Feature is pk (#124)

* Added is_legit test cases for the rest of the libraries

* Added pk tests

cuallee/__init__.py

@@ -257,11 +257,23 @@ def is_unique(self, column: str, pct: float = 1.0):
         """Validation for unique values in column"""
         Rule("is_unique", column, "N/A", CheckDataType.AGNOSTIC, pct) >> self._rule
         return self
+
+    def is_primary_key(self, column: str, pct: float = 1.0):
+        """Validation for unique values in column"""
+        Rule("is_unique", column, "N/A", CheckDataType.AGNOSTIC, pct) >> self._rule
+        return self
+
 
     def are_unique(self, column: Union[List[str], Tuple[str, str]], pct: float = 1.0):
         """Validation for unique values in a group of columns"""
         Rule("are_unique", column, "N/A", CheckDataType.AGNOSTIC, pct) >> self._rule
         return self
+
+    def is_composite_key(self, column: Union[List[str], Tuple[str, str]], pct: float = 1.0):
+        """Validation for unique values in a group of columns"""
+        Rule("are_unique", column, "N/A", CheckDataType.AGNOSTIC, pct) >> self._rule
+        return self
+
 
     def is_greater_than(self, column: str, value: float, pct: float = 1.0):
         """Validation for numeric greater than value"""

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cuallee"
-version = "0.5.4"
+version = "0.5.5"
 authors = [
   { name="Herminio Vazquez", email="[email protected]"},
   { name="Virginie Grosboillot", email="[email protected]" }

setup.cfg

@@ -1,5 +1,5 @@
 [metadata]
 name = cuallee
-version = 0.5.4
+version = 0.5.5
 [options]
 packages = find:

test/unit/duckdb_dataframe/test_has_pattern.py

@@ -11,13 +11,25 @@ def test_positive(check: Check, db: duckdb.DuckDBPyConnection):
     check.table_name = "df"
     assert check.validate(db).status.str.match("PASS").all()
 
+def test_is_legit(check: Check, db: duckdb.DuckDBPyConnection):
+    check.is_legit("id")
+    df = pd.DataFrame({"id": ["Herminio", "Hola", "Heroe"]})
+    check.table_name = "df"
+    assert check.validate(db).status.str.match("PASS").all()
+
 
 def test_negative(check: Check, db: duckdb.DuckDBPyConnection):
     check.has_pattern("id", r"^H.*")
     df = pd.DataFrame({"id": ["Herminio", "Hola", "Villain"]})
     check.table_name = "df"
     assert check.validate(db).status.str.match("FAIL").all()
 
+def test_is_not_legit(check: Check, db: duckdb.DuckDBPyConnection):
+    check.is_legit("id")
+    df = pd.DataFrame({"id": ["Herminio", "Hola", ""]})
+    check.table_name = "df"
+    assert check.validate(db).status.str.match("FAIL").all()
+
 
 @pytest.mark.parametrize(
     "pattern", ["^H.*", "^H.*"], ids=("single_quote", "double_quote")

test/unit/pandas_dataframe/test_has_pattern.py

@@ -9,12 +9,22 @@ def test_positive(check: Check):
     df = pd.DataFrame({"id": ["Herminio", "Hola", "Heroe"]})
     assert check.validate(df).status.str.match("PASS").all()
 
+def test_is_legit(check: Check):
+    check.is_legit("id")
+    df = pd.DataFrame({"id": ["Herminio", "Hola", "Heroe"]})
+    assert check.validate(df).status.str.match("PASS").all()
+
 
 def test_negative(check: Check):
     check.has_pattern("id", r"^H.*")
     df = pd.DataFrame({"id": ["Herminio", "Hola", "Villain"]})
     assert check.validate(df).status.str.match("FAIL").all()
 
+def test_is_not_legit(check: Check):
+    check.is_legit("id")
+    df = pd.DataFrame({"id": ["Herminio", "Hola", ""]})
+    assert check.validate(df).status.str.match("FAIL").all()
+
 
 @pytest.mark.parametrize(
     "pattern", ["^H.*", "^H.*"], ids=("single_quote", "double_quote")

test/unit/polars_dataframe/test_has_pattern.py

@@ -8,3 +8,15 @@ def test_positive(check: Check):
     check.has_pattern("id", r"^H.*")
     result = check.validate(df).select(pl.col("status")) == "PASS"
     assert all(result.to_series().to_list())
+
+def test_is_legit(check: Check):
+    df = pl.DataFrame({"id": ["Herminio", "Herbert", "Harry"]})
+    check.is_legit("id")
+    result = check.validate(df).select(pl.col("status")) == "PASS"
+    assert all(result.to_series().to_list())
+
+def test_is_not_legit(check: Check):
+    df = pl.DataFrame({"id": ["Herminio", "Herbert", ""]})
+    check.is_legit("id")
+    result = check.validate(df).select(pl.col("status")) == "FAIL"
+    assert all(result.to_series().to_list())

test/unit/pyspark_dataframe/test_are_unique.py

@@ -11,6 +11,13 @@ def test_positive(spark):
     rs = check.validate(df)
     assert rs.first().status == "PASS"
 
+def test_is_composite_key(spark):
+    df = spark.range(10).withColumn("id2", F.col("id") + 10)
+    check = Check(CheckLevel.WARNING, "pytest")
+    check.are_unique(("id", "id2"))
+    rs = check.validate(df)
+    assert rs.first().status == "PASS"
+
 
 def test_negative(spark):
     df = spark.createDataFrame(

test/unit/pyspark_dataframe/test_is_unique.py

@@ -13,6 +13,14 @@ def test_positive(spark):
     assert rs.first().violations == 0.0
     assert rs.first().pass_rate == 1.0
 
+def test_is_primary_key(spark):
+    df = spark.range(10)
+    check = Check(CheckLevel.WARNING, "pytest")
+    check.is_primary_key("id")
+    rs = check.validate(df)
+    assert rs.first().status == "PASS"
+    assert rs.first().violations == 0.0
+    assert rs.first().pass_rate == 1.0
 
 def test_negative(spark):
     df = spark.createDataFrame([[0], [2], [2], [3]], ["id"])