From 7de2e877c2dbfd895f669e72b45e3adf1afa19f0 Mon Sep 17 00:00:00 2001 From: Gerda Shank Date: Thu, 5 Sep 2024 17:07:23 -0400 Subject: [PATCH 01/25] Check if warning exists, for compatibility with 1.8 (#292) --- .../macros/materializations/snapshots/helpers.sql | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/dbt/include/global_project/macros/materializations/snapshots/helpers.sql b/dbt/include/global_project/macros/materializations/snapshots/helpers.sql index 29566094..9e8575e9 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/helpers.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/helpers.sql @@ -199,6 +199,8 @@ {% set dbt_updated_at_data_type = get_updated_at_column_data_type(sql) %} {% set snapshot_get_time_data_type = get_snapshot_get_time_data_type() %} {% if snapshot_get_time_data_type is not none and dbt_updated_at_data_type is not none and snapshot_get_time_data_type != dbt_updated_at_data_type %} - {{ exceptions.warn_snapshot_timestamp_data_types(snapshot_get_time_data_type, dbt_updated_at_data_type) }} + {% if exceptions.warn_snapshot_timestamp_data_types %} + {{ exceptions.warn_snapshot_timestamp_data_types(snapshot_get_time_data_type, dbt_updated_at_data_type) }} + {% endif %} {% endif %} {% endmacro %} From 8a570fa03ccac033de98512fa9aff8b0be4a7302 Mon Sep 17 00:00:00 2001 From: Mike Alfare <13974384+mikealfare@users.noreply.github.com> Date: Fri, 6 Sep 2024 16:24:38 -0400 Subject: [PATCH 02/25] Add Behavior Flag Framework (#282) --- .../unreleased/Features-20240818-005131.yaml | 6 + .pre-commit-config.yaml | 2 +- dbt/adapters/base/impl.py | 25 ++- tests/unit/conftest.py | 1 + tests/unit/fixtures/__init__.py | 1 + tests/unit/fixtures/adapter.py | 146 ++++++++++++++++++ tests/unit/fixtures/connection_manager.py | 58 +++++++ tests/unit/fixtures/credentials.py | 13 ++ tests/unit/test_behavior_flags.py | 42 +++++ 9 files changed, 292 insertions(+), 2 deletions(-) create mode 100644 .changes/unreleased/Features-20240818-005131.yaml create mode 100644 tests/unit/conftest.py create mode 100644 tests/unit/fixtures/__init__.py create mode 100644 tests/unit/fixtures/adapter.py create mode 100644 tests/unit/fixtures/connection_manager.py create mode 100644 tests/unit/fixtures/credentials.py create mode 100644 tests/unit/test_behavior_flags.py diff --git a/.changes/unreleased/Features-20240818-005131.yaml b/.changes/unreleased/Features-20240818-005131.yaml new file mode 100644 index 00000000..17260206 --- /dev/null +++ b/.changes/unreleased/Features-20240818-005131.yaml @@ -0,0 +1,6 @@ +kind: Features +body: Add Behavior Flag framework +time: 2024-08-18T00:51:31.753656-04:00 +custom: + Author: mikealfare + Issue: "281" diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index caf34209..0f2a03f7 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -38,7 +38,7 @@ repos: - --max-line-length=99 - --select=E,F,W - --ignore=E203,E501,E704,E741,W503,W504 - - --per-file-ignores=*/__init__.py:F401 + - --per-file-ignores=*/__init__.py:F401,*/conftest.py:F401 - repo: https://github.com/pre-commit/mirrors-mypy rev: v1.9.0 diff --git a/dbt/adapters/base/impl.py b/dbt/adapters/base/impl.py index e0627c47..541c9846 100644 --- a/dbt/adapters/base/impl.py +++ b/dbt/adapters/base/impl.py @@ -24,6 +24,7 @@ ) import pytz +from dbt_common.behavior_flags import Behavior, BehaviorFlag from dbt_common.clients.jinja import CallableMacroGenerator from dbt_common.contracts.constraints import ( ColumnLevelConstraint, @@ -261,7 +262,7 @@ class BaseAdapter(metaclass=AdapterMeta): MAX_SCHEMA_METADATA_RELATIONS = 100 - # This static member variable can be overriden in concrete adapter + # This static member variable can be overridden in concrete adapter # implementations to indicate adapter support for optional capabilities. _capabilities = CapabilityDict({}) @@ -271,6 +272,7 @@ def __init__(self, config, mp_context: SpawnContext) -> None: self.connections = self.ConnectionManager(config, mp_context) self._macro_resolver: Optional[MacroResolverProtocol] = None self._macro_context_generator: Optional[MacroContextGeneratorCallable] = None + self.behavior = [] # this will be updated to include global behavior flags once they exist ### # Methods to set / access a macro resolver @@ -291,6 +293,27 @@ def set_macro_context_generator( ) -> None: self._macro_context_generator = macro_context_generator + @property + def behavior(self) -> Behavior: + return self._behavior + + @behavior.setter + def behavior(self, flags: List[BehaviorFlag]) -> None: + flags.extend(self._behavior_flags) + try: + # we don't always get project flags, for example during `dbt debug` + self._behavior = Behavior(flags, self.config.flags) + except AttributeError: + # in that case, don't load any behavior to avoid unexpected defaults + self._behavior = Behavior([], {}) + + @property + def _behavior_flags(self) -> List[BehaviorFlag]: + """ + This method should be overwritten by adapter maintainers to provide platform-specific flags + """ + return [] + ### # Methods that pass through to the connection manager ### diff --git a/tests/unit/conftest.py b/tests/unit/conftest.py new file mode 100644 index 00000000..346634df --- /dev/null +++ b/tests/unit/conftest.py @@ -0,0 +1 @@ +from tests.unit.fixtures import adapter, behavior_flags, config, flags diff --git a/tests/unit/fixtures/__init__.py b/tests/unit/fixtures/__init__.py new file mode 100644 index 00000000..78135a2c --- /dev/null +++ b/tests/unit/fixtures/__init__.py @@ -0,0 +1 @@ +from tests.unit.fixtures.adapter import adapter, behavior_flags, config, flags diff --git a/tests/unit/fixtures/adapter.py b/tests/unit/fixtures/adapter.py new file mode 100644 index 00000000..b59b0423 --- /dev/null +++ b/tests/unit/fixtures/adapter.py @@ -0,0 +1,146 @@ +from multiprocessing import get_context +from types import SimpleNamespace +from typing import Any, Dict, List + +import agate +from dbt_common.behavior_flags import BehaviorFlag +import pytest + +from dbt.adapters.base.column import Column +from dbt.adapters.base.impl import BaseAdapter +from dbt.adapters.base.relation import BaseRelation +from dbt.adapters.contracts.connection import AdapterRequiredConfig, QueryComment + +from tests.unit.fixtures.connection_manager import ConnectionManagerStub +from tests.unit.fixtures.credentials import CredentialsStub + + +@pytest.fixture +def adapter(config, behavior_flags) -> BaseAdapter: + + class BaseAdapterStub(BaseAdapter): + """ + A stub for an adapter that uses the cache as the database + """ + + ConnectionManager = ConnectionManagerStub + + @property + def _behavior_flags(self) -> List[BehaviorFlag]: + return behavior_flags + + ### + # Abstract methods for database-specific values, attributes, and types + ### + @classmethod + def date_function(cls) -> str: + return "date_function" + + @classmethod + def is_cancelable(cls) -> bool: + return False + + def list_schemas(self, database: str) -> List[str]: + return list(self.cache.schemas) + + ### + # Abstract methods about relations + ### + def drop_relation(self, relation: BaseRelation) -> None: + self.cache_dropped(relation) + + def truncate_relation(self, relation: BaseRelation) -> None: + self.cache_dropped(relation) + + def rename_relation(self, from_relation: BaseRelation, to_relation: BaseRelation) -> None: + self.cache_renamed(from_relation, to_relation) + + def get_columns_in_relation(self, relation: BaseRelation) -> List[Column]: + # there's no database, so these need to be added as kwargs in the existing_relations fixture + return relation.columns + + def expand_column_types(self, goal: BaseRelation, current: BaseRelation) -> None: + # there's no database, so these need to be added as kwargs in the existing_relations fixture + object.__setattr__(current, "columns", goal.columns) + + def list_relations_without_caching( + self, schema_relation: BaseRelation + ) -> List[BaseRelation]: + # there's no database, so use the cache as the database + return self.cache.get_relations(schema_relation.database, schema_relation.schema) + + ### + # ODBC FUNCTIONS -- these should not need to change for every adapter, + # although some adapters may override them + ### + def create_schema(self, relation: BaseRelation): + # there's no database, this happens implicitly by adding a relation to the cache + pass + + def drop_schema(self, relation: BaseRelation): + for each_relation in self.cache.get_relations(relation.database, relation.schema): + self.cache_dropped(each_relation) + + @classmethod + def quote(cls, identifier: str) -> str: + quote_char = "" + return f"{quote_char}{identifier}{quote_char}" + + ### + # Conversions: These must be implemented by concrete implementations, for + # converting agate types into their sql equivalents. + ### + @classmethod + def convert_text_type(cls, agate_table: agate.Table, col_idx: int) -> str: + return "str" + + @classmethod + def convert_number_type(cls, agate_table: agate.Table, col_idx: int) -> str: + return "float" + + @classmethod + def convert_boolean_type(cls, agate_table: agate.Table, col_idx: int) -> str: + return "bool" + + @classmethod + def convert_datetime_type(cls, agate_table: agate.Table, col_idx: int) -> str: + return "datetime" + + @classmethod + def convert_date_type(cls, *args, **kwargs): + return "date" + + @classmethod + def convert_time_type(cls, *args, **kwargs): + return "time" + + return BaseAdapterStub(config, get_context("spawn")) + + +@pytest.fixture +def config(flags) -> AdapterRequiredConfig: + raw_config = { + "credentials": CredentialsStub("test_database", "test_schema"), + "profile_name": "test_profile", + "target_name": "test_target", + "threads": 4, + "project_name": "test_project", + "query_comment": QueryComment(), + "cli_vars": {}, + "target_path": "path/to/nowhere", + "log_cache_events": False, + "flags": flags, + } + return SimpleNamespace(**raw_config) + + +@pytest.fixture +def flags() -> Dict[str, Any]: + # this is the flags collection in dbt_project.yaml + return {} + + +@pytest.fixture +def behavior_flags() -> List[BehaviorFlag]: + # this is the collection of behavior flags for a specific adapter + return [] diff --git a/tests/unit/fixtures/connection_manager.py b/tests/unit/fixtures/connection_manager.py new file mode 100644 index 00000000..8b353fbe --- /dev/null +++ b/tests/unit/fixtures/connection_manager.py @@ -0,0 +1,58 @@ +from contextlib import contextmanager +from typing import ContextManager, List, Optional, Tuple + +import agate + +from dbt.adapters.base.connections import BaseConnectionManager +from dbt.adapters.contracts.connection import AdapterResponse, Connection, ConnectionState + + +class ConnectionManagerStub(BaseConnectionManager): + """ + A stub for a connection manager that does not connect to a database + """ + + raised_exceptions: List[Exception] + + @contextmanager + def exception_handler(self, sql: str) -> ContextManager: # type: ignore + # catch all exceptions and put them on this class for inspection in tests + try: + yield + except Exception as exc: + self.raised_exceptions.append(exc) + finally: + pass + + def cancel_open(self) -> Optional[List[str]]: + names = [] + for connection in self.thread_connections.values(): + if connection.state == ConnectionState.OPEN: + connection.state = ConnectionState.CLOSED + if name := connection.name: + names.append(name) + return names + + @classmethod + def open(cls, connection: Connection) -> Connection: + # there's no database, so just change the state + connection.state = ConnectionState.OPEN + return connection + + def begin(self) -> None: + # there's no database, so there are no transactions + pass + + def commit(self) -> None: + # there's no database, so there are no transactions + pass + + def execute( + self, + sql: str, + auto_begin: bool = False, + fetch: bool = False, + limit: Optional[int] = None, + ) -> Tuple[AdapterResponse, agate.Table]: + # there's no database, so just return the sql + return AdapterResponse(_message="", code=sql), agate.Table([]) diff --git a/tests/unit/fixtures/credentials.py b/tests/unit/fixtures/credentials.py new file mode 100644 index 00000000..88817f6b --- /dev/null +++ b/tests/unit/fixtures/credentials.py @@ -0,0 +1,13 @@ +from dbt.adapters.contracts.connection import Credentials + + +class CredentialsStub(Credentials): + """ + A stub for a database credentials that does not connect to a database + """ + + def type(self) -> str: + return "test" + + def _connection_keys(self): + return {"database": self.database, "schema": self.schema} diff --git a/tests/unit/test_behavior_flags.py b/tests/unit/test_behavior_flags.py new file mode 100644 index 00000000..0ae1a021 --- /dev/null +++ b/tests/unit/test_behavior_flags.py @@ -0,0 +1,42 @@ +from typing import Any, Dict, List + +from dbt_common.behavior_flags import BehaviorFlag +from dbt_common.exceptions import DbtBaseException +import pytest + + +@pytest.fixture +def flags() -> Dict[str, Any]: + return { + "unregistered_flag": True, + "default_false_user_false_flag": False, + "default_false_user_true_flag": True, + "default_true_user_false_flag": False, + "default_true_user_true_flag": True, + } + + +@pytest.fixture +def behavior_flags() -> List[BehaviorFlag]: + return [ + {"name": "default_false_user_false_flag", "default": False}, + {"name": "default_false_user_true_flag", "default": False}, + {"name": "default_false_user_skip_flag", "default": False}, + {"name": "default_true_user_false_flag", "default": True}, + {"name": "default_true_user_true_flag", "default": True}, + {"name": "default_true_user_skip_flag", "default": True}, + ] + + +def test_register_behavior_flags(adapter): + # make sure that users cannot add arbitrary flags to this collection + with pytest.raises(DbtBaseException): + assert adapter.behavior.unregistered_flag + + # check the values of the valid behavior flags + assert not adapter.behavior.default_false_user_false_flag + assert adapter.behavior.default_false_user_true_flag + assert not adapter.behavior.default_false_user_skip_flag + assert not adapter.behavior.default_true_user_false_flag + assert adapter.behavior.default_true_user_true_flag + assert adapter.behavior.default_true_user_skip_flag From 95f7daba22af8283886fd3d3e3acfe1a03f3858a Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Mon, 9 Sep 2024 13:11:21 +0000 Subject: [PATCH 03/25] Bumping version to 1.4.2 and generate changelog --- .changes/1.4.2.md | 6 ++++++ .changes/unreleased/Features-20240621-143024.yaml | 6 ------ .changes/unreleased/Features-20240818-005131.yaml | 6 ------ CHANGELOG.md | 10 +++++++++- dbt/adapters/__about__.py | 2 +- 5 files changed, 16 insertions(+), 14 deletions(-) create mode 100644 .changes/1.4.2.md delete mode 100644 .changes/unreleased/Features-20240621-143024.yaml delete mode 100644 .changes/unreleased/Features-20240818-005131.yaml diff --git a/.changes/1.4.2.md b/.changes/1.4.2.md new file mode 100644 index 00000000..3735f93c --- /dev/null +++ b/.changes/1.4.2.md @@ -0,0 +1,6 @@ +## dbt-adapters 1.4.2 - September 09, 2024 + +### Features + +- Compare 'snapshot_get_time' and snapshot 'updated_at' data types ([#242](https://github.com/dbt-labs/dbt-adapters/issues/242)) +- Add Behavior Flag framework ([#281](https://github.com/dbt-labs/dbt-adapters/issues/281)) diff --git a/.changes/unreleased/Features-20240621-143024.yaml b/.changes/unreleased/Features-20240621-143024.yaml deleted file mode 100644 index 526745a7..00000000 --- a/.changes/unreleased/Features-20240621-143024.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Features -body: Compare 'snapshot_get_time' and snapshot 'updated_at' data types -time: 2024-06-21T14:30:24.336219-04:00 -custom: - Author: gshank - Issue: "242" diff --git a/.changes/unreleased/Features-20240818-005131.yaml b/.changes/unreleased/Features-20240818-005131.yaml deleted file mode 100644 index 17260206..00000000 --- a/.changes/unreleased/Features-20240818-005131.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Features -body: Add Behavior Flag framework -time: 2024-08-18T00:51:31.753656-04:00 -custom: - Author: mikealfare - Issue: "281" diff --git a/CHANGELOG.md b/CHANGELOG.md index 9a6a3cc8..ffdab26d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,15 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). +## dbt-adapters 1.4.2 - September 09, 2024 + +### Features + +- Compare 'snapshot_get_time' and snapshot 'updated_at' data types ([#242](https://github.com/dbt-labs/dbt-adapters/issues/242)) +- Add Behavior Flag framework ([#281](https://github.com/dbt-labs/dbt-adapters/issues/281)) + + + ## dbt-adapters 1.4.1 - August 09, 2024 ### Fixes @@ -19,7 +28,6 @@ and is generated by [Changie](https://github.com/miniscruff/changie). - [@jeancochrane](https://github.com/jeancochrane) ([#5273](https://github.com/dbt-labs/dbt-adapters/issues/5273)) - [@leahwicz](https://github.com/leahwicz) ([#219](https://github.com/dbt-labs/dbt-adapters/issues/219)) - ## dbt-adapters 1.4.0 - July 30, 2024 ### Features diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index 6abaa204..841aad2c 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.4.1" +version = "1.4.2" From dadd0f253144831e3a00dd0f4cb74b13dd6a81aa Mon Sep 17 00:00:00 2001 From: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> Date: Mon, 9 Sep 2024 14:18:38 -0700 Subject: [PATCH 04/25] Revert "Bumping version to 1.4.2 and generate changelog" (#298) --- .changes/1.4.2.md | 6 ------ .changes/unreleased/Features-20240621-143024.yaml | 6 ++++++ .changes/unreleased/Features-20240818-005131.yaml | 6 ++++++ CHANGELOG.md | 10 +--------- dbt/adapters/__about__.py | 2 +- 5 files changed, 14 insertions(+), 16 deletions(-) delete mode 100644 .changes/1.4.2.md create mode 100644 .changes/unreleased/Features-20240621-143024.yaml create mode 100644 .changes/unreleased/Features-20240818-005131.yaml diff --git a/.changes/1.4.2.md b/.changes/1.4.2.md deleted file mode 100644 index 3735f93c..00000000 --- a/.changes/1.4.2.md +++ /dev/null @@ -1,6 +0,0 @@ -## dbt-adapters 1.4.2 - September 09, 2024 - -### Features - -- Compare 'snapshot_get_time' and snapshot 'updated_at' data types ([#242](https://github.com/dbt-labs/dbt-adapters/issues/242)) -- Add Behavior Flag framework ([#281](https://github.com/dbt-labs/dbt-adapters/issues/281)) diff --git a/.changes/unreleased/Features-20240621-143024.yaml b/.changes/unreleased/Features-20240621-143024.yaml new file mode 100644 index 00000000..526745a7 --- /dev/null +++ b/.changes/unreleased/Features-20240621-143024.yaml @@ -0,0 +1,6 @@ +kind: Features +body: Compare 'snapshot_get_time' and snapshot 'updated_at' data types +time: 2024-06-21T14:30:24.336219-04:00 +custom: + Author: gshank + Issue: "242" diff --git a/.changes/unreleased/Features-20240818-005131.yaml b/.changes/unreleased/Features-20240818-005131.yaml new file mode 100644 index 00000000..17260206 --- /dev/null +++ b/.changes/unreleased/Features-20240818-005131.yaml @@ -0,0 +1,6 @@ +kind: Features +body: Add Behavior Flag framework +time: 2024-08-18T00:51:31.753656-04:00 +custom: + Author: mikealfare + Issue: "281" diff --git a/CHANGELOG.md b/CHANGELOG.md index ffdab26d..9a6a3cc8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,15 +5,6 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). -## dbt-adapters 1.4.2 - September 09, 2024 - -### Features - -- Compare 'snapshot_get_time' and snapshot 'updated_at' data types ([#242](https://github.com/dbt-labs/dbt-adapters/issues/242)) -- Add Behavior Flag framework ([#281](https://github.com/dbt-labs/dbt-adapters/issues/281)) - - - ## dbt-adapters 1.4.1 - August 09, 2024 ### Fixes @@ -28,6 +19,7 @@ and is generated by [Changie](https://github.com/miniscruff/changie). - [@jeancochrane](https://github.com/jeancochrane) ([#5273](https://github.com/dbt-labs/dbt-adapters/issues/5273)) - [@leahwicz](https://github.com/leahwicz) ([#219](https://github.com/dbt-labs/dbt-adapters/issues/219)) + ## dbt-adapters 1.4.0 - July 30, 2024 ### Features diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index 841aad2c..6abaa204 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.4.2" +version = "1.4.1" From cffa724ce415d5fcffca244425fc8b3bd2ce9449 Mon Sep 17 00:00:00 2001 From: Michelle Ark Date: Mon, 9 Sep 2024 22:45:33 -0400 Subject: [PATCH 05/25] Add EventTimeFilter and BaseRelation.render_event_time_filtered (#285) Co-authored-by: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> --- .../unreleased/Features-20240905-180956.yaml | 7 ++ dbt/adapters/base/relation.py | 54 ++++++++++++- tests/unit/test_relation.py | 77 ++++++++++++++++++- 3 files changed, 134 insertions(+), 4 deletions(-) create mode 100644 .changes/unreleased/Features-20240905-180956.yaml diff --git a/.changes/unreleased/Features-20240905-180956.yaml b/.changes/unreleased/Features-20240905-180956.yaml new file mode 100644 index 00000000..6ca843c4 --- /dev/null +++ b/.changes/unreleased/Features-20240905-180956.yaml @@ -0,0 +1,7 @@ +kind: Features +body: Add EventTimeFilter to BaseRelation, which renders a filtered relation when + start or end is set +time: 2024-09-05T18:09:56.159385-04:00 +custom: + Author: 'michelleark QMalcolm' + Issue: "294" diff --git a/dbt/adapters/base/relation.py b/dbt/adapters/base/relation.py index 1aab7b2f..0053265f 100644 --- a/dbt/adapters/base/relation.py +++ b/dbt/adapters/base/relation.py @@ -1,5 +1,6 @@ from collections.abc import Hashable from dataclasses import dataclass, field +from datetime import datetime from typing import ( Any, Dict, @@ -36,6 +37,13 @@ SerializableIterable = Union[Tuple, FrozenSet] +@dataclass(frozen=True, eq=False, repr=False) +class EventTimeFilter(FakeAPIObject, Hashable): + field_name: str + start: Optional[datetime] = None + end: Optional[datetime] = None + + @dataclass(frozen=True, eq=False, repr=False) class BaseRelation(FakeAPIObject, Hashable): path: Path @@ -47,6 +55,7 @@ class BaseRelation(FakeAPIObject, Hashable): quote_policy: Policy = field(default_factory=lambda: Policy()) dbt_created: bool = False limit: Optional[int] = None + event_time_filter: Optional[EventTimeFilter] = None require_alias: bool = ( True # used to govern whether to add an alias when render_limited is called ) @@ -208,14 +217,19 @@ def render(self) -> str: # if there is nothing set, this will return the empty string. return ".".join(part for _, part in self._render_iterator() if part is not None) - def _render_limited_alias(self) -> str: + def _render_subquery_alias(self, namespace: str) -> str: """Some databases require an alias for subqueries (postgres, mysql) for all others we want to avoid adding an alias as it has the potential to introduce issues with the query if the user also defines an alias. """ if self.require_alias: - return f" _dbt_limit_subq_{self.table}" + return f" _dbt_{namespace}_subq_{self.table}" return "" + def _render_limited_alias( + self, + ) -> str: + return self._render_subquery_alias(namespace="limit") + def render_limited(self) -> str: rendered = self.render() if self.limit is None: @@ -225,6 +239,31 @@ def render_limited(self) -> str: else: return f"(select * from {rendered} limit {self.limit}){self._render_limited_alias()}" + def render_event_time_filtered(self, rendered: Optional[str] = None) -> str: + rendered = rendered or self.render() + if self.event_time_filter is None: + return rendered + + filter = self._render_event_time_filtered(self.event_time_filter) + if not filter: + return rendered + + return f"(select * from {rendered} where {filter}){self._render_subquery_alias(namespace='et_filter')}" + + def _render_event_time_filtered(self, event_time_filter: EventTimeFilter) -> str: + """ + Returns "" if start and end are both None + """ + filter = "" + if event_time_filter.start and event_time_filter.end: + filter = f"{event_time_filter.field_name} >= '{event_time_filter.start}' and {event_time_filter.field_name} < '{event_time_filter.end}'" + elif event_time_filter.start: + filter = f"{event_time_filter.field_name} >= '{event_time_filter.start}'" + elif event_time_filter.end: + filter = f"{event_time_filter.field_name} < '{event_time_filter.end}'" + + return filter + def quoted(self, identifier): return "{quote_char}{identifier}{quote_char}".format( quote_char=self.quote_character, @@ -240,6 +279,7 @@ def create_ephemeral_from( cls: Type[Self], relation_config: RelationConfig, limit: Optional[int] = None, + event_time_filter: Optional[EventTimeFilter] = None, ) -> Self: # Note that ephemeral models are based on the identifier, which will # point to the model's alias if one exists and otherwise fall back to @@ -250,6 +290,7 @@ def create_ephemeral_from( type=cls.CTE, identifier=identifier, limit=limit, + event_time_filter=event_time_filter, ).quote(identifier=False) @classmethod @@ -315,7 +356,14 @@ def __hash__(self) -> int: return hash(self.render()) def __str__(self) -> str: - return self.render() if self.limit is None else self.render_limited() + rendered = self.render() if self.limit is None else self.render_limited() + + # Limited subquery is wrapped by the event time filter subquery, and not the other way around. + # This is because in the context of resolving limited refs, we care more about performance than reliably producing a sample of a certain size. + if self.event_time_filter: + rendered = self.render_event_time_filtered(rendered) + + return rendered @property def database(self) -> Optional[str]: diff --git a/tests/unit/test_relation.py b/tests/unit/test_relation.py index 97d56419..6d835e0d 100644 --- a/tests/unit/test_relation.py +++ b/tests/unit/test_relation.py @@ -1,8 +1,9 @@ from dataclasses import dataclass, replace - +from datetime import datetime import pytest from dbt.adapters.base import BaseRelation +from dbt.adapters.base.relation import EventTimeFilter from dbt.adapters.contracts.relation import RelationType @@ -81,6 +82,80 @@ def test_render_limited(limit, require_alias, expected_result): assert str(my_relation) == expected_result +@pytest.mark.parametrize( + "event_time_filter,require_alias,expected_result", + [ + (None, False, '"test_database"."test_schema"."test_identifier"'), + ( + EventTimeFilter(field_name="column"), + False, + '"test_database"."test_schema"."test_identifier"', + ), + (None, True, '"test_database"."test_schema"."test_identifier"'), + ( + EventTimeFilter(field_name="column"), + True, + '"test_database"."test_schema"."test_identifier"', + ), + ( + EventTimeFilter(field_name="column", start=datetime(year=2020, month=1, day=1)), + False, + """(select * from "test_database"."test_schema"."test_identifier" where column >= '2020-01-01 00:00:00')""", + ), + ( + EventTimeFilter(field_name="column", start=datetime(year=2020, month=1, day=1)), + True, + """(select * from "test_database"."test_schema"."test_identifier" where column >= '2020-01-01 00:00:00') _dbt_et_filter_subq_test_identifier""", + ), + ( + EventTimeFilter(field_name="column", end=datetime(year=2020, month=1, day=1)), + False, + """(select * from "test_database"."test_schema"."test_identifier" where column < '2020-01-01 00:00:00')""", + ), + ( + EventTimeFilter( + field_name="column", + start=datetime(year=2020, month=1, day=1), + end=datetime(year=2020, month=1, day=2), + ), + False, + """(select * from "test_database"."test_schema"."test_identifier" where column >= '2020-01-01 00:00:00' and column < '2020-01-02 00:00:00')""", + ), + ], +) +def test_render_event_time_filtered(event_time_filter, require_alias, expected_result): + my_relation = BaseRelation.create( + database="test_database", + schema="test_schema", + identifier="test_identifier", + event_time_filter=event_time_filter, + require_alias=require_alias, + ) + actual_result = my_relation.render_event_time_filtered() + assert actual_result == expected_result + assert str(my_relation) == expected_result + + +def test_render_event_time_filtered_and_limited(): + my_relation = BaseRelation.create( + database="test_database", + schema="test_schema", + identifier="test_identifier", + event_time_filter=EventTimeFilter( + field_name="column", + start=datetime(year=2020, month=1, day=1), + end=datetime(year=2020, month=1, day=2), + ), + limit=0, + require_alias=False, + ) + expected_result = """(select * from (select * from "test_database"."test_schema"."test_identifier" where false limit 0) where column >= '2020-01-01 00:00:00' and column < '2020-01-02 00:00:00')""" + + actual_result = my_relation.render_event_time_filtered(my_relation.render_limited()) + assert actual_result == expected_result + assert str(my_relation) == expected_result + + def test_create_ephemeral_from_uses_identifier(): @dataclass class Node: From a5256765de7681c07a2429bdac85c69ea53076fc Mon Sep 17 00:00:00 2001 From: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> Date: Mon, 9 Sep 2024 20:42:09 -0700 Subject: [PATCH 06/25] update dbt-common pin to >=1.8 (#299) --- .changes/unreleased/Dependencies-20240909-200011.yaml | 6 ++++++ pyproject.toml | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) create mode 100644 .changes/unreleased/Dependencies-20240909-200011.yaml diff --git a/.changes/unreleased/Dependencies-20240909-200011.yaml b/.changes/unreleased/Dependencies-20240909-200011.yaml new file mode 100644 index 00000000..a6364130 --- /dev/null +++ b/.changes/unreleased/Dependencies-20240909-200011.yaml @@ -0,0 +1,6 @@ +kind: Dependencies +body: Update dbt-common pin to >=1.8 +time: 2024-09-09T20:00:11.335813-07:00 +custom: + Author: colin-rogers-dbt + PR: "299" diff --git a/pyproject.toml b/pyproject.toml index e794781c..0bd36d4f 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -24,7 +24,7 @@ classifiers = [ "Programming Language :: Python :: 3.12", ] dependencies = [ - "dbt-common>=1.6,<2.0", + "dbt-common>=1.8,<2.0", "pytz>=2015.7", # installed via dbt-common but used directly "agate>=1.0,<2.0", From d1c252e6207951ab887c1e7d4c371c09b6f4eeb3 Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Tue, 10 Sep 2024 03:46:53 +0000 Subject: [PATCH 07/25] Bumping version to 1.5.0 and generate changelog --- .changes/1.5.0.md | 11 +++++++++++ .../unreleased/Dependencies-20240909-200011.yaml | 6 ------ .changes/unreleased/Features-20240621-143024.yaml | 6 ------ .changes/unreleased/Features-20240818-005131.yaml | 6 ------ .changes/unreleased/Features-20240905-180956.yaml | 7 ------- CHANGELOG.md | 15 ++++++++++++++- dbt/adapters/__about__.py | 2 +- 7 files changed, 26 insertions(+), 27 deletions(-) create mode 100644 .changes/1.5.0.md delete mode 100644 .changes/unreleased/Dependencies-20240909-200011.yaml delete mode 100644 .changes/unreleased/Features-20240621-143024.yaml delete mode 100644 .changes/unreleased/Features-20240818-005131.yaml delete mode 100644 .changes/unreleased/Features-20240905-180956.yaml diff --git a/.changes/1.5.0.md b/.changes/1.5.0.md new file mode 100644 index 00000000..e4c54bdc --- /dev/null +++ b/.changes/1.5.0.md @@ -0,0 +1,11 @@ +## dbt-adapters 1.5.0 - September 10, 2024 + +### Features + +- Compare 'snapshot_get_time' and snapshot 'updated_at' data types ([#242](https://github.com/dbt-labs/dbt-adapters/issues/242)) +- Add Behavior Flag framework ([#281](https://github.com/dbt-labs/dbt-adapters/issues/281)) +- Add EventTimeFilter to BaseRelation, which renders a filtered relation when start or end is set ([#294](https://github.com/dbt-labs/dbt-adapters/issues/294)) + +### Dependencies + +- Update dbt-common pin to >=1.8 ([#299](https://github.com/dbt-labs/dbt-adapters/pull/299)) diff --git a/.changes/unreleased/Dependencies-20240909-200011.yaml b/.changes/unreleased/Dependencies-20240909-200011.yaml deleted file mode 100644 index a6364130..00000000 --- a/.changes/unreleased/Dependencies-20240909-200011.