docstrings for parsers and test parsers

Author: Akol125

lambdas/shared/src/common/validator/parsers/csv_parser.py

@@ -16,6 +16,12 @@ def __init__(self):
         self.csv_file_data = {}
 
     # parse the CSV into a Dictionary
+    """
+    Takes a CSV file with numerous fields (that uses pipe delimiter) and parses it into a list of dictionaries using csv.DictReader.
+    Then create a key for each header and attached a list of all the value to that key. So a one to many relationship 
+    is created between the header and the values.
+    """
+
     def parse_csv_file(self, csv_filename: str, delimiter: str = "|") -> None:
         with open(csv_filename, newline="", encoding="utf-8") as file:
             csv_to_dict = csv.DictReader(file, delimiter=delimiter)
@@ -25,6 +31,12 @@ def parse_csv_file(self, csv_filename: str, delimiter: str = "|") -> None:
                 for key in csv_header_to_keys:
                     self.csv_file_data[key].append(row[key])
 
+    """
+    Retrieves all values associated with the specified column header (key).
+    :param field_name: The column header whose values are to be retrieved.
+    :return: A list of values under the specified column header or key.
+    """
+
     # retrieve a column of data to work with
     def get_key_value(self, field_name: str) -> list[str]:
         retrieve_column_data = self.csv_file_data[field_name]

lambdas/shared/src/common/validator/validator.py

@@ -1,4 +1,8 @@
-# Main validation engine
+"""
+1. Runs the CSV and FHIR Parsers (where Extraction of the values occurs and collates extraction error reports)
+2. Runs the Expresssion Checker against each expression in the schema
+3. Collects all error records and builds the final error report
+"""
 
 from enum import Enum
 
@@ -213,7 +217,6 @@ def run_validation(
 
         return self.error_records
 
-    # -------------------------------------------------------------------------
     # Report Generation
     # Build the error Report
     def build_error_report(self, event_id):

lambdas/shared/tests/test_common/validator/test_csv_parser.py

@@ -8,6 +8,10 @@
 
 
 class TestCSVParser(unittest.TestCase):
+    """
+    Unit tests for the CSVParser class to ensure correct parsing of Full CSV files
+    """
+
     def _write_temp_csv(self, content: str) -> str:
         fd, path = tempfile.mkstemp(suffix=".csv")
         Path(path).write_text(content, encoding="utf-8")
@@ -24,13 +28,12 @@ def test_parse_file_with_pipe_delimiter(self):
             Path(path).unlink(missing_ok=True)
 
     def test_missing_column_raises_keyerror(self):
-        csv_content = "a|b\n1|2\n"
-        path = self._write_temp_csv(csv_content)
+        path = self._write_temp_csv(CSV_FILE)
         try:
             p = CSVParser()
             p.parse_csv_file(path, delimiter="|")
             with self.assertRaises(KeyError):
-                _ = p.get_key_value("c")
+                _ = p.get_key_value("NHS_CODE")
         finally:
             Path(path).unlink(missing_ok=True)
 

lambdas/shared/tests/test_common/validator/test_key_data.py

@@ -4,6 +4,10 @@
 
 
 class TestKeyData(unittest.TestCase):
+    """
+    Unit tests for the KeyData lookup class to ensure correct key code validation
+    """
+
     def setUp(self):
         self.kd = KeyData()
 

lambdas/shared/tests/test_common/validator/test_lookup_data.py

@@ -4,6 +4,10 @@
 
 
 class TestLookUpData(unittest.TestCase):
+    """
+    Unit tests for the LookUpData lookup class to ensure correct lookup code validation
+    """
+
     def setUp(self):
         self.lookup = LookUpData()
 

…ommon/validator/test_validate_csv_row.py …mon/validator/test_validation_csv_row.pylambdas/shared/tests/test_common/validator/test_validate_csv_row.py renamed to lambdas/shared/tests/test_common/validator/test_validation_csv_row.py lambdas/shared/tests/test_common/validator/test_validate_csv_row.py renamed to lambdas/shared/tests/test_common/validator/test_validation_csv_row.py

@@ -6,6 +6,10 @@
 
 
 class TestValidator(unittest.TestCase):
+    """
+    Unit tests for the CSV validation logic using the Validator class with a small CSV schema.
+    """
+
     def setUp(self):
         self.parent_folder = Path(__file__).parent
         schema_file_path = self.parent_folder / "test_schemas/test_small_schema.json"