本番環境でAmazon Redshift Spectrum, Amazon Athena, およびAWS GlueをNode.jsで使用する

SELECT 
  user, 
  COUNT(*) 
FROM 
  events_table 
WHERE 
  ts BETWEEN ‘2017-08-01 14:00:00’ AND ‘2017-08-01 14:00:59’ 
GROUP BY 
  user;

create external TABLE spectrum.blog_clicks (
    user_id varchar(50),
    campaign_id varchar(50),
    os varchar(50),
    ua varchar(255),
    ts bigint,
    billing float
)
partitioned by (date date, hour smallint)  
stored as parquet
location 's3://nuviad-temp/blog/clicks/';

SELECT 
  * 
FROM 
  svv_external_columns 
WHERE 
  tablename = 'blog_clicks';

const rtb_request_schema = {
    "name": "clicks",
    "items": {
        "user_id": {
            "type": "string",
            "max_length": 100
        },
        "campaign_id": {
            "type": "string",
            "max_length": 50
        },
        "os": {
            "type": "string",
            "max_length": 50            
        },
        "ua": {
            "type": "string",
            "max_length": 255            
        },
        "ts": {
            "type": "integer",
            "min_value": 0,
            "max_value": 9999999999999
        },
        "billing": {
            "type": "float",
            "min_value": 0,
            "max_value": 9999999999999
        }
    }
};

Delivery stream name: events
Source: Direct PUT
S3 bucket: nuviad-events
S3 prefix: rtb/
IAM role: firehose_delivery_role_1
Data transformation: Disabled
Source record backup: Disabled
S3 buffer size (MB): 100
S3 buffer interval (sec): 60
S3 Compression: GZIP
S3 Encryption: No Encryption
Status: ACTIVE
Error logging: Enabled

if (validated) {
    let itemString = item.join('|')+'\n'; //Sending csv delimited by pipe and adding new line
    let params = {
        DeliveryStreamName: 'events',
        Record: {
            Data: itemString
        }
    };

    firehose.putRecord(params, function(err, data) {
        if (err) {
            console.error(err, err.stack);        
        }
        else {
            // Continue to your next step 
        }
    });
}

S3://your-bucket/your-prefix/2017/08/01/20/events-4-2017-08-01-20-06-06-536f5c40-6893-4ee4-907d-81e4d3b09455.gz

/*

	object key structure in the event object:

your-prefix/2017/08/01/20/event-4-2017-08-01-20-06-06-536f5c40-6893-4ee4-907d-81e4d3b09455.gz

	*/

let key_parts = event.Records[0].s3.object.key.split('/'); 

let event_type = key_parts[0];
let date = key_parts[1] + '-' + key_parts[2] + '-' + key_parts[3];
let hour = key_parts[4];
if (hour.indexOf('0') == 0) {
 		hour = parseInt(hour, 10) + '';
}

let parts1 = key_parts[5].split('-');
let minute = parts1[7];
if (minute.indexOf('0') == 0) {
        minute = parseInt(minute, 10) + '';
}

    copyObjectToHourlyFolder(event, date, hour, minute)
        .then(copyObjectToMinuteFolder.bind(null, event, date, hour, minute))
        .then(addPartitionToSpectrum.bind(null, event, date, hour, minute))
        .then(deleteOldMinuteObjects.bind(null, event))
        .then(deleteStreamObject.bind(null, event))        
        .then(result => {
            callback(null, { message: 'done' });            
        })
        .catch(err => {
            console.error(err);
            callback(null, { message: err });            
        }); 

ALTER TABLE 
  spectrum.events 
ADD partition
  (date='2017-08-01', hour=0) 
  LOCATION 's3://nuviad-temp/events/2017-08-01/0/';

import sys
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job
import boto3

## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME','day_partition_key', 'hour_partition_key', 'day_partition_value', 'hour_partition_value' ])

#day_partition_key = "partition_0"
#hour_partition_key = "partition_1"
#day_partition_value = "2017-08-01"
#hour_partition_value = "0"

day_partition_key = args['day_partition_key']
hour_partition_key = args['hour_partition_key']
day_partition_value = args['day_partition_value']
hour_partition_value = args['hour_partition_value']

print("Running for " + day_partition_value + "/" + hour_partition_value)

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)

df = spark.read.option("delimiter","|").csv("s3://nuviad-temp/events/"+day_partition_value+"/"+hour_partition_value)
df.registerTempTable("data")

df1 = spark.sql("select _c0 as user_id, _c1 as campaign_id, _c2 as os, _c3 as ua, cast(_c4 as bigint) as ts, cast(_c5 as double) as billing from data")

df1.repartition(1).write.mode("overwrite").parquet("s3://nuviad-temp/parquet/"+day_partition_value+"/hour="+hour_partition_value)

client = boto3.client('athena', region_name='us-east-1')

response = client.start_query_execution(
    QueryString='alter table parquet_events add if not exists partition(' + day_partition_key + '=\'' + day_partition_value + '\',' + hour_partition_key + '=' + hour_partition_value + ')  location \'s3://nuviad-temp/parquet/' + day_partition_value + '/hour=' + hour_partition_value + '\'' ,
    QueryExecutionContext={
        'Database': 'spectrumdb'
    },
    ResultConfiguration={
        'OutputLocation': 's3://nuviad-temp/convertresults'
    }
)

response = client.start_query_execution(
    QueryString='alter table parquet_events partition(' + day_partition_key + '=\'' + day_partition_value + '\',' + hour_partition_key + '=' + hour_partition_value + ') set location \'s3://nuviad-temp/parquet/' + day_partition_value + '/hour=' + hour_partition_value + '\'' ,
    QueryExecutionContext={
        'Database': 'spectrumdb'
    },
    ResultConfiguration={
        'OutputLocation': 's3://nuviad-temp/convertresults'
    }
)

job.commit()

import boto3
import json
from datetime import datetime, timedelta
 
client = boto3.client('glue')
 
def lambda_handler(event, context):
    last_hour_date_time = datetime.now() - timedelta(hours = 1)
    day_partition_value = last_hour_date_time.strftime("%Y-%m-%d") 
    hour_partition_value = last_hour_date_time.strftime("%-H") 
    response = client.start_job_run(
    JobName='convertEventsParquetHourly',
    Arguments={
         '--day_partition_key': 'date',
         '--hour_partition_key': 'hour',
         '--day_partition_value': day_partition_value,
         '--hour_partition_value': hour_partition_value
         }
    )