Merge pull request #16 from jabardigitalservice/feature/string_is_in_…

…contain

Feature/string is in contain

datasae/string.py

@@ -34,6 +34,42 @@ def __init__(self, dataFrame: pd.DataFrame):
         """
         self.dataFrame = dataFrame
 
+    @staticmethod
+    def check_is_in_contain(string_data: str, compare_data: list) -> tuple:
+        """
+        check_is_in_contain method.
+
+        Check if a given string value is not present in a specified
+            dict
+
+        Args:
+            string_data (str): The string value to be checked.
+            compare_data: The list  of values to check against.
+
+        Returns:
+            tuple: A tuple containing the following elements:
+                - valid (int): The number of valid values (either 0 or 1).
+                - invalid (int): The number of invalid values (either 0 or 1).
+                - warning_data (dict): A dictionary with warning data if the
+                    value is invalid, including the warning message,
+                    the actual value, and a detailed message.
+        """
+        valid = 0
+        invalid = 0
+        warning_data = {}
+        if any(
+            strings in compare_data for strings in string_data
+        ):
+            valid = 1
+        else:
+            invalid = 1
+            warning_data = create_warning_data(
+                compare_data,
+                f"Value should be contain to {string_data}",
+            )
+
+        return valid, invalid, warning_data
+
     @staticmethod
     def check_contain(string_data: str, compare_data: str) -> tuple:
         """
@@ -297,6 +333,51 @@ def check_is_capitalize_all_word(str_data: str) -> tuple:
 
         return valid, invalid, warning_data
 
+    def is_in_contain(self, str_is_in_contain: list, column: str) -> dict:
+        """
+        is_in_contain method.
+
+        data quality for is_in_contain.
+
+        Args:
+            str_is_in_contain: string that want to check
+            column: column name that want to check
+
+        Returns:
+            dict: A dictionary containing the result of the data quality check,
+                including the number of valid and invalid values,
+                and any warning messages.
+        """
+        valid = 0
+        invalid = 0
+        warning = {}
+
+        for index, str_data in enumerate(self.dataFrame[column]):
+            try:
+                if isinstance(str_data, (str)) is False:
+                    raise InvalidDataTypeWarning(warning)
+                (valid_row,
+                 invalid_row,
+                 warning_data) = self.check_is_in_contain(
+                    str_is_in_contain, str_data
+                )
+                valid += valid_row
+                invalid += invalid_row
+                if warning_data != {}:
+                    warning[index] = InvalidDataValueWarning(
+                        warning_data
+                    ).message
+            except InvalidDataTypeWarning:
+                invalid += 1
+                warning_data = create_warning_data(
+                    str_data,
+                    WarningDataDetailMessage.STRING_DATA_TYPE,
+                    WarningDataMessage.INVALID_DATA_TYPE,
+                )
+                warning[index] = InvalidDataTypeWarning(warning_data).message
+        result = self.response(valid, invalid, warning)
+        return result
+
     def contain(self, str_contain, column) -> dict:
         """
         Contain method.

tests/test_string.py

@@ -23,6 +23,76 @@ def __init__(self, methodName: str = "TestString"):
         super().__init__(methodName)
         self.maxDiff = None
 
+    def test_is_in_contain_valid(self):
+        """test_is_in_contain_valid."""
+        dummy = pd.DataFrame(
+            {
+                "column": [
+                    "Masa",
+                    "Jelas",
+                    "Gelas",
+                    "Keras",
+                    "Panas",
+                    "Masak",
+                    "Bersama-sama",
+                    "Jelas",
+                    "Pantas",
+                    "Tas",
+                ]
+            }
+        )
+
+        actual_result = String(dummy).is_in_contain(['sa', "as"], "column")
+        expected_result = {
+            "score": 1.0,
+            "valid": 10,
+            "invalid": 0,
+            "warning": {},
+        }
+
+        self.assertDictEqual(actual_result, expected_result, MESSAGE)
+
+    def test_is_in_contain_invalid(self):
+        """test_contain_invalid."""
+        dummy = pd.DataFrame(
+            {
+                "column": [
+                    "Masa",
+                    "Jelas",
+                    "Gelas",
+                    "Keras",
+                    "Panas",
+                    "Masak",
+                    "Bersama-sama",
+                    "Jelas",
+                    "Pantas",
+                    "Tas",
+                    "Laptop",
+                    10
+                ]
+            }
+        )
+
+        actual_result = String(dummy).is_in_contain(['sa', "as"], "column")
+        expected_result = {
+            "score": 0.8333333333333334,
+            "valid": 10,
+            "invalid": 2,
+            "warning": {
+                10: create_warning_data(
+                    "Laptop",
+                    "Value should be contain to ['sa', 'as']",
+                    WarningDataMessage.INVALID_VALUE,
+                ),
+                11: create_warning_data(
+                    10,
+                    WarningDataDetailMessage.STRING_DATA_TYPE,
+                    WarningDataMessage.INVALID_DATA_TYPE,
+                ),
+            },
+        }
+        self.assertDictEqual(actual_result, expected_result, MESSAGE)
+
     def test_contain_valid(self):
         """test_contain_valid."""
         dummy = pd.DataFrame(