From fb2488ebb6c0b48ff1d24bcb14d4301dc7f006ea Mon Sep 17 00:00:00 2001
From: Alex Schofield <git@ajschof.me>
Date: Tue, 18 Feb 2025 23:27:30 +0000
Subject: add function to return byte-stream of obfuscated csv file

---
 obfuscator/csv_writer.py | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)
 create mode 100644 obfuscator/csv_writer.py

diff --git a/obfuscator/csv_writer.py b/obfuscator/csv_writer.py
new file mode 100644
index 0000000..f8cd27d
--- /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 data_to_csv_bytes(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")
-- 
cgit v1.2.3


From b40cf894d21f23bf38b2d122365fc3b9a4f8d4e1 Mon Sep 17 00:00:00 2001
From: Alex Schofield <git@ajschof.me>
Date: Tue, 18 Feb 2025 23:32:04 +0000
Subject: rename data_to_csv_bytes function to create_byte_stream in
 csv_writer.py

---
 obfuscator/csv_writer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/obfuscator/csv_writer.py b/obfuscator/csv_writer.py
index f8cd27d..aa5ac3f 100644
--- a/obfuscator/csv_writer.py
+++ b/obfuscator/csv_writer.py
@@ -7,7 +7,7 @@ from obfuscator.logger import get_logger
 logger = get_logger("CSVWriter")
 
 
-def data_to_csv_bytes(data: List[Dict[str, str]]) -> bytes:
+def create_byte_stream(data: List[Dict[str, str]]) -> bytes:
     if not data:
         logger.info("No valid data was provided to write")
         return b""
-- 
cgit v1.2.3


From a655b62cbf2899e683a152039a8c6bd38b9d636d Mon Sep 17 00:00:00 2001
From: Alex Schofield <git@ajschof.me>
Date: Tue, 18 Feb 2025 23:32:19 +0000
Subject: add placeholder tests for create_byte_stream

(until I get around to finishing my testing stack using LocalStack/Docker)
---
 test/test_csv_writer.py | 57 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)
 create mode 100644 test/test_csv_writer.py

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
-- 
cgit v1.2.3


From 90542cfe838376988982fb5c9062fc8dee0b7c87 Mon Sep 17 00:00:00 2001
From: Alex Schofield <git@ajschof.me>
Date: Tue, 18 Feb 2025 23:34:26 +0000
Subject: update cli.py to use create_byte_stream

---
 cli.py | 2 ++
 1 file changed, 2 insertions(+)

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
-- 
cgit v1.2.3