github.com/apache/beam/sdks/v2@v2.48.2/go/examples/readavro/readavro.go (about)

     1  // Licensed to the Apache Software Foundation (ASF) under one or more
     2  // contributor license agreements.  See the NOTICE file distributed with
     3  // this work for additional information regarding copyright ownership.
     4  // The ASF licenses this file to You under the Apache License, Version 2.0
     5  // (the "License"); you may not use this file except in compliance with
     6  // the License.  You may obtain a copy of the License at
     7  //
     8  //    http://www.apache.org/licenses/LICENSE-2.0
     9  //
    10  // Unless required by applicable law or agreed to in writing, software
    11  // distributed under the License is distributed on an "AS IS" BASIS,
    12  // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    13  // See the License for the specific language governing permissions and
    14  // limitations under the License.
    15  
    16  // readavro is a simple Avro read/write Example
    17  // This example uses a 500 Byte sample avro file [twitter.avro]
    18  // download here: https://s3-eu-west-1.amazonaws.com/daidokoro-dev/apache/twitter.avro
    19  package main
    20  
    21  import (
    22  	"context"
    23  	"encoding/json"
    24  	"flag"
    25  	"log"
    26  	"reflect"
    27  
    28  	"github.com/apache/beam/sdks/v2/go/pkg/beam"
    29  	"github.com/apache/beam/sdks/v2/go/pkg/beam/io/avroio"
    30  	"github.com/apache/beam/sdks/v2/go/pkg/beam/x/beamx"
    31  	"github.com/apache/beam/sdks/v2/go/pkg/beam/x/debug"
    32  )
    33  
    34  var (
    35  	input  = flag.String("input", "./twitter.avro", "input avro file")
    36  	output = flag.String("output", "./output.avro", "output avro file")
    37  )
    38  
    39  // Doc type used to unmarshal avro json data
    40  type Doc struct {
    41  	Stamp int64  `json:"timestamp"`
    42  	Tweet string `json:"tweet"`
    43  	User  string `json:"username"`
    44  }
    45  
    46  // Note that the schema is only required for Writing avro.
    47  // not Reading.
    48  const schema = `{
    49  	"type": "record",
    50  	"name": "tweet",
    51  	"namespace": "twitter",
    52  	"fields": [
    53  		{ "name": "timestamp", "type": "double" },
    54  		{ "name": "tweet", "type": "string" },
    55  		{ "name": "username", "type": "string" }
    56  	]
    57  }`
    58  
    59  func main() {
    60  	flag.Parse()
    61  	beam.Init()
    62  
    63  	p := beam.NewPipeline()
    64  	s := p.Root()
    65  
    66  	// read rows and return JSON string PCollection - PCollection<string>
    67  	rows := avroio.Read(s, *input, reflect.TypeOf(""))
    68  	debug.Print(s, rows)
    69  
    70  	// read rows and return Doc Type PCollection - PCollection<Doc>
    71  	docs := avroio.Read(s, *input, reflect.TypeOf(Doc{}))
    72  	debug.Print(s, docs)
    73  
    74  	// update all values with a single user and tweet.
    75  	format := beam.ParDo(s, func(d Doc, emit func(string)) {
    76  		d.User = "daidokoro"
    77  		d.Tweet = "I was here......"
    78  
    79  		b, _ := json.Marshal(d)
    80  		emit(string(b))
    81  	}, docs)
    82  
    83  	debug.Print(s, format)
    84  
    85  	// write output
    86  	avroio.Write(s, *output, schema, format)
    87  
    88  	if err := beamx.Run(context.Background(), p); err != nil {
    89  		log.Fatalf("Failed to execute job: %v", err)
    90  	}
    91  }