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Dependencies -body: Update dbt-common pin to >=1.8 -time: 2024-09-09T20:00:11.335813-07:00 -custom: - Author: colin-rogers-dbt - PR: "299" diff --git a/.changes/unreleased/Features-20240621-143024.yaml b/.changes/unreleased/Features-20240621-143024.yaml deleted file mode 100644 index 526745a7..00000000 --- a/.changes/unreleased/Features-20240621-143024.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Features -body: Compare 'snapshot_get_time' and snapshot 'updated_at' data types -time: 2024-06-21T14:30:24.336219-04:00 -custom: - Author: gshank - Issue: "242" diff --git a/.changes/unreleased/Features-20240818-005131.yaml b/.changes/unreleased/Features-20240818-005131.yaml deleted file mode 100644 index 17260206..00000000 --- a/.changes/unreleased/Features-20240818-005131.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Features -body: Add Behavior Flag framework -time: 2024-08-18T00:51:31.753656-04:00 -custom: - Author: mikealfare - Issue: "281" diff --git a/.changes/unreleased/Features-20240905-180956.yaml b/.changes/unreleased/Features-20240905-180956.yaml deleted file mode 100644 index 6ca843c4..00000000 --- a/.changes/unreleased/Features-20240905-180956.yaml +++ /dev/null @@ -1,7 +0,0 @@ -kind: Features -body: Add EventTimeFilter to BaseRelation, which renders a filtered relation when - start or end is set -time: 2024-09-05T18:09:56.159385-04:00 -custom: - Author: 'michelleark QMalcolm' - Issue: "294" diff --git a/CHANGELOG.md b/CHANGELOG.md index 9a6a3cc8..7d80911c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,20 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). +## dbt-adapters 1.5.0 - September 10, 2024 + +### Features + +- Compare 'snapshot_get_time' and snapshot 'updated_at' data types ([#242](https://github.com/dbt-labs/dbt-adapters/issues/242)) +- Add Behavior Flag framework ([#281](https://github.com/dbt-labs/dbt-adapters/issues/281)) +- Add EventTimeFilter to BaseRelation, which renders a filtered relation when start or end is set ([#294](https://github.com/dbt-labs/dbt-adapters/issues/294)) + +### Dependencies + +- Update dbt-common pin to >=1.8 ([#299](https://github.com/dbt-labs/dbt-adapters/pull/299)) + + + ## dbt-adapters 1.4.1 - August 09, 2024 ### Fixes @@ -19,7 +33,6 @@ and is generated by [Changie](https://github.com/miniscruff/changie). - [@jeancochrane](https://github.com/jeancochrane) ([#5273](https://github.com/dbt-labs/dbt-adapters/issues/5273)) - [@leahwicz](https://github.com/leahwicz) ([#219](https://github.com/dbt-labs/dbt-adapters/issues/219)) - ## dbt-adapters 1.4.0 - July 30, 2024 ### Features diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index 6abaa204..e3a0f015 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.4.1" +version = "1.5.0" From 629f22fb959d0b85b355dbb23cadedc9f15565df Mon Sep 17 00:00:00 2001 From: Michelle Ark Date: Wed, 11 Sep 2024 17:05:03 -0400 Subject: [PATCH 08/25] base microbatch support + tests (#300) --- .../unreleased/Features-20240911-135404.yaml | 6 ++ .../test_incremental_microbatch.py | 91 +++++++++++++++++++ dbt/adapters/__about__.py | 2 +- dbt/adapters/base/impl.py | 2 +- dbt/adapters/base/relation.py | 4 +- .../models/incremental/strategies.sql | 13 +++ 6 files changed, 114 insertions(+), 4 deletions(-) create mode 100644 .changes/unreleased/Features-20240911-135404.yaml create mode 100644 dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py diff --git a/.changes/unreleased/Features-20240911-135404.yaml b/.changes/unreleased/Features-20240911-135404.yaml new file mode 100644 index 00000000..5ff9630d --- /dev/null +++ b/.changes/unreleased/Features-20240911-135404.yaml @@ -0,0 +1,6 @@ +kind: Features +body: Default microbatch strategy implementation and base tests +time: 2024-09-11T13:54:04.231977-04:00 +custom: + Author: michelleark + Issue: "302" diff --git a/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py b/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py new file mode 100644 index 00000000..dae91c97 --- /dev/null +++ b/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py @@ -0,0 +1,91 @@ +import os +from pprint import pformat +from unittest import mock + +import pytest +from freezegun import freeze_time + +from dbt.tests.util import relation_from_name, run_dbt + +_input_model_sql = """ +{{ config(materialized='table', event_time='event_time') }} +select 1 as id, TIMESTAMP '2020-01-01 00:00:00-0' as event_time +union all +select 2 as id, TIMESTAMP '2020-01-02 00:00:00-0' as event_time +union all +select 3 as id, TIMESTAMP '2020-01-03 00:00:00-0' as event_time +""" + +_microbatch_model_sql = """ +{{ config(materialized='incremental', incremental_strategy='microbatch', unique_key='id', event_time='event_time', batch_size='day') }} +select * from {{ ref('input_model') }} +""" + + +class BaseMicrobatch: + @pytest.fixture(scope="class") + def microbatch_model_sql(self) -> str: + """ + This is the SQL that defines the microbatch model, including any {{ config(..) }} + """ + return _microbatch_model_sql + + @pytest.fixture(scope="class") + def input_model_sql(self) -> str: + """ + This is the SQL that defines the input model to the microbatch model, including any {{ config(..) }}. + event_time is a required configuration of this input + """ + return _input_model_sql + + @pytest.fixture(scope="class") + def insert_two_rows_sql(self, project) -> str: + test_schema_relation = project.adapter.Relation.create( + database=project.database, schema=project.test_schema + ) + return f"insert into {test_schema_relation}.input_model (id, event_time) values (4, TIMESTAMP '2020-01-04 00:00:00-0'), (5, TIMESTAMP '2020-01-05 00:00:00-0')" + + @pytest.fixture(scope="class") + def models(self, microbatch_model_sql, input_model_sql): + return { + "input_model.sql": input_model_sql, + "microbatch_model.sql": microbatch_model_sql, + } + + def assert_row_count(self, project, relation_name: str, expected_row_count: int): + relation = relation_from_name(project.adapter, relation_name) + result = project.run_sql(f"select * from {relation}", fetch="all") + + assert len(result) == expected_row_count, f"{relation_name}:{pformat(result)}" + + @mock.patch.dict(os.environ, {"DBT_EXPERIMENTAL_MICROBATCH": "True"}) + def test_run_with_event_time(self, project, insert_two_rows_sql): + # initial run -- backfills all data + with freeze_time("2020-01-03 13:57:00"): + run_dbt(["run"]) + self.assert_row_count(project, "microbatch_model", 3) + + # our partition grain is "day" so running the same day without new data should produce the same results + with freeze_time("2020-01-03 14:57:00"): + run_dbt(["run"]) + self.assert_row_count(project, "microbatch_model", 3) + + # add next two days of data + project.run_sql(insert_two_rows_sql) + + self.assert_row_count(project, "input_model", 5) + + # re-run without changing current time => no insert + with freeze_time("2020-01-03 14:57:00"): + run_dbt(["run", "--select", "microbatch_model"]) + self.assert_row_count(project, "microbatch_model", 3) + + # re-run by advancing time by one day changing current time => insert 1 row + with freeze_time("2020-01-04 14:57:00"): + run_dbt(["run", "--select", "microbatch_model"]) + self.assert_row_count(project, "microbatch_model", 4) + + # re-run by advancing time by one more day changing current time => insert 1 more row + with freeze_time("2020-01-05 14:57:00"): + run_dbt(["run", "--select", "microbatch_model"]) + self.assert_row_count(project, "microbatch_model", 5) diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index e3a0f015..50e7f5d8 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.5.0" +version = "1.6.0a" diff --git a/dbt/adapters/base/impl.py b/dbt/adapters/base/impl.py index 541c9846..7d776b91 100644 --- a/dbt/adapters/base/impl.py +++ b/dbt/adapters/base/impl.py @@ -1572,7 +1572,7 @@ def valid_incremental_strategies(self): return ["append"] def builtin_incremental_strategies(self): - return ["append", "delete+insert", "merge", "insert_overwrite"] + return ["append", "delete+insert", "merge", "insert_overwrite", "microbatch"] @available.parse_none def get_incremental_strategy_macro(self, model_context, strategy: str): diff --git a/dbt/adapters/base/relation.py b/dbt/adapters/base/relation.py index 0053265f..80dbd34b 100644 --- a/dbt/adapters/base/relation.py +++ b/dbt/adapters/base/relation.py @@ -37,8 +37,8 @@ SerializableIterable = Union[Tuple, FrozenSet] -@dataclass(frozen=True, eq=False, repr=False) -class EventTimeFilter(FakeAPIObject, Hashable): +@dataclass +class EventTimeFilter(FakeAPIObject): field_name: str start: Optional[datetime] = None end: Optional[datetime] = None diff --git a/dbt/include/global_project/macros/materializations/models/incremental/strategies.sql b/dbt/include/global_project/macros/materializations/models/incremental/strategies.sql index 72082cca..111d3887 100644 --- a/dbt/include/global_project/macros/materializations/models/incremental/strategies.sql +++ b/dbt/include/global_project/macros/materializations/models/incremental/strategies.sql @@ -66,6 +66,19 @@ {% endmacro %} +{% macro get_incremental_microbatch_sql(arg_dict) %} + + {{ return(adapter.dispatch('get_incremental_microbatch_sql', 'dbt')(arg_dict)) }} + +{% endmacro %} + +{% macro default__get_incremental_microbatch_sql(arg_dict) %} + + {{ exceptions.raise_not_implemented('microbatch