Actor: Enhance Dockerfile with additional utilities and env vars

- Add installation of `time` and `procps` packages for better resource monitoring.
- Set environment variables `PYTHONUNBUFFERED`, `MALLOC_ARENA_MAX`, and `EASYOCR_DOWNLOAD_CACHE` for improved performance.
- Create a cache directory for EasyOCR to optimize storage usage.

Signed-off-by: Václav Vančura <commit@vancura.dev>

.actor/Dockerfile

@@ -26,7 +26,13 @@ RUN groupadd -r appuser && useradd -r -g appuser -s /sbin/nologin appuser && \
     npm cache clean --force && \
     \
     mkdir -p /home/appuser && \
-    chown -R appuser:appuser /home/appuser
+    chown -R appuser:appuser /home/appuser && \
+    \
+    apt-get update && apt-get install -y --no-install-recommends \
+    time \
+    procps \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
@@ -39,4 +45,13 @@ COPY --chown=appuser:appuser . .
 
 USER appuser
 
+# Set environment variables for better resource management
+ENV PYTHONUNBUFFERED=1
+ENV MALLOC_ARENA_MAX=2
+ENV EASYOCR_DOWNLOAD_CACHE="/tmp/easyocr"
+
+# Create cache directory for EasyOCR
+RUN mkdir -p /tmp/easyocr && \
+    chown -R appuser:appuser /tmp/easyocr
+
 ENTRYPOINT [".actor/actor.sh"]

.actor/actor.sh

@@ -67,6 +67,10 @@ if [ "$(echo "${INPUT}" | jq -r '.ocr')" = "true" ]; then
     DOC_CONVERT_CMD="${DOC_CONVERT_CMD} --ocr"
 fi
 
+# Print the exact command that will be executed
+echo "Debug: Command string: $DOC_CONVERT_CMD"
+echo "Debug: Full command: /usr/bin/time -v bash -c \"$DOC_CONVERT_CMD\""
+
 # --- Process document with Docling ---
 
 echo "Processing document with Docling CLI..."
@@ -79,15 +83,17 @@ touch "$TIMESTAMP_FILE" || {
     exit 1
 }
 
-# Execute the command
+# Execute the command with timeout and memory monitoring
-set +e # Temporarily disable exit on error to handle the error ourselves
+echo "Starting document processing with memory monitoring..."
-eval "$DOC_CONVERT_CMD"
+/usr/bin/time -v bash -c "$DOC_CONVERT_CMD" 2>&1 | tee -a "$LOG_FILE"
-DOCLING_EXIT_CODE=$?
+DOCLING_EXIT_CODE=${PIPESTATUS[0]}
-set -e # Re-enable exit on error
 
 # Check if the command failed and handle the error
 if [ $DOCLING_EXIT_CODE -ne 0 ]; then
     echo "Error: Docling command failed with exit code $DOCLING_EXIT_CODE"
+    echo "Memory usage information:"
+    free -h
+    df -h
     exit 1
 fi