File size: 11,259 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 |
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
# distutils: language = c++
from pyarrow.includes.common cimport *
from pyarrow.includes.libarrow cimport *
ctypedef CInvalidRowResult PyInvalidRowCallback(object,
const CCSVInvalidRow&)
cdef extern from "arrow/python/csv.h" namespace "arrow::py::csv":
function[CInvalidRowHandler] MakeInvalidRowHandler(
function[PyInvalidRowCallback], object handler)
cdef extern from "arrow/python/api.h" namespace "arrow::py":
# Requires GIL
CResult[shared_ptr[CDataType]] InferArrowType(
object obj, object mask, c_bool pandas_null_sentinels)
cdef extern from "arrow/python/api.h" namespace "arrow::py::internal":
object NewMonthDayNanoTupleType()
CResult[PyObject*] MonthDayNanoIntervalArrayToPyList(
const CMonthDayNanoIntervalArray& array)
CResult[PyObject*] MonthDayNanoIntervalScalarToPyObject(
const CMonthDayNanoIntervalScalar& scalar)
cdef extern from "arrow/python/arrow_to_pandas.h" namespace "arrow::py::MapConversionType":
cdef enum MapConversionType "arrow::py::MapConversionType":
DEFAULT,
LOSSY,
STRICT_
cdef extern from "arrow/python/api.h" namespace "arrow::py" nogil:
shared_ptr[CDataType] GetPrimitiveType(Type type)
object PyHalf_FromHalf(npy_half value)
cdef cppclass PyConversionOptions:
PyConversionOptions()
shared_ptr[CDataType] type
int64_t size
CMemoryPool* pool
c_bool from_pandas
c_bool ignore_timezone
c_bool strict
# TODO Some functions below are not actually "nogil"
CResult[shared_ptr[CChunkedArray]] ConvertPySequence(
object obj, object mask, const PyConversionOptions& options,
CMemoryPool* pool)
CResult[shared_ptr[CDataType]] NumPyDtypeToArrow(object dtype)
CStatus NdarrayToArrow(CMemoryPool* pool, object ao, object mo,
c_bool from_pandas,
const shared_ptr[CDataType]& type,
shared_ptr[CChunkedArray]* out)
CStatus NdarrayToArrow(CMemoryPool* pool, object ao, object mo,
c_bool from_pandas,
const shared_ptr[CDataType]& type,
const CCastOptions& cast_options,
shared_ptr[CChunkedArray]* out)
CStatus NdarrayToTensor(CMemoryPool* pool, object ao,
const vector[c_string]& dim_names,
shared_ptr[CTensor]* out)
CStatus TensorToNdarray(const shared_ptr[CTensor]& tensor, object base,
PyObject** out)
CStatus SparseCOOTensorToNdarray(
const shared_ptr[CSparseCOOTensor]& sparse_tensor, object base,
PyObject** out_data, PyObject** out_coords)
CStatus SparseCSRMatrixToNdarray(
const shared_ptr[CSparseCSRMatrix]& sparse_tensor, object base,
PyObject** out_data, PyObject** out_indptr, PyObject** out_indices)
CStatus SparseCSCMatrixToNdarray(
const shared_ptr[CSparseCSCMatrix]& sparse_tensor, object base,
PyObject** out_data, PyObject** out_indptr, PyObject** out_indices)
CStatus SparseCSFTensorToNdarray(
const shared_ptr[CSparseCSFTensor]& sparse_tensor, object base,
PyObject** out_data, PyObject** out_indptr, PyObject** out_indices)
CStatus NdarraysToSparseCOOTensor(CMemoryPool* pool, object data_ao,
object coords_ao,
const vector[int64_t]& shape,
const vector[c_string]& dim_names,
shared_ptr[CSparseCOOTensor]* out)
CStatus NdarraysToSparseCSRMatrix(CMemoryPool* pool, object data_ao,
object indptr_ao, object indices_ao,
const vector[int64_t]& shape,
const vector[c_string]& dim_names,
shared_ptr[CSparseCSRMatrix]* out)
CStatus NdarraysToSparseCSCMatrix(CMemoryPool* pool, object data_ao,
object indptr_ao, object indices_ao,
const vector[int64_t]& shape,
const vector[c_string]& dim_names,
shared_ptr[CSparseCSCMatrix]* out)
CStatus NdarraysToSparseCSFTensor(CMemoryPool* pool, object data_ao,
object indptr_ao, object indices_ao,
const vector[int64_t]& shape,
const vector[int64_t]& axis_order,
const vector[c_string]& dim_names,
shared_ptr[CSparseCSFTensor]* out)
CStatus TensorToSparseCOOTensor(shared_ptr[CTensor],
shared_ptr[CSparseCOOTensor]* out)
CStatus TensorToSparseCSRMatrix(shared_ptr[CTensor],
shared_ptr[CSparseCSRMatrix]* out)
CStatus TensorToSparseCSCMatrix(shared_ptr[CTensor],
shared_ptr[CSparseCSCMatrix]* out)
CStatus TensorToSparseCSFTensor(shared_ptr[CTensor],
shared_ptr[CSparseCSFTensor]* out)