materialization strategy not implemented for adapter ' + adapter.type()) }} + +{% endmacro %} + + {% macro get_insert_into_sql(target_relation, temp_relation, dest_columns) %} {%- set dest_cols_csv = get_quoted_csv(dest_columns | map(attribute="name")) -%} From efed8a9164fe1facb0739c4991689a03f68d54c5 Mon Sep 17 00:00:00 2001 From: Michelle Ark Date: Thu, 12 Sep 2024 12:43:34 -0400 Subject: [PATCH 09/25] add freezegun to dbt-tests-adapter dependencies (#305) --- dbt-tests-adapter/pyproject.toml | 1 + 1 file changed, 1 insertion(+) diff --git a/dbt-tests-adapter/pyproject.toml b/dbt-tests-adapter/pyproject.toml index 73bce49e..c9082d43 100644 --- a/dbt-tests-adapter/pyproject.toml +++ b/dbt-tests-adapter/pyproject.toml @@ -31,6 +31,7 @@ dependencies = [ # `dbt-core` takes the packages below as dependencies, so they are unpinned to avoid conflicts "dbt-adapters", "pyyaml", + "freezegun", ] [project.urls] Homepage = "https://github.com/dbt-labs/dbt-adapters" From 97a6687f46def41b26535409aae175704c4ee3af Mon Sep 17 00:00:00 2001 From: Mike Alfare <13974384+mikealfare@users.noreply.github.com> Date: Thu, 12 Sep 2024 15:35:40 -0400 Subject: [PATCH 10/25] Add behavior flags to jinja context (#306) --- dbt/adapters/base/impl.py | 9 +++++---- dbt/adapters/base/meta.py | 19 +++++++++++++++++++ 2 files changed, 24 insertions(+), 4 deletions(-) diff --git a/dbt/adapters/base/impl.py b/dbt/adapters/base/impl.py index 7d776b91..310306ff 100644 --- a/dbt/adapters/base/impl.py +++ b/dbt/adapters/base/impl.py @@ -55,7 +55,7 @@ BaseConnectionManager, Connection, ) -from dbt.adapters.base.meta import AdapterMeta, available +from dbt.adapters.base.meta import AdapterMeta, available, available_property from dbt.adapters.base.relation import ( BaseRelation, ComponentName, @@ -272,7 +272,8 @@ def __init__(self, config, mp_context: SpawnContext) -> None: self.connections = self.ConnectionManager(config, mp_context) self._macro_resolver: Optional[MacroResolverProtocol] = None self._macro_context_generator: Optional[MacroContextGeneratorCallable] = None - self.behavior = [] # this will be updated to include global behavior flags once they exist + # this will be updated to include global behavior flags once they exist + self.behavior = [] # type: ignore ### # Methods to set / access a macro resolver @@ -293,11 +294,11 @@ def set_macro_context_generator( ) -> None: self._macro_context_generator = macro_context_generator - @property + @available_property def behavior(self) -> Behavior: return self._behavior - @behavior.setter + @behavior.setter # type: ignore def behavior(self, flags: List[BehaviorFlag]) -> None: flags.extend(self._behavior_flags) try: diff --git a/dbt/adapters/base/meta.py b/dbt/adapters/base/meta.py index ca7aef9f..e522a056 100644 --- a/dbt/adapters/base/meta.py +++ b/dbt/adapters/base/meta.py @@ -92,6 +92,25 @@ def parse_list(self, func: Callable) -> Callable: available = _Available() +class available_property(property): + """ + This supports making dynamic properties (`@property`) available in the jinja context. + + We use `@available` to make methods available in the jinja context, but this mechanism relies on the method being callable. + Intuitively, we should be able to use both `@available` and `@property` to create a dynamic property that's available in the jinja context. + + Using the `@property` decorator as the inner decorator supplies `@available` with something that is not callable. + Instead of returning the method, `@property` returns the value itself, not the method that is called to create the value. + + Using the `@available` decorator as the inner decorator adds `_is_available_ = True` to the function. + However, when the `@property` decorator executes, it returns a `property` object which does not have the `_is_available_` attribute. + + This decorator solves this problem by simply adding `_is_available_ = True` as an attribute on the `property` built-in. + """ + + _is_available_ = True + + class AdapterMeta(abc.ABCMeta): _available_: FrozenSet[str] _parse_replacements_: Dict[str, Callable] From 66964ae857bec7b7988674412bb8c2def2e6f785 Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Thu, 12 Sep 2024 19:52:57 +0000 Subject: [PATCH 11/25] Bumping version to 1.6.0 and generate changelog --- .changes/1.6.0.md | 5 +++++ .changes/unreleased/Features-20240911-135404.yaml | 6 ------ CHANGELOG.md | 10 ++++++++-- dbt/adapters/__about__.py | 2 +- 4 files changed, 14 insertions(+), 9 deletions(-) create mode 100644 .changes/1.6.0.md delete mode 100644 .changes/unreleased/Features-20240911-135404.yaml diff --git a/.changes/1.6.0.md b/.changes/1.6.0.md new file mode 100644 index 00000000..c109454a --- /dev/null +++ b/.changes/1.6.0.md @@ -0,0 +1,5 @@ +## dbt-adapters 1.6.0 - September 12, 2024 + +### Features + +- Default microbatch strategy implementation and base tests ([#302](https://github.com/dbt-labs/dbt-adapters/issues/302)) diff --git a/.changes/unreleased/Features-20240911-135404.yaml b/.changes/unreleased/Features-20240911-135404.yaml deleted file mode 100644 index 5ff9630d..00000000 --- a/.changes/unreleased/Features-20240911-135404.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Features -body: Default microbatch strategy implementation and base tests -time: 2024-09-11T13:54:04.231977-04:00 -custom: - Author: michelleark - Issue: "302" diff --git a/CHANGELOG.md b/CHANGELOG.md index 7d80911c..41b445ba 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,14 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). +## dbt-adapters 1.6.0 - September 12, 2024 + +### Features + +- Default microbatch strategy implementation and base tests ([#302](https://github.com/dbt-labs/dbt-adapters/issues/302)) + + + ## dbt-adapters 1.5.0 - September 10, 2024 ### Features @@ -17,8 +25,6 @@ and is generated by [Changie](https://github.com/miniscruff/changie). - Update dbt-common pin to >=1.8 ([#299](https://github.com/dbt-labs/dbt-adapters/pull/299)) - - ## dbt-adapters 1.4.1 - August 09, 2024 ### Fixes diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index 50e7f5d8..38ec8ede 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.6.0a" +version = "1.6.0" From 7a6e4e3c62a47c038a2092e9c97c2edbd62576a0 Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Thu, 12 Sep 2024 20:30:05 +0000 Subject: [PATCH 12/25] Bumping version to 1.10.0 and generate changelog --- .changes/1.10.0.md | 1 + CHANGELOG.md | 6 ++++-- dbt-tests-adapter/dbt/tests/__about__.py | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) create mode 100644 .changes/1.10.0.md diff --git a/.changes/1.10.0.md b/.changes/1.10.0.md new file mode 100644 index 00000000..10fc93bc --- /dev/null +++ b/.changes/1.10.0.md @@ -0,0 +1 @@ +## dbt-adapters 1.10.0 - September 12, 2024 diff --git a/CHANGELOG.md b/CHANGELOG.md index 41b445ba..4078984b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,14 +5,16 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). +## dbt-adapters 1.10.0 - September 12, 2024 + + + ## dbt-adapters 1.6.0 - September 12, 2024 ### Features - Default microbatch strategy implementation and base tests ([#302](https://github.com/dbt-labs/dbt-adapters/issues/302)) - - ## dbt-adapters 1.5.0 - September 10, 2024 ### Features diff --git a/dbt-tests-adapter/dbt/tests/__about__.py b/dbt-tests-adapter/dbt/tests/__about__.py index 1b022739..bd1378f4 100644 --- a/dbt-tests-adapter/dbt/tests/__about__.py +++ b/dbt-tests-adapter/dbt/tests/__about__.py @@ -1 +1 @@ -version = "1.9.2" +version = "1.10.0" From 85292d38158bbc977f739568f21a98cf512b3199 Mon Sep 17 00:00:00 2001 From: Michelle Ark Date: Mon, 16 Sep 2024 12:31:26 -0400 Subject: [PATCH 13/25] Temporarily gate microbatch behind env var DBT_EXPERIMENTAL_MICROBATCH (#308) --- dbt/adapters/base/impl.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/dbt/adapters/base/impl.py b/dbt/adapters/base/impl.py index 310306ff..07b65c40 100644 --- a/dbt/adapters/base/impl.py +++ b/dbt/adapters/base/impl.py @@ -22,7 +22,7 @@ Union, TYPE_CHECKING, ) - +import os import pytz from dbt_common.behavior_flags import Behavior, BehaviorFlag from dbt_common.clients.jinja import CallableMacroGenerator @@ -1573,7 +1573,11 @@ def valid_incremental_strategies(self): return ["append"] def builtin_incremental_strategies(self): - return ["append", "delete+insert", "merge", "insert_overwrite", "microbatch"] + builtin_strategies = ["append", "delete+insert", "merge", "insert_overwrite"] + if os.environ.get("DBT_EXPERIMENTAL_MICROBATCH"): + builtin_strategies.append("microbatch") + + return builtin_strategies @available.parse_none def get_incremental_strategy_macro(self, model_context, strategy: str): From 035340f77ea217b3f5fe466d063a1c3ee323fd29 Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Mon, 16 Sep 2024 16:42:54 +0000 Subject: [PATCH 14/25] Bumping version to 1.10.1 and generate changelog --- .changes/1.10.1.md | 1 + CHANGELOG.md | 4 +++- dbt-tests-adapter/dbt/tests/__about__.py | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-) create mode 100644 .changes/1.10.1.md diff --git a/.changes/1.10.1.md b/.changes/1.10.1.md new file mode 100644 index 00000000..01d6fda2 --- /dev/null +++ b/.changes/1.10.1.md @@ -0,0 +1 @@ +## dbt-adapters 1.10.1 - September 16, 2024 diff --git a/CHANGELOG.md b/CHANGELOG.md index 4078984b..3b0d66bd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,9 +5,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). -## dbt-adapters 1.10.0 - September 12, 2024 +## dbt-adapters 1.10.1 - September 16, 2024 + +## dbt-adapters 1.10.0 - September 12, 2024 ## dbt-adapters 1.6.0 - September 12, 2024 diff --git a/dbt-tests-adapter/dbt/tests/__about__.py b/dbt-tests-adapter/dbt/tests/__about__.py index bd1378f4..8c5bf7a0 100644 --- a/dbt-tests-adapter/dbt/tests/__about__.py +++ b/dbt-tests-adapter/dbt/tests/__about__.py @@ -1 +1 @@ -version = "1.10.0" +version = "1.10.1" From 8aaaa86a7218c802a2a61561ab50d51f00b6eb1a Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Mon, 16 Sep 2024 16:52:53 +0000 Subject: [PATCH 15/25] Bumping version to 1.6.1 and generate changelog --- .changes/1.6.1.md | 1 + CHANGELOG.md | 4 +++- dbt/adapters/__about__.py | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-) create mode 100644 .changes/1.6.1.md