public class WordCountExample {
    public static void main(String[] args) throws Exception {
        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSet<String> text = env.fromElements(
            "Who's there?",
            "I think I hear them. Stand, ho! Who's there?");
        DataSet<Tuple2<String, Integer>> wordCounts = text
            .flatMap(new LineSplitter())
            .groupBy(0)
            .sum(1);
        wordCounts.print();
    }
    public static class LineSplitter implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String line, Collector<Tuple2<String, Integer>> out) {
            for (String word : line.split(" ")) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }
}

import org.apache.flink.api.scala._
object WordCount {
  def main(args: Array[String]) {
    val env = ExecutionEnvironment.getExecutionEnvironment
    val text = env.fromElements(
      "Who's there?",
      "I think I hear them. Stand, ho! Who's there?")
    val counts = text.flatMap { _.toLowerCase.split("\\W+") filter { _.nonEmpty } }
      .map { (_, 1) }
      .groupBy(0)
      .sum(1)
    counts.print()
  }
}

ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
// read text file from local files system
DataSet<String> localLines = env.readTextFile("file:///path/to/my/textfile");
// read text file from a HDFS running at nnHost:nnPort
DataSet<String> hdfsLines = env.readTextFile("hdfs://nnHost:nnPort/path/to/my/textfile");
// read a CSV file with three fields
DataSet<Tuple3<Integer, String, Double>> csvInput = env.readCsvFile("hdfs:///the/CSV/file")
                           .types(Integer.class, String.class, Double.class);
// read a CSV file with five fields, taking only two of them
DataSet<Tuple2<String, Double>> csvInput = env.readCsvFile("hdfs:///the/CSV/file")
                               .includeFields("10010")  // take the first and the fourth field
                           .types(String.class, Double.class);
// read a CSV file with three fields into a POJO (Person.class) with corresponding fields
DataSet<Person>> csvInput = env.readCsvFile("hdfs:///the/CSV/file")
                         .pojoType(Person.class, "name", "age", "zipcode");
// read a file from the specified path of type SequenceFileInputFormat
DataSet<Tuple2<IntWritable, Text>> tuples =
 env.readSequenceFile(IntWritable.class, Text.class, "hdfs://nnHost:nnPort/path/to/file");
// creates a set from some given elements
DataSet<String> value = env.fromElements("Foo", "bar", "foobar", "fubar");
// generate a number sequence
DataSet<Long> numbers = env.generateSequence(1, 10000000);
// Read data from a relational database using the JDBC input format
DataSet<Tuple2<String, Integer> dbData =
    env.createInput(
      JDBCInputFormat.buildJDBCInputFormat()
                     .setDrivername("org.apache.derby.jdbc.EmbeddedDriver")
                     .setDBUrl("jdbc:derby:memory:persons")
                     .setQuery("select name, age from persons")
                     .setRowTypeInfo(new RowTypeInfo(BasicTypeInfo.STRING_TYPE_INFO, BasicTypeInfo.INT_TYPE_INFO))
                     .finish()
    );
// Note: Flink's program compiler needs to infer the data types of the data items which are returned
// by an InputFormat. If this information cannot be automatically inferred, it is necessary to
// manually provide the type information as shown in the examples above.

final ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
// Create a DataSet from a list of elements
DataSet<Integer> myInts = env.fromElements(1, 2, 3, 4, 5);
// Create a DataSet from any Java collection
List<Tuple2<String, Integer>> data = ...
DataSet<Tuple2<String, Integer>> myTuples = env.fromCollection(data);
// Create a DataSet from an Iterator
Iterator<Long> longIt = ...
DataSet<Long> myLongs = env.fromCollection(longIt, Long.class);

// 1. The DataSet to be broadcast
DataSet<Integer> toBroadcast = env.fromElements(1, 2, 3);
DataSet<String> data = env.fromElements("a", "b");
data.map(new RichMapFunction<String, String>() {
    @Override
    public void open(Configuration parameters) throws Exception {
      // 3. Access the broadcast DataSet as a Collection
      Collection<Integer> broadcastSet = getRuntimeContext().getBroadcastVariable("broadcastSetName");
    }
    @Override
    public String map(String value) throws Exception {
        ...
    }
}).withBroadcastSet(toBroadcast, "broadcastSetName"); // 2. Broadcast the DataSet

ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
// register a file from HDFS
env.registerCachedFile("hdfs:///path/to/your/file", "hdfsFile")
// register a local executable file (script, executable, ...)
env.registerCachedFile("file:///path/to/exec/file", "localExecFile", true)
// define your program and execute
...
DataSet<String> input = ...
DataSet<Integer> result = input.map(new MyMapper());
...
env.execute();