#!/bin/bash

set -e # Exit immediately if a command exits with a non-zero status.

DATA_DIR="data"
TARGET_DIR="$DATA_DIR/PennFudanPed"
ZIP_FILE="$DATA_DIR/PennFudanPed.zip"
URL="https://www.cis.upenn.edu/~jshi/ped_html/PennFudanPed.zip"

# 1. Check if the target directory already exists
if [ -d "$TARGET_DIR" ]; then
    echo "Dataset already exists at $TARGET_DIR. Skipping download."
    exit 0
fi

# 2. Create the data directory if it doesn't exist
mkdir -p "$DATA_DIR"
echo "Created directory $DATA_DIR (if it didn't exist)."

# 3. Download the dataset
echo "Downloading dataset from $URL..."
wget -O "$ZIP_FILE" "$URL"
echo "Download complete."

# 4. Extract the dataset
echo "Extracting $ZIP_FILE to $DATA_DIR..."
unzip -q "$ZIP_FILE" -d "$DATA_DIR" # -q for quiet mode
echo "Extraction complete."

# 5. Remove the zip file
rm "$ZIP_FILE"
echo "Removed $ZIP_FILE."

echo "Dataset setup complete in $TARGET_DIR."