diff --git a/.changes/1.6.1.md b/.changes/1.6.1.md new file mode 100644 index 00000000..45b41bcd --- /dev/null +++ b/.changes/1.6.1.md @@ -0,0 +1 @@ +## dbt-adapters 1.6.1 - September 16, 2024 diff --git a/CHANGELOG.md b/CHANGELOG.md index 3b0d66bd..58869e8e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,9 +7,11 @@ and is generated by [Changie](https://github.com/miniscruff/changie). ## dbt-adapters 1.10.1 - September 16, 2024 +## dbt-adapters 1.10.0 - September 12, 2024 + +## dbt-adapters 1.6.1 - September 16, 2024 -## dbt-adapters 1.10.0 - September 12, 2024 ## dbt-adapters 1.6.0 - September 12, 2024 diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index 38ec8ede..cead7e89 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.6.0" +version = "1.6.1" From 2ba660f7f5e80607925c95214905ce3ee49aa303 Mon Sep 17 00:00:00 2001 From: Michelle Ark Date: Mon, 16 Sep 2024 17:26:39 -0400 Subject: [PATCH 16/25] use patch_microbatch_end_time (#307) Co-authored-by: Quigley Malcolm Co-authored-by: Mike Alfare <13974384+mikealfare@users.noreply.github.com> Co-authored-by: Quigley Malcolm Co-authored-by: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> --- .../incremental/test_incremental_microbatch.py | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py b/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py index dae91c97..62c21c55 100644 --- a/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py +++ b/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py @@ -3,10 +3,15 @@ from unittest import mock import pytest -from freezegun import freeze_time from dbt.tests.util import relation_from_name, run_dbt +try: + # patch_microbatch_end_time introduced in dbt 1.9.0 + from dbt.tests.util import patch_microbatch_end_time +except ImportError: + from freezegun import freeze_time as patch_microbatch_end_time + _input_model_sql = """ {{ config(materialized='table', event_time='event_time') }} select 1 as id, TIMESTAMP '2020-01-01 00:00:00-0' as event_time @@ -61,12 +66,12 @@ def assert_row_count(self, project, relation_name: str, expected_row_count: int) @mock.patch.dict(os.environ, {"DBT_EXPERIMENTAL_MICROBATCH": "True"}) def test_run_with_event_time(self, project, insert_two_rows_sql): # initial run -- backfills all data - with freeze_time("2020-01-03 13:57:00"): + with patch_microbatch_end_time("2020-01-03 13:57:00"): run_dbt(["run"]) self.assert_row_count(project, "microbatch_model", 3) # our partition grain is "day" so running the same day without new data should produce the same results - with freeze_time("2020-01-03 14:57:00"): + with patch_microbatch_end_time("2020-01-03 14:57:00"): run_dbt(["run"]) self.assert_row_count(project, "microbatch_model", 3) @@ -76,16 +81,16 @@ def test_run_with_event_time(self, project, insert_two_rows_sql): self.assert_row_count(project, "input_model", 5) # re-run without changing current time => no insert - with freeze_time("2020-01-03 14:57:00"): + with patch_microbatch_end_time("2020-01-03 14:57:00"): run_dbt(["run", "--select", "microbatch_model"]) self.assert_row_count(project, "microbatch_model", 3) # re-run by advancing time by one day changing current time => insert 1 row - with freeze_time("2020-01-04 14:57:00"): + with patch_microbatch_end_time("2020-01-04 14:57:00"): run_dbt(["run", "--select", "microbatch_model"]) self.assert_row_count(project, "microbatch_model", 4) # re-run by advancing time by one more day changing current time => insert 1 more row - with freeze_time("2020-01-05 14:57:00"): + with patch_microbatch_end_time("2020-01-05 14:57:00"): run_dbt(["run", "--select", "microbatch_model"]) self.assert_row_count(project, "microbatch_model", 5) From db11adc6e6519c42cccd77c465cab3a942e577c7 Mon Sep 17 00:00:00 2001 From: Gerda Shank Date: Wed, 18 Sep 2024 18:27:23 -0400 Subject: [PATCH 17/25] Snapshot column names (#290) --- .../unreleased/Features-20240903-155618.yaml | 6 +++ dbt/adapters/base/impl.py | 20 ++++------ dbt/adapters/exceptions/compilation.py | 6 ++- .../materializations/snapshots/helpers.sql | 40 +++++++++++-------- .../materializations/snapshots/snapshot.sql | 9 +++-- .../snapshots/snapshot_merge.sql | 8 ++-- .../materializations/snapshots/strategies.sql | 24 ++++++----- 7 files changed, 66 insertions(+), 47 deletions(-) create mode 100644 .changes/unreleased/Features-20240903-155618.yaml diff --git a/.changes/unreleased/Features-20240903-155618.yaml b/.changes/unreleased/Features-20240903-155618.yaml new file mode 100644 index 00000000..fdafceb3 --- /dev/null +++ b/.changes/unreleased/Features-20240903-155618.yaml @@ -0,0 +1,6 @@ +kind: Features +body: Allow configuring of snapshot column names +time: 2024-09-03T15:56:18.211492-04:00 +custom: + Author: gshank + Issue: "289" diff --git a/dbt/adapters/base/impl.py b/dbt/adapters/base/impl.py index 07b65c40..f3788fe3 100644 --- a/dbt/adapters/base/impl.py +++ b/dbt/adapters/base/impl.py @@ -83,7 +83,6 @@ QuoteConfigTypeError, RelationReturnedMultipleResultsError, RenameToNoneAttemptedError, - SnapshotTargetIncompleteError, SnapshotTargetNotSnapshotTableError, UnexpectedNonTimestampError, ) @@ -764,7 +763,9 @@ def get_missing_columns( return [col for (col_name, col) in from_columns.items() if col_name in missing_columns] @available.parse_none - def valid_snapshot_target(self, relation: BaseRelation) -> None: + def valid_snapshot_target( + self, relation: BaseRelation, column_names: Optional[Dict[str, str]] = None + ) -> None: """Ensure that the target relation is valid, by making sure it has the expected columns. @@ -782,21 +783,16 @@ def valid_snapshot_target(self, relation: BaseRelation) -> None: columns = self.get_columns_in_relation(relation) names = set(c.name.lower() for c in columns) - expanded_keys = ("scd_id", "valid_from", "valid_to") - extra = [] missing = [] - for legacy in expanded_keys: - desired = "dbt_" + legacy + # Note: we're not checking dbt_updated_at here because it's not + # always present. + for column in ("dbt_scd_id", "dbt_valid_from", "dbt_valid_to"): + desired = column_names[column] if column_names else column if desired not in names: missing.append(desired) - if legacy in names: - extra.append(legacy) if missing: - if extra: - raise SnapshotTargetIncompleteError(extra, missing) - else: - raise SnapshotTargetNotSnapshotTableError(missing) + raise SnapshotTargetNotSnapshotTableError(missing) @available.parse_none def expand_target_column_types( diff --git a/dbt/adapters/exceptions/compilation.py b/dbt/adapters/exceptions/compilation.py index 46ca5219..d82924e3 100644 --- a/dbt/adapters/exceptions/compilation.py +++ b/dbt/adapters/exceptions/compilation.py @@ -150,8 +150,10 @@ def __init__(self, missing: List): super().__init__(msg=self.get_message()) def get_message(self) -> str: - msg = 'Snapshot target is not a snapshot table (missing "{}")'.format( - '", "'.join(self.missing) + missing = '", "'.join(self.missing) + msg = ( + f'Snapshot target is missing configured columns (missing "{missing}"). ' + "See https://docs.getdbt.com/docs/build/snapshots#snapshot-meta-fields for more information." ) return msg diff --git a/dbt/include/global_project/macros/materializations/snapshots/helpers.sql b/dbt/include/global_project/macros/materializations/snapshots/helpers.sql index 9e8575e9..8d982855 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/helpers.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/helpers.sql @@ -34,7 +34,12 @@ {{ adapter.dispatch('snapshot_staging_table', 'dbt')(strategy, source_sql, target_relation) }} {% endmacro %} +{% macro get_snapshot_table_column_names() %} + {{ return({'dbt_valid_to': 'dbt_valid_to', 'dbt_valid_from': 'dbt_valid_from', 'dbt_scd_id': 'dbt_scd_id', 'dbt_updated_at': 'dbt_updated_at'}) }} +{% endmacro %} + {% macro default__snapshot_staging_table(strategy, source_sql, target_relation) -%} + {% set columns = config.get('snapshot_table_column_names') or get_snapshot_table_column_names() %} with snapshot_query as ( @@ -48,7 +53,7 @@ {{ strategy.unique_key }} as dbt_unique_key from {{ target_relation }} - where dbt_valid_to is null + where {{ columns.dbt_valid_to }} is null ), @@ -57,10 +62,10 @@ select *, {{ strategy.unique_key }} as dbt_unique_key, - {{ strategy.updated_at }} as dbt_updated_at, - {{ strategy.updated_at }} as dbt_valid_from, - nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as dbt_valid_to, - {{ strategy.scd_id }} as dbt_scd_id + {{ strategy.updated_at }} as {{ columns.dbt_updated_at }}, + {{ strategy.updated_at }} as {{ columns.dbt_valid_from }}, + nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as {{ columns.dbt_valid_to }}, + {{ strategy.scd_id }} as {{ columns.dbt_scd_id }} from snapshot_query ), @@ -70,9 +75,9 @@ select *, {{ strategy.unique_key }} as dbt_unique_key, - {{ strategy.updated_at }} as dbt_updated_at, - {{ strategy.updated_at }} as dbt_valid_from, - {{ strategy.updated_at }} as dbt_valid_to + {{ strategy.updated_at }} as {{ columns.dbt_updated_at }}, + {{ strategy.updated_at }} as {{ columns.dbt_valid_from }}, + {{ strategy.updated_at }} as {{ columns.dbt_valid_to }} from snapshot_query ), @@ -111,7 +116,7 @@ select 'update' as dbt_change_type, source_data.*, - snapshotted_data.dbt_scd_id + snapshotted_data.{{ columns.dbt_scd_id }} from updates_source_data as source_data join snapshotted_data on snapshotted_data.dbt_unique_key = source_data.dbt_unique_key @@ -128,10 +133,10 @@ select 'delete' as dbt_change_type, source_data.*, - {{ snapshot_get_time() }} as dbt_valid_from, - {{ snapshot_get_time() }} as dbt_updated_at, - {{ snapshot_get_time() }} as dbt_valid_to, - snapshotted_data.dbt_scd_id + {{ snapshot_get_time() }} as {{ columns.dbt_valid_from }}, + {{ snapshot_get_time() }} as {{ columns.dbt_updated_at }}, + {{ snapshot_get_time() }} as {{ columns.dbt_valid_to }}, + snapshotted_data.