.28</version>
</dependency>
<!-- HikariCP -->
<dependency>
<groupId>com.zaxxer</groupId>
<artifactId>HikariCP</artifactId>
<version>4.0.3</version>
</dependency>
<!-- DbUtils -->
<dependency>
<groupId>commons-dbutils</groupId>
<artifactId>commons-dbutils</artifactId>
<version>1.6</version>
</dependency>
<!-- JUnit -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
</dependencies>
<build>
<!-- Scala 源码目录 -->
<sourceDirectory>src/main/scala</sourceDirectory>
<plugins>
<!-- Scala 编译插件 -->
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>4.8.1</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<!-- 打包插件 -->
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<version>3.7.1</version>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
+38
View File
@@ -0,0 +1,38 @@
package org.example;
import junit.framework.Test;
import junit.framework.TestCase;
import junit.framework.TestSuite;
/**
* Unit test for simple App.
*/
public class AppTest
extends TestCase
{
/**
* Create the test case
*
* @param testName name of the test case
*/
public AppTest( String testName )
{
super( testName );
}
/**
* @return the suite of tests being tested
*/
public static Test suite()
{
return new TestSuite( AppTest.class );
}
/**
* Rigourous Test :-)
*/
public void testApp()
{
assertTrue( true );
}
}
+25
View File
@@ -0,0 +1,25 @@
-- m.movieId,m.title,r.avg_rating
create table `top_ten_avg_ratings`
(
`id` int(11) not null AUTO_INCREMENT comment '自增id',
`movie_id` int(11) not null comment '电影id',
`title` varchar(200) not null comment '电影名称',
`avg_rating` decimal(10, 2) not null comment '电影名称',
`update_time` datetime default current_timestamp comment '更新时间',
primary key (`id`),
unique key `movie_id_unique` (`movie_id`)
) ENGINE = InnoDB
DEFAULT CHARSET = utf8;
CREATE TABLE genres_average_rating
(
`id` INT(11) NOT NULL AUTO_INCREMENT COMMENT '自增id',
`genres` VARCHAR(100) NOT NULL COMMENT '电影类别',
`avg_rating` DECIMAL(10, 2) NOT NULL COMMENT '电影类别平均评分',
`update_time` datetime DEFAULT CURRENT_TIMESTAMP COMMENT '更新时间',
PRIMARY KEY (`id`),
UNIQUE KEY `genres_UNIQUE` (`genres`)
) ENGINE = INNODB
DEFAULT CHARSET = utf8;
+4
View File
@@ -0,0 +1,4 @@
log4j.rootLogger=error, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%-4r [%t] %-5p %c %x - %m%n
+3
View File
@@ -0,0 +1,3 @@
hello world
hello spark
hello scala
@@ -0,0 +1,33 @@
package com.example.spark
import org.apache.spark.{SparkConf, SparkContext}
object App {
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf()
.setMaster("local[2]")
.setAppName("scala spark app")
.set("spark.driver.host", "127.0.0.1")
.set("spark.driver.bindAddress", "127.0.0.1")
val sc = new SparkContext(sparkConf)
val textFile = sc.textFile("src/main/resources/word.txt")
println(textFile.count())
val me = textFile.filter(line => line.contains("me"))
println("me.collect() = " + me.collect().mkString(","))
val value = textFile
.flatMap(_.split(" "))
.map((_, 1))
.reduceByKey(_+_)
println(value.collect().mkString("\n"))
sc.stop()
}
}
@@ -0,0 +1,14 @@
package com.example.spark
import org.apache.spark.{SparkConf, SparkContext}
object test {
def main(args: Array[String]): Unit = {
val sc = new SparkContext(new SparkConf()
.setMaster("local")
.setAppName("test")
.set("spark.driver.host", "127.0.0.1")
.set("spark.driver.bindAddress", "127.0.0.1"))
sc.textFile("src/main/resources/word.txt").foreach(println)
}
}