Github user zasdfgbnm commented on a diff in the pull request:
https://github.com/apache/spark/pull/18444#discussion_r127521525
--- Diff: python/pyspark/sql/types.py ---
@@ -915,6 +916,90 @@ def _parse_datatype_json_value(json_value):
long: LongType,
})
+# Mapping Python array types to Spark SQL DataType
+# We should be careful here. The size of these types in python depends on C
+# implementation. We need to make sure that this conversion does not lose
any
+# precision.
+#
+# Reference for C integer size, see:
+# ISO/IEC 9899:201x specification, chapter 5.2.4.2.1 Sizes of integer
types <limits.h>.
+# Reference for python array typecode, see:
+# https://docs.python.org/2/library/array.html
+# https://docs.python.org/3.6/library/array.html
+
+_array_int_typecode_ctype_mappings = {
+ 'b': ctypes.c_byte,
+ 'B': ctypes.c_ubyte,
+ 'h': ctypes.c_short,
+ 'H': ctypes.c_ushort,
+ 'i': ctypes.c_int,
+ 'I': ctypes.c_uint,
+ 'l': ctypes.c_long,
+ 'L': ctypes.c_ulong
+}
+
+# TODO: Uncomment this when 'q' and 'Q' are supported by
net.razorvine.pickle
+# Type code 'q' and 'Q' are not available at python 2
+# if sys.version_info[0] >= 3:
+# _array_int_typecode_ctype_mappings.update({
+# 'q': ctypes.c_longlong,
+# 'Q': ctypes.c_ulonglong
+# })
+
+
+def _int_size_to_type(size):
+ """
+ Return the Scala type from the size of integers.
+ """
+ if size <= 8:
+ return ByteType
+ if size <= 16:
+ return ShortType
+ if size <= 32:
+ return IntegerType
+ if size <= 64:
+ return LongType
+ raise TypeError("not supported type: integer size too large.")
+
+# The list of all supported array typecodes is stored here
+_array_type_mappings = {
+ # Warning: Actual properties for float and double in C is not
specified in C.
+ # On almost every system supported by both python and JVM, they are
IEEE 754
+ # single-precision binary floating-point format and IEEE 754
double-precision
+ # binary floating-point format. And we do assume the same thing here
for now.
+ 'f': FloatType,
+ 'd': DoubleType
+}
+
+# compute array typecode mappings for integer types
+for _typecode in _array_int_typecode_ctype_mappings.keys():
+ size = ctypes.sizeof(_array_int_typecode_ctype_mappings[_typecode]) * 8
+ if _typecode.isupper(): # 1 extra bit is required to store unsigned
types
--- End diff --
This is actually a good suggestion!
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