{{ columns.dbt_scd_id }} from snapshotted_data left join deletes_source_data as source_data on snapshotted_data.dbt_unique_key = source_data.dbt_unique_key @@ -155,12 +160,13 @@ {% endmacro %} {% macro default__build_snapshot_table(strategy, sql) %} + {% set columns = config.get('snapshot_table_column_names') or get_snapshot_table_column_names() %} select *, - {{ strategy.scd_id }} as dbt_scd_id, - {{ strategy.updated_at }} as dbt_updated_at, - {{ strategy.updated_at }} as dbt_valid_from, - nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as dbt_valid_to + {{ strategy.scd_id }} as {{ columns.dbt_scd_id }}, + {{ strategy.updated_at }} as {{ columns.dbt_updated_at }}, + {{ strategy.updated_at }} as {{ columns.dbt_valid_from }}, + nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as {{ columns.dbt_valid_to }} from ( {{ sql }} ) sbq diff --git a/dbt/include/global_project/macros/materializations/snapshots/snapshot.sql b/dbt/include/global_project/macros/materializations/snapshots/snapshot.sql index 7be94701..5daead4c 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/snapshot.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/snapshot.sql @@ -1,5 +1,4 @@ {% materialization snapshot, default %} - {%- set config = model['config'] -%} {%- set target_table = model.get('alias', model.get('name')) -%} @@ -24,7 +23,9 @@ {{ run_hooks(pre_hooks, inside_transaction=True) }} {% set strategy_macro = strategy_dispatch(strategy_name) %} - {% set strategy = strategy_macro(model, "snapshotted_data", "source_data", config, target_relation_exists) %} + {# The model['config'] parameter below is no longer used, but passing anyway for compatibility #} + {# It was a dictionary of config, instead of the config object from the context #} + {% set strategy = strategy_macro(model, "snapshotted_data", "source_data", model['config'], target_relation_exists) %} {% if not target_relation_exists %} @@ -34,7 +35,9 @@ {% else %} - {{ adapter.valid_snapshot_target(target_relation) }} + {% set columns = config.get("snapshot_table_column_names") or get_snapshot_table_column_names() %} + + {{ adapter.valid_snapshot_target(target_relation, columns) }} {% set build_or_select_sql = snapshot_staging_table(strategy, sql, target_relation) %} {% set staging_table = build_snapshot_staging_table(strategy, sql, target_relation) %} diff --git a/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql b/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql index 56798811..74494ed2 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql @@ -7,15 +7,17 @@ {% macro default__snapshot_merge_sql(target, source, insert_cols) -%} {%- set insert_cols_csv = insert_cols | join(', ') -%} + {%- set columns = config.get("snapshot_table_column_names") or get_snapshot_table_column_names() -%} + merge into {{ target.render() }} as DBT_INTERNAL_DEST using {{ source }} as DBT_INTERNAL_SOURCE - on DBT_INTERNAL_SOURCE.dbt_scd_id = DBT_INTERNAL_DEST.dbt_scd_id + on DBT_INTERNAL_SOURCE.{{ columns.dbt_scd_id }} = DBT_INTERNAL_DEST.{{ columns.dbt_scd_id }} when matched - and DBT_INTERNAL_DEST.dbt_valid_to is null + and DBT_INTERNAL_DEST.{{ columns.dbt_valid_to }} is null and DBT_INTERNAL_SOURCE.dbt_change_type in ('update', 'delete') then update - set dbt_valid_to = DBT_INTERNAL_SOURCE.dbt_valid_to + set {{ columns.dbt_valid_to }} = DBT_INTERNAL_SOURCE.{{ columns.dbt_valid_to }} when not matched and DBT_INTERNAL_SOURCE.dbt_change_type = 'insert' diff --git a/dbt/include/global_project/macros/materializations/snapshots/strategies.sql b/dbt/include/global_project/macros/materializations/snapshots/strategies.sql index d22cc336..8c086182 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/strategies.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/strategies.sql @@ -49,10 +49,13 @@ {# Core strategy definitions #} -{% macro snapshot_timestamp_strategy(node, snapshotted_rel, current_rel, config, target_exists) %} - {% set primary_key = config['unique_key'] %} - {% set updated_at = config['updated_at'] %} - {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes', false) %} + +{% macro snapshot_timestamp_strategy(node, snapshotted_rel, current_rel, model_config, target_exists) %} + {# The model_config parameter is no longer used, but is passed in anyway for compatibility. #} + {% set primary_key = config.get('unique_key') %} + {% set updated_at = config.get('updated_at') %} + {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes') or false %} + {% set columns = config.get("snapshot_table_column_names") or get_snapshot_table_column_names() %} {#/* The snapshot relation might not have an {{ updated_at }} value if the @@ -64,7 +67,7 @@ See https://github.com/dbt-labs/dbt-core/issues/2350 */ #} {% set row_changed_expr -%} - ({{ snapshotted_rel }}.dbt_valid_from < {{ current_rel }}.{{ updated_at }}) + ({{ snapshotted_rel }}.{{ columns.dbt_valid_from }} < {{ current_rel }}.{{ updated_at }}) {%- endset %} {% set scd_id_expr = snapshot_hash_arguments([primary_key, updated_at]) %} @@ -133,11 +136,12 @@ {%- endmacro %} -{% macro snapshot_check_strategy(node, snapshotted_rel, current_rel, config, target_exists) %} - {% set check_cols_config = config['check_cols'] %} - {% set primary_key = config['unique_key'] %} - {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes', false) %} - {% set updated_at = config.get('updated_at', snapshot_get_time()) %} +{% macro snapshot_check_strategy(node, snapshotted_rel, current_rel, model_config, target_exists) %} + {# The model_config parameter is no longer used, but is passed in anyway for compatibility. #} + {% set check_cols_config = config.get('check_cols') %} + {% set primary_key = config.get('unique_key') %} + {% set invalidate_hard_deletes = config.get('invalidate_hard_deletes') or false %} + {% set updated_at = config.get('updated_at') or snapshot_get_time() %} {% set column_added = false %} From a5590b4c2b2a6670ab2adb2847c5c96bfb185bfb Mon Sep 17 00:00:00 2001 From: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> Date: Thu, 19 Sep 2024 08:53:19 -0700 Subject: [PATCH 18/25] update Behavior Flag unit test fixtures (#313) --- tests/unit/test_behavior_flags.py | 36 +++++++++++++++++++++++++------ 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/tests/unit/test_behavior_flags.py b/tests/unit/test_behavior_flags.py index 0ae1a021..7f3abb89 100644 --- a/tests/unit/test_behavior_flags.py +++ b/tests/unit/test_behavior_flags.py @@ -19,12 +19,36 @@ def flags() -> Dict[str, Any]: @pytest.fixture def behavior_flags() -> List[BehaviorFlag]: return [ - {"name": "default_false_user_false_flag", "default": False}, - {"name": "default_false_user_true_flag", "default": False}, - {"name": "default_false_user_skip_flag", "default": False}, - {"name": "default_true_user_false_flag", "default": True}, - {"name": "default_true_user_true_flag", "default": True}, - {"name": "default_true_user_skip_flag", "default": True}, + { + "name": "default_false_user_false_flag", + "default": False, + "docs_url": "https://docs.com", + }, + { + "name": "default_false_user_true_flag", + "default": False, + "description": "This is a false flag.", + }, + { + "name": "default_false_user_skip_flag", + "default": False, + "description": "This is a true flag.", + }, + { + "name": "default_true_user_false_flag", + "default": True, + "description": "This is fake news.", + }, + { + "name": "default_true_user_true_flag", + "default": True, + "docs_url": "https://moar.docs.com", + }, + { + "name": "default_true_user_skip_flag", + "default": True, + "description": "This is a true flag.", + }, ] From d937d86dac43f3b93e0b58d80b4727eca177ccf6 Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Thu, 19 Sep 2024 16:19:24 +0000 Subject: [PATCH 19/25] Bumping version to 1.7.0 and generate changelog --- .changes/1.7.0.md | 5 +++++ .changes/unreleased/Features-20240903-155618.yaml | 6 ------ CHANGELOG.md | 8 +++++++- dbt/adapters/__about__.py | 2 +- 4 files changed, 13 insertions(+), 8 deletions(-) create mode 100644 .changes/1.7.0.md delete mode 100644 .changes/unreleased/Features-20240903-155618.yaml diff --git a/.changes/1.7.0.md b/.changes/1.7.0.md new file mode 100644 index 00000000..efbdc601 --- /dev/null +++ b/.changes/1.7.0.md @@ -0,0 +1,5 @@ +## dbt-adapters 1.7.0 - September 19, 2024 + +### Features + +- Allow configuring of snapshot column names ([#289](https://github.com/dbt-labs/dbt-adapters/issues/289)) diff --git a/.changes/unreleased/Features-20240903-155618.yaml b/.changes/unreleased/Features-20240903-155618.yaml deleted file mode 100644 index fdafceb3..00000000 --- a/.changes/unreleased/Features-20240903-155618.yaml +++ /dev/null @@ -1,6 +0,0 @@ -kind: Features -body: Allow configuring of snapshot column names -time: 2024-09-03T15:56:18.211492-04:00 -custom: - Author: gshank - Issue: "289" diff --git a/CHANGELOG.md b/CHANGELOG.md index 58869e8e..1287c432 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,10 +9,16 @@ and is generated by [Changie](https://github.com/miniscruff/changie). ## dbt-adapters 1.10.0 - September 12, 2024 -## dbt-adapters 1.6.1 - September 16, 2024 +## dbt-adapters 1.7.0 - September 19, 2024 + +### Features +- Allow configuring of snapshot column names ([#289](https://github.com/dbt-labs/dbt-adapters/issues/289)) + +## dbt-adapters 1.6.1 - September 16, 2024 + ## dbt-adapters 1.6.0 - September 12, 2024 ### Features diff --git a/dbt/adapters/__about__.py b/dbt/adapters/__about__.py index cead7e89..a55413d1 100644 --- a/dbt/adapters/__about__.py +++ b/dbt/adapters/__about__.py @@ -1 +1 @@ -version = "1.6.1" +version = "1.7.0" From 1f629de3a630126d3e38b3445d788b4f145e1b55 Mon Sep 17 00:00:00 2001 From: Mike Alfare <13974384+mikealfare@users.noreply.github.com> Date: Fri, 20 Sep 2024 16:21:22 -0400 Subject: [PATCH 20/25] Add pre-commit autoupdate workflow (#296) Co-authored-by: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> --- .github/workflows/precommit-autoupdate.yml | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 .github/workflows/precommit-autoupdate.yml diff --git a/.github/workflows/precommit-autoupdate.yml b/.github/workflows/precommit-autoupdate.yml new file mode 100644 index 00000000..74976c48 --- /dev/null +++ b/.github/workflows/precommit-autoupdate.yml @@ -0,0 +1,22 @@ +name: "Run pre-commit autoupdate" + +on: + schedule: + - cron: "30 1 * * SAT" + workflow_dispatch: + +permissions: + contents: write + +concurrency: + group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.sha }} + cancel-in-progress: true + +jobs: + precommit-autoupdate: + name: "Run pre-commit autoupdate" + uses: dbt-labs/actions/.github/workflows/pre-commit-autoupdate.yml + secrets: + TOKEN: ${{ secrets.FISHTOWN_BOT_PAT }} + SLACK_WEBHOOK_PR_URL: ${{ secrets.SLACK_DEV_ADAPTER_PULL_REQUESTS }} + SLACK_WEBHOOK_ALERTS_URL: ${{ secrets.SLACK_DEV_ADAPTER_ALERTS }} From f37b4cd834b92d20cea5606415d24f7150295aa1 Mon Sep 17 00:00:00 2001 From: Michelle Ark Date: Mon, 23 Sep 2024 22:56:43 +0100 Subject: [PATCH 21/25] Add required 'begin' config for testing microbatch models (#314) --- .changes/unreleased/Under the Hood-20240923-184719.yaml | 7 +++++++ .../adapter/incremental/test_incremental_microbatch.py | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) create mode 100644 .changes/unreleased/Under the Hood-20240923-184719.yaml diff --git a/.changes/unreleased/Under the Hood-20240923-184719.yaml b/.changes/unreleased/Under the Hood-20240923-184719.yaml new file mode 100644 index 00000000..35e66b90 --- /dev/null +++ b/.changes/unreleased/Under the Hood-20240923-184719.yaml @@ -0,0 +1,7 @@ +kind: Under the Hood +body: 'dbt-tests-adapters: Add required begin to microbatch model config to BaseMicrobatch + test' +time: 2024-09-23T18:47:19.171618+01:00 +custom: + Author: michelleark + Issue: "315" diff --git a/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py b/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py index 62c21c55..5bbabbe1 100644 --- a/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py +++ b/dbt-tests-adapter/dbt/tests/adapter/incremental/test_incremental_microbatch.py @@ -22,7 +22,7 @@ """ _microbatch_model_sql = """ -{{ config(materialized='incremental', incremental_strategy='microbatch', unique_key='id', event_time='event_time', batch_size='day') }} +{{ config(materialized='incremental', incremental_strategy='microbatch', unique_key='id', event_time='event_time', batch_size='day', begin=modules.datetime.datetime(2020, 1, 1, 0, 0, 0)) }} select * from {{ ref('input_model') }} """ From b414668cd046ce9b68c03b68ca7fc94f190b4e99 Mon Sep 17 00:00:00 2001 From: Colin Rogers <111200756+colin-rogers-dbt@users.noreply.github.com> Date: Thu, 26 Sep 2024 16:49:55 -0700 Subject: [PATCH 22/25] update dbt-common dependency to 1.10 (#318) --- pyproject.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 0bd36d4f..76ca3dee 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -24,7 +24,7 @@ classifiers = [ "Programming Language :: Python :: 3.12", ] dependencies = [ - "dbt-common>=1.8,<2.0", + "dbt-common>=1.10,<2.0", "pytz>=2015.7", # installed via dbt-common but used directly "agate>=1.0,<2.0", From 96e3a341ccc286ee51deaaced8066a32672559ed Mon Sep 17 00:00:00 2001 From: Kshitij Aranke Date: Tue, 1 Oct 2024 18:42:32 +0100 Subject: [PATCH 23/25] Add DbtDatabaseError to test_missing_column_pre_hook (#324) --- .../dbt/tests/adapter/hooks/test_run_hooks.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/dbt-tests-adapter/dbt/tests/adapter/hooks/test_run_hooks.py b/dbt-tests-adapter/dbt/tests/adapter/hooks/test_run_hooks.py index 89565c70..0136e3f6 100644 --- a/dbt-tests-adapter/dbt/tests/adapter/hooks/test_run_hooks.py +++ b/dbt-tests-adapter/dbt/tests/adapter/hooks/test_run_hooks.py @@ -3,6 +3,7 @@ import pytest +from dbt_common.exceptions import DbtDatabaseError from dbt.tests.adapter.hooks import fixtures from dbt.tests.util import check_table_does_not_exist, run_dbt @@ -11,8 +12,8 @@ class BasePrePostRunHooks: @pytest.fixture(scope="function") def setUp(self, project): project.run_sql_file(project.test_data_dir / Path("seed_run.sql")) - project.run_sql(f"drop table if exists { project.test_schema }.schemas") - project.run_sql(f"drop table if exists { project.test_schema }.db_schemas") + project.run_sql(f"drop table if exists {project.test_schema}.schemas") + project.run_sql(f"drop table if exists {project.test_schema}.db_schemas") os.environ["TERM_TEST"] = "TESTING" @pytest.fixture(scope="class") @@ -158,7 +159,8 @@ def project_config_update(self): } def test_missing_column_pre_hook(self, project): - run_dbt(["run"], expect_pass=False) + with pytest.raises(DbtDatabaseError): + run_dbt(["run"], expect_pass=False) class TestAfterRunHooks(BaseAfterRunHooks): From c78745ee161db17df50581ad0610c53553301de2 Mon Sep 17 00:00:00 2001 From: Github Build Bot Date: Tue, 1 Oct 2024 17:55:18 +0000 Subject: [PATCH 24/25] Bumping version to 1.10.2 and generate changelog --- .changes/1.10.2.md | 5 +++++ .../unreleased/Under the Hood-20240923-184719.yaml | 7 ------- CHANGELOG.md | 10 ++++++++-- dbt-tests-adapter/dbt/tests/__about__.py | 2 +- 4 files changed, 14 insertions(+), 10 deletions(-) create mode 100644 .changes/1.10.2.md delete mode 100644 .changes/unreleased/Under the Hood-20240923-184719.yaml diff --git a/.changes/1.10.2.md b/.changes/1.10.2.md new file mode 100644 index 00000000..09244521 --- /dev/null +++ b/.changes/1.10.2.md @@ -0,0 +1,5 @@ +## dbt-adapters 1.10.2 - October 01, 2024 + +### Under the Hood + +- dbt-tests-adapters: Add required begin to microbatch model config to BaseMicrobatch test ([#315](https://github.com/dbt-labs/dbt-adapters/issues/315)) diff --git a/.changes/unreleased/Under the Hood-20240923-184719.yaml b/.changes/unreleased/Under the Hood-20240923-184719.yaml deleted file mode 100644 index 35e66b90..00000000 --- a/.changes/unreleased/Under the Hood-20240923-184719.yaml +++ /dev/null @@ -1,7 +0,0 @@ -kind: Under the Hood -body: 'dbt-tests-adapters: Add required begin to microbatch model config to BaseMicrobatch - test' -time: 2024-09-23T18:47:19.171618+01:00 -custom: - Author: michelleark - Issue: "315" diff --git a/CHANGELOG.md b/CHANGELOG.md index 1287c432..dfb37ad5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,14 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html), and is generated by [Changie](https://github.com/miniscruff/changie). +## dbt-adapters 1.10.2 - October 01, 2024 + +### Under the Hood + +- dbt-tests-adapters: Add required begin to microbatch model config to BaseMicrobatch test ([#315](https://github.com/dbt-labs/dbt-adapters/issues/315)) + + + ## dbt-adapters 1.10.1 - September 16, 2024 ## dbt-adapters 1.10.0 - September 12, 2024 @@ -15,8 +23,6 @@ and is generated by [Changie](https://github.com/miniscruff/changie). - Allow configuring of snapshot column names ([#289](https://github.com/dbt-labs/dbt-adapters/issues/289)) - - ## dbt-adapters 1.6.1 - September 16, 2024 ## dbt-adapters 1.6.0 - September 12, 2024 diff --git a/dbt-tests-adapter/dbt/tests/__about__.py b/dbt-tests-adapter/dbt/tests/__about__.py index 8c5bf7a0..8c657eec 100644 --- a/dbt-tests-adapter/dbt/tests/__about__.py +++ b/dbt-tests-adapter/dbt/tests/__about__.py @@ -1 +1 @@ -version = "1.10.1" +version = "1.10.2" From 4df6e54b8214da49f60aa0486ede477de55359d9 Mon Sep 17 00:00:00 2001 From: Gerda Shank Date: Thu, 10 Oct 2024 15:17:20 -0400 Subject: [PATCH 25/25] Enable setting current value of dbt_valid_to (#321) --- .../unreleased/Features-20240927-134248.yaml | 6 ++++++ .../materializations/snapshots/helpers.sql | 18 +++++++++++++++--- .../snapshots/snapshot_merge.sql | 7 ++++++- 3 files changed, 27 insertions(+), 4 deletions(-) create mode 100644 .changes/unreleased/Features-20240927-134248.yaml diff --git a/.changes/unreleased/Features-20240927-134248.yaml b/.changes/unreleased/Features-20240927-134248.yaml new file mode 100644 index 00000000..0b456244 --- /dev/null +++ b/.changes/unreleased/Features-20240927-134248.yaml @@ -0,0 +1,6 @@ +kind: Features +body: Enable setting current value of dbt_valid_to +time: 2024-09-27T13:42:48.654556-04:00 +custom: + Author: gshank + Issue: "320" diff --git a/dbt/include/global_project/macros/materializations/snapshots/helpers.sql b/dbt/include/global_project/macros/materializations/snapshots/helpers.sql index 8d982855..52fdb9bf 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/helpers.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/helpers.sql @@ -53,7 +53,13 @@ {{ strategy.unique_key }} as dbt_unique_key from {{ target_relation }} - where {{ columns.dbt_valid_to }} is null + where + {% if config.get('dbt_valid_to_current') %} + {# Check for either dbt_valid_to_current OR null, in order to correctly update records with nulls #} + ( {{ columns.dbt_valid_to }} = {{ config.get('dbt_valid_to_current') }} or {{ columns.dbt_valid_to }} is null) + {% else %} + {{ columns.dbt_valid_to }} is null + {% endif %} ), @@ -64,7 +70,7 @@ {{ strategy.unique_key }} as dbt_unique_key, {{ strategy.updated_at }} as {{ columns.dbt_updated_at }}, {{ strategy.updated_at }} as {{ columns.dbt_valid_from }}, - nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as {{ columns.dbt_valid_to }}, + {{ get_dbt_valid_to_current(strategy, columns) }}, {{ strategy.scd_id }} as {{ columns.dbt_scd_id }} from snapshot_query @@ -166,7 +172,7 @@ {{ strategy.scd_id }} as {{ columns.dbt_scd_id }}, {{ strategy.updated_at }} as {{ columns.dbt_updated_at }}, {{ strategy.updated_at }} as {{ columns.dbt_valid_from }}, - nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}) as {{ columns.dbt_valid_to }} + {{ get_dbt_valid_to_current(strategy, columns) }} from ( {{ sql }} ) sbq @@ -210,3 +216,9 @@ {% endif %} {% endif %} {% endmacro %} + +{% macro get_dbt_valid_to_current(strategy, columns) %} + {% set dbt_valid_to_current = config.get('dbt_valid_to_current') or "null" %} + coalesce(nullif({{ strategy.updated_at }}, {{ strategy.updated_at }}), {{dbt_valid_to_current}}) + as {{ columns.dbt_valid_to }} +{% endmacro %} diff --git a/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql b/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql index 74494ed2..cf787e4f 100644 --- a/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql +++ b/dbt/include/global_project/macros/materializations/snapshots/snapshot_merge.sql @@ -14,7 +14,12 @@ on DBT_INTERNAL_SOURCE.{{ columns.dbt_scd_id }} = DBT_INTERNAL_DEST.{{ columns.dbt_scd_id }} when matched - and DBT_INTERNAL_DEST.{{ columns.dbt_valid_to }} is null + {% if config.get("dbt_valid_to_current") %} + and (DBT_INTERNAL_DEST.{{ columns.dbt_valid_to }} = {{ config.get('dbt_valid_to_current') }} or + DBT_INTERNAL_DEST.{{ columns.dbt_valid_to }} is null) + {% else %} + and DBT_INTERNAL_DEST.{{ columns.dbt_valid_to }} is null + {% endif %} and DBT_INTERNAL_SOURCE.dbt_change_type in ('update', 'delete') then update set {{ columns.dbt_valid_to }} = DBT_INTERNAL_SOURCE.{{ columns.dbt_valid_to }}