Main

.github/workflows/cd.yml

@@ -16,6 +16,8 @@ on:
 jobs:
   deployment:
     runs-on: ubuntu-latest
+    # Only deploy if CI workflow succeeded
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
     environment:
       name: production
       url: ${{ vars.RENDER_APP_URL }}

Dockerfile

@@ -3,7 +3,11 @@ WORKDIR /usr/local/app
 
 # Install the application dependencies
 COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt && \
+    python -c "import nltk; \
+    nltk.download('punkt', download_dir='/usr/local/share/nltk_data'); \
+    nltk.download('punkt_tab', download_dir='/usr/local/share/nltk_data'); \
+    nltk.download('stopwords', download_dir='/usr/local/share/nltk_data')"
 
 # Copy in the source code
 COPY src ./src
@@ -13,4 +17,9 @@ EXPOSE 5000
 RUN useradd app
 USER app
 
+# Set cache directories to /tmp to avoid permission issues
+ENV MPLCONFIGDIR=/tmp/matplotlib
+ENV XDG_CACHE_HOME=/tmp/.cache
+ENV NLTK_DATA=/tmp/nltk_data
+
 CMD [ "python", "-m", "src.app.main"]

src/pipeline/text_stats.py

@@ -8,6 +8,18 @@
 import os
 import glob
 
+def ensure_nltk_resources():
+    try:
+        nltk.data.find("tokenizers/punkt")
+    except LookupError:
+        nltk.download("punkt")
+        nltk.download("punkt_tab")
+
+    try:
+        nltk.data.find("corpora/stopwords")
+    except LookupError:
+        nltk.download("stopwords")
+
 def import_data(filename, rootpath):
     """Load a text file from rootpath and return its contents as a DataFrame."""
     fullpath = os.path.join(rootpath, filename)