table-validator 0.1.7__tar.gz → 0.1.8__tar.gz

{table_validator-0.1.7/table_validator.egg-info → table_validator-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: table-validator
-Version: 0.1.7
+Version: 0.1.8
 Summary: CLI tool for validating data migrations between Azure (Blob Storage / SQL Database) and Databricks Delta Lake catalogs
 License: MIT
 Requires-Python: >=3.9

{table_validator-0.1.7 → table_validator-0.1.8}/table_validator/cli/wizard.py

@@ -117,6 +117,52 @@ def _prompt_primary_key(existing: Optional[list]) -> Optional[list]:
     return [col.strip() for col in answer.split(",") if col.strip()]
 
 
+def _prompt_column_list(prompt_text: str, existing: Optional[list]) -> Optional[list]:
+    """Shared free-text parser for a comma-separated column list answer -
+    used by all three customization sub-options below. Returns None for
+    a blank answer (caller decides the actual default: None vs [])."""
+    default_str = ", ".join(existing) if existing else ""
+    answer = _ask(questionary.text(prompt_text, default=default_str))
+    if not answer:
+        return None
+    return [col.strip() for col in answer.split(",") if col.strip()]
+
+
+def _prompt_column_customization(config: ValidatorConfig) -> None:
+    """Optional column-level customization, asked right after the
+    primary key - only meaningful for the single named table
+    (primary_key's same scope). Skipped entirely (leaving any existing
+    only_columns/ignore_columns/ignore_datatype_columns untouched) unless
+    the user opts in, so a user who never touches this gets identical
+    behavior to before this feature existed."""
+    customize = questionary.confirm(
+        "Customize column validation? (skip specific columns, compare "
+        "only specific columns, or ignore datatype mismatches for "
+        "specific columns)",
+        default=False,
+    ).ask()
+
+    if not customize:
+        return
+
+    config.only_columns = _prompt_column_list(
+        "Compare ONLY these columns, comma-separated (leave blank to "
+        "compare every common column as usual):",
+        config.only_columns,
+    )
+    config.ignore_columns = _prompt_column_list(
+        "SKIP these columns entirely, comma-separated (leave blank to "
+        "skip none):",
+        config.ignore_columns,
+    ) or []
+    config.ignore_datatype_columns = _prompt_column_list(
+        "Ignore DATATYPE mismatches only for these columns, "
+        "comma-separated - their other checks (nullable, statistics, "
+        "row values) still run (leave blank to skip none):",
+        config.ignore_datatype_columns,
+    ) or []
+
+
 def _write_env_file(values: Dict[str, str], env_path: Optional[Path] = None) -> None:
     """
     Write secrets to env_path (default: ENV_PATH, resolved at call time)
@@ -394,8 +440,18 @@ def run_configure_wizard() -> None:
 
     if source_table_named and config.target_table.table:
         config.primary_key = _prompt_primary_key(config.primary_key)
+        # Column-level customization - same single-table scope as the
+        # primary key above (only_columns/ignore_columns/
+        # ignore_datatype_columns are only meaningful when there's one
+        # specific table to compare). Optional: a user who declines gets
+        # identical behavior to before this feature existed.
+        typer.echo("\n== Customize validation (optional) ==")
+        _prompt_column_customization(config)
     else:
         config.primary_key = None
+        config.only_columns = None
+        config.ignore_columns = []
+        config.ignore_datatype_columns = []
 
     # ------------------------------------------------------------------
     # 5. Validations to run

{table_validator-0.1.7 → table_validator-0.1.8/table_validator.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: table-validator
-Version: 0.1.7
+Version: 0.1.8
 Summary: CLI tool for validating data migrations between Azure (Blob Storage / SQL Database) and Databricks Delta Lake catalogs
 License: MIT
 Requires-Python: >=3.9

{table_validator-0.1.7 → table_validator-0.1.8}/table_validator.egg-info/scm_version.json

@@ -1,7 +1,7 @@
 {
-  "tag": "0.1.7",
+  "tag": "0.1.8",
   "distance": 0,
-  "node": "g989192ab5b13d03c174b2c33883a8569f5437e2a",
+  "node": "g5004811d73585508b803dc003e03bd1da62ede4a",
   "dirty": false,
   "branch": "HEAD",
   "node_date": "2026-09-02"

{table_validator-0.1.7 → table_validator-0.1.8}/tests/test_wizard.py

@@ -335,6 +335,7 @@ def test_databricks_source_type_prompts_for_source_table(tmp_path, monkeypatch):
         "src_cat", "bronze", "customers",   # source table
         "tgt_cat", "silver", "customers",   # target table
         "",                                   # primary key (left blank)
+        False,                                # customize validation? (declined)
         [],                                  # validations
     ])
 
