从 App Engine MapReduce 迁移到 Apache Beam 和 Dataflow

p.apply(TextIO.read().from("gs://apache-beam-samples/shakespeare/*"))

 // Apply a ParDo that returns a PCollection, where each element is an
 // individual word in Shakespeare's texts.
 .apply("ExtractWords", ParDo.of(new DoFn<String, String>() {
                   @ProcessElement
                   public void processElement(ProcessContext c) {
                     for (String word : c.element().split(ExampleUtils.TOKENIZER_PATTERN)) {
                       if (!word.isEmpty()) {
                         c.output(word);
                       }
                     }
                   }
                 }))

 // Apply the Count transform that returns a new PCollection of key/value pairs,
 // where each key represents a unique word in the text.
 .apply(Count.perElement())

 // Apply a MapElements transform that formats our PCollection of word counts
 // into a printable string, suitable for writing to an output file.
 .apply("FormatResults", MapElements.via(new SimpleFunction<KV<String, Long>, String>() {
                   @Override
                   public String apply(KV<String, Long> input) {
                     return input.getKey() + ": " + input.getValue();
                   }
                 }))

 // Apply a write transform that writes the contents of the PCollection to a
 // series of text files.
 .apply(TextIO.write().to("wordcounts"));

# Read the text file[pattern] into a PCollection.
lines = p | ReadFromText(known_args.input)

# Count the occurrences of each word.
counts = (
    lines
    | 'Split' >> (beam.FlatMap(lambda x: re.findall(r'[A-Za-z\']+', x))
                  .with_output_types(unicode))
    | 'PairWithOne' >> beam.Map(lambda x: (x, 1))
    | 'GroupAndSum' >> beam.CombinePerKey(sum))

# Format the counts into a PCollection of strings.
output = counts | 'Format' >> beam.Map(lambda (w, c): '%s: %s' % (w, c))

# Write the output using a "Write" transform that has side effects.
# pylint: disable=expression-not-assigned
output | WriteToText(known_args.output)

// beam.Init() is an initialization hook that must be called on startup.
beam.Init()

// Create the Pipeline object and root scope.
p := beam.NewPipeline()
s := p.Root()
lines := textio.Read(s, "gs://apache-beam-samples/shakespeare/kinglear.txt")

// Invoke a ParDo transform on our PCollection of text lines.
// This ParDo invokes a DoFn (defined in-line) on each element that
// tokenizes the text line into individual words. The ParDo returns a
// PCollection of type string, where each element is an individual word in
// Shakespeare's collected texts.
words := beam.ParDo(s, func(line string, emit func(string)) {
    for _, word := range wordRE.FindAllString(line, -1) {
        emit(word)
    }
}, lines)

// Invoke the stats.Count transform on our PCollection of
// individual words. The Count transform returns a new PCollection of
// key/value pairs, where each key represents a unique word in the text.
// The associated value is the occurrence count for that word.
counted := stats.Count(s, words)

// Use a ParDo to format our PCollection of word counts into a printable
// string, suitable for writing to an output file. When each element
// produces exactly one element, the DoFn can simply return it.
formatted := beam.ParDo(s, func(w string, c int) string {
    return fmt.Sprintf("%s: %v", w, c)
}, counted)

// Invoke textio.Write at the end of the pipeline to write
// the contents of a PCollection (in this case, our PCollection of
// formatted strings) to a text file.
textio.Write(s, "wordcounts.txt", formatted)