GH-50398/GH-50829 2/6: Remove pyarrow.benchmark and simplify parse helpers

python/CMakeLists.txt

@@ -386,7 +386,6 @@ configure_file("${PYARROW_CPP_SOURCE_DIR}/config_internal.h.cmake"
 
 set(PYARROW_CPP_SRCS
     ${PYARROW_CPP_SOURCE_DIR}/arrow_to_pandas.cc
-    ${PYARROW_CPP_SOURCE_DIR}/benchmark.cc
     ${PYARROW_CPP_SOURCE_DIR}/common.cc
     ${PYARROW_CPP_SOURCE_DIR}/config.cc
     ${PYARROW_CPP_SOURCE_DIR}/datetime.cc

python/pyarrow/includes/libarrow_python.pxd

@@ -279,10 +279,6 @@ cdef extern from "arrow/python/extension_type.h" namespace "arrow::py":
     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"()
 

python/pyarrow/io.pxi

@@ -415,7 +415,7 @@ cdef class NativeFile(_Weakrefable):
         # Allocate empty write space
         obj = PyBytes_FromStringAndSizeNative(NULL, c_nbytes)
 
-        cdef uint8_t* buf = <uint8_t*> cp.PyBytes_AS_STRING(<object> obj)
+        cdef uint8_t* buf = <uint8_t*> cp.PyBytes_AsString(<object> obj)
         with nogil:
             bytes_read = GetResultValue(handle.get().Read(c_nbytes, buf))
 
@@ -488,7 +488,7 @@ cdef class NativeFile(_Weakrefable):
         # Allocate empty write space
         obj = PyBytes_FromStringAndSizeNative(NULL, c_nbytes)
 
-        cdef uint8_t* buf = <uint8_t*> cp.PyBytes_AS_STRING(<object> obj)
+        cdef uint8_t* buf = <uint8_t*> cp.PyBytes_AsString(<object> obj)
         with nogil:
             bytes_read = GetResultValue(handle.get().
                                         ReadAt(c_offset, c_nbytes, buf))
@@ -1614,7 +1614,7 @@ cdef class Buffer(_Weakrefable):
         if buffer.buf == NULL:
             # ARROW-16048: Ensure we don't export a NULL address.
             assert buffer.len == 0
-            buffer.buf = cp.PyBytes_AS_STRING(b"")
+            buffer.buf = cp.PyBytes_AsString(b"")
         buffer.format = 'b'
         buffer.internal = NULL
         buffer.itemsize = 1
@@ -2643,7 +2643,7 @@ cdef class Codec(_Weakrefable):
 
         if asbytes:
             pyobj = PyBytes_FromStringAndSizeNative(NULL, max_output_size)
-            output_buffer = <uint8_t*> cp.PyBytes_AS_STRING(<object> pyobj)
+            output_buffer = <uint8_t*> cp.PyBytes_AsString(<object> pyobj)
         else:
             out_buf = allocate_buffer(
                 max_output_size, memory_pool=memory_pool, resizable=True
@@ -2705,7 +2705,7 @@ cdef class Codec(_Weakrefable):
 
         if asbytes:
             pybuf = cp.PyBytes_FromStringAndSize(NULL, output_size)
-            output_buffer = <uint8_t*> cp.PyBytes_AS_STRING(pybuf)
+            output_buffer = <uint8_t*> cp.PyBytes_AsString(pybuf)
         else:
             out_buf = allocate_buffer(output_size, memory_pool=memory_pool)
             output_buffer = out_buf.buffer.get().mutable_data()

python/pyarrow/lib.pyx

@@ -243,8 +243,5 @@ include "io.pxi"
 # IPC / Messaging
 include "ipc.pxi"
 
-# Micro-benchmark routines
-include "benchmark.pxi"
-
 # Public API
 include "public-api.pxi"

python/pyarrow/src/arrow/python/arrow_to_pandas.cc

@@ -1027,8 +1027,8 @@ Status ConvertMap(PandasOptions options, const ChunkedArray& data,
           return CheckPyError();
         },
         [&list_item](int64_t idx, OwnedRef& key_value, OwnedRef& item_value) {
-          PyList_SET_ITEM(list_item.obj(), idx,
-                          PyTuple_Pack(2, key_value.obj(), item_value.obj()));
+          PyList_SetItem(list_item.obj(), idx,
+                         PyTuple_Pack(2, key_value.obj(), item_value.obj()));
           return CheckPyError();
         },
         [&list_item] { return list_item.detach(); }, data, py_keys, py_items, item_arrays,

python/pyarrow/src/arrow/python/common.h

@@ -23,9 +23,11 @@
 #include <utility>
 
 #include "arrow/buffer.h"
+#include "arrow/python/helpers.h"
 #include "arrow/python/pyarrow.h"
 #include "arrow/python/visibility.h"
 #include "arrow/result.h"
+#include "arrow/util/logging.h"
 #include "arrow/util/macros.h"
 
