def test_jvm_array_empty(root_allocator):
cls = "org.apache.arrow.vector.{}".format('IntVector')
jvm_vector = jpype.JClass(cls)("vector", root_allocator)
jvm_vector.allocateNew()
jvm_array = pa_jvm.array(jvm_vector)
assert len(jvm_array) == 0
assert jvm_array.type == pa.int32()
def test_jvm_array(root_allocator, pa_type, py_data, jvm_type):
# Create vector
cls = "org.apache.arrow.vector.{}".format(jvm_type)
jvm_vector = jpype.JClass(cls)("vector", root_allocator)
jvm_vector.allocateNew(len(py_data))
for i, val in enumerate(py_data):
jvm_vector.setSafe(i, val)
jvm_vector.setValueCount(len(py_data))
py_array = pa.array(py_data, type=pa_type)
jvm_array = pa_jvm.array(jvm_vector)
assert py_array.equals(jvm_array)
def test_jvm_array(root_allocator, pa_type, py_data, jvm_type):
# Create vector
cls = "org.apache.arrow.vector.{}".format(jvm_type)
jvm_vector = jpype.JClass(cls)("vector", root_allocator)
jvm_vector.allocateNew(len(py_data))
for i, val in enumerate(py_data):
jvm_vector.setSafe(i, val)
jvm_vector.setValueCount(len(py_data))
py_array = pa.array(py_data, type=pa_type)
jvm_array = pa_jvm.array(jvm_vector)
assert py_array.equals(jvm_array)
def test_jvm_string_array(root_allocator):
data = [u"string", None, u"töst"]
cls = "org.apache.arrow.vector.VarCharVector"
jvm_vector = jpype.JClass(cls)("vector", root_allocator)
jvm_vector.allocateNew()
for i, string in enumerate(data):
holder = _string_to_varchar_holder(root_allocator, "string")
jvm_vector.setSafe(i, holder)
jvm_vector.setValueCount(i + 1)
py_array = pa.array(data, type=pa.string())
jvm_array = pa_jvm.array(jvm_vector)
assert py_array.equals(jvm_array)
def test_jvm_string_array(root_allocator):
data = ["string", None, "töst"]
cls = "org.apache.arrow.vector.VarCharVector"
jvm_vector = jpype.JClass(cls)("vector", root_allocator)
jvm_vector.allocateNew()
for i, string in enumerate(data):
holder = _string_to_varchar_holder(root_allocator, "string")
jvm_vector.setSafe(i, holder)
jvm_vector.setValueCount(i + 1)
py_array = pa.array(data, type=pa.string())
jvm_array = pa_jvm.array(jvm_vector)
assert py_array.equals(jvm_array)
def test_jvm_array(root_allocator, pa_type, py_data, jvm_type):
# Create vector
cls = "org.apache.arrow.vector.{}".format(jvm_type)
jvm_vector = jpype.JClass(cls)("vector", root_allocator)
jvm_vector.allocateNew(len(py_data))
for i, val in enumerate(py_data):
# char and int are ambiguous overloads for these two setSafe calls
if jvm_type in {'UInt1Vector', 'UInt2Vector'}:
val = jpype.JInt(val)
jvm_vector.setSafe(i, val)
jvm_vector.setValueCount(len(py_data))
py_array = pa.array(py_data, type=pa_type)
jvm_array = pa_jvm.array(jvm_vector)
assert py_array.equals(jvm_array)