Fix tests and parquet read performance (#19)

* Fix tests #2

* use a bufreader for sync_reader

* enable back simd

datafusion/Cargo.toml

@@ -40,8 +40,8 @@ path = "src/lib.rs"
 [features]
 default = ["crypto_expressions", "regex_expressions", "unicode_expressions"]
 # FIXME: https://github.com/jorgecarleitao/arrow2/issues/580
-#simd = ["arrow/simd"]
-simd = []
+simd = ["arrow/simd"]
+#simd = []
 crypto_expressions = ["md-5", "sha2", "blake2", "blake3"]
 regex_expressions = ["regex"]
 unicode_expressions = ["unicode-segmentation"]

datafusion/src/avro_to_arrow/reader.rs

@@ -111,13 +111,14 @@ impl ReaderBuilder {
         let (mut avro_schemas, mut schema, codec, file_marker) =
             read::read_metadata(&mut source)?;
         if let Some(proj) = self.projection {
-            let indices: Vec<usize> = schema
+            let mut indices: Vec<usize> = schema
                 .fields
                 .iter()
                 .filter(|f| !proj.contains(&f.name))
                 .enumerate()
                 .map(|(i, _)| i)
                 .collect();
+            indices.sort_by(|i1, i2| i2.cmp(i1));
             for i in indices {
                 avro_schemas.remove(i);
                 schema.fields.remove(i);

datafusion/src/datasource/file_format/avro.rs

@@ -141,7 +141,7 @@ mod tests {
                 "double_col: Float64",
                 "date_string_col: Binary",
                 "string_col: Binary",
-                "timestamp_col: Timestamp(Microsecond, None)",
+                "timestamp_col: Timestamp(Microsecond, Some(\"00:00\"))",
             ],
             x
         );

datafusion/src/datasource/object_store/local.rs

@@ -33,8 +33,6 @@ use crate::error::Result;
 
 use super::{ObjectReaderStream, SizedFile};
 
-impl ReadSeek for std::fs::File {}
-
 #[derive(Debug)]
 /// Local File System as Object Store.
 pub struct LocalFileSystem;
@@ -81,7 +79,9 @@ impl ObjectReader for LocalFileReader {
     }
 
     fn sync_reader(&self) -> Result<Box<dyn ReadSeek + Send + Sync>> {
-        Ok(Box::new(File::open(&self.file.path)?))
+        let file = File::open(&self.file.path)?;
+        let buf_reader = BufReader::new(file);
+        Ok(Box::new(buf_reader))
     }
 
     fn sync_chunk_reader(

datafusion/src/datasource/object_store/mod.rs

@@ -36,8 +36,7 @@ use crate::error::{DataFusionError, Result};
 /// Both Read and Seek
 pub trait ReadSeek: Read + Seek {}
 
-impl<R: Read + Seek> ReadSeek for std::io::BufReader<R> {}
-impl<R: AsRef<[u8]>> ReadSeek for std::io::Cursor<R> {}
+impl<R: Read + Seek> ReadSeek for R {}
 
 /// Object Reader for one file in an object store.
 ///