tablevalidator-databricks 0.1.2__tar.gz → 0.1.3__tar.gz

{tablevalidator_databricks-0.1.2 → tablevalidator_databricks-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablevalidator-databricks
-Version: 0.1.2
+Version: 0.1.3
 Summary: Generates a widget-driven Databricks notebook UI on top of the table-validator package - no code required to run a comparison.
 License: MIT
 Requires-Python: >=3.9
@@ -45,12 +45,12 @@ Writes `./TableValidator.py` - a ready-to-use Databricks notebook. Options:
 tablevalidator-databricks init --output MyValidation.py --mode full
 ```
 
-- `--mode basic` - only the check-group multiselect and table pickers.
+- `--mode basic` - only the check-group Yes/No dropdowns and table pickers.
 - `--mode full` (default) - also shows optional filter widgets (only/
-  ignore columns, row filter, primary key).
-- `--mode schema` - same widgets as `basic`; intended for a lightweight
-  schema-shape-only comparison (just deselect Column/Row in the checks
-  multiselect after opening the notebook).
+  ignore columns, row filter, primary key). Every check defaults to "Yes".
+- `--mode schema` - same widgets as `basic`, but Column/Row default to
+  "No" - a lightweight schema-shape-only comparison out of the box (still
+  changeable per-run).
 
 Then, in your Databricks workspace: **Workspace -> Import**, format
 "Source", and select the generated file. Databricks recognizes the
@@ -63,7 +63,7 @@ markers and opens it as a real notebook.
 2. Queries Unity Catalog (`SHOW CATALOGS` / `SHOW SCHEMAS IN ...` /
    `SHOW TABLES IN ...` via the notebook's own ambient Spark session) to
    populate Source/Target Catalog, Schema, and Table dropdowns.
-3. Shows a "Validation Checks" multiselect (Catalog & Schema / Column /
+3. Shows a Yes/No dropdown per check group (Catalog & Schema / Column /
    Row - the three independently-selectable check groups the engine
    actually supports) plus, in `full` mode, optional text widgets for
    column filtering, a row filter, and a primary key.

{tablevalidator_databricks-0.1.2 → tablevalidator_databricks-0.1.3}/README.md

@@ -31,12 +31,12 @@ Writes `./TableValidator.py` - a ready-to-use Databricks notebook. Options:
 tablevalidator-databricks init --output MyValidation.py --mode full
 ```
 
-- `--mode basic` - only the check-group multiselect and table pickers.
+- `--mode basic` - only the check-group Yes/No dropdowns and table pickers.
 - `--mode full` (default) - also shows optional filter widgets (only/
-  ignore columns, row filter, primary key).
-- `--mode schema` - same widgets as `basic`; intended for a lightweight
-  schema-shape-only comparison (just deselect Column/Row in the checks
-  multiselect after opening the notebook).
+  ignore columns, row filter, primary key). Every check defaults to "Yes".
+- `--mode schema` - same widgets as `basic`, but Column/Row default to
+  "No" - a lightweight schema-shape-only comparison out of the box (still
+  changeable per-run).
 
 Then, in your Databricks workspace: **Workspace -> Import**, format
 "Source", and select the generated file. Databricks recognizes the
@@ -49,7 +49,7 @@ markers and opens it as a real notebook.
 2. Queries Unity Catalog (`SHOW CATALOGS` / `SHOW SCHEMAS IN ...` /
    `SHOW TABLES IN ...` via the notebook's own ambient Spark session) to
    populate Source/Target Catalog, Schema, and Table dropdowns.
-3. Shows a "Validation Checks" multiselect (Catalog & Schema / Column /
+3. Shows a Yes/No dropdown per check group (Catalog & Schema / Column /
    Row - the three independently-selectable check groups the engine
    actually supports) plus, in `full` mode, optional text widgets for
    column filtering, a row filter, and a primary key.

{tablevalidator_databricks-0.1.2 → tablevalidator_databricks-0.1.3}/tablevalidator_databricks/templates/widget_notebook.py.tmpl

