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

Remove get_columns implementation for column metadata generation #940

Merged
merged 2 commits into from
Nov 1, 2024
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
7 changes: 7 additions & 0 deletions .changes/unreleased/Fixes-20241101-150335.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
kind: Fixes
body: Remove `redshift_connector`'s `get_columns` method for column metadata generation,
avoiding a warning on every run
time: 2024-11-01T15:03:35.44697-04:00
custom:
Author: "mikealfare"
Issue: "914"
53 changes: 0 additions & 53 deletions dbt/adapters/redshift/connections.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@
from contextlib import contextmanager
from typing import Any, Callable, Dict, Tuple, Union, Optional, List, TYPE_CHECKING
from dataclasses import dataclass, field
import time

import sqlparse
import redshift_connector
Expand All @@ -13,14 +12,10 @@
from dbt.adapters.sql import SQLConnectionManager
from dbt.adapters.contracts.connection import AdapterResponse, Connection, Credentials
from dbt.adapters.events.logging import AdapterLogger
from dbt.adapters.events.types import SQLQuery, SQLQueryStatus
from dbt_common.contracts.util import Replaceable
from dbt_common.dataclass_schema import dbtClassMixin, StrEnum, ValidationError
from dbt_common.events.contextvars import get_node_info
from dbt_common.events.functions import fire_event
from dbt_common.helper_types import Port
from dbt_common.exceptions import DbtRuntimeError, CompilationError, DbtDatabaseError
from dbt_common.utils import cast_to_str

if TYPE_CHECKING:
# Indirectly imported via agate_helper, which is lazy loaded further downfile.
Expand Down Expand Up @@ -465,51 +460,3 @@ def _initialize_sqlparse_lexer():

if hasattr(Lexer, "get_default_instance"):
Lexer.get_default_instance()

def columns_in_relation(self, relation) -> List[Dict[str, Any]]:
connection = self.get_thread_connection()

fire_event(
SQLQuery(
conn_name=cast_to_str(connection.name),
sql=f"call redshift_connector.Connection.get_columns({relation.database}, {relation.schema}, {relation.identifier})",
node_info=get_node_info(),
)
)

pre = time.perf_counter()

cursor = connection.handle.cursor()
columns = cursor.get_columns(
catalog=relation.database,
schema_pattern=relation.schema,
tablename_pattern=relation.identifier,
)

fire_event(
SQLQueryStatus(
status=str(self.get_response(cursor)),
elapsed=time.perf_counter() - pre,
node_info=get_node_info(),
)
)

return [self._parse_column_results(column) for column in columns]

@staticmethod
def _parse_column_results(record: Tuple[Any, ...]) -> Dict[str, Any]:
_, _, _, column_name, dtype_code, dtype_name, column_size, _, decimals, *_ = record

char_dtypes = [1, 12]
num_dtypes = [2, 3, 4, 5, 6, 7, 8, -5, 2003]

if dtype_code in char_dtypes:
return {"column": column_name, "dtype": dtype_name, "char_size": column_size}
elif dtype_code in num_dtypes:
return {
"column": column_name,
"dtype": dtype_name,
"numeric_precision": column_size,
"numeric_scale": decimals,
}
return {"column": column_name, "dtype": dtype_name, "char_size": column_size}
27 changes: 1 addition & 26 deletions dbt/adapters/redshift/impl.py
Original file line number Diff line number Diff line change
@@ -1,12 +1,10 @@
import os
from dataclasses import dataclass

from dbt_common.behavior_flags import BehaviorFlag
from dbt_common.contracts.constraints import ConstraintType
from typing import Optional, Set, Any, Dict, Type, TYPE_CHECKING, List
from typing import Optional, Set, Any, Dict, Type, TYPE_CHECKING
from collections import namedtuple
from dbt.adapters.base import PythonJobHelper
from dbt.adapters.base.column import Column
from dbt.adapters.base.impl import AdapterConfig, ConstraintSupport
from dbt.adapters.base.meta import available
from dbt.adapters.capability import Capability, CapabilityDict, CapabilitySupport, Support
Expand Down Expand Up @@ -68,23 +66,6 @@ class RedshiftAdapter(SQLAdapter):
}
)

@property
def _behavior_flags(self) -> List[BehaviorFlag]:
return [
{
"name": "restrict_direct_pg_catalog_access",
"default": False,
"description": (
"The dbt-redshift adapter is migrating from using pg_ tables "
"to using Redshift Metadata API and information_schema tables "
"in order to support additional Redshift functionalities.\n"
"We do not expect this to impact your dbt experience. "
"Please report any issues using this GitHub discussion: https://github.com/dbt-labs/dbt-redshift/discussions/921"
),
"docs_url": "https://docs.getdbt.com/reference/global-configs/behavior-changes#redshift-restrict_direct_pg_catalog_access",
}
]

@classmethod
def date_function(cls):
return "getdate()"
Expand All @@ -107,12 +88,6 @@ def drop_relation(self, relation):
with self.connections.fresh_transaction():
return super().drop_relation(relation)

def get_columns_in_relation(self, relation) -> List[Column]:
if self.behavior.restrict_direct_pg_catalog_access:
column_configs = self.connections.columns_in_relation(relation)
return [Column(**column) for column in column_configs]
return super().get_columns_in_relation(relation)

@classmethod
def convert_text_type(cls, agate_table: "agate.Table", col_idx):
column = agate_table.columns[col_idx]
Expand Down
14 changes: 12 additions & 2 deletions tests/functional/test_columns_in_relation.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,3 @@
import os

from dbt.adapters.base import Column
from dbt.tests.util import run_dbt, run_dbt_and_capture
import pytest
Expand Down Expand Up @@ -47,6 +45,12 @@ def expected_columns(self):
]


@pytest.mark.skip(
"""
There is a discrepancy between our custom query and the get_columns SDK call.
This test should be skipped for now, but re-enabled once get_columns is implemented.
"""
)
class TestColumnsInRelationBehaviorFlagOn(ColumnsInRelation):
@pytest.fixture(scope="class")
def project_config_update(self):
Expand Down Expand Up @@ -74,6 +78,12 @@ def expected_columns(self):
"""


@pytest.mark.skip(
"""
There is a discrepancy between our custom query and the get_columns SDK call.
This test should be skipped for now, but re-enabled once get_columns is implemented.
"""
)
class TestBehaviorFlagFiresOnce:
@pytest.fixture(scope="class")
def project_config_update(self):
Expand Down
Loading