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

IO: Remove deprecations #1519

Merged
merged 1 commit into from
Jan 15, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
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
9 changes: 0 additions & 9 deletions pyiceberg/io/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -48,14 +48,6 @@

logger = logging.getLogger(__name__)

ADLFS_CONNECTION_STRING = "adlfs.connection-string"
ADLFS_ACCOUNT_NAME = "adlfs.account-name"
ADLFS_ACCOUNT_KEY = "adlfs.account-key"
ADLFS_SAS_TOKEN = "adlfs.sas-token"
ADLFS_TENANT_ID = "adlfs.tenant-id"
ADLFS_CLIENT_ID = "adlfs.client-id"
ADLFS_ClIENT_SECRET = "adlfs.client-secret"
ADLFS_PREFIX = "adlfs"
AWS_REGION = "client.region"
AWS_ACCESS_KEY_ID = "client.access-key-id"
AWS_SECRET_ACCESS_KEY = "client.secret-access-key"
Expand Down Expand Up @@ -94,7 +86,6 @@
GCS_CACHE_TIMEOUT = "gcs.cache-timeout"
GCS_REQUESTER_PAYS = "gcs.requester-pays"
GCS_SESSION_KWARGS = "gcs.session-kwargs"
GCS_ENDPOINT = "gcs.endpoint"
GCS_SERVICE_HOST = "gcs.service.host"
GCS_DEFAULT_LOCATION = "gcs.default-bucket-location"
GCS_VERSION_AWARE = "gcs.version-aware"
Expand Down
68 changes: 8 additions & 60 deletions pyiceberg/io/fsspec.py
Original file line number Diff line number Diff line change
Expand Up @@ -40,13 +40,6 @@
from pyiceberg.catalog import TOKEN
from pyiceberg.exceptions import SignError
from pyiceberg.io import (
ADLFS_ACCOUNT_KEY,
ADLFS_ACCOUNT_NAME,
ADLFS_CLIENT_ID,
ADLFS_CONNECTION_STRING,
ADLFS_PREFIX,
ADLFS_SAS_TOKEN,
ADLFS_TENANT_ID,
ADLS_ACCOUNT_KEY,
ADLS_ACCOUNT_NAME,
ADLS_CLIENT_ID,
Expand All @@ -61,7 +54,6 @@
GCS_CACHE_TIMEOUT,
GCS_CONSISTENCY,
GCS_DEFAULT_LOCATION,
GCS_ENDPOINT,
GCS_PROJECT_ID,
GCS_REQUESTER_PAYS,
GCS_SERVICE_HOST,
Expand All @@ -78,7 +70,6 @@
S3_SIGNER_ENDPOINT,
S3_SIGNER_ENDPOINT_DEFAULT,
S3_SIGNER_URI,
ADLFS_ClIENT_SECRET,
ADLS_ClIENT_SECRET,
FileIO,
InputFile,
Expand All @@ -87,7 +78,6 @@
OutputStream,
)
from pyiceberg.typedef import Properties
from pyiceberg.utils.deprecated import deprecation_message
from pyiceberg.utils.properties import get_first_property_value, property_as_bool

logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -172,12 +162,6 @@ def _gs(properties: Properties) -> AbstractFileSystem:
# https://gcsfs.readthedocs.io/en/latest/api.html#gcsfs.core.GCSFileSystem
from gcsfs import GCSFileSystem

if properties.get(GCS_ENDPOINT):
deprecation_message(
deprecated_in="0.8.0",
removed_in="0.9.0",
help_message=f"The property {GCS_ENDPOINT} is deprecated, please use {GCS_SERVICE_HOST} instead",
)
return GCSFileSystem(
project=properties.get(GCS_PROJECT_ID),
access=properties.get(GCS_ACCESS, "full_control"),
Expand All @@ -186,7 +170,7 @@ def _gs(properties: Properties) -> AbstractFileSystem:
cache_timeout=properties.get(GCS_CACHE_TIMEOUT),
requester_pays=property_as_bool(properties, GCS_REQUESTER_PAYS, False),
session_kwargs=json.loads(properties.get(GCS_SESSION_KWARGS, "{}")),
endpoint_url=get_first_property_value(properties, GCS_SERVICE_HOST, GCS_ENDPOINT),
endpoint_url=properties.get(GCS_SERVICE_HOST),
default_location=properties.get(GCS_DEFAULT_LOCATION),
version_aware=property_as_bool(properties, GCS_VERSION_AWARE, False),
)
Expand All @@ -195,50 +179,14 @@ def _gs(properties: Properties) -> AbstractFileSystem:
def _adls(properties: Properties) -> AbstractFileSystem:
from adlfs import AzureBlobFileSystem

