CDH 版本 6.3

    spark 版本  2.4.0-cdh6.3.2
    hadoop 版本 3.0.0-cdh6.3.2
    hive 版本 2.1.1-cdh6.3.2
1
2
3

pom文件

<?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>bigdata</groupId>
    <artifactId>data_shuffle_demo</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>

        <scala.version>2.11.12</scala.version>
        <spark.version>2.4.0-cdh6.3.2</spark.version>
        <hadoop.version>3.0.0-cdh6.3.2</hadoop.version>
        <!--项目打包: provided  项目本地运行调试: compile-->
        <mvn.scop.pro>provided</mvn.scop.pro>
        <!-- 加了provided的依赖要保证在spark服务器的sparkJar目录里存在, 具体路径/opt/cloudera/parcels/CDH/lib/spark/jars -->
        <!--jar包前缀-->
        <jar.pre.name>optimization</jar.pre.name>
    </properties>

    <repositories>

        <repository>

            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>

    </repositories>

        <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
            <scope>${mvn.scop.pro}</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
            <scope>${mvn.scop.pro}</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
            <exclusions>
                <exclusion>
                    <artifactId>hadoop-client</artifactId>
                    <groupId>org.apache.hadoop</groupId>
                </exclusion>
            </exclusions>
            <scope>${mvn.scop.pro}</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
            <scope>${mvn.scop.pro}</scope>
        </dependency>


        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>2.1.1-cdh6.3.2</version>
        </dependency>

        <dependency>
        <groupId>org.apache.hive</groupId>
        <artifactId>hive-jdbc</artifactId>
        <version>2.1.1-cdh6.3.2</version>
        <scope>${mvn.scop.pro}</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>${spark.version}</version>
            <scope>${mvn.scop.pro}</scope>
        </dependency>

    </dependencies>

    <build>
        <finalName>${jar.pre.name}</finalName>
        <plugins>


            <!--设置编译版本-->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>


            <!--声明并引入构建插件-->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>


        </plugins>
    </build>

</project>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129

sparksession 连接hive

//spark链接
  def sparkSession(): SparkSession = {

    var conf = new SparkConf()
      .set("spark.sql.legacy.allowCreatingManagedTableUsingNonemptyLocation", "true")
      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
      .set("spark.sql.warehouse.dir", "your hive warehouse")
      .set("hive.metastore.uris", "your hive metastore uris")
    SparkSession.builder()
      .config(conf)
      .enableHiveSupport()
      .getOrCreate()
  }
1
2
3
4
5
6
7
8
9
10
11
12
13