@@ -359,12 +360,100 @@ def test_databricks_source_type_prompts_for_primary_key_when_both_tables_named(
         "src_cat", "bronze", "customers",
         "tgt_cat", "silver", "customers",
         "id, region_id ",                    # primary key, comma-separated with stray spaces
+        False,                                # customize validation? (declined)
         [],
     ])
 
     assert config.primary_key == ["id", "region_id"]
 
 
+def test_databricks_wizard_declining_customization_leaves_defaults_untouched(
+    tmp_path, monkeypatch
+):
+    """Answering No to the customize-validation gate must leave
+    only_columns/ignore_columns/ignore_datatype_columns at their defaults
+    - a user who never opts in gets identical behavior to before this
+    feature existed."""
+    config = _run_wizard_with_answers(tmp_path, monkeypatch, [
+        "Databricks catalog -> Databricks catalog",
+        "https://adb-1.databricks.net", "/sql/1.0/warehouses/x", "tok",
+        "src_cat", "bronze", "customers",
+        "tgt_cat", "silver", "customers",
+        "",                                    # primary key (left blank)
+        False,                                 # customize validation? (declined)
+        [],
+    ])
+
+    assert config.only_columns is None
+    assert config.ignore_columns == []
+    assert config.ignore_datatype_columns == []
+
+
+def test_databricks_wizard_customize_populates_all_three_column_lists(
+    tmp_path, monkeypatch
+):
+    """Answering Yes to the customize-validation gate must ask for and
+    save all three column lists - only_columns (allowlist),
+    ignore_columns (denylist), ignore_datatype_columns."""
+    config = _run_wizard_with_answers(tmp_path, monkeypatch, [
+        "Databricks catalog -> Databricks catalog",
+        "https://adb-1.databricks.net", "/sql/1.0/warehouses/x", "tok",
+        "src_cat", "bronze", "customers",
+        "tgt_cat", "silver", "customers",
+        "id",                                  # primary key
+        True,                                  # customize validation? (accepted)
+        "id, name ",                            # only_columns, stray spaces
+        "updated_at",                           # ignore_columns
+        "legacy_flag, notes",                   # ignore_datatype_columns
+        [],
+    ])
+
+    assert config.only_columns == ["id", "name"]
+    assert config.ignore_columns == ["updated_at"]
+    assert config.ignore_datatype_columns == ["legacy_flag", "notes"]
+
+
+def test_databricks_wizard_customize_all_three_left_blank(tmp_path, monkeypatch):
+    """Opting into customization but leaving all three prompts blank must
+    resolve to only_columns=None, ignore_columns=[], ignore_datatype_columns=[] -
+    the same effective defaults as declining outright."""
+    config = _run_wizard_with_answers(tmp_path, monkeypatch, [
+        "Databricks catalog -> Databricks catalog",
+        "https://adb-1.databricks.net", "/sql/1.0/warehouses/x", "tok",
+        "src_cat", "bronze", "customers",
+        "tgt_cat", "silver", "customers",
+        "id",
+        True,                                  # customize validation? (accepted)
+        "",                                    # only_columns left blank
+        "",                                    # ignore_columns left blank
+        "",                                    # ignore_datatype_columns left blank
+        [],
+    ])
+
+    assert config.only_columns is None
+    assert config.ignore_columns == []
+    assert config.ignore_datatype_columns == []
+
+
+def test_databricks_wizard_catalog_wide_sweep_skips_customization_prompt(
+    tmp_path, monkeypatch
+):
+    """Catalog-wide sweep (no specific table named) must skip the
+    customize-validation gate entirely, same scope rule as primary_key -
+    a single column list can't apply to many different tables."""
+    config = _run_wizard_with_answers(tmp_path, monkeypatch, [
+        "Databricks catalog -> Databricks catalog",
+        "https://adb-1.databricks.net", "/sql/1.0/warehouses/x", "tok",
+        "src_cat", "", "",                    # source: catalog only
+        "tgt_cat", "", "",                    # target: catalog only
+        [],                                    # validations (no customize prompt in between)
+    ])
+
+    assert config.only_columns is None
+    assert config.ignore_columns == []
+    assert config.ignore_datatype_columns == []
+
+
 def test_databricks_wizard_skips_primary_key_prompt_for_catalog_wide_sweep(
     tmp_path, monkeypatch
 ):
@@ -457,6 +546,7 @@ def test_azure_sql_prompts_for_primary_key_when_table_named(tmp_path, monkeypatc
         "employees",                          # sql_source table
         "tgt_cat", "dbo", "employees_sample",  # target table
         "EmployeeID",                         # primary key
+        False,                                # customize validation? (declined)
         [],                                   # validations
     ])
 
@@ -498,6 +588,7 @@ def test_azure_blob_prompts_for_primary_key_when_blob_path_named(tmp_path, monke
         "validation/customers.csv",            # blob_path (explicit)
         "tgt_cat", "bronze", "customers",      # target table
         "id",                                  # primary key
+        False,                                 # customize validation? (declined)
         [],                                    # validations
     ])