java框架中的大数据处理技术有哪些？

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount {

  public static class MyMapper extends Mapper<Object, Text, Text, IntWritable> {

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    @Override
    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
      String[] tokens = value.toString().split(" ");
      for (String token : tokens) {
        word.set(token);
        context.write(word, one);
      }
    }
  }

  public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable result = new IntWritable();

    @Override
    public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    job.waitForCompletion(true);
  }
}

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructType;

public class SparkWordCount {

  public static void main(String[] args) {
    SparkSession spark = SparkSession.builder().appName("word count").master("local").getOrCreate();
    JavaSparkContext jsc = new JavaSparkContext(spark.sparkContext());

    JavaRDD<String> lines = jsc.textFile(args[0]);
    JavaRDD<String> words = lines.flatMap(line -> Arrays.asList(line.split(" ")).iterator());
    JavaPairRDD<String, Integer> wordCounts = words.mapToPair(word -> new Tuple2<>(word, 1)).reduceByKey((a, b) -> a + b);

    StructType schema = DataTypes.createStructType(new StructField[] { DataTypes.createStructField("word", DataTypes.StringType, false), DataTypes.createStructField("count", DataTypes.IntegerType, false) });
    Dataset<Row> df = spark.createDataFrame(wordCounts.rdd(), schema);
    df.show();
  }
}

import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;

public class FlinkWordCount {

  public static void main(String[] args) throws Exception {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

    ParameterTool params = ParameterTool.fromArgs(args);
    String input = params.has("input") ? params.get("input") : "data.txt";

    DataStream<String> text = env.readTextFile(input);
    DataStream<Tuple2<String, Integer>> counts = text
      .flatMap(line -> Arrays.asList(line.split(" ")).iterator())
      .map(word -> Tuple2.of(word, 1))
      .keyBy(0)
      .timeWindow(Time.seconds(1))
      .sum(1);

    counts.print().setParallelism(1);
    env.execute();
  }
}