Hard coded env vars for test environment and fixed warehouse clash wi…

…th existing tests in e2e.

src/matchbox/client/helpers/selector.py

@@ -30,7 +30,7 @@ def select(
 
     Args:
         selection: Full source names and optionally a subset of columns to select
-        engine: the engine to connect to the data warehouse hosting the source.
+        engine: The engine to connect to the data warehouse hosting the source.
             If not provided, will use a connection string from the
             `MB__CLIENT__DEFAULT_WAREHOUSE` environment variable.
         non_indexed: Whether you intend to select non-indexed columns. Will raise a
@@ -101,20 +101,20 @@ def query(
     """Runs queries against the selected backend.
 
     Args:
-        selectors: each selector is the output of `select()`
+        selectors: Each selector is the output of `select()`.
             This allows querying sources coming from different engines
-        resolution_name (optional): the name of the resolution point to query
+        resolution_name (optional): The name of the resolution point to query
             If not set:
 
             * If querying a single source, it will use the source resolution
             * If querying 2 or more sources, it will look for a default resolution
-        return_type: the form to return data in, one of "pandas" or "arrow"
+        return_type: The form to return data in, one of "pandas" or "arrow"
             Defaults to pandas for ease of use
-        threshold (optional): the threshold to use for creating clusters
+        threshold (optional): The threshold to use for creating clusters
             If None, uses the resolutions' default threshold
             If an integer, uses that threshold for the specified resolution, and the
             resolution's cached thresholds for its ancestors
-        limit (optional): the number to use in a limit clause. Useful for testing
+        limit (optional): The number to use in a limit clause. Useful for testing
 
     Returns:
         Data in the requested return type
@@ -214,13 +214,13 @@ def match(
     """Matches IDs against the selected backend.
 
     Args:
-        targets: each target is the output of `select()`
+        targets: Each target is the output of `select()`.
             This allows matching against sources coming from different engines
         source: The output of using `select()` on a single source.
         source_pk: The primary key value to match from the source.
-        resolution_name (optional): the resolution name to use for filtering results.
+        resolution_name (optional): The resolution name to use for filtering results.
             If not set, it will look for a default resolution.
-        threshold (optional): the threshold to use for creating clusters
+        threshold (optional): The threshold to use for creating clusters.
             If None, uses the resolutions' default threshold
             If an integer, uses that threshold for the specified resolution, and the
             resolution's cached thresholds for its ancestors

test/e2e/test_e2e.py

@@ -67,7 +67,7 @@ def setup_environment(self, matchbox_client: Client, warehouse_engine: Engine):
         # Create source configurations that match our test fixtures
         source_configs = (
             SourceConfig(
-                full_name="test.crn",
+                full_name="e2e.crn",
                 engine=warehouse_engine,
                 features=(
                     features["company_name"].add_variations(
@@ -82,7 +82,7 @@ def setup_environment(self, matchbox_client: Client, warehouse_engine: Engine):
                 repetition=0,  # No duplicates within the variations
             ),
             SourceConfig(
-                full_name="test.duns",
+                full_name="e2e.duns",
                 engine=warehouse_engine,
                 features=(
                     features["company_name"],
@@ -92,7 +92,7 @@ def setup_environment(self, matchbox_client: Client, warehouse_engine: Engine):
                 repetition=0,
             ),
             SourceConfig(
-                full_name="test.cdms",
+                full_name="e2e.cdms",
                 engine=warehouse_engine,
                 features=(
                     features["crn"],
@@ -109,6 +109,12 @@ def setup_environment(self, matchbox_client: Client, warehouse_engine: Engine):
             seed=42,  # For reproducibility
         )
 
+        # Use a separate schema to avoid conflict with legacy test data
+        # TODO: Remove once legacy tests are refactored
+        with warehouse_engine.connect() as conn:
+            conn.execute(text("create schema e2e;"))
+            conn.commit()
+
         # Setup code - Create tables in warehouse
         for source_name, source_testkit in self.linked_testkit.sources.items():
             # Use pandas to write the data to the warehouse
@@ -266,13 +272,13 @@ def _clean_company_name(df: DataFrame, prefix: str) -> DataFrame:
         # Define linking pairs based on common fields
         linking_pairs = [
             (
-                self.linked_testkit.sources["test.crn"],
-                self.linked_testkit.sources["test.duns"],
+                self.linked_testkit.sources["e2e.crn"],
+                self.linked_testkit.sources["e2e.duns"],
                 "company_name",
             ),  # CRN-DUNS via company_name
             (
-                self.linked_testkit.sources["test.crn"],
-                self.linked_testkit.sources["test.cdms"],
+                self.linked_testkit.sources["e2e.crn"],
+                self.linked_testkit.sources["e2e.cdms"],
                 "crn",
             ),  # CRN-CDMS via crn
         ]
@@ -375,9 +381,9 @@ def _clean_company_name(df: DataFrame, prefix: str) -> DataFrame:
 
         # === FINAL LINKING PHASE ===
         # Now link the first linked pair (crn-duns) with the third source (cdms)
-        crn_source = "test.crn"
-        duns_source = "test.duns"
-        cdms_source = "test.cdms"
+        crn_source = "e2e.crn"
+        duns_source = "e2e.duns"
+        cdms_source = "e2e.cdms"
         first_pair = (crn_source, duns_source)
 
         # Get prefixes for column names
@@ -469,9 +475,9 @@ def _clean_company_name(df: DataFrame, prefix: str) -> DataFrame:
 
         # === FINAL VERIFICATION PHASE ===
         # Query the final linked data with specific columns
-        crn_source = "test.crn"
-        duns_source = "test.duns"
-        cdms_source = "test.cdms"
+        crn_source = "e2e.crn"
+        duns_source = "e2e.duns"
+        cdms_source = "e2e.cdms"
 
         # Get necessary columns from each source
         final_df = query(

test/fixtures/db.py

@@ -15,7 +15,6 @@
 from matchbox import index, make_model
 from matchbox.client._handler import create_client
 from matchbox.client._settings import ClientSettings
-from matchbox.client._settings import settings as client_settings
 from matchbox.common.sources import Source, SourceAddress
 from matchbox.server.base import MatchboxDatastoreSettings, MatchboxDBAdapter
 from matchbox.server.postgresql import MatchboxPostgres, MatchboxPostgresSettings
@@ -396,15 +395,19 @@ def s3(aws_credentials: None) -> Generator[S3Client, None, None]:
 def matchbox_api() -> Generator[MockRouter, None, None]:
     """Client for the mocked Matchbox API."""
     with respx.mock(
-        base_url=client_settings.api_root, assert_all_called=True
+        base_url="http://localhost:8000", assert_all_called=True
     ) as respx_mock:
         yield respx_mock
 
 
 @pytest.fixture(scope="session")
 def matchbox_client_settings() -> ClientSettings:
     """Client settings for the Matchbox API running in Docker."""
-    return client_settings
+    return ClientSettings(
+        api_root="http://localhost:8000",
+        timeout=10,
+        retry_delay=2,
+    )
 
 
 @pytest.fixture(scope="session")