Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use botocore for s3 kwargs #832

Merged
merged 2 commits into from
Jul 29, 2021
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions awswrangler/mysql.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
_logger: logging.Logger = logging.getLogger(__name__)


def _validate_connection(con: pymysql.connections.Connection) -> None:
def _validate_connection(con: "pymysql.connections.Connection[Any]") -> None:
if not isinstance(con, pymysql.connections.Connection):
raise exceptions.InvalidConnection(
"Invalid 'conn' argument, please pass a "
Expand Down Expand Up @@ -77,7 +77,7 @@ def connect(
read_timeout: Optional[int] = None,
write_timeout: Optional[int] = None,
connect_timeout: int = 10,
) -> pymysql.connections.Connection:
) -> "pymysql.connections.Connection[Any]":
"""Return a pymysql connection from a Glue Catalog Connection or Secrets Manager.

https://pymysql.readthedocs.io
Expand Down Expand Up @@ -150,7 +150,7 @@ def connect(

def read_sql_query(
sql: str,
con: pymysql.connections.Connection,
con: "pymysql.connections.Connection[Any]",
index_col: Optional[Union[str, List[str]]] = None,
params: Optional[Union[List[Any], Tuple[Any, ...], Dict[Any, Any]]] = None,
chunksize: Optional[int] = None,
Expand Down Expand Up @@ -206,7 +206,7 @@ def read_sql_query(

def read_sql_table(
table: str,
con: pymysql.connections.Connection,
con: "pymysql.connections.Connection[Any]",
schema: Optional[str] = None,
index_col: Optional[Union[str, List[str]]] = None,
params: Optional[Union[List[Any], Tuple[Any, ...], Dict[Any, Any]]] = None,
Expand Down Expand Up @@ -268,7 +268,7 @@ def read_sql_table(
@apply_configs
def to_sql(
df: pd.DataFrame,
con: pymysql.connections.Connection,
con: "pymysql.connections.Connection[Any]",
table: str,
schema: str,
mode: str = "append",
Expand Down
88 changes: 13 additions & 75 deletions awswrangler/s3/_fs.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,12 @@
import socket
from contextlib import contextmanager
from errno import ESPIPE
from typing import Any, BinaryIO, Dict, Iterator, List, Optional, Set, Tuple, Union, cast
from typing import Any, BinaryIO, Dict, Iterator, List, Optional, Tuple, Union, cast

import boto3
from botocore.exceptions import ReadTimeoutError
from botocore.loaders import Loader
from botocore.model import ServiceModel

from awswrangler import _utils, exceptions
from awswrangler._config import apply_configs
Expand All @@ -24,84 +26,20 @@
_MIN_WRITE_BLOCK: int = 5_242_880 # 5 MB (5 * 2**20)
_MIN_PARALLEL_READ_BLOCK: int = 5_242_880 # 5 MB (5 * 2**20)

BOTOCORE_ACCEPTED_KWARGS: Dict[str, Set[str]] = {
"get_object": {
"SSECustomerAlgorithm",
"SSECustomerKey",
"RequestPayer",
"ExpectedBucketOwner",
"VersionId",
},
"copy_object": {
"ACL",
"Metadata",
"ServerSideEncryption",
"StorageClass",
"SSECustomerAlgorithm",
"SSECustomerKey",
"SSEKMSKeyId",
"SSEKMSEncryptionContext",
"Tagging",
"RequestPayer",
"ExpectedBucketOwner",
"CopySource",
},
"create_multipart_upload": {
"ACL",
"Metadata",
"ServerSideEncryption",
"StorageClass",
"SSECustomerAlgorithm",
"SSECustomerKey",
"SSEKMSKeyId",
"SSEKMSEncryptionContext",
"Tagging",
"RequestPayer",
"ExpectedBucketOwner",
},
"upload_part": {
"SSECustomerAlgorithm",
"SSECustomerKey",
"RequestPayer",
"ExpectedBucketOwner",
},
"complete_multipart_upload": {
"RequestPayer",
"ExpectedBucketOwner",
},
"put_object": {
"ACL",
"Metadata",
"ServerSideEncryption",
"StorageClass",
"SSECustomerAlgorithm",
"SSECustomerKey",
"SSEKMSKeyId",
"SSEKMSEncryptionContext",
"Tagging",
"RequestPayer",
"ExpectedBucketOwner",
},
"list_objects_v2": {
"RequestPayer",
"ExpectedBucketOwner",
},
"delete_objects": {
"RequestPayer",
"ExpectedBucketOwner",
"Objects",
},
"head_object": {
"RequestPayer",
"ExpectedBucketOwner",
"VersionId",
},
}
_BOTOCORE_LOADER = Loader()
_S3_JSON_MODEL = _BOTOCORE_LOADER.load_service_model(service_name="s3", type_name="service-2")
_S3_SERVICE_MODEL = ServiceModel(_S3_JSON_MODEL, service_name="s3")


def _snake_to_camel_case(s: str) -> str:
return "".join(c.title() for c in s.split("_"))


def get_botocore_valid_kwargs(function_name: str, s3_additional_kwargs: Dict[str, Any]) -> Dict[str, Any]:
"""Filter and keep only the valid botocore key arguments."""
return {k: v for k, v in s3_additional_kwargs.items() if k in BOTOCORE_ACCEPTED_KWARGS[function_name]}
s3_operation_model = _S3_SERVICE_MODEL.operation_model(_snake_to_camel_case(function_name))
allowed_kwargs = s3_operation_model.input_shape.members.keys() # pylint: disable=E1101
return {k: v for k, v in s3_additional_kwargs.items() if k in allowed_kwargs}


def _fetch_range(
Expand Down