zeroshade commented on code in PR #35769:
URL: https://github.com/apache/arrow/pull/35769#discussion_r1237575843
##########
dev/archery/archery/integration/datagen.py:
##########
@@ -743,6 +763,72 @@ class LargeStringColumn(_BaseStringColumn,
_LargeOffsetsMixin):
pass
+class BinaryViewColumn(PrimitiveColumn):
+
+ def _encode_value(self, x):
+ return frombytes(binascii.hexlify(x).upper())
+
+ def _get_buffers(self):
+ char_buffers = []
+ DEFAULT_BUFFER_SIZE = 32 # ¯\_(ツ)_/¯
+ INLINE_SIZE = 12
+
+ data = []
+ for i, v in enumerate(self.values):
+ if not self.is_valid[i]:
+ v = b''
+ assert isinstance(v, bytes)
+
+ if len(v) > INLINE_SIZE:
+ offset = 0
+ if len(v) > DEFAULT_BUFFER_SIZE:
+ char_buffers.append(v)
+ else:
+ if len(char_buffers) == 0:
+ char_buffers.append(v)
+ elif len(char_buffers[-1]) + len(v) > DEFAULT_BUFFER_SIZE:
+ char_buffers.append(v)
+ else:
+ offset = len(char_buffers[-1])
+ char_buffers[-1] += v
+ assert len(char_buffers[-1]) <= DEFAULT_BUFFER_SIZE
Review Comment:
@bkietz Is there a reason for this assert to exist given the if/elif clauses
above it? I pretty much just took this from your C++ PR for the integration
tests.
--
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]
