From ee81a96c9ead5975e70208d5ba9f4a7a09e6398c Mon Sep 17 00:00:00 2001
From: ijl <ijl@mailbox.org>
Date: Mon, 15 Apr 2024 13:59:17 +0000
Subject: [PATCH] numpy serialization rejects non-native endianness

---
 README.md                       |  8 ++++++--
 src/serialize/error.rs          |  5 +++++
 src/serialize/per_type/numpy.rs | 13 ++++++++++++-
 test/test_numpy.py              | 11 +++++++++++
 4 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 1bbcad6f..724bde5e 100644
--- a/README.md
+++ b/README.md
@@ -864,8 +864,12 @@ b'"2021-01-01T00:00:00+00:00"'
 If an array is not a contiguous C array, contains an unsupported datatype,
 or contains a `numpy.datetime64` using an unsupported representation
 (e.g., picoseconds), orjson falls through to `default`. In `default`,
-`obj.tolist()` can be specified. If an array is malformed, which
-is not expected, `orjson.JSONEncodeError` is raised.
+`obj.tolist()` can be specified.
+
+If an array is not in the native endianness, e.g., an array of big-endian values
+on a little-endian system, `orjson.JSONEncodeError`  is raised.
+
+If an array is malformed, `orjson.JSONEncodeError` is raised.
 
 This measures serializing 92MiB of JSON from an `numpy.ndarray` with
 dimensions of `(50000, 100)` and `numpy.float64` values:
diff --git a/src/serialize/error.rs b/src/serialize/error.rs
index f1acd629..744404be 100644
--- a/src/serialize/error.rs
+++ b/src/serialize/error.rs
@@ -17,6 +17,7 @@ pub enum SerializeError {
     DictKeyInvalidType,
     NumpyMalformed,
     NumpyNotCContiguous,
+    NumpyNotNativeEndian,
     NumpyUnsupportedDatatype,
     UnsupportedType(NonNull<pyo3_ffi::PyObject>),
 }
@@ -48,6 +49,10 @@ impl std::fmt::Display for SerializeError {
                 f,
                 "numpy array is not C contiguous; use ndarray.tolist() in default"
             ),
+            SerializeError::NumpyNotNativeEndian => write!(
+                f,
+                "numpy array is not native-endianness"
+            ),
             SerializeError::NumpyUnsupportedDatatype => {
                 write!(f, "unsupported datatype in numpy array")
             }
diff --git a/src/serialize/per_type/numpy.rs b/src/serialize/per_type/numpy.rs
index dede7996..045f9553 100644
--- a/src/serialize/per_type/numpy.rs
+++ b/src/serialize/per_type/numpy.rs
@@ -42,6 +42,9 @@ impl<'a> Serialize for NumpySerializer<'a> {
             Err(PyArrayError::NotContiguous) => {
                 err!(SerializeError::NumpyNotCContiguous)
             }
+            Err(PyArrayError::NotNativeEndian) => {
+                err!(SerializeError::NumpyNotNativeEndian)
+            }
             Err(PyArrayError::UnsupportedDataType) => {
                 err!(SerializeError::NumpyUnsupportedDatatype)
             }
@@ -101,6 +104,9 @@ pub struct PyCapsule {
 
 // https://docs.scipy.org/doc/numpy/reference/arrays.interface.html#c.__array_struct__
 
+const NPY_ARRAY_C_CONTIGUOUS: c_int = 0x1;
+const NPY_ARRAY_NOTSWAPPED: c_int = 0x200;
+
 #[repr(C)]
 pub struct PyArrayInterface {
     pub two: c_int,
@@ -154,9 +160,11 @@ impl ItemType {
         }
     }
 }
+
 pub enum PyArrayError {
     Malformed,
     NotContiguous,
+    NotNativeEndian,
     UnsupportedDataType,
 }
 
@@ -187,9 +195,12 @@ impl NumpyArray {
         if unsafe { (*array).two != 2 } {
             ffi!(Py_DECREF(capsule));
             Err(PyArrayError::Malformed)
-        } else if unsafe { (*array).flags } & 0x1 != 0x1 {
+        } else if unsafe { (*array).flags } & NPY_ARRAY_C_CONTIGUOUS != NPY_ARRAY_C_CONTIGUOUS {
             ffi!(Py_DECREF(capsule));
             Err(PyArrayError::NotContiguous)
+        } else if unsafe { (*array).flags } & NPY_ARRAY_NOTSWAPPED != NPY_ARRAY_NOTSWAPPED {
+            ffi!(Py_DECREF(capsule));
+            Err(PyArrayError::NotNativeEndian)
         } else {
             let num_dimensions = unsafe { (*array).nd as usize };
             if num_dimensions == 0 {
diff --git a/test/test_numpy.py b/test/test_numpy.py
index e997ae76..28eacd5a 100644
--- a/test/test_numpy.py
+++ b/test/test_numpy.py
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: (Apache-2.0 OR MIT)
 
 
+import sys
+
 import pytest
 
 import orjson
@@ -864,3 +866,12 @@ def test_numpy_float64(self):
                 [-1.7976931348623157e308, 1.7976931348623157e308], numpy.float64
             )
         )
+
+
+@pytest.mark.skipif(numpy is None, reason="numpy is not installed")
+class NumpyEndianness:
+    def test_numpy_array_dimension_zero(self):
+        wrong_endianness = ">" if sys.byteorder == "little" else "<"
+        array = numpy.array([0, 1, 0.4, 5.7], dtype=f"{wrong_endianness}f8")
+        with pytest.raises(orjson.JSONEncodeError):
+            orjson.dumps(array, option=orjson.OPT_SERIALIZE_NUMPY)