#!/bin/sh

# Exit if any of the command doesn't exit with code 0
set -e

test -z "$EXEC_DIR" && EXEC_DIR=.
DATA_PATH="$EXEC_DIR/../data"
test ! -d "$DATA_PATH" && mkdir -v "$DATA_PATH"

if [ ! -f "$DATA_PATH"/X_train.bin ] || [ ! -f "$DATA_PATH"/X_test.bin ] \
|| [ ! -f "$DATA_PATH"/y_train.bin ] || [ ! -f "$DATA_PATH"/y_test.bin ]; then
	if [ ! -f "$DATA_PATH"/faces.tar.gz ]; then
		echo 'Downloading raw dataset'
		curl -o "$DATA_PATH"/faces.tar.gz http://www.ai.mit.edu/courses/6.899/lectures/faces.tar.gz
	fi

	echo 'Extracting raw files'
	tar xvzf "$DATA_PATH"/faces.tar.gz -C "$DATA_PATH"
	rm -v "$DATA_PATH"/README "$DATA_PATH"/svm.*

	echo 'Extracting raw train set'
	tar xvzf "$DATA_PATH"/face.train.tar.gz -C "$DATA_PATH"
	rm -v "$DATA_PATH"/face.train.tar.gz

	echo 'Extracting raw test set'
	tar xvzf "$DATA_PATH"/face.test.tar.gz -C "$DATA_PATH"
	rm -v "$DATA_PATH"/face.test.tar.gz

	echo 'Converting raw dataset to bin file'
	export EXEC_DIR
	. "$EXEC_DIR"/activate.sh
	python "$EXEC_DIR"/convert_dataset.py "$DATA_PATH"

	echo 'Removing leftovers'
	rm -rvf "$DATA_PATH"/train "$DATA_PATH"/test

	echo 'Done !'
fi