def _copy_single_object(
self,
gcs_hook: GCSHook,
sftp_hook: SFTPHook,
source_path: str,
destination_object: str,
) -> None:
"""
Helper function to copy single object.
"""
self.log.info(
"Executing copy of %s to gs://%s/%s",
source_path,
self.destination_bucket,
destination_object,
)
with NamedTemporaryFile("w") as tmp:
sftp_hook.retrieve_file(source_path, tmp.name)
gcs_hook.upload(
bucket_name=self.destination_bucket,
object_name=destination_object,
filename=tmp.name,
mime_type=self.mime_type,
)
if self.move_object:
self.log.info("Executing delete of %s", source_path)
sftp_hook.delete_file(source_path)
def _upload_to_gcs(self, files_to_upload: Dict[str, Any]):
hook = GCSHook(google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
for obj, tmp_file_handle in files_to_upload.items():
hook.upload(bucket_name=self.bucket,
object_name=obj,
filename=tmp_file_handle.name,
mime_type='application/json',
gzip=self.gzip)
def _upload_to_gcs(self, files_to_upload):
"""
Upload all of the file splits (and optionally the schema .json file) to
Google Cloud Storage.
"""
hook = GCSHook(
google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
for tmp_file in files_to_upload:
hook.upload(self.bucket, tmp_file.get('file_name'),
tmp_file.get('file_handle').name,
mime_type=tmp_file.get('file_mime_type'),
gzip=self.gzip if tmp_file.get('file_name') == self.schema_filename else False)
def execute(self, context):
"""
Uploads the file to Google Cloud Storage
"""
hook = GCSHook(google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
hook.upload(
bucket_name=self.bucket,
object_name=self.dst,
mime_type=self.mime_type,
filename=self.src,
gzip=self.gzip,
)
def execute(self, context):
hook = CloudTextToSpeechHook(gcp_conn_id=self.gcp_conn_id)
result = hook.synthesize_speech(
input_data=self.input_data,
voice=self.voice,
audio_config=self.audio_config,
retry=self.retry,
timeout=self.timeout,
)
with NamedTemporaryFile() as temp_file:
temp_file.write(result.audio_content)
cloud_storage_hook = GCSHook(
google_cloud_storage_conn_id=self.gcp_conn_id)
cloud_storage_hook.upload(bucket_name=self.target_bucket_name,
object_name=self.target_filename,
filename=temp_file.name)
def execute(self, context: Dict):
hook = GoogleDisplayVideo360Hook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
api_version=self.api_version,
)
gcs_hook = GCSHook(
google_cloud_storage_conn_id=self.gcp_conn_id, delegate_to=self.delegate_to
)
resource = hook.get_query(query_id=self.report_id)
# Check if report is ready
if resource["metadata"]["running"]:
raise AirflowException('Report {} is still running'.format(self.report_id))
# If no custom report_name provided, use DV360 name
file_url = resource["metadata"]["googleCloudStoragePathForLatestReport"]
report_name = self.report_name or urlparse(file_url).path.split('/')[2]
report_name = self._resolve_file_name(report_name)
# Download the report
self.log.info("Starting downloading report %s", self.report_id)
with tempfile.NamedTemporaryFile(delete=False) as temp_file:
with urllib.request.urlopen(file_url) as response:
shutil.copyfileobj(response, temp_file, length=self.chunk_size)
temp_file.flush()
# Upload the local file to bucket
gcs_hook.upload(
bucket_name=self.bucket_name,
object_name=report_name,
gzip=self.gzip,
filename=temp_file.name,
mime_type="text/csv",
)
self.log.info(
"Report %s was saved in bucket %s as %s.",
self.report_id,
self.bucket_name,
report_name,
)
self.xcom_push(context, key='report_name', value=report_name)
def execute(self, context: Dict):
hook = GoogleSearchAdsHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
api_version=self.api_version,
)
gcs_hook = GCSHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
# Resolve file name of the report
report_name = self.report_name or self.report_id
report_name = self._resolve_file_name(report_name)
response = hook.get(report_id=self.report_id)
if not response['isReportReady']:
raise AirflowException('Report {} is not ready yet'.format(
self.report_id))
# Resolve report fragments
fragments_count = len(response["files"])
# Download chunks of report's data
self.log.info("Downloading Search Ads report %s", self.report_id)
with NamedTemporaryFile() as temp_file:
for i in range(fragments_count):
byte_content = hook.get_file(report_fragment=i,
report_id=self.report_id)
fragment = (byte_content if i == 0 else
self._handle_report_fragment(byte_content))
temp_file.write(fragment)
temp_file.flush()
gcs_hook.upload(
bucket_name=self.bucket_name,
object_name=report_name,
gzip=self.gzip,
filename=temp_file.name,
)
self.xcom_push(context, key="file_name", value=report_name)
def execute(self, context):
# use the super to list all files in an Azure Data Lake path
files = super().execute(context)
g_hook = GCSHook(
google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
if not self.replace:
# if we are not replacing -> list all files in the ADLS path
# and only keep those files which are present in
# ADLS and not in Google Cloud Storage
bucket_name, prefix = _parse_gcs_url(self.dest_gcs)
existing_files = g_hook.list(bucket_name=bucket_name, prefix=prefix)
files = set(files) - set(existing_files)
if files:
hook = AzureDataLakeHook(
azure_data_lake_conn_id=self.azure_data_lake_conn_id
)
for obj in files:
with NamedTemporaryFile(mode='wb', delete=True) as f:
hook.download_file(local_path=f.name, remote_path=obj)
f.flush()
dest_gcs_bucket, dest_gcs_prefix = _parse_gcs_url(self.dest_gcs)
dest_path = os.path.join(dest_gcs_prefix, obj)
self.log.info("Saving file to %s", dest_path)
g_hook.upload(
bucket_name=dest_gcs_bucket,
object_name=dest_path,
filename=f.name,
gzip=self.gzip
)
self.log.info("All done, uploaded %d files to GCS", len(files))
else:
self.log.info("In sync, no files needed to be uploaded to GCS")
return files
def execute(self, context: Dict):
hook = GoogleCampaignManagerHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
api_version=self.api_version,
)
gcs_hook = GCSHook(google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
# Get name of the report
report = hook.get_report(file_id=self.file_id,
profile_id=self.profile_id,
report_id=self.report_id)
report_name = self.report_name or report.get("fileName",
str(uuid.uuid4()))
report_name = self._resolve_file_name(report_name)
# Download the report
self.log.info("Starting downloading report %s", self.report_id)
request = hook.get_report_file(profile_id=self.profile_id,
report_id=self.report_id,
file_id=self.file_id)
with tempfile.NamedTemporaryFile() as temp_file:
downloader = http.MediaIoBaseDownload(fd=temp_file,
request=request,
chunksize=self.chunk_size)
download_finished = False
while not download_finished:
_, download_finished = downloader.next_chunk()
temp_file.flush()
# Upload the local file to bucket
gcs_hook.upload(
bucket_name=self.bucket_name,
object_name=report_name,
gzip=self.gzip,
filename=temp_file.name,
mime_type="text/csv",
)
self.xcom_push(context, key="report_name", value=report_name)
def execute(self, context: Dict):
hook = GCSHook(gcp_conn_id=self.gcp_conn_id)
with NamedTemporaryFile() as source_file, NamedTemporaryFile(
) as destination_file:
self.log.info("Downloading file from %s", self.source_bucket)
hook.download(bucket_name=self.source_bucket,
object_name=self.source_object,
filename=source_file.name)
self.log.info("Starting the transformation")
cmd = [self.transform_script] if isinstance(
self.transform_script, str) else self.transform_script
cmd += [source_file.name, destination_file.name]
process = subprocess.Popen(args=cmd,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
close_fds=True)
self.log.info("Process output:")
for line in iter(process.stdout.readline, b''):
self.log.info(line.decode(self.output_encoding).rstrip())
process.wait()
if process.returncode > 0:
raise AirflowException("Transform script failed: {0}".format(
process.returncode))
self.log.info(
"Transformation succeeded. Output temporarily located at %s",
destination_file.name)
self.log.info("Uploading file to %s as %s",
self.destination_bucket, self.destination_object)
hook.upload(bucket_name=self.destination_bucket,
object_name=self.destination_object,
filename=destination_file.name)
def execute(self, context):
# use the super method to list all the files in an S3 bucket/key
files = super().execute(context)
gcs_hook = GCSHook(google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
if not self.replace:
# if we are not replacing -> list all files in the GCS bucket
# and only keep those files which are present in
# S3 and not in Google Cloud Storage
bucket_name, object_prefix = _parse_gcs_url(self.dest_gcs)
existing_files_prefixed = gcs_hook.list(bucket_name,
prefix=object_prefix)
existing_files = []
if existing_files_prefixed:
# Remove the object prefix itself, an empty directory was found
if object_prefix in existing_files_prefixed:
existing_files_prefixed.remove(object_prefix)
# Remove the object prefix from all object string paths
for f in existing_files_prefixed:
if f.startswith(object_prefix):
existing_files.append(f[len(object_prefix):])
else:
existing_files.append(f)
files = list(set(files) - set(existing_files))
if len(files) > 0:
self.log.info('%s files are going to be synced: %s.',
len(files), files)
else:
self.log.info(
'There are no new files to sync. Have a nice day!')
if files:
hook = S3Hook(aws_conn_id=self.aws_conn_id, verify=self.verify)
for file in files:
# GCS hook builds its own in-memory file so we have to create
# and pass the path
file_object = hook.get_key(file, self.bucket)
with NamedTemporaryFile(mode='wb', delete=True) as f:
file_object.download_fileobj(f)
f.flush()
dest_gcs_bucket, dest_gcs_object_prefix = _parse_gcs_url(
self.dest_gcs)
# There will always be a '/' before file because it is
# enforced at instantiation time
dest_gcs_object = dest_gcs_object_prefix + file
# Sync is sequential and the hook already logs too much
# so skip this for now
# self.log.info(
# 'Saving file {0} from S3 bucket {1} in GCS bucket {2}'
# ' as object {3}'.format(file, self.bucket,
# dest_gcs_bucket,
# dest_gcs_object))
gcs_hook.upload(dest_gcs_bucket,
dest_gcs_object,
f.name,
gzip=self.gzip)
self.log.info(
"All done, uploaded %d files to Google Cloud Storage",
len(files))
else:
self.log.info(
'In sync, no files needed to be uploaded to Google Cloud'
'Storage')
return files