@@ -180,18 +180,20 @@ print(
 
 # COMMAND ----------
 
-_ALL_CHECKS = ["Catalog & Schema", "Column", "Row"]
-# dbutils.widgets.multiselect's default value must itself be one of the
-# combinations Databricks is willing to accept - in practice this means
-# "all choices, comma-joined in the declared order" is the only default
-# guaranteed to work across Databricks runtime versions (a narrower
-# default, e.g. just "Catalog & Schema", was observed to fail with
-# "DefaultValueNotInChoicesList: Selection sequence must include ..." on
-# some runtimes). --mode schema still gets its narrower intent honored -
-# see the checks-selection cell below, which treats an EMPTY selection as
-# "run everything" and a real narrowing as an explicit choice; this
-# widget just always starts fully selected regardless of --mode.
-dbutils.widgets.multiselect("checks", ",".join(_ALL_CHECKS), _ALL_CHECKS, "Validation Checks")
+# One Yes/No dropdown per check group, instead of a single multiselect -
+# dbutils.widgets.multiselect enforces an internal "selection sequence"
+# validation against its own default that was observed to reject even a
+# same-length, same-items default on some Databricks runtimes/existing-
+# widget states (DefaultValueNotInChoicesList), with no reliable
+# workaround. Three independent dropdowns have no such cross-widget
+# validation and are the more robust primitive for this.
+_YES_NO = ["Yes", "No"]
+_schema_default = "Yes"
+_column_default = "No" if MODE == "schema" else "Yes"
+_row_default = "No" if MODE == "schema" else "Yes"
+dbutils.widgets.dropdown("check_catalog_schema", _schema_default, _YES_NO, "Run Catalog & Schema checks?")
+dbutils.widgets.dropdown("check_column", _column_default, _YES_NO, "Run Column checks?")
+dbutils.widgets.dropdown("check_row", _row_default, _YES_NO, "Run Row checks?")
 
 if SHOW_OPTIONAL_WIDGETS:
     dbutils.widgets.text("only_columns", "", "Only compare these columns (comma-separated, optional)")
@@ -279,15 +281,13 @@ def _source_or_target_string(prefix: str) -> str:
 source = _source_or_target_string("source")
 target = _source_or_target_string("target")
 
-_CHECK_MAP = {
-    "Catalog & Schema": {ValidationType.CATALOG, ValidationType.SCHEMA},
-    "Column": {ValidationType.COLUMN},
-    "Row": {ValidationType.ROW},
-}
-selected_checks = [c for c in dbutils.widgets.get("checks").split(",") if c]
 enabled_validations = set()
-for check in selected_checks:
-    enabled_validations |= _CHECK_MAP.get(check, set())
+if dbutils.widgets.get("check_catalog_schema") == "Yes":
+    enabled_validations |= {ValidationType.CATALOG, ValidationType.SCHEMA}
+if dbutils.widgets.get("check_column") == "Yes":
+    enabled_validations |= {ValidationType.COLUMN}
+if dbutils.widgets.get("check_row") == "Yes":
+    enabled_validations |= {ValidationType.ROW}
 if not enabled_validations:
     enabled_validations = None  # fall back to validate_tables()'s own "run everything" default
 

