Adding equality row-level checks

src/databricks/labs/dqx/check_funcs.py

@@ -398,6 +398,68 @@ def is_not_in_near_future(column: str | Column, offset: int = 0, curr_timestamp:
     )
 
 
+@register_rule("row")
+def is_equal_to(
+    column: str | Column, value: int | float | str | datetime.date | datetime.datetime | Column | None = None
+) -> Column:
+    """Check whether the values in the input column are equal to the given value.
+
+    Args:
+        column (str | Column): Column to check. Can be a string column name or a column expression.
+        value (int | float | str | datetime.date | datetime.datetime | Column | None, optional):
+            The value to compare with. Can be a literal or a Spark Column. Defaults to None.
+
+    Returns:
+        Column: A Spark Column condition that fails if the column value is not equal to the given value.
+    """
+    col_str_norm, col_expr_str, col_expr = _get_normalized_column_and_expr(column)
+    value_expr = _get_limit_expr(value)
+    condition = col_expr != value_expr
+
+    return make_condition(
+        condition,
+        F.concat_ws(
+            "",
+            F.lit("Value '"),
+            col_expr.cast("string"),
+            F.lit(f"' in Column '{col_expr_str}' is not equal to value: "),
+            value_expr.cast("string"),
+        ),
+        f"{col_str_norm}_not_equal_to_value",
+    )
+
+
+@register_rule("row")
+def is_not_equal_to(
+    column: str | Column, value: int | float | str | datetime.date | datetime.datetime | Column | None = None
+) -> Column:
+    """Check whether the values in the input column are not equal to the given value.
+
+    Args:
+        column (str | Column): Column to check. Can be a string column name or a column expression.
+        value (int | float | str | datetime.date | datetime.datetime | Column | None, optional):
+            The value to compare with. Can be a literal or a Spark Column. Defaults to None.
+
+    Returns:
+        Column: A Spark Column condition that fails if the column value is equal to the given value.
+    """
+    col_str_norm, col_expr_str, col_expr = _get_normalized_column_and_expr(column)
+    value_expr = _get_limit_expr(value)
+    condition = col_expr == value_expr
+
+    return make_condition(
+        condition,
+        F.concat_ws(
+            "",
+            F.lit("Value '"),
+            col_expr.cast("string"),
+            F.lit(f"' in Column '{col_expr_str}' is equal to value: "),
+            value_expr.cast("string"),
+        ),
+        f"{col_str_norm}_equal_to_value",
+    )
+
+
 @register_rule("row")
 def is_not_less_than(
     column: str | Column, limit: int | datetime.date | datetime.datetime | str | Column | None = None

src/databricks/labs/dqx/llm/resources/yaml_checks_examples.yml

@@ -93,6 +93,42 @@
       column: col3
       min_limit: col2 + 10
       max_limit: col2 * 10
+- criticality: error
+  check:
+    function: is_equal_to
+    arguments:
+      column: col10
+      value: 2
+- criticality: error
+  check:
+    function: is_equal_to
+    arguments:
+      column: col3
+      value: col2
+- criticality: error
+  check:
+    function: is_not_equal_to
+    arguments:
+      column: col1
+      value: '''unknown'''
+- criticality: error
+  check:
+    function: is_not_equal_to
+    arguments:
+      column: col5
+      value: 2025-02-24
+- criticality: error
+  check:
+    function: is_not_equal_to
+    arguments:
+      column: col6
+      value: 2025-02-24 01:00:00
+- criticality: error
+  check:
+    function: is_not_equal_to
+    arguments:
+      column: col3
+      value: col2 + 5
 - criticality: error
   check:
     function: is_not_less_than
@@ -290,16 +326,28 @@
       column: try_element_at(col4, 1)
 - criticality: error
   check:
-    function: is_not_greater_than
+    function: is_equal_to
     arguments:
-      column: array_max(col4)
-      limit: 10
+      column: col8.field1
+      value: 1
+- criticality: error
+  check:
+    function: is_not_equal_to
+    arguments:
+      column: try_element_at(col7, 'key1')
+      value: col10
 - criticality: error
   check:
     function: is_not_less_than
     arguments:
       column: array_min(col4)
       limit: 1
+- criticality: error
+  check:
+    function: is_not_greater_than
+    arguments:
+      column: array_max(col4)
+      limit: 10
 - criticality: error
   check:
     function: sql_expression