From 0bf209e93ec76fad8753bd00684f8dcaa72649d0 Mon Sep 17 00:00:00 2001
From: DouPache <douenergy@gmail.com>
Date: Tue, 17 Sep 2024 18:00:35 +0800
Subject: [PATCH] we should also extrac the tar after download

---
 benchmarks/bench.sh | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/benchmarks/bench.sh b/benchmarks/bench.sh
index 44fb1444a393..24efab6c6ca5 100755
--- a/benchmarks/bench.sh
+++ b/benchmarks/bench.sh
@@ -493,6 +493,10 @@ data_imdb() {
             
             # Download the dataset
             curl -o "${imdb_temp_gz}" "${imdb_url}"
+            
+            # Extract the dataset
+            tar -xzvf "${imdb_temp_gz}" -C "${imdb_dir}"
+            $CARGO_COMMAND --bin imdb -- convert --input ${imdb_dir} --output ${imdb_dir} --format parquet
         else 
             echo "IMDB.tgz already exists."