Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions obstore/python/obstore/_buffered.pyi
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ from typing import Dict, List, Self

from ._attributes import Attributes
from ._bytes import Bytes
from ._list import ObjectMeta
from .store import ObjectStore

if sys.version_info >= (3, 12):
Expand Down Expand Up @@ -65,6 +66,10 @@ class ReadableFile:
This is currently a no-op.
"""

@property
def meta(self) -> ObjectMeta:
"""Access the metadata of the underlying file"""

def read(self, size: int | None = None, /) -> Bytes:
"""
Read up to `size` bytes from the object and return them. As a convenience, if
Expand Down Expand Up @@ -97,6 +102,10 @@ class ReadableFile:
def seekable(self) -> bool:
"""Return True if the stream supports random access."""

@property
def size(self) -> int:
"""The size in bytes of the object."""

def tell(self) -> int:
"""Return the current stream position."""

Expand Down Expand Up @@ -129,6 +138,10 @@ class AsyncReadableFile:
This is currently a no-op.
"""

@property
def meta(self) -> ObjectMeta:
"""Access the metadata of the underlying file"""

async def read(self, size: int | None = None, /) -> Bytes:
"""
Read up to `size` bytes from the object and return them. As a convenience, if
Expand Down Expand Up @@ -161,6 +174,10 @@ class AsyncReadableFile:
def seekable(self) -> bool:
"""Return True if the stream supports random access."""

@property
def size(self) -> int:
"""The size in bytes of the object."""

async def tell(self) -> int:
"""Return the current stream position."""

Expand Down
37 changes: 26 additions & 11 deletions obstore/src/buffered.rs
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ use std::sync::Arc;

use bytes::Bytes;
use object_store::buffered::{BufReader, BufWriter};
use object_store::ObjectStore;
use object_store::{ObjectMeta, ObjectStore};
use pyo3::exceptions::{PyIOError, PyStopAsyncIteration, PyStopIteration};
use pyo3::prelude::*;
use pyo3::types::PyString;
Expand All @@ -15,6 +15,7 @@ use tokio::io::{AsyncBufReadExt, AsyncReadExt, AsyncSeekExt, AsyncWriteExt, Line
use tokio::sync::Mutex;

use crate::attributes::PyAttributes;
use crate::list::PyObjectMeta;
use crate::runtime::get_runtime;
use crate::tags::PyTagSet;

Expand All @@ -28,8 +29,9 @@ pub(crate) fn open_reader(
) -> PyObjectStoreResult<PyReadableFile> {
let store = store.into_inner();
let runtime = get_runtime(py)?;
let reader = py.allow_threads(|| runtime.block_on(create_reader(store, path, buffer_size)))?;
Ok(PyReadableFile::new(reader, false))
let (reader, meta) =
py.allow_threads(|| runtime.block_on(create_reader(store, path, buffer_size)))?;
Ok(PyReadableFile::new(reader, meta, false))
}

#[pyfunction]
Expand All @@ -42,34 +44,37 @@ pub(crate) fn open_reader_async(
) -> PyResult<Bound<PyAny>> {
let store = store.into_inner();
future_into_py(py, async move {
let reader = create_reader(store, path, buffer_size).await?;
Ok(PyReadableFile::new(reader, true))
let (reader, meta) = create_reader(store, path, buffer_size).await?;
Ok(PyReadableFile::new(reader, meta, true))
})
}

async fn create_reader(
store: Arc<dyn ObjectStore>,
path: String,
capacity: usize,
) -> PyObjectStoreResult<Arc<Mutex<BufReader>>> {
) -> PyObjectStoreResult<(BufReader, ObjectMeta)> {
let meta = store
.head(&path.into())
.await
.map_err(PyObjectStoreError::ObjectStoreError)?;
Ok(Arc::new(Mutex::new(BufReader::with_capacity(
store, &meta, capacity,
))))
Ok((BufReader::with_capacity(store, &meta, capacity), meta))
}

#[pyclass(name = "ReadableFile", frozen)]
pub(crate) struct PyReadableFile {
reader: Arc<Mutex<BufReader>>,
meta: ObjectMeta,
r#async: bool,
}

impl PyReadableFile {
fn new(reader: Arc<Mutex<BufReader>>, r#async: bool) -> Self {
Self { reader, r#async }
fn new(reader: BufReader, meta: ObjectMeta, r#async: bool) -> Self {
Self {
reader: Arc::new(Mutex::new(reader)),
meta,
r#async,
}
}
}

Expand All @@ -88,6 +93,11 @@ impl PyReadableFile {
// `Option<Arc<Mutex<BufReader>>>`.
fn close(&self) {}

#[getter]
fn meta(&self) -> PyObjectMeta {
self.meta.clone().into()
}

#[pyo3(signature = (size = None, /))]
fn read<'py>(&'py self, py: Python<'py>, size: Option<usize>) -> PyResult<PyObject> {
let reader = self.reader.clone();
Expand Down Expand Up @@ -163,6 +173,11 @@ impl PyReadableFile {
true
}

#[getter]
fn size(&self) -> usize {
self.meta.size
}

fn tell<'py>(&'py self, py: Python<'py>) -> PyResult<PyObject> {
let reader = self.reader.clone();
if self.r#async {
Expand Down
6 changes: 6 additions & 0 deletions obstore/src/list.rs
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,12 @@ impl AsRef<ObjectMeta> for PyObjectMeta {
}
}

impl From<ObjectMeta> for PyObjectMeta {
fn from(value: ObjectMeta) -> Self {
Self(value)
}
}

impl<'py> IntoPyObject<'py> for PyObjectMeta {
type Target = PyDict;
type Output = Bound<'py, PyDict>;
Expand Down