配置pom文件
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">
4.0.0
org.example
learning
1.0-SNAPSHOT
UTF-8
2.2.0
2.11.8
2.6.5
1.2.1
org.apache.spark
spark-core_2.11
${spark.version}
org.apache.spark
spark-sql_2.11
${spark.version}
org.apache.spark
spark-hive_2.11
${spark.version}
org.apache.spark
spark-streaming_2.11
${spark.version}
org.apache.hadoop
hadoop-common
${hadoop.version}
org.apache.hive
hive-exec
${hive.version}
mysql
mysql-connector-java
5.1.38
新建JavaWordCount
package spark;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.sql.SparkSession;
import scala.Tuple2;
import java.util.Arrays;
import java.util.List;
import java.util.regex.Pattern;
public class JavaWordCount {
private static final Pattern SPACE = Pattern.compile(" ");
public static void main(String[] args) {
SparkSession spark = SparkSession
.builder()
.master("local[*]")
.appName("WordCount")
.getOrCreate();
String paths = "D:\\workspace\\IdeaProjects\\learning\\src\\main\\resources\\word_count.txt";
JavaRDD lines = spark.read().textFile(paths).javaRDD();
JavaRDD words = lines.flatMap(s -> Arrays.asList(SPACE.split(s)).iterator());
JavaPairRDD ones = words.mapToPair(s -> new Tuple2<>(s, 1));
JavaPairRDD counts = ones.reduceByKey((i1, i2) -> (i1 + i2));
List> output = counts.collect();
for (Tuple2, ?> tuple : output) {
System.out.println(tuple._1() + ": " + tuple._2());
}
spark.stop();
}
}
在resources目录下新建log4j.properties和word_count.txt
log4j.properties文件
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Set everything to be logged to the console
log4j.rootCategory=WARN, console
log4j.appender.console=org.apache.log4j.ConsoleAppender
log4j.appender.console.target=System.err
log4j.appender.console.layout=org.apache.log4j.PatternLayout
log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
# Set the default spark-shell log level to WARN. When running the spark-shell, the
# log level for this class is used to overwrite the root logger's log level, so that
# the user can have different defaults for the shell and regular Spark apps.
log4j.logger.org.apache.spark.repl.Main=WARN
# Settings to quiet third party logs that are too verbose
log4j.logger.org.spark_project.jetty=WARN
log4j.logger.org.spark_project.jetty.util.component.AbstractLifeCycle=ERROR
log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
log4j.logger.org.apache.parquet=ERROR
log4j.logger.parquet=ERROR
# SPARK-9183: Settings to avoid annoying messages when looking up nonexistent UDFs in SparkSQL with Hive support
log4j.logger.org.apache.hadoop.hive.metastore.RetryingHMSHandler=FATAL
log4j.logger.org.apache.hadoop.hive.ql.exec.FunctionRegistry=ERROR
word_count.txt文件
Give me the strength lightly to bear my joys and sorrows.
Give me the strength to make my love fruitful in service.
Give me the strength never to disown the poor or bend my knees before insolent might.
Give me the strength to raise my mind high above daily trifles.
And give me the strength to surrender my strength to thy will with love.
运行验证