Skip to content

[Python] support BucketByteBuffer and BucketUUID #2836

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
TGooch44 merged 2 commits into from
Jul 28, 2021
Merged

[Python] support BucketByteBuffer and BucketUUID #2836

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3dd78c7
[Python] support BucketByteBuffer and BucketUUID
jun-he Jul 18, 2021
cecad17
Add additional unit tests for bucket hash methods.
jun-he Jul 26, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 16 additions & 5 deletions python/iceberg/api/transforms/bucket.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
Operation)
from ..types.types import (IntegerType,
TypeID)
from ...api.types.conversions import Conversions


class Bucket(Transform):
Expand Down Expand Up @@ -69,7 +70,7 @@ def __key(self):
return Bucket.__class__, self.n

def __repr__(self):
return "Bucket(n)" % self.n
return "Bucket[%s]" % self.n

def __str__(self):
return "bucket[%s]" % self.n
Expand Down Expand Up @@ -167,14 +168,24 @@ def can_transform(self, type_var):

class BucketByteBuffer(Bucket):
def __init__(self, n):
# super(BucketByteBuffer, self).__init__(n)
raise NotImplementedError()
super(BucketByteBuffer, self).__init__(n)

def hash(self, value):
return Bucket.MURMUR3.hash(value)

def can_transform(self, type_var):
return type_var.type_id in [TypeID.BINARY, TypeID.FIXED]


class BucketUUID(Bucket):
def __init__(self, n):
# super(BucketUUID, self).__init__(n)
raise NotImplementedError()
super(BucketUUID, self).__init__(n)

def hash(self, value):
return Bucket.MURMUR3.hash(Conversions.to_byte_buffer(TypeID.UUID, value))

def can_transform(self, type_var):
return type_var.type_id == TypeID.UUID


def to_bytes(n, length, byteorder='big'):
Expand Down
12 changes: 5 additions & 7 deletions python/tests/api/test_partition_spec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,10 +60,9 @@ def test_transforms(self):
PartitionSpec.builder_for(schema).bucket("ts", 128).build(),
PartitionSpec.builder_for(schema).bucket("dec", 128).build(),
PartitionSpec.builder_for(schema).bucket("s", 128).build(),
# todo support them
# PartitionSpec.builder_for(schema).bucket("u", 128).build(),
# PartitionSpec.builder_for(schema).bucket("f", 128).build(),
# PartitionSpec.builder_for(schema).bucket("b", 128).build(),
PartitionSpec.builder_for(schema).bucket("u", 128).build(),
PartitionSpec.builder_for(schema).bucket("f", 128).build(),
PartitionSpec.builder_for(schema).bucket("b", 128).build(),
PartitionSpec.builder_for(schema).year("d").build(),
PartitionSpec.builder_for(schema).month("d").build(),
PartitionSpec.builder_for(schema).day("d").build(),
Expand All @@ -75,9 +74,8 @@ def test_transforms(self):
PartitionSpec.builder_for(schema).truncate("l", 10).build(),
PartitionSpec.builder_for(schema).truncate("dec", 10).build(),
PartitionSpec.builder_for(schema).truncate("s", 10).build(),
# todo support them
# PartitionSpec.builder_for(schema).add_without_field_id(6, "dec_unsupported", "unsupported").build(),
# PartitionSpec.builder_for(schema).add(6, 1111, "dec_unsupported", "unsupported").build(),
PartitionSpec.builder_for(schema).add_without_field_id(6, "dec_unsupported", "unsupported").build(),
PartitionSpec.builder_for(schema).add(6, 1111, "dec_unsupported", "unsupported").build(),
]

for spec in specs:
Expand Down