update arrow (#2762)

pola-rs · Feb 24, 2022 · 330db8d · 330db8d
1 parent 43fd1aa
commit 330db8d
Show file tree

Hide file tree

Showing 7 changed files with 27 additions and 10 deletions.
diff --git a/polars/polars-arrow/Cargo.toml b/polars/polars-arrow/Cargo.toml
@@ -9,7 +9,7 @@ description = "Arrow interfaces for Polars DataFrame library"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "22bf173ec297fbc2ce156bd482cb410b7769073d", default-features = false }
+arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "fb5d4330544d9d746dfc9bdacab5f1f5c1de9203", default-features = false }
 # arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "no_null_propagate_comp", default-features = false }
 # arrow = { package = "arrow2", version = "0.9", default-features = false, features = ["compute_concatenate"] }
 hashbrown = "0.12"

diff --git a/polars/polars-core/Cargo.toml b/polars/polars-core/Cargo.toml
@@ -165,7 +165,7 @@ unsafe_unwrap = "^0.1.0"
 package = "arrow2"
 git = "https://github.com/jorgecarleitao/arrow2"
 # git = "https://github.com/ritchie46/arrow2"
-rev = "22bf173ec297fbc2ce156bd482cb410b7769073d"
+rev = "fb5d4330544d9d746dfc9bdacab5f1f5c1de9203"
 # branch = "no_null_propagate_comp"
 # version = "0.9"
 default-features = false

diff --git a/polars/polars-io/Cargo.toml b/polars/polars-io/Cargo.toml
@@ -34,7 +34,7 @@ private = []
 [dependencies]
 ahash = "0.7"
 anyhow = "1.0"
-arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "22bf173ec297fbc2ce156bd482cb410b7769073d", default-features = false }
+arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "fb5d4330544d9d746dfc9bdacab5f1f5c1de9203", default-features = false }
 # arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "no_null_propagate_comp", default-features = false }
 # arrow = { package = "arrow2", version = "0.9", default-features = false }
 csv-core = { version = "0.1.10", optional = true }

diff --git a/py-polars/Cargo.lock b/py-polars/Cargo.lock
diff --git a/py-polars/src/arrow_interop/to_py.rs b/py-polars/src/arrow_interop/to_py.rs
@@ -6,8 +6,8 @@ use pyo3::prelude::*;
 
 /// Arrow array to Python.
 pub(crate) fn to_py_array(array: ArrayRef, py: Python, pyarrow: &PyModule) -> PyResult<PyObject> {
-    let array_ptr = Box::new(ffi::Ffi_ArrowArray::empty());
-    let schema_ptr = Box::new(ffi::Ffi_ArrowSchema::empty());
+    let array_ptr = Box::new(ffi::ArrowArray::empty());
+    let schema_ptr = Box::new(ffi::ArrowSchema::empty());
 
     let array_ptr = Box::into_raw(array_ptr);
     let schema_ptr = Box::into_raw(schema_ptr);

diff --git a/py-polars/src/arrow_interop/to_rust.rs b/py-polars/src/arrow_interop/to_rust.rs
@@ -9,11 +9,11 @@ use pyo3::prelude::*;
 
 pub fn array_to_rust(obj: &PyAny) -> PyResult<ArrayRef> {
     // prepare a pointer to receive the Array struct
-    let array = Box::new(ffi::Ffi_ArrowArray::empty());
-    let schema = Box::new(ffi::Ffi_ArrowSchema::empty());
+    let array = Box::new(ffi::ArrowArray::empty());
+    let schema = Box::new(ffi::ArrowSchema::empty());
 
-    let array_ptr = &*array as *const ffi::Ffi_ArrowArray;
-    let schema_ptr = &*schema as *const ffi::Ffi_ArrowSchema;
+    let array_ptr = &*array as *const ffi::ArrowArray;
+    let schema_ptr = &*schema as *const ffi::ArrowSchema;
 
     // make the conversion through PyArrow's private API
     // this changes the pointer's memory and is thus unsafe. In particular, `_export_to_c` can go out of bounds

diff --git a/py-polars/tests/test_datelike.py b/py-polars/tests/test_datelike.py
@@ -1,6 +1,8 @@
+import io
 from datetime import date, datetime, timedelta
 
 import numpy as np
+import pandas as pd
 import pyarrow as pa
 import pytest
 from test_series import verify_series_and_expr_api
@@ -510,3 +512,18 @@ def test_cast_time_units() -> None:
     assert dates.dt.cast_time_unit("ms").cast(int).to_list() == list(
         dates_in_ns // 1_000_000
     )
+
+
+def test_read_utc_times_parquet() -> None:
+    df = pd.DataFrame(
+        data={
+            "Timestamp": pd.date_range(
+                "2022-01-01T00:00+00:00", "2022-01-01T10:00+00:00", freq="H"
+            )
+        }
+    )
+    f = io.BytesIO()
+    df.to_parquet(f)
+    f.seek(0)
+    df_in = pl.read_parquet(f)
+    assert df_in["Timestamp"][0] == datetime(2022, 1, 1, 0, 0)