執行範本範例

「WordCount 範本」是一個批次管道，可從 Cloud Storage 讀取文字，並將文字行代碼化為個別字詞，然後再計算每個字詞出現的頻率。如要進一步瞭解 WordCount，請參閱 WordCount 範例管道。

如果 Cloud Storage bucket 位於服務範圍外，請建立輸出規則，允許存取該 bucket。

範本參數

參數	說明
inputFile	Cloud Storage 輸入檔案的路徑。
outputFile	Cloud Storage 輸出檔案的路徑和前置字串。

執行 WordCount 範本

控制台

1. 前往 Dataflow 的「Create job from template」(透過範本建立工作) 頁面。
前往「依範本建立工作」
2. 在「Job name」(工作名稱) 欄位中，輸入不重複的工作名稱。
3. 選用：如要使用區域端點，請從下拉式選單中選取值。預設區域為 us-central1。

   如需可執行 Dataflow 工作的地區清單，請參閱「Dataflow 位置」。

4. 從「Dataflow template」(Dataflow 範本) 下拉式選單中，選取 the WordCount template。
5. 在提供的參數欄位中輸入參數值。
6. 按一下「Run Job」(執行工作)。

gcloud

注意：如要使用 Google Cloud CLI 執行範本，您必須具備 Google Cloud CLI 版本 138.0.0 或更新版本。 classic

在殼層或終端機中執行範本：

gcloud dataflow jobs run JOB_NAME \
    --gcs-location gs://dataflow-templates/latest/Word_Count \
    --region REGION_NAME \
    --parameters \
    inputFile=gs://dataflow-samples/shakespeare/kinglear.txt,output=gs://BUCKET_NAME/output/my_output

更改下列內容：

• JOB_NAME： 您選擇的不重複工作名稱

• REGION_NAME：您要部署 Dataflow 工作的區域，例如 us-central1

• BUCKET_NAME：Cloud Storage bucket 的名稱

API

如要使用 REST API 執行範本，請傳送 HTTP POST 要求。如要進一步瞭解 API 和授權範圍，請參閱 projects.templates.launch。

POST https://dataflow.googleapis.com/v1b3/projects/PROJECT_ID/locations/LOCATION/templates:launch?gcsPath=gs://dataflow-templates/latest/Word_Count
{
    "jobName": "JOB_NAME",
    "parameters": {
       "inputFile" : "gs://dataflow-samples/shakespeare/kinglear.txt",
       "output": "gs://BUCKET_NAME/output/my_output"
    },
    "environment": { "zone": "us-central1-f" }
}

更改下列內容：

• PROJECT_ID： 您要執行 Dataflow 工作的 Google Cloud 專案 ID

• JOB_NAME： 您選擇的不重複工作名稱

• LOCATION：您要部署 Dataflow 工作的區域，例如 us-central1

• BUCKET_NAME：Cloud Storage bucket 的名稱

範本原始碼

Java

/*
 * Copyright (C) 2016 Google LLC
 *
 * Licensed 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.
 */
package com.google.cloud.teleport.templates;

import com.google.cloud.teleport.metadata.Template;
import com.google.cloud.teleport.metadata.TemplateCategory;
import com.google.cloud.teleport.metadata.TemplateParameter;
import com.google.cloud.teleport.templates.WordCount.WordCountOptions;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.io.TextIO;
import org.apache.beam.sdk.metrics.Counter;
import org.apache.beam.sdk.metrics.Metrics;
import org.apache.beam.sdk.options.PipelineOptions;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.options.ValueProvider;
import org.apache.beam.sdk.transforms.Count;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.transforms.PTransform;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.beam.sdk.transforms.SimpleFunction;
import org.apache.beam.sdk.values.KV;
import org.apache.beam.sdk.values.PCollection;

/**
 * A template that counts words in text files.
 *
 * <p>Check out <a
 * href="https://github.com/GoogleCloudPlatform/DataflowTemplates/blob/main/v1/README_Word_Count.md">README</a>
 * for instructions on how to use or modify this template.
 */
@Template(
    name = "Word_Count",
    category = TemplateCategory.GET_STARTED,
    displayName = "Word Count",
    description =
        "Batch pipeline. Reads text from Cloud Storage, tokenizes text lines into individual words,"
            + " and performs frequency count on each of the words.",
    optionsClass = WordCountOptions.class,
    contactInformation = "https://cloud.google.com/support")
public class WordCount {

  static class ExtractWordsFn extends DoFn<String, String> {
    private final Counter emptyLines = Metrics.counter(ExtractWordsFn.class, "emptyLines");

    @ProcessElement
    public void processElement(ProcessContext c) {
      // Check if the line is empty.
      if (c.element().trim().isEmpty()) {
        emptyLines.inc();
        return;
      }

      // Split the line into words.
      String[] words = c.element().split("[^a-zA-Z']+");

      // Output each word encountered into the output PCollection.
      for (String word : words) {
        if (!word.isEmpty()) {
          c.output(word);
        }
      }
    }
  }

  /** A SimpleFunction that converts a Word and Count into a printable string. */
  public static class FormatAsTextFn extends SimpleFunction<KV<String, Long>, String> {
    @Override
    public String apply(KV<String, Long> input) {
      return input.getKey() + ": " + input.getValue();
    }
  }

  /**
   * A PTransform that converts a PCollection containing lines of text into a PCollection of
   * formatted word counts.
   */
  public static class CountWords
      extends PTransform<PCollection<String>, PCollection<KV<String, Long>>> {
    @Override
    public PCollection<KV<String, Long>> expand(PCollection<String> lines) {

      // Convert lines of text into individual words.
      PCollection<String> words = lines.apply(ParDo.of(new ExtractWordsFn()));

      // Count the number of times each word occurs.
      PCollection<KV<String, Long>> wordCounts = words.apply(Count.<String>perElement());

      return wordCounts;
    }
  }

  /**
   * Options supported by {@link com.google.cloud.teleport.templates.WordCount}.
   *
   * <p>Inherits standard configuration options.
   */
  public interface WordCountOptions extends PipelineOptions {

    @TemplateParameter.GcsReadFile(
        order = 1,
        description = "Input file(s) in Cloud Storage",
        helpText =
            "The input file pattern Dataflow reads from. Use the example file "
                + "(gs://dataflow-samples/shakespeare/kinglear.txt) or enter the path to your own "
                + "using the same format: gs://your-bucket/your-file.txt")
    ValueProvider<String> getInputFile();

    void setInputFile(ValueProvider<String> value);

    @TemplateParameter.GcsWriteFolder(
        order = 2,
        description = "Output Cloud Storage file prefix",
        helpText = "Path and filename prefix for writing output files. Ex: gs://your-bucket/counts")
    ValueProvider<String> getOutput();

    void setOutput(ValueProvider<String> value);
  }

  public static void main(String[] args) {
    WordCountOptions options =
        PipelineOptionsFactory.fromArgs(args).withValidation().as(WordCountOptions.class);
    Pipeline p = Pipeline.create(options);
    p.apply("ReadLines", TextIO.read().from(options.getInputFile()))
        .apply(new CountWords())
        .apply(MapElements.via(new FormatAsTextFn()))
        .apply("WriteCounts", TextIO.write().to(options.getOutput()));

    p.run();
  }
}