CStatus ConvertArrayToPandas(const PandasOptions& options,
shared_ptr[CArray] arr,
object py_ref, PyObject** out)
CStatus ConvertChunkedArrayToPandas(const PandasOptions& options,
shared_ptr[CChunkedArray] arr,
object py_ref, PyObject** out)
CStatus ConvertTableToPandas(const PandasOptions& options,
shared_ptr[CTable] table,
PyObject** out)
void c_set_default_memory_pool \
" arrow::py::set_default_memory_pool"(CMemoryPool* pool)\
CMemoryPool* c_get_memory_pool \
" arrow::py::get_memory_pool"()
cdef cppclass PyBuffer(CBuffer):
@staticmethod
CResult[shared_ptr[CBuffer]] FromPyObject(object obj)
cdef cppclass PyForeignBuffer(CBuffer):
@staticmethod
CStatus Make(const uint8_t* data, int64_t size, object base,
shared_ptr[CBuffer]* out)
cdef cppclass PyReadableFile(CRandomAccessFile):
PyReadableFile(object fo)
cdef cppclass PyOutputStream(COutputStream):
PyOutputStream(object fo)
cdef cppclass PandasOptions:
CMemoryPool* pool
c_bool strings_to_categorical
c_bool zero_copy_only
c_bool integer_object_nulls
c_bool date_as_object
c_bool timestamp_as_object
c_bool use_threads
c_bool coerce_temporal_nanoseconds
c_bool ignore_timezone
c_bool deduplicate_objects
c_bool safe_cast
c_bool split_blocks
c_bool self_destruct
MapConversionType maps_as_pydicts
c_bool decode_dictionaries
unordered_set[c_string] categorical_columns
unordered_set[c_string] extension_columns
c_bool to_numpy
cdef extern from "arrow/python/api.h" namespace "arrow::py::internal" nogil:
cdef cppclass CTimePoint "arrow::py::internal::TimePoint":
pass
CTimePoint PyDateTime_to_TimePoint(PyDateTime_DateTime* pydatetime)
int64_t TimePoint_to_ns(CTimePoint val)
CTimePoint TimePoint_from_s(double val)
CTimePoint TimePoint_from_ns(int64_t val)
CResult[c_string] TzinfoToString(PyObject* pytzinfo)
CResult[PyObject*] StringToTzinfo(c_string)
cdef extern from "arrow/python/numpy_init.h" namespace "arrow::py":
int arrow_init_numpy() except -1
cdef extern from "arrow/python/pyarrow.h" namespace "arrow::py":
int import_pyarrow() except -1
cdef extern from "arrow/python/common.h" namespace "arrow::py":
c_bool IsPyError(const CStatus& status)
void RestorePyError(const CStatus& status) except *
cdef extern from "arrow/python/common.h" namespace "arrow::py" nogil:
cdef cppclass SharedPtrNoGIL[T](shared_ptr[T]):
# This looks like the only way to satisfy both Cython 2 and Cython 3
SharedPtrNoGIL& operator=(...)
cdef cppclass UniquePtrNoGIL[T, DELETER=*](unique_ptr[T, DELETER]):
UniquePtrNoGIL& operator=(...)
cdef extern from "arrow/python/inference.h" namespace "arrow::py":
c_bool IsPyBool(object o)
c_bool IsPyInt(object o)
c_bool IsPyFloat(object o)
cdef extern from "arrow/python/ipc.h" namespace "arrow::py":
cdef cppclass CPyRecordBatchReader" arrow::py::PyRecordBatchReader" \
(CRecordBatchReader):
@staticmethod
CResult[shared_ptr[CRecordBatchReader]] Make(shared_ptr[CSchema],
object)
cdef extern from "arrow/python/ipc.h" namespace "arrow::py" nogil:
cdef cppclass CCastingRecordBatchReader" arrow::py::CastingRecordBatchReader" \
(CRecordBatchReader):
@staticmethod
CResult[shared_ptr[CRecordBatchReader]] Make(shared_ptr[CRecordBatchReader],
shared_ptr[CSchema])
cdef extern from "arrow/python/extension_type.h" namespace "arrow::py":
cdef cppclass CPyExtensionType \
" arrow::py::PyExtensionType"(CExtensionType):
@staticmethod
CStatus FromClass(const shared_ptr[CDataType] storage_type,
const c_string extension_name, object typ,
shared_ptr[CExtensionType]* out)
@staticmethod
CStatus FromInstance(shared_ptr[CDataType] storage_type,
object inst, shared_ptr[CExtensionType]* out)
object GetInstance()
CStatus SetInstance(object)
c_string PyExtensionName()
CStatus RegisterPyExtensionType(shared_ptr[CDataType])
CStatus UnregisterPyExtensionType(c_string type_name)
cdef extern from "arrow/python/benchmark.h" namespace "arrow::py::benchmark":
void Benchmark_PandasObjectIsNull(object lst) except *
cdef extern from "arrow/python/gdb.h" namespace "arrow::gdb" nogil:
void GdbTestSession "arrow::gdb::TestSession"()
cdef extern from "arrow/python/helpers.h" namespace "arrow::py::internal":
c_bool IsThreadingEnabled()
|