From ecbd0d3f1c22808e9d9547030d9fb49af8d969c7 Mon Sep 17 00:00:00 2001
From: Mikhail Kot <mikhail@spiraldb.com>
Date: Fri, 4 Sep 2026 17:25:20 +0100
Subject: [PATCH] FileSystem for local reads

Signed-off-by: Mikhail Kot <mikhail@spiraldb.com>
---
 vortex-duckdb/src/file_reader.rs     |   3 +-
 vortex-io/src/std_file/filesystem.rs | 107 +++++++++++++++++++++++++++
 vortex-io/src/std_file/mod.rs        |   2 +
 3 files changed, 111 insertions(+), 1 deletion(-)
 create mode 100644 vortex-io/src/std_file/filesystem.rs

diff --git a/vortex-duckdb/src/file_reader.rs b/vortex-duckdb/src/file_reader.rs
index 5048aa8a025..f4c9bb67995 100644
--- a/vortex-duckdb/src/file_reader.rs
+++ b/vortex-duckdb/src/file_reader.rs
@@ -23,6 +23,7 @@ use vortex::io::compat::Compat;
 use vortex::io::filesystem::FileSystemRef;
 use vortex::io::object_store::ObjectStoreFileSystem;
 use vortex::io::runtime::BlockingRuntime as _;
+use vortex::io::std_file::StdFileSystem;
 use vortex::layout::LayoutReaderRef;
 use vortex::layout::scan::scan_builder::ScanBuilder;
 use vortex::mask::Mask;
@@ -80,7 +81,7 @@ fn resolve_filesystem(url: &Url) -> VortexResult<(FileSystemRef, String)> {
     // high-core machines because reads go into blocking pool
     if url.scheme() == "file" {
         return Ok((
-            Arc::new(ObjectStoreFileSystem::local(RUNTIME.handle())),
+            Arc::new(StdFileSystem::new(RUNTIME.handle())),
             url.path().to_string(),
         ));
     }
diff --git a/vortex-io/src/std_file/filesystem.rs b/vortex-io/src/std_file/filesystem.rs
new file mode 100644
index 00000000000..9c71be47516
--- /dev/null
+++ b/vortex-io/src/std_file/filesystem.rs
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright the Vortex contributors
+
+use std::fmt::Debug;
+use std::fmt::Formatter;
+use std::fs;
+use std::io;
+use std::path::Path;
+use std::path::PathBuf;
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use futures::StreamExt;
+use futures::stream;
+use futures::stream::BoxStream;
+use vortex_error::VortexResult;
+
+use crate::VortexReadAt;
+use crate::filesystem::FileListing;
+use crate::filesystem::FileSystem;
+use crate::runtime::Handle;
+use crate::std_file::FileReadAt;
+
+/// A FileSystem over local filesystem.
+pub struct StdFileSystem {
+    handle: Handle,
+}
+
+impl Debug for StdFileSystem {
+    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("StdFileSystem").finish()
+    }
+}
+
+impl StdFileSystem {
+    pub fn new(handle: Handle) -> Self {
+        Self { handle }
+    }
+}
+
+fn walk(dir: &Path, out: &mut Vec<FileListing>) -> io::Result<()> {
+    for entry in fs::read_dir(dir)? {
+        let entry = entry?;
+        let file_type = entry.file_type()?;
+        if file_type.is_dir() {
+            walk(&entry.path(), out)?;
+        } else {
+            let metadata = entry.metadata()?;
+            out.push(FileListing {
+                path: entry.path().to_string_lossy().into_owned(),
+                size: Some(metadata.len()),
+            });
+        }
+    }
+    Ok(())
+}
+
+#[async_trait]
+impl FileSystem for StdFileSystem {
+    fn list(&self, prefix: &str) -> BoxStream<'_, VortexResult<FileListing>> {
+        let dir = PathBuf::from(prefix);
+        let listing = self.handle.spawn_blocking(move || {
+            let mut out = Vec::new();
+            walk(&dir, &mut out)?;
+            Ok::<_, io::Error>(out)
+        });
+        stream::once(listing)
+            .flat_map(|result| match result {
+                Ok(listings) => stream::iter(listings.into_iter().map(Ok)).boxed(),
+                Err(e) => stream::once(async move { Err(e.into()) }).boxed(),
+            })
+            .boxed()
+    }
+
+    async fn head(&self, path: &str) -> VortexResult<Option<FileListing>> {
+        let path = path.to_owned();
+        self.handle
+            .spawn_blocking(move || match fs::metadata(&path) {
+                Ok(metadata) if metadata.is_file() => Ok(Some(FileListing {
+                    path,
+                    size: Some(metadata.len()),
+                })),
+                Ok(_) => Ok(None),
+                Err(e) if e.kind() == io::ErrorKind::NotFound => Ok(None),
+                Err(e) => Err(e.into()),
+            })
+            .await
+    }
+
+    async fn open_read(&self, path: &str) -> VortexResult<Arc<dyn VortexReadAt>> {
+        let handle = self.handle.clone();
+        let path = path.to_owned();
+        let reader = self
+            .handle
+            .spawn_blocking(move || FileReadAt::open(path, handle))
+            .await?;
+        Ok(Arc::new(reader))
+    }
+
+    async fn delete(&self, path: &str) -> VortexResult<()> {
+        let path = path.to_owned();
+        self.handle
+            .spawn_blocking(move || fs::remove_file(path))
+            .await?;
+        Ok(())
+    }
+}
diff --git a/vortex-io/src/std_file/mod.rs b/vortex-io/src/std_file/mod.rs
index c30248ed496..3345089a023 100644
--- a/vortex-io/src/std_file/mod.rs
+++ b/vortex-io/src/std_file/mod.rs
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright the Vortex contributors
 
+mod filesystem;
 mod read_at;
 mod write;
 
+pub use filesystem::*;
 pub use read_at::*;
 pub use write::*;