def storage_copy_table(ctx, dataset_id, table_id, source_bucket_name,
dst_bucket_name, mode):
Storage(dataset_id, table_id, **ctx.obj).copy_table(
source_bucket_name=source_bucket_name,
destination_bucket_name=dst_bucket_name,
mode=mode,
)
def append(self,
filepath,
partitions=None,
if_exists="replace",
**upload_args):
"""Appends new data to existing BigQuery table.
As long as the data has the same schema. It appends the data in the
filepath to the existing table.
Args:
filepath (str or pathlib.PosixPath): Where to find the file that you want to upload to create a table with
partitions (str, pathlib.PosixPath, dict): Optional.
Hive structured partition as a string or dict
* str : `<key>=<value>/<key2>=<value2>`
* dict: `dict(key=value, key2=value2)`
if_exists (str): 0ptional.
What to do if data with same name exists in storage
* 'raise' : Raises Conflict exception
* 'replace' : Replace table
* 'pass' : Do nothing
"""
if not self.table_exists("staging"):
raise BaseDosDadosException(
"You cannot append to a table that does not exist")
else:
Storage(self.dataset_id, self.table_id, **self.main_vars).upload(
filepath,
mode="staging",
partitions=partitions,
if_exists=if_exists,
**upload_args,
)
def storage_delete_table(ctx, dataset_id, table_id, mode, not_found_ok,
bucket_name):
Storage(dataset_id, table_id,
**ctx.obj).delete_table(mode=mode,
not_found_ok=not_found_ok,
bucket_name=bucket_name)
click.echo(
click.style(
f"Data was deleted from bucket `{bucket_name}`",
fg="green",
))
def download_storage(ctx, dataset_id, table_id, filename, savepath, partitions,
mode, if_not_exists):
Storage(dataset_id, table_id,
**ctx.obj).download(filename, savepath, partitions, mode,
if_not_exists)
click.echo(
click.style(
f"Data was downloaded to `{savepath}`",
fg="green",
))
def init_storage(ctx, bucket_name, replace, very_sure):
# TODO: Create config file to store bucket_name, etc...
ctx.obj.pop("bucket_name")
Storage(bucket_name=bucket_name, **ctx.obj).init(replace=replace,
very_sure=very_sure)
click.echo(click.style(
f"Bucket `{bucket_name}` was created",
fg="green",
))
def upload_storage(ctx, dataset_id, table_id, filepath, mode, partitions,
if_exists):
ctx.obj.pop("bucket_name")
blob_name = Storage(dataset_id, table_id,
**ctx.obj).upload(filepath=filepath,
mode=mode,
partitions=partitions,
if_exists=if_exists)
click.echo(click.style(
f"Data was added to `{blob_name}`",
fg="green",
))
def create(
self,
path=None,
job_config_params=None,
force_dataset=True,
if_table_exists="raise",
if_storage_data_exists="raise",
if_table_config_exists="raise",
source_format="csv",
columns_config_url=None,
):
"""Creates BigQuery table at staging dataset.
If you add a path, it automatically saves the data in the storage,
creates a datasets folder and BigQuery location, besides creating the
table and its configuration files.
The new table should be located at `<dataset_id>_staging.<table_id>` in BigQuery.
It looks for data saved in Storage at `<bucket_name>/staging/<dataset_id>/<table_id>/*`
and builds the table.
It currently supports the types:
- Comma Delimited CSV
Data can also be partitioned following the hive partitioning scheme
`<key1>=<value1>/<key2>=<value2>` - for instance,
`year=2012/country=BR`. The partition is automatcally detected
by searching for `partitions` on the `table_config.yaml`.
Args:
path (str or pathlib.PosixPath): Where to find the file that you want to upload to create a table with
job_config_params (dict): Optional.
Job configuration params from bigquery
if_table_exists (str): Optional
What to do if table exists
* 'raise' : Raises Conflict exception
* 'replace' : Replace table
* 'pass' : Do nothing
force_dataset (bool): Creates `<dataset_id>` folder and BigQuery Dataset if it doesn't exists.
if_table_config_exists (str): Optional.
What to do if config files already exist
* 'raise': Raises FileExistError
* 'replace': Replace with blank template
* 'pass'; Do nothing
if_storage_data_exists (str): Optional.
What to do if data already exists on your bucket:
* 'raise' : Raises Conflict exception
* 'replace' : Replace table
* 'pass' : Do nothing
source_format (str): Optional
Data source format. Only 'csv' is supported. Defaults to 'csv'.
columns_config_url (str): google sheets URL.
The URL must be in the format https://docs.google.com/spreadsheets/d/<table_key>/edit#gid=<table_gid>.
The sheet must contain the column name: "coluna" and column description: "descricao"
"""
if path is None:
# Look if table data already exists at Storage
data = self.client["storage_staging"].list_blobs(
self.bucket_name,
prefix=f"staging/{self.dataset_id}/{self.table_id}")
# Raise: Cannot create table without external data
if not data:
raise BaseDosDadosException(
"You must provide a path for uploading data")
# Add data to storage
if isinstance(
path,
(
str,
Path,
),
):
Storage(self.dataset_id, self.table_id,
**self.main_vars).upload(path,
mode="staging",
if_exists=if_storage_data_exists)
# Create Dataset if it doesn't exist
if force_dataset:
dataset_obj = Dataset(self.dataset_id, **self.main_vars)
try:
dataset_obj.init()
except FileExistsError:
pass
dataset_obj.create(if_exists="pass")
self.init(
data_sample_path=path,
if_folder_exists="replace",
if_table_config_exists=if_table_config_exists,
columns_config_url=columns_config_url,
)
table = bigquery.Table(self.table_full_name["staging"])
table.external_data_configuration = Datatype(
self, source_format, "staging",
partitioned=self._is_partitioned()).external_config
# Lookup if table alreay exists
table_ref = None
try:
table_ref = self.client["bigquery_staging"].get_table(
self.table_full_name["staging"])
except google.api_core.exceptions.NotFound:
pass
if isinstance(table_ref, google.cloud.bigquery.table.Table):
if if_table_exists == "pass":
return None
elif if_table_exists == "raise":
raise FileExistsError(
"Table already exists, choose replace if you want to overwrite it"
)
if if_table_exists == "replace":
self.delete(mode="staging")
self.client["bigquery_staging"].create_table(table)
