Merge branch 'main' into pr/290

Author: rich-iannone

Makefile

@@ -12,6 +12,19 @@ test:
 		--doctest-modules pointblank \
 		--durations 10
 
+.PHONY: test-core
+test-core: ## Run core libraries only; useful for local CI
+	@SKIP_PYSPARK_TESTS=1 \
+		SKIP_SQLITE_TESTS=1 \
+		SKIP_PARQUET_TESTS=1 \
+		uv run pytest \
+		--cov=pointblank \
+		--cov-report=term-missing \
+		--randomly-seed 123 \
+		-n auto \
+		--durations=10
+
+
 test-update:
 	pytest --snapshot-update
 

docs/user-guide/schema-validation.qmd

@@ -377,14 +377,6 @@ validation.get_step_report(i=1)
 
 ## Common Schema Validation Patterns
 
-This section explores common patterns for applying schema validation to different scenarios. Each
-pattern addresses specific validation needs you might encounter when working with real-world data.
-We'll examine the step reports for these validations since they provide more detailed information
-about what was checked and how the validation performed, offering an intuitive way to understand
-the results beyond simple pass/fail indicators.
-
-## Common Schema Validation Patterns
-
 This section explores common patterns for applying schema validation to different scenarios. Each
 pattern addresses specific validation needs you might encounter when working with real-world data.
 We'll examine the step reports (`~~Validate.get_step_report()`) for these validations since they

tests/test_validate.py

@@ -75,6 +75,15 @@ class StrEnum(str, Enum):
 except ImportError:
     PYSPARK_AVAILABLE = False
 
+## If we specifically disable tests in pytest set the availability to False
+if os.environ.get("SKIP_PYSPARK_TESTS", "").lower() in ("true", "1", "yes"):
+    PYSPARK_AVAILABLE = False
+SQLITE_AVAILABLE = True
+if os.environ.get("SKIP_SQLITE_TESTS", "").lower() in ("true", "1", "yes"):
+    SQLITE_AVAILABLE = False
+PARQUET_AVAILABLE = True
+if os.environ.get("SKIP_PARQUET_TESTS", "").lower() in ("true", "1", "yes"):
+    PARQUET_AVAILABLE = False
 
 from great_tables import vals
 import great_tables as GT
@@ -180,12 +189,15 @@ def get_spark_session():
 TBL_LIST = [
     "tbl_pd",
     "tbl_pl",
-    "tbl_parquet",
     "tbl_duckdb",
-    "tbl_sqlite",
 ]
 
-# Add PySpark to lists if available
+if PARQUET_AVAILABLE:
+    TBL_LIST.append("tbl_parquet")
+
+if SQLITE_AVAILABLE:
+    TBL_LIST.append("tbl_sqlite")
+
 if PYSPARK_AVAILABLE:
     TBL_LIST.append("tbl_pyspark")