jubins commented on code in PR #59214:
URL: https://github.com/apache/spark/pull/59214#discussion_r4247108318
##########
python/pyspark/sql/variant_utils.py:
##########
@@ -413,10 +417,105 @@ def handle_array(value_pos_list: List[int]) -> str:
if isinstance(value, bytes):
# decoding simply converts byte array to string
return '"' + base64.b64encode(value).decode("utf-8") + '"'
- if isinstance(value, (datetime.date, datetime.datetime)):
+ if isinstance(value, float):
+ return cls._float_to_json(value, is_float32)
+ if isinstance(value, decimal.Decimal):
+ return cls._decimal_to_json(value)
+ if isinstance(value, datetime.datetime):
+ return '"' + cls._timestamp_to_json(value) + '"'
+ if isinstance(value, datetime.date):
return '"' + str(value) + '"'
return str(value)
+ # The helpers below format scalars the same way as the JVM
`Variant.toJson` on JDK 19+, so
+ # that `VariantVal.toJson` and the `to_json` SQL function produce the same
output. On older
+ # JDKs, `to_json` can print a longer, still round-tripping digit string
for some doubles and
+ # floats (see `_float_to_json`).
+
+ @classmethod
+ def _float_to_json(cls, f: float, is_float32: bool) -> str:
+ """
+ Formats a double or float like Java's `Double.toString` and
`Float.toString` on JDK 19+,
+ which print the shortest digits (JDK-4511638). Older JDKs can print a
longer, still
+ round-tripping digit string for some values, e.g. 2^-24 as
5.9604644775390625E-8 instead
+ of 5.960464477539063E-8. Non-finite values are quoted because they are
not valid JSON
+ numbers.
+ """
+ if math.isnan(f):
+ return '"NaN"'
+ if math.isinf(f):
+ return '"Infinity"' if f > 0 else '"-Infinity"'
+
+ def round_trips(s: str) -> bool:
+ if not is_float32:
+ return float(s) == f
+ try:
+ return struct.pack("<f", float(s)) == struct.pack("<f", f)
+ except OverflowError:
+ return False
+
+ # Use an explicit context so that the result does not depend on the
caller's decimal
+ # context, e.g. a lowered `decimal.getcontext().prec`.
+ context = decimal.Context(prec=VariantUtils.MAX_DECIMAL16_PRECISION)
+
+ # Like Java, pick the shortest decimal that round-trips, using at
least 2 significant
+ # digits (e.g. Double.MIN_VALUE is "4.9E-324", not "5.0E-324"), and
the one closest to
+ # `f` among those of that length.
+ for precision in range(2, 18):
Review Comment:
both shortcuts applied, output is unchanged on ~500k doubles and floats, and
a double formats about 5.7x faster.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
