- Recipes
- Dremio to Google Storage CSV file
Connect Dremio and Google Storage CSV file in our serverless environment
Use this template to Read data from Dremio using them to create CSV file entries in Google Storage Bucket.
Share
Read data from Dremio
Used integrations:
JavaScript
Python
class HttpSourceDremioSelect {
async init() {
// TODO: Create your http credential with dremio information:
// More info at https://yepcode.io/docs/integrations/http/#credential-configuration
// Official docs: https://docs.dremio.com/cloud/reference/api/
this.dremio = await yepcode.integration.http(
"your-dremio-credential-name"
);
}
async fetch(publish, done) {
// TODO: Customize your select query
// Double-quotation marks within a SQL statement need to be escaped
const query = 'SELECT * FROM path_to_your_dataset."your_dataset_name"';
// Use the SQL API to submit queries. The response contains the ID for the job associated with the SQL query
// Official docs: https://docs.dremio.com/cloud/reference/api/sql
const projectId = "<your-dremio-project-id>";
const {
data: job
} = this.dremio.post(`${projectId}/sql`, {
sql: query,
});
// Use the Job API to check the job status. Jobs final status are COMPLETED, FAILED and CANCELED
// Official docs: https://docs.dremio.com/cloud/reference/api/job/
const finalJobStates = ["COMPLETED", "FAILED", "CANCELED"];
let jobInfoResponse = null;
do {
jobInfoResponse = await this.dremio.get(
`${this.projectId}/job/${job.id}`
);
} while (!finalJobStates.includes(jobInfoResponse.data.jobState));
const {
data: jobInfo
} = jobInfoResponse;
// When the job is finished, if it's been completed, get the result from Job Results endpoint
// Official docs: https://docs.dremio.com/cloud/reference/api/job/job-results/
// Otherwise, show the job status
if (jobInfo.jobState === "COMPLETED") {
const {
data: result
} = await this.dremio.get(
`${this.projectId}/job/${job.id}/results`
);
publish(result.rows);
} else if (jobInfo.jobState === "FAILED") {
publish(`Uups! Something was wrong: ${jobInfo.errorMessage}`);
} else {
publish(`The job's been cancelled: ${jobInfo.cancellationReason}`);
}
done();
}
async close() {}
}
class HttpSourceDremioSelect:
def setup(self):
## TODO: Create your http credential with dremio information
## More info at https://yepcode.io/docs/integrations/http/#credential-configuration
## Official docs: https://docs.dremio.com/cloud/reference/api/
self.dremio = yepcode.integration.http(
"your-dremio-credential-name"
)
def generator(self):
## TODO: Customize your select query
## Double-quotation marks withing a SQL statement need to be escaped
query = 'SELECT * FROM path_to_your_dataset."your_dataset_name"'
## Use the SQL API to submit queries. The response contains the ID for the job ssociated with the SQL query
## Official docs: https://docs.dremio.com/cloud/reference/api/sql
project_id = "<your-dremio-project-id>"
query_response = self.dremio.post(
f"{project_id}/sql",
json={"sql" : query}
)
job_id = query_response.json()['id']
## Use the Job API to check the job status. Jobs final status are COMPLETED, FAILED and CANCELED
## Official docs: https://docs.dremio.com/cloud/reference/api/job/
job_state = 'INIT'
job_info_response = None
FINAL_JOB_STATES = ['COMPLETED', 'FAILED', 'CANCELED']
while job_state not in FINAL_JOB_STATES:
job_info_response = self.dremio.get(f"{project_id}/job/{job_id}")
job_state = job_info_response.json()['jobState']
## When the job is finished, if it's been completed, get the result from Job Results endpoint
## Official docs: https://docs.dremio.com/cloud/reference/api/job/job-results/
## Otherwise, show the job status
if job_state == 'COMPLETED':
job_result_response = self.dremio.get(f"{project_id}/job/{job_id}/results")
rows = job_result_response.json()['rows']
for row in rows:
yield row
elif job_state == 'FAILED':
yield f"Uups! Something was wrong: {job_info_response.json()['errorMessage']}"
else:
yield f"The job's been cancelled: {job_info_response.json()['cancellationReason']}"
def close(self):
pass
Do you need help solving this integration with YepCode?
Let's talkCreate CSV file entries in Google Storage Bucket
Used integrations:
- JavaScript
- Python
class GoogleStorageTargetUploadCsv {
async init() {
// TODO: Create your google-storage credential
// More info at https://yepcode.io/docs/integrations/google-storage/#credential-configuration
const googleStorage = yepcode.integration.googleStorage(
"your-google-storage-credential-name"
);
// TODO: Customize your bucket name
const bucket = googleStorage.bucket("your-bucket-name");
// TODO: choose a destination file
const blob = bucket.file(`one-folder/my-filename-${Date.now()}.csv`);
this.ws = blob.createWriteStream({
metadata: {
contentType: "text/csv",
},
});
// Transform the items into a csv format
this.stringifier = csv.stringify({
delimiter: ",",
});
this.stringifier.pipe(this.ws);
}
async consume(item) {
// TODO: Customize csv row content with your item content
const csvRow = [item.id, item.name];
this.stringifier.write(csvRow);
}
async close() {
this.stringifier.end();
}
}
import csv
import io
class AccumulatingStream:
def __init__(self):
self.data = io.BytesIO()
def write(self, item):
self.data.write(item.encode("utf-8"))
def get_stream(self):
self.data.seek(0)
return self.data
class GoogleStorageTargetUploadCsv:
def setup(self):
# TODO: Create your Google Storage credential:
# More info at https://yepcode.io/docs/integrations/google-storage/#credential-configuration
self.storage_client = yepcode.integration.googleStorage("your-storage-credential-name")
self.acc_stream = AccumulatingStream()
self.stringifier = csv.writer(self.acc_stream, delimiter=",")
def consume(self, generator, done):
for item in generator:
# TODO: customize the csv row to create from your item content
csv_row = [item["value"], item["text"]]
self.stringifier.writerow(csv_row)
done()
def close(self):
# TODO: customize the bucket name and object key
try:
bucket = self.storage_client.get_bucket("bucket_name")
blob = bucket.blob("object_key")
# Upload from a stream
blob.upload_from_file(self.acc_stream.get_stream())
except Exception as error:
print(f"Error uploading object: {error}")
CSVFAQs
YepCode is a SaaS platform that allows to create, execute and monitor integrations and automations using source code in a serverless environment.
We like to call it the Zapier for developers, since we bring all the agility and benefits of NoCode tools (avoid server provisioning, environment configuration, deployments,...), but with all the power of being able to use a programming language like JavaScript or Python.
These recipes are a good starting point for you to build your own YepCode processes and solve your integration and automation problems.
You only have to fill the sign up form and your account will be created with our FREE plan (no credit card required).
YepCode has been created with a clear enterprise approach (multi-tenant environment, team management, high security and auditing standards, IdP integrations, on-premise options,...) so we can be the Swiss army knife of any team of engineering, especially those that need to extract or send information to external systems, and where a certain dynamism or adaptation to change is necessary in that process.
Sure! You just need to do some configuration to allow YepCode servers to connect to that service. Check our docs page to get more information.