interloper-google-cloud 0.110.2__tar.gz → 0.112.0__tar.gz

{interloper_google_cloud-0.110.2 → interloper_google_cloud-0.112.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: interloper-google-cloud
-Version: 0.110.2
+Version: 0.112.0
 Summary: Interloper Google Cloud integration: BigQuery, Cloud Storage and Google Sheets destinations
 Author: Guillaume Onfroy
 Author-email: Guillaume Onfroy <guillaume@digitlcloud.com>

{interloper_google_cloud-0.110.2 → interloper_google_cloud-0.112.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "interloper-google-cloud"
-version = "0.110.2"
+version = "0.112.0"
 description = "Interloper Google Cloud integration: BigQuery, Cloud Storage and Google Sheets destinations"
 readme = "README.md"
 requires-python = ">=3.10"

{interloper_google_cloud-0.110.2 → interloper_google_cloud-0.112.0}/pyproject.toml.orig

@@ -3,7 +3,7 @@
 # ###############
 [project]
 name = "interloper-google-cloud"
-version = "0.110.2"
+version = "0.112.0"
 description = "Interloper Google Cloud integration: BigQuery, Cloud Storage and Google Sheets destinations"
 readme = "README.md"
 authors = [{ name = "Guillaume Onfroy", email = "guillaume@digitlcloud.com" }]

{interloper_google_cloud-0.110.2 → interloper_google_cloud-0.112.0}/src/interloper_google_cloud/bigquery/destination.py

@@ -8,14 +8,14 @@ import json
 import warnings
 from collections.abc import Sequence
 from functools import cached_property
-from typing import Any
+from typing import Any, ClassVar
 
 import google.auth
 import pandas as pd
 from google.cloud import bigquery
 from google.cloud.exceptions import Conflict, NotFound
 from google.oauth2 import service_account
-from interloper.destination import IOContext, destination
+from interloper.destination import Destination, IOContext, destination
 from interloper.destination.database import DatabaseDestination, PartitionFilter
 from interloper.errors import ConfigError, DataNotFoundError
 from interloper.partitioning import PartitionConfig, TimeGranularity, TimePartitionConfig
@@ -35,6 +35,8 @@ from interloper_google_cloud.connection import GoogleCloudConnection
 class BigQueryDestination(DatabaseDestination):
     """BigQuery destination."""
 
+    dialect: ClassVar[str | None] = "bigquery"
+
     connection: GoogleCloudConnection
 
     project: str = FetchField(
@@ -108,10 +110,9 @@ class BigQueryDestination(DatabaseDestination):
             dataset: The BigQuery dataset, or ``None`` for the destination's default.
 
         Returns:
-            ``project.dataset.table`` string.
+            ``project.dataset.table`` string, as the API wants it.
         """
-        ds = self._resolve_dataset(dataset)
-        return f"{self.project}.{ds}.{table}"
+        return ".".join(self.table_parts(table, dataset))
 
     def _get_table(self, table: str, dataset: str | None) -> bigquery.Table | None:
         """Fetch a BigQuery table.
@@ -219,6 +220,63 @@ class BigQueryDestination(DatabaseDestination):
             except Conflict:
                 pass  # Created by a concurrent asset — already exists
 
+    # -- Views -----------------------------------------------------------------
+
+    def table_parts(self, table: str, dataset: str | None) -> tuple[str, str, str]:
+        """The project, dataset and table a reference names.
+
+        Args:
+            table: Table name.
+            dataset: The BigQuery dataset, or ``None`` for the destination's default.
+
+        Returns:
+            ``(project, dataset, table)``.
+        """
+        return (self.project, self._resolve_dataset(dataset), table)
+
+    def qualified_name(self, table: str, dataset: str | None) -> str:
+        """The whole path in one pair of backticks, the form a wildcard table needs.
+
+        Args:
+            table: Table name.
+            dataset: The BigQuery dataset, or ``None`` for the destination's default.
+
+        Returns:
+            The path ``project.dataset.table`` wrapped in backticks.
+        """
+        return f"`{self._table_ref(table, dataset)}`"
+
+    def replace_view(self, table: str, dataset: str | None, sql: str) -> None:
+        """Create or replace a view, creating its dataset first.
+
+        A view whose query is already ``sql`` is left alone: a backfill
+        recreates every view once per partition, and BigQuery rate-limits
+        metadata updates.
+
+        Args:
+            table: The view's name.
+            dataset: The BigQuery dataset, or ``None`` for the destination's default.
+            sql: The view's query.
+        """
+        existing = self._get_table(table, dataset)
+        if existing is not None and existing.view_query == sql:
+            return
+        self._ensure_dataset(dataset)
+        self.client.query(f"CREATE OR REPLACE VIEW {self.qualified_name(table, dataset)} AS {sql}").result()
+
+    def reaches(self, other: Destination) -> bool:
+        """Whether *other* is a BigQuery destination in the same location.
+
+        BigQuery queries across projects but not across locations.
+
+        Args:
+            other: The destination holding an upstream's table.
+
+        Returns:
+            True for BigQuery in the same location.
+        """
+        return isinstance(other, BigQueryDestination) and other.location == self.location
+
     # -- DatabaseDestination hooks ---------------------------------------------
 
     def insert(self, table: str, dataset: str | None, data: Any, context: IOContext) -> None:
@@ -466,8 +524,7 @@ def _time_partitioning(
                     + (" (hourly partitioning needs DATETIME or TIMESTAMP)" if field.field_type == "DATE" else "")
                 )
                 warnings.warn(
-                    f"Partition column '{config.column}' is {reason}; "
-                    "the BigQuery table will not be time-partitioned.",
+                    f"Partition column '{config.column}' is {reason}; the BigQuery table will not be time-partitioned.",
                     UserWarning,
                     stacklevel=2,
                 )
@@ -577,8 +634,10 @@ def _partition_param(
             value = datetime.datetime.fromisoformat(value)
         except ValueError:
             pass
-    if param_type in ("TIMESTAMP", "DATETIME") and isinstance(value, datetime.date) and not isinstance(
-        value, datetime.datetime
+    if (
+        param_type in ("TIMESTAMP", "DATETIME")
+        and isinstance(value, datetime.date)
+        and not isinstance(value, datetime.datetime)
     ):
         # A date bound against a datetime-typed column: promote to midnight so
         # the client serializes it in the parameter's declared type.
@@ -602,4 +661,3 @@ def _iso_string(value: Any) -> str:
         The ISO rendering of *value*.
     """
     return value.isoformat() if isinstance(value, (datetime.date, datetime.datetime)) else str(value)
-