Merge pull request #7 from ajschofield/feat/csv-writer

add create_byte_stream for obfuscation output

3 files changed, 85 insertions, 0 deletions

diff --git a/cli.py b/cli.py
index b1d4000..f2c8771 100644
--- a/cli.py
+++ b/cli.py
@@ -3,6 +3,7 @@ import json
 from obfuscator.csv_reader import CSVReader
 from obfuscator.obfuscate import obfuscate
 from obfuscator.logger import get_logger
+from obfuscator.csv_writer import create_byte_stream
 
 # Create the logger
 logger = get_logger("CLI")
@@ -44,6 +45,7 @@ def main():
     obfuscated_data = obfuscate(data, args.pii)
     # For debug purposes, log the obfuscated data as JSON for readability
     logger.debug("Obfuscated data (JSON): " + json.dumps(obfuscated_data, indent=4))
+    return create_byte_stream(obfuscated_data)
 
 
 # If the script is run directly (as it should be), call the main function
diff --git a/obfuscator/csv_writer.py b/obfuscator/csv_writer.py
new file mode 100644
index 0000000..aa5ac3f
--- /dev/null
+++ b/obfuscator/csv_writer.py
@@ -0,0 +1,26 @@
+import csv
+import io
+from typing import List, Dict
+from obfuscator.logger import get_logger
+
+# Create the logger
+logger = get_logger("CSVWriter")
+
+
+def create_byte_stream(data: List[Dict[str, str]]) -> bytes:
+    if not data:
+        logger.info("No valid data was provided to write")
+        return b""
+
+    output = io.StringIO()
+
+    headers = list(data[0].keys())
+
+    writer = csv.DictWriter(output, fieldnames=headers)
+    writer.writeheader()
+    writer.writerows(data)
+
+    csv_string = output.getvalue()
+    logger.debug(f"CSV data: {csv_string}")
+
+    return csv_string.encode("utf-8")
diff --git a/test/test_csv_writer.py b/test/test_csv_writer.py
new file mode 100644
index 0000000..eceac28
--- /dev/null
+++ b/test/test_csv_writer.py
@@ -0,0 +1,57 @@
+import io
+import csv
+from obfuscator.csv_writer import create_byte_stream
+
+
+def csv_bytes_to_list(csv_bytes: bytes):
+    csv_string = csv_bytes.decode("utf-8")
+    f = io.StringIO(csv_string)
+    reader = csv.DictReader(f)
+    return [dict(row) for row in reader]
+
+
+def test_create_byte_stream_valid_data():
+    data = [
+        {"student_id": "1234", "name": "Student 1", "course": "Course 1"},
+        {"student_id": "5678", "name": "Student 2", "course": "Course 2"},
+    ]
+    csv_bytes = create_byte_stream(data)
+    result = csv_bytes_to_list(csv_bytes)
+    assert result == data
+
+
+def test_create_byte_stream_empty_data():
+    csv_bytes = create_byte_stream([])
+    assert csv_bytes == b""
+
+
+def test_create_byte_stream_handles_quoted_fields():
+    data = [
+        {"student_id": "1234", "name": 'Student "One"', "course": "Course, A"},
+        {"student_id": "5678", "name": 'Student "Two"', "course": "Course, B"},
+    ]
+    csv_bytes = create_byte_stream(data)
+    result = csv_bytes_to_list(csv_bytes)
+    assert result == data
+
+
+def test_create_byte_stream_consistent_header_order():
+    data = [
+        {"student_id": "1234", "name": "Alice", "course": "Math"},
+        {"student_id": "5678", "name": "Bob", "course": "Science"},
+    ]
+    csv_bytes = create_byte_stream(data)
+    csv_string = csv_bytes.decode("utf-8")
+    header_line = csv_string.splitlines()[0]
+    expected_header = ",".join(data[0].keys())
+    assert header_line == expected_header
+
+
+def test_create_byte_stream_special_characters():
+    data = [
+        {"student_id": "1234", "name": "Student 1", "course": "Line1\nLine2"},
+        {"student_id": "5678", "name": "Student 2", "course": "Value with, comma"},
+    ]
+    csv_bytes = create_byte_stream(data)
+    result = csv_bytes_to_list(csv_bytes)
+    assert result == data