updated for datafusion release 43.0.0

datafusion/README.md

@@ -20,7 +20,7 @@ The benchmark should be completed in under an hour. On-demand pricing is $0.6 pe
 1. `cd ClickBench/datafusion`
 1. `vi benchmark.sh` and modify following line to target Datafusion version
     ```
-    git checkout 40.0.0
+    git checkout 43.0.0
     ```
 1. `bash benchmark.sh`
 

datafusion/benchmark.sh

@@ -14,7 +14,7 @@ sudo yum install gcc -y
 # Install DataFusion main branch
 git clone https://github.com/apache/arrow-datafusion.git
 cd arrow-datafusion/datafusion-cli
-git checkout 40.0.0
+git checkout 43.0.0
 CARGO_PROFILE_RELEASE_LTO=true RUSTFLAGS="-C codegen-units=1" cargo build --release
 export PATH="`pwd`/target/release:$PATH"
 cd ../..

datafusion/create_partitioned.sql

@@ -1,3 +1,4 @@
 CREATE EXTERNAL TABLE hits
 STORED AS PARQUET
-LOCATION 'partitioned';
+LOCATION 'partitioned'
+OPTIONS ('binary_as_string' 'true');

datafusion/create_single.sql

@@ -1,3 +1,4 @@
 CREATE EXTERNAL TABLE hits
 STORED AS PARQUET
-LOCATION 'hits.parquet';
+LOCATION 'hits.parquet'
+OPTIONS ('binary_as_string' 'true');