 namespace arrow {
@@ -398,12 +400,14 @@ struct PyBytesView {
   // View the given Python object as binary-like, i.e. bytes
   Status ParseBinary(PyObject* obj) {
     if (PyBytes_Check(obj)) {
-      bytes = PyBytes_AS_STRING(obj);
-      size = PyBytes_GET_SIZE(obj);
+      bytes = PyBytes_AsString(obj);
+      size = PyBytes_Size(obj);
+      ARROW_DCHECK(!PyErr_Occurred());
       is_utf8 = false;
     } else if (PyByteArray_Check(obj)) {
-      bytes = PyByteArray_AS_STRING(obj);
-      size = PyByteArray_GET_SIZE(obj);
+      bytes = PyByteArray_AsString(obj);
+      size = PyByteArray_Size(obj);
+      ARROW_DCHECK(!PyErr_Occurred());
       is_utf8 = false;
     } else if (PyMemoryView_Check(obj)) {
       PyObject* ref = PyMemoryView_GetContiguous(obj, PyBUF_READ, 'C');
@@ -413,8 +417,8 @@ struct PyBytesView {
       size = buffer->len;
       is_utf8 = false;
     } else {
-      return Status::TypeError("Expected bytes, got a '", Py_TYPE(obj)->tp_name,
-                               "' object");
+      return Status::TypeError("Expected bytes, got a '",
+                               internal::PyObject_StdStringTypeName(obj), "' object");
     }
     return Status::OK();
   }
@@ -425,10 +429,12 @@ struct PyBytesView {
     RETURN_IF_PYERROR();
     if (!PyBytes_Check(ref.obj())) {
       return Status::TypeError("Expected uuid.UUID.bytes to return bytes, got '",
-                               Py_TYPE(ref.obj())->tp_name, "' object");
+                               internal::PyObject_StdStringTypeName(ref.obj()),
+                               "' object");
     }
-    bytes = PyBytes_AS_STRING(ref.obj());
-    size = PyBytes_GET_SIZE(ref.obj());
+    bytes = PyBytes_AsString(ref.obj());
+    size = PyBytes_Size(ref.obj());
+    ARROW_DCHECK(!PyErr_Occurred());
     is_utf8 = false;
     return Status::OK();
   }

python/pyarrow/src/arrow/python/datetime.cc

@@ -58,7 +58,7 @@ constexpr char* NonConst(const char* st) {
   return const_cast<char*>(st);
 }
 
-static PyTypeObject MonthDayNanoTupleType = {};
+static PyTypeObject* MonthDayNanoTupleType = nullptr;
 
 static PyStructSequence_Field MonthDayNanoField[] = {
     {NonConst("months"), NonConst("The number of months in the interval")},
@@ -67,8 +67,13 @@ static PyStructSequence_Field MonthDayNanoField[] = {
     {nullptr, nullptr}};
 
 static PyStructSequence_Desc MonthDayNanoTupleDesc = {
-    NonConst("MonthDayNano"),
-    NonConst("A calendar interval consisting of months, days and nanoseconds."),
+    NonConst("pyarrow.lib.MonthDayNano"),
+    NonConst("A calendar interval consisting of months, days and nanoseconds.\n"
+             "\n"
+             "Parameters\n"
+             "----------\n"
+             "iterable : sequence\n"
+             "    The months, days and nanoseconds fields of the interval.\n"),
     MonthDayNanoField,
     /*n_in_sequence=*/3};
 
@@ -274,13 +279,14 @@ static inline Status PyDate_convert_int(int64_t val, const DateUnit unit, int64_
 }
 
 PyObject* NewMonthDayNanoTupleType() {
-  if (MonthDayNanoTupleType.tp_name == nullptr) {
-    if (PyStructSequence_InitType2(&MonthDayNanoTupleType, &MonthDayNanoTupleDesc) != 0) {
+  if (MonthDayNanoTupleType == nullptr) {
+    MonthDayNanoTupleType = PyStructSequence_NewType(&MonthDayNanoTupleDesc);
+    if (MonthDayNanoTupleType == nullptr) {
       Py_FatalError("Could not initialize MonthDayNanoTuple");
     }
   }
-  Py_INCREF(&MonthDayNanoTupleType);
-  return (PyObject*)&MonthDayNanoTupleType;
+  Py_INCREF(MonthDayNanoTupleType);
+  return (PyObject*)MonthDayNanoTupleType;
 }
 
 Status PyTime_from_int(int64_t val, const TimeUnit::type unit, PyObject** out) {
@@ -596,7 +602,7 @@ Result<std::string> TzinfoToString(PyObject* tzinfo) {
 
 PyObject* MonthDayNanoIntervalToNamedTuple(
     const MonthDayNanoIntervalType::MonthDayNanos& interval) {
-  OwnedRef tuple(PyStructSequence_New(&MonthDayNanoTupleType));
+  OwnedRef tuple(PyStructSequence_New(MonthDayNanoTupleType));
   if (ARROW_PREDICT_FALSE(tuple.obj() == nullptr)) {
     return nullptr;
   }

python/pyarrow/src/arrow/python/decimal.cc

@@ -159,7 +159,7 @@ Status InternalDecimalFromPyObject(PyObject* obj, const DecimalType& arrow_type,
     return InternalDecimalFromPythonDecimal<ArrowDecimal>(obj, arrow_type, out);
   } else {
     return Status::TypeError("int or Decimal object expected, got ",
-                             Py_TYPE(obj)->tp_name);
+                             internal::PyObject_StdStringTypeName(obj));
   }
 }
 

python/pyarrow/src/arrow/python/extension_type.cc

@@ -78,8 +78,8 @@ std::string PyExtensionType::ToString(bool show_metadata) const {
 
   std::stringstream ss;
   OwnedRef instance(GetInstance());
-  ss << "extension<" << this->extension_name() << "<" << Py_TYPE(instance.obj())->tp_name
-     << ">>";
+  ss << "extension<" << this->extension_name() << "<"
+     << internal::PyObject_StdStringTypeName(instance.obj()) << ">>";
   return ss.str();
 }