From 35881893f64031d8d887a4c33a7e96d8083b94e7 Mon Sep 17 00:00:00 2001
From: Akash Sivakumar <akashsiva2001@gmail.com>
Date: Thu, 14 Nov 2024 18:32:17 -0700
Subject: [PATCH] Incomplete - dockerizing kafka streaming

---
 preprocessing/Dockerfile.python | 20 ++++++++++++++++++++
 preprocessing/pcap_processor.py |  1 +
 preprocessing/requirements.txt  |  2 ++
 3 files changed, 23 insertions(+)
 create mode 100644 preprocessing/Dockerfile.python
 create mode 100644 preprocessing/requirements.txt

diff --git a/preprocessing/Dockerfile.python b/preprocessing/Dockerfile.python
new file mode 100644
index 0000000..bba0ca6
--- /dev/null
+++ b/preprocessing/Dockerfile.python
@@ -0,0 +1,20 @@
+# Start with a base image that includes Python
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy only the requirements.txt file to the container
+COPY requirements.txt /app
+
+# Install the dependencies using the requirements.txt file
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy only the pcap_processor.py file to the container
+COPY pcap_processor.py /app
+
+# Expose the port Kafka uses (optional, for communication with other services)
+EXPOSE 9092
+
+# Command to run your Python application
+CMD ["python", "pcap_processor.py"]
diff --git a/preprocessing/pcap_processor.py b/preprocessing/pcap_processor.py
index 21a9e6f..bcda443 100644
--- a/preprocessing/pcap_processor.py
+++ b/preprocessing/pcap_processor.py
@@ -14,6 +14,7 @@ dbg_print = lambda *x: DEBUG and print(f"[DEBUG] {x}")
 # Kafka Configuration
 KAFKA_TOPIC = 'pcap_stream'
 KAFKA_SERVER = 'localhost:9092'  # Adjust to your Kafka server
+#KAFKA_SERVER = 'kafka_service:9092'  
 
 # Initialize Kafka Producer
 producer = KafkaProducer(
diff --git a/preprocessing/requirements.txt b/preprocessing/requirements.txt
new file mode 100644
index 0000000..b89fb74
--- /dev/null
+++ b/preprocessing/requirements.txt
@@ -0,0 +1,2 @@
+kafka-python
+scapy
\ No newline at end of file