def setUp(self):
self.temp_schema = TEMP_SCHEMA
self.rs = Redshift()
self.tbl = Table([['ID', 'Name'],
[1, 'Jim'],
[2, 'John'],
[3, 'Sarah']])
# Create a schema, create a table, create a view
setup_sql = f"""
drop schema if exists {self.temp_schema} cascade;
create schema {self.temp_schema};
"""
other_sql = f"""
create table {self.temp_schema}.test (id int,name varchar(5));
create view {self.temp_schema}.test_view as (
select * from {self.temp_schema}.test
);
"""
self.rs.query(setup_sql)
self.rs.query(other_sql)
self.s3 = S3()
self.temp_s3_bucket = os.environ['S3_TEMP_BUCKET']
self.temp_s3_prefix = 'test/'
def from_s3_csv(cls, bucket, key, aws_access_key_id=None, aws_secret_access_key=None,
**csvargs):
"""
Create a ``parsons table`` from a key in an S3 bucket.
`Args:`
bucket: str
The S3 bucket.
key: str
The S3 key
aws_access_key_id: str
Required if not included as environmental variable.
aws_secret_access_key: str
Required if not included as environmental variable.
\**csvargs: kwargs
``csv_reader`` optional arguments
`Returns:`
`parsons.Table` object
""" # noqa: W605
from parsons.aws import S3
s3 = S3(aws_access_key_id, aws_secret_access_key)
file_obj = s3.get_file(bucket, key)
if files.compression_type_for_path(key) == 'zip':
file_obj = files.zip_archive.unzip_archive(file_obj)
return cls(petl.fromcsv(file_obj, **csvargs))
def from_s3_csv(cls,
bucket,
key,
from_manifest=False,
aws_access_key_id=None,
aws_secret_access_key=None,
**csvargs):
"""
Create a ``parsons table`` from a key in an S3 bucket.
`Args:`
bucket: str
The S3 bucket.
key: str
The S3 key
from_manifest: bool
If True, treats `key` as a manifest file and loads all urls into a `parsons.Table`.
Defaults to False.
aws_access_key_id: str
Required if not included as environmental variable.
aws_secret_access_key: str
Required if not included as environmental variable.
\**csvargs: kwargs
``csv_reader`` optional arguments
`Returns:`
`parsons.Table` object
""" # noqa: W605
from parsons.aws import S3
s3 = S3(aws_access_key_id, aws_secret_access_key)
if from_manifest:
with open(s3.get_file(bucket, key)) as fd:
manifest = json.load(fd)
s3_keys = [x["url"] for x in manifest["entries"]]
else:
s3_keys = [f"s3://{bucket}/{key}"]
tbls = []
for key in s3_keys:
# TODO handle urls that end with '/', i.e. urls that point to "folders"
_, _, bucket_, key_ = key.split("/", 3)
file_ = s3.get_file(bucket_, key_)
if files.compression_type_for_path(key_) == 'zip':
file_ = files.zip_archive.unzip_archive(file_)
tbls.append(petl.fromcsv(file_, **csvargs))
return cls(petl.cat(*tbls))
def to_s3_csv(self,
bucket,
key,
aws_access_key_id=None,
aws_secret_access_key=None,
compression=None,
encoding=None,
errors='strict',
write_header=True,
acl='bucket-owner-full-control',
public_url=False,
public_url_expires=3600,
**csvargs):
"""
Writes the table to an s3 object as a CSV
`Args:`
bucket: str
The s3 bucket to upload to
key: str
The s3 key to name the file. If it ends in '.gz' or '.zip', the file will be
compressed.
aws_access_key_id: str
Required if not included as environmental variable
aws_secret_access_key: str
Required if not included as environmental variable
compression: str
The compression type for the s3 object. Currently "None", "zip" and "gzip" are
supported. If specified, will override the key suffix.
encoding: str
The CSV encoding type for `csv.writer()
<https://docs.python.org/2/library/csv.html#csv.writer/>`_
errors: str
Raise an Error if encountered
write_header: boolean
Include header in output
public_url: boolean
Create a public link to the file
public_url_expire: 3600
The time, in seconds, until the url expires if ``public_url`` set to ``True``.
acl: str
The S3 permissions on the file
\**csvargs: kwargs
``csv_writer`` optional arguments
`Returns:`
Public url if specified. If not ``None``.
""" # noqa: W605
compression = compression or files.compression_type_for_path(key)
csv_name = files.extract_file_name(key, include_suffix=False) + '.csv'
# Save the CSV as a temp file
local_path = self.to_csv(temp_file_compression=compression,
encoding=encoding,
errors=errors,
write_header=write_header,
csv_name=csv_name,
**csvargs)
# Put the file on S3
from parsons.aws import S3
self.s3 = S3(aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key)
self.s3.put_file(bucket, key, local_path, acl=acl)
if public_url:
return self.s3.get_url(bucket, key, expires_in=public_url_expires)
else:
return None