The returned path value of get_by_uri should be self-described with e…

…ntire path (#1779)

* Make the return path value of get_by_uri() in ObjectStoreRegistry self-described for which object store to be used

* Improve the uri parse logic with considering host and port

* Revert "Improve the uri parse logic with considering host and port"

This reverts commit e5e8dd3.

Co-authored-by: yangzhong <[email protected]>

datafusion/src/datasource/object_store/local.rs

@@ -39,6 +39,11 @@ pub struct LocalFileSystem;
 #[async_trait]
 impl ObjectStore for LocalFileSystem {
     async fn list_file(&self, prefix: &str) -> Result<FileMetaStream> {
+        let prefix = if let Some((_scheme, path)) = prefix.split_once("://") {
+            path
+        } else {
+            prefix
+        };
         list_all(prefix.to_owned()).await
     }
 

datafusion/src/datasource/object_store/mod.rs

@@ -220,13 +220,12 @@ impl ObjectStoreRegistry {
     /// Get a suitable store for the URI based on it's scheme. For example:
     /// - URI with scheme `file://` or no schema will return the default LocalFS store
     /// - URI with scheme `s3://` will return the S3 store if it's registered
-    /// Returns a tuple with the store and the path of the file in that store
-    /// (URI=scheme://path).
+    /// Returns a tuple with the store and the self-described uri of the file in that store
     pub fn get_by_uri<'a>(
         &self,
         uri: &'a str,
     ) -> Result<(Arc<dyn ObjectStore>, &'a str)> {
-        if let Some((scheme, path)) = uri.split_once("://") {
+        if let Some((scheme, _path)) = uri.split_once("://") {
             let stores = self.object_stores.read();
             let store = stores
                 .get(&*scheme.to_lowercase())
@@ -237,7 +236,7 @@ impl ObjectStoreRegistry {
                         scheme
                     ))
                 })?;
-            Ok((store, path))
+            Ok((store, uri))
         } else {
             Ok((Arc::new(LocalFileSystem), uri))
         }