From 9925db192565241de840bf7737ca2feb4d9a0cd5 Mon Sep 17 00:00:00 2001
From: andrewso <9V5f1FkzI2LD>
Date: Fri, 6 Mar 2020 11:33:58 +0000
Subject: [PATCH] [06.03.20] nltk downloads

---
 Dockerfile                    | 3 ++-
 configuration/scripts/nltk.py | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)
 create mode 100644 configuration/scripts/nltk.py

diff --git a/Dockerfile b/Dockerfile
index 01cfc0a..ede3b72 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -3,7 +3,8 @@ MAINTAINER Andrew Sotheran <cryptosky.user@gmail.com>
 RUN apt update -y && \
     apt install -y python3-pip && \
     pip3 install nltk numpy sklearn flask pandas && \
-    rm -rf /var/lib/apt/lists/*
+    rm -rf /var/lib/apt/lists/* && \
 COPY . /home/spam-filter/.
 EXPOSE 9090
+CMD ["python", "/home/spam-filter/configuration/scripts/nltk.py"]
 CMD ["python", "/home/spam-filter/src/main.py"]
\ No newline at end of file
diff --git a/configuration/scripts/nltk.py b/configuration/scripts/nltk.py
new file mode 100644
index 0000000..df69da2
--- /dev/null
+++ b/configuration/scripts/nltk.py
@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+
+import nltk
+
+nltk.download('pubkt')
+nltk.download('stopwords')
\ No newline at end of file