{tablevalidator_databricks-0.1.2 → tablevalidator_databricks-0.1.3}/tablevalidator_databricks.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tablevalidator-databricks
-Version: 0.1.2
+Version: 0.1.3
 Summary: Generates a widget-driven Databricks notebook UI on top of the table-validator package - no code required to run a comparison.
 License: MIT
 Requires-Python: >=3.9
@@ -45,12 +45,12 @@ Writes `./TableValidator.py` - a ready-to-use Databricks notebook. Options:
 tablevalidator-databricks init --output MyValidation.py --mode full
 ```
 
-- `--mode basic` - only the check-group multiselect and table pickers.
+- `--mode basic` - only the check-group Yes/No dropdowns and table pickers.
 - `--mode full` (default) - also shows optional filter widgets (only/
-  ignore columns, row filter, primary key).
-- `--mode schema` - same widgets as `basic`; intended for a lightweight
-  schema-shape-only comparison (just deselect Column/Row in the checks
-  multiselect after opening the notebook).
+  ignore columns, row filter, primary key). Every check defaults to "Yes".
+- `--mode schema` - same widgets as `basic`, but Column/Row default to
+  "No" - a lightweight schema-shape-only comparison out of the box (still
+  changeable per-run).
 
 Then, in your Databricks workspace: **Workspace -> Import**, format
 "Source", and select the generated file. Databricks recognizes the
@@ -63,7 +63,7 @@ markers and opens it as a real notebook.
 2. Queries Unity Catalog (`SHOW CATALOGS` / `SHOW SCHEMAS IN ...` /
    `SHOW TABLES IN ...` via the notebook's own ambient Spark session) to
    populate Source/Target Catalog, Schema, and Table dropdowns.
-3. Shows a "Validation Checks" multiselect (Catalog & Schema / Column /
+3. Shows a Yes/No dropdown per check group (Catalog & Schema / Column /
    Row - the three independently-selectable check groups the engine
    actually supports) plus, in `full` mode, optional text widgets for
    column filtering, a row filter, and a primary key.

{tablevalidator_databricks-0.1.2 → tablevalidator_databricks-0.1.3}/tablevalidator_databricks.egg-info/scm_version.json

@@ -1,7 +1,7 @@
 {
-  "tag": "0.1.2",
+  "tag": "0.1.3",
   "distance": 0,
-  "node": "gae96a50",
+  "node": "gd05d199",
   "dirty": false,
   "branch": "HEAD",
   "node_date": "2026-09-08"

{tablevalidator_databricks-0.1.2 → tablevalidator_databricks-0.1.3}/tests/test_generated_notebook_execution.py

@@ -15,6 +15,7 @@ from unittest.mock import MagicMock
 
 import pytest
 
+from table_validator.config.schema import ValidationType
 from tablevalidator_databricks.generator.generator import generate_notebook
 
 
@@ -254,42 +255,83 @@ def test_catalog_override_drives_schema_and_table_lookup(notebook_path):
 
 
 # ---------------------------------------------------------------------------
-# --mode schema: regression test for a real production bug. The checks
-# multiselect's default used to be a narrower subset of its choices in
-# --mode schema (just "Catalog & Schema"), which Databricks rejected with
-# DefaultValueNotInChoicesList - _FakeWidgets.multiselect above replicates
-# that exact constraint.
+# Validation-checks selection - three independent Yes/No dropdowns
+# (check_catalog_schema / check_column / check_row), replacing an earlier
+# single dbutils.widgets.multiselect that was observed in production to
+# raise DefaultValueNotInChoicesList even with a default that appeared to
+# satisfy multiselect's own documented constraints - three independent
+# dropdowns have no equivalent cross-widget validation.
 # ---------------------------------------------------------------------------
-def test_schema_mode_multiselect_default_does_not_crash(tmp_path: Path) -> None:
-    path = tmp_path / "TableValidator.py"
-    generate_notebook(path, "schema")
+def test_full_and_basic_mode_default_all_checks_to_yes(tmp_path: Path) -> None:
+    for mode in ("full", "basic"):
+        path = tmp_path / f"{mode}.py"
+        generate_notebook(path, mode)
+        spark = _fake_spark(
+            catalogs=["main"], schemas_by_catalog={"main": ["sales"]},
+            tables_by_schema={("main", "sales"): ["orders"]},
+        )
+        captured = {}
+
+        def fake_validate_tables(source, target, **kwargs):
+            captured["enabled_validations"] = kwargs.get("enabled_validations")
+            m = MagicMock()
+            m.__str__ = MagicMock(return_value="Overall status: PASS")
+            return m
 
+        _run_notebook(path, widget_values={}, spark=spark, validate_tables_mock=fake_validate_tables)
+
+        assert captured["enabled_validations"] == {
+            ValidationType.CATALOG, ValidationType.SCHEMA,
+            ValidationType.COLUMN, ValidationType.ROW,
+        }, f"mode={mode}"
+
+
+def test_schema_mode_defaults_column_and_row_checks_to_no(tmp_path: Path) -> None:
+    path = tmp_path / "schema.py"
+    generate_notebook(path, "schema")
     spark = _fake_spark(
-        catalogs=["main"],
-        schemas_by_catalog={"main": ["sales"]},
+        catalogs=["main"], schemas_by_catalog={"main": ["sales"]},
         tables_by_schema={("main", "sales"): ["orders"]},
     )
+    captured = {}
+
+    def fake_validate_tables(source, target, **kwargs):
+        captured["enabled_validations"] = kwargs.get("enabled_validations")
+        m = MagicMock()
+        m.__str__ = MagicMock(return_value="Overall status: PASS")
+        return m
 
-    # Must not raise _DefaultValueNotInChoicesList.
-    _run_notebook(path, widget_values={}, spark=spark, validate_tables_mock=MagicMock())
+    _run_notebook(path, widget_values={}, spark=spark, validate_tables_mock=fake_validate_tables)
 
+    assert captured["enabled_validations"] == {ValidationType.CATALOG, ValidationType.SCHEMA}
 
-def test_multiselect_default_is_every_choice(notebook_path):
-    """The checks widget's default must always be the full choices list,
-    comma-joined in the declared order - the only default guaranteed to
-    be accepted by dbutils.widgets.multiselect across Databricks runtime
-    versions."""
+
+def test_deselecting_every_check_falls_back_to_run_everything(notebook_path):
+    """All three Yes/No dropdowns set to "No" must fall back to
+    validate_tables()'s own "run everything" default (enabled_validations=
+    None), not silently run nothing."""
     spark = _fake_spark(
-        catalogs=["main"],
-        schemas_by_catalog={"main": ["sales"]},
+        catalogs=["main"], schemas_by_catalog={"main": ["sales"]},
         tables_by_schema={("main", "sales"): ["orders"]},
     )
+    captured = {}
+
+    def fake_validate_tables(source, target, **kwargs):
+        captured["enabled_validations"] = kwargs.get("enabled_validations")
+        m = MagicMock()
+        m.__str__ = MagicMock(return_value="Overall status: PASS")
+        return m
 
-    globs = _run_notebook(notebook_path, widget_values={}, spark=spark, validate_tables_mock=MagicMock())
+    _run_notebook(
+        notebook_path,
+        widget_values={
+            "check_catalog_schema": "No", "check_column": "No", "check_row": "No",
+        },
+        spark=spark,
+        validate_tables_mock=fake_validate_tables,
+    )
 
-    fake_widgets = globs["dbutils"].widgets
-    choices = fake_widgets.multiselect_choices["checks"]
-    assert fake_widgets.get("checks") == ",".join(choices)
+    assert captured["enabled_validations"] is None
 
 
 # ---------------------------------------------------------------------------