for property_name in properties:
if property_name.startswith(ADLFS_PREFIX):
deprecation_message(
deprecated_in="0.8.0",
removed_in="0.9.0",
help_message=f"The property {property_name} is deprecated. Please use properties that start with adls.",
)

return AzureBlobFileSystem(
connection_string=get_first_property_value(
properties,
ADLS_CONNECTION_STRING,
ADLFS_CONNECTION_STRING,
),
account_name=get_first_property_value(
properties,
ADLS_ACCOUNT_NAME,
ADLFS_ACCOUNT_NAME,
),
account_key=get_first_property_value(
properties,
ADLS_ACCOUNT_KEY,
ADLFS_ACCOUNT_KEY,
),
sas_token=get_first_property_value(
properties,
ADLS_SAS_TOKEN,
ADLFS_SAS_TOKEN,
),
tenant_id=get_first_property_value(
properties,
ADLS_TENANT_ID,
ADLFS_TENANT_ID,
),
client_id=get_first_property_value(
properties,
ADLS_CLIENT_ID,
ADLFS_CLIENT_ID,
),
client_secret=get_first_property_value(
properties,
ADLS_ClIENT_SECRET,
ADLFS_ClIENT_SECRET,
),
connection_string=properties.get(ADLS_CONNECTION_STRING),
account_name=properties.get(ADLS_ACCOUNT_NAME),
account_key=properties.get(ADLS_ACCOUNT_KEY),
sas_token=properties.get(ADLS_SAS_TOKEN),
tenant_id=properties.get(ADLS_TENANT_ID),
client_id=properties.get(ADLS_CLIENT_ID),
client_secret=properties.get(ADLS_ClIENT_SECRET),
)


Expand Down
10 changes: 1 addition & 9 deletions pyiceberg/io/pyarrow.py
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,6 @@
AWS_SECRET_ACCESS_KEY,
AWS_SESSION_TOKEN,
GCS_DEFAULT_LOCATION,
GCS_ENDPOINT,
GCS_SERVICE_HOST,
GCS_TOKEN,
GCS_TOKEN_EXPIRES_AT_MS,
Expand Down Expand Up @@ -166,7 +165,6 @@
from pyiceberg.utils.concurrent import ExecutorFactory
from pyiceberg.utils.config import Config
from pyiceberg.utils.datetime import millis_to_datetime
from pyiceberg.utils.deprecated import deprecation_message
from pyiceberg.utils.properties import get_first_property_value, property_as_bool, property_as_int
from pyiceberg.utils.singleton import Singleton
from pyiceberg.utils.truncate import truncate_upper_bound_binary_string, truncate_upper_bound_text_string
Expand Down Expand Up @@ -471,13 +469,7 @@ def _initialize_gcs_fs(self) -> FileSystem:
gcs_kwargs["credential_token_expiration"] = millis_to_datetime(int(expiration))
if bucket_location := self.properties.get(GCS_DEFAULT_LOCATION):
gcs_kwargs["default_bucket_location"] = bucket_location
if endpoint := get_first_property_value(self.properties, GCS_SERVICE_HOST, GCS_ENDPOINT):
if self.properties.get(GCS_ENDPOINT):
deprecation_message(
deprecated_in="0.8.0",
removed_in="0.9.0",
help_message=f"The property {GCS_ENDPOINT} is deprecated, please use {GCS_SERVICE_HOST} instead",
)
if endpoint := self.properties.get(GCS_SERVICE_HOST):
url_parts = urlparse(endpoint)
gcs_kwargs["scheme"] = url_parts.scheme
gcs_kwargs["endpoint_override"] = url_parts.netloc
Expand Down