Skip to content
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

Jump to bottom

Nested struct binary comparison operator support #6062

Merged
merged 7 commits into from
Aug 12, 2022
Merged

Nested struct binary comparison operator support #6062

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
36867cd
struct binop support
rwlee Jul 21, 2022
2dfe2f0
Merge remote-tracking branch 'pub/branch-22.08' into rwlee/structbinops
rwlee Jul 21, 2022
1a61988
Merge remote-tracking branch 'pub/branch-22.08' into rwlee/structbinops
rwlee Jul 27, 2022
6388743
Merge remote-tracking branch 'pub/branch-22.08' into rwlee/structbinops
rwlee Jul 28, 2022
663ad20
switch to integration tests
rwlee Aug 1, 2022
e6321b3
Merge remote-tracking branch 'pub/branch-22.08' into rwlee/structbinops
rwlee Aug 1, 2022
0419d31
avoid DayTimeIntervalGen errors with < 330
rwlee Aug 3, 2022
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
20 changes: 10 additions & 10 deletions docs/supported_ops.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5406,7 +5406,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand All @@ -5427,7 +5427,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand Down Expand Up @@ -6298,7 +6298,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand All @@ -6319,7 +6319,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand Down Expand Up @@ -6456,7 +6456,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand All @@ -6477,7 +6477,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand Down Expand Up @@ -7847,7 +7847,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand All @@ -7868,7 +7868,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand Down Expand Up @@ -8005,7 +8005,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand All @@ -8026,7 +8026,7 @@ are limited.
<td><b>NS</b></td>
<td><b>NS</b></td>
<td> </td>
<td><b>NS</b></td>
<td><em>PS<br/>UTC is only supported TZ for child TIMESTAMP;<br/>unsupported child types BINARY, CALENDAR, ARRAY, UDT</em></td>
<td><b>NS</b></td>
</tr>
<tr>
Expand Down
167 changes: 102 additions & 65 deletions integration_tests/src/main/python/cmp_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
from pyspark.sql.types import *
import pyspark.sql.functions as f

@pytest.mark.parametrize('data_gen', eq_gens_with_decimal_gen, ids=idfn)
@pytest.mark.parametrize('data_gen', eq_gens_with_decimal_gen + struct_gens_sample_with_decimal128_no_list, ids=idfn)
def test_eq(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
Expand All @@ -34,16 +34,23 @@ def test_eq(data_gen):

@pytest.mark.skipif(is_before_spark_330(), reason='DayTimeInterval is not supported before Pyspark 3.3.0')
def test_eq_for_interval():
data_gen = DayTimeIntervalGen()
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') == s1,
s2 == f.col('b'),
f.lit(None).cast(data_type) == f.col('a'),
f.col('b') == f.lit(None).cast(data_type),
f.col('a') == f.col('b')))
def test_func(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') == s1,
s2 == f.col('b'),
f.lit(None).cast(data_type) == f.col('a'),
f.col('b') == f.lit(None).cast(data_type),
f.col('a') == f.col('b')))
# DayTimeIntervalType not supported inside Structs -- issue #6184
# data_gens = [DayTimeIntervalGen(),
# StructGen([['child0', StructGen([['child2', DayTimeIntervalGen()]])], ['child1', short_gen]])]
data_gens = [DayTimeIntervalGen()]
for data_gen in data_gens:
test_func(data_gen)


@pytest.mark.parametrize('data_gen', eq_gens_with_decimal_gen, ids=idfn)
def test_eq_ns(data_gen):
Expand All @@ -70,7 +77,7 @@ def test_eq_ns_for_interval():
f.col('b').eqNullSafe(f.lit(None).cast(data_type)),
f.col('a').eqNullSafe(f.col('b'))))

@pytest.mark.parametrize('data_gen', eq_gens_with_decimal_gen, ids=idfn)
@pytest.mark.parametrize('data_gen', eq_gens_with_decimal_gen + struct_gens_sample_with_decimal128_no_list, ids=idfn)
def test_ne(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
Expand All @@ -84,18 +91,24 @@ def test_ne(data_gen):

@pytest.mark.skipif(is_before_spark_330(), reason='DayTimeInterval is not supported before Pyspark 3.3.0')
def test_ne_for_interval():
data_gen = DayTimeIntervalGen()
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') != s1,
s2 != f.col('b'),
f.lit(None).cast(data_type) != f.col('a'),
f.col('b') != f.lit(None).cast(data_type),
f.col('a') != f.col('b')))
def test_func(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') != s1,
s2 != f.col('b'),
f.lit(None).cast(data_type) != f.col('a'),
f.col('b') != f.lit(None).cast(data_type),
f.col('a') != f.col('b')))
# DayTimeIntervalType not supported inside Structs -- issue #6184
# data_gens = [DayTimeIntervalGen(),
# StructGen([['child0', StructGen([['child2', DayTimeIntervalGen()]])], ['child1', short_gen]])]
data_gens = [DayTimeIntervalGen()]
for data_gen in data_gens:
test_func(data_gen)

@pytest.mark.parametrize('data_gen', orderable_gens, ids=idfn)
@pytest.mark.parametrize('data_gen', orderable_gens + struct_gens_sample_with_decimal128_no_list, ids=idfn)
def test_lt(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
Expand All @@ -109,18 +122,24 @@ def test_lt(data_gen):

@pytest.mark.skipif(is_before_spark_330(), reason='DayTimeInterval is not supported before Pyspark 3.3.0')
def test_lt_for_interval():
data_gen = DayTimeIntervalGen()
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') < s1,
s2 < f.col('b'),
f.lit(None).cast(data_type) < f.col('a'),
f.col('b') < f.lit(None).cast(data_type),
f.col('a') < f.col('b')))
def test_func(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') < s1,
s2 < f.col('b'),
f.lit(None).cast(data_type) < f.col('a'),
f.col('b') < f.lit(None).cast(data_type),
f.col('a') < f.col('b')))
# DayTimeIntervalType not supported inside Structs -- issue #6184
# data_gens = [DayTimeIntervalGen(),
# StructGen([['child0', StructGen([['child2', DayTimeIntervalGen()]])], ['child1', short_gen]])]
data_gens = [DayTimeIntervalGen()]
for data_gen in data_gens:
test_func(data_gen)

@pytest.mark.parametrize('data_gen', orderable_gens, ids=idfn)
@pytest.mark.parametrize('data_gen', orderable_gens + struct_gens_sample_with_decimal128_no_list, ids=idfn)
def test_lte(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
Expand All @@ -134,16 +153,22 @@ def test_lte(data_gen):

@pytest.mark.skipif(is_before_spark_330(), reason='DayTimeInterval is not supported before Pyspark 3.3.0')
def test_lte_for_interval():
data_gen = DayTimeIntervalGen()
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') <= s1,
s2 <= f.col('b'),
f.lit(None).cast(data_type) <= f.col('a'),
f.col('b') <= f.lit(None).cast(data_type),
f.col('a') <= f.col('b')))
def test_func(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') <= s1,
s2 <= f.col('b'),
f.lit(None).cast(data_type) <= f.col('a'),
f.col('b') <= f.lit(None).cast(data_type),
f.col('a') <= f.col('b')))
# DayTimeIntervalType not supported inside Structs -- issue #6184
# data_gens = [DayTimeIntervalGen(),
# StructGen([['child0', StructGen([['child2', DayTimeIntervalGen()]])], ['child1', short_gen]])]
data_gens = [DayTimeIntervalGen()]
for data_gen in data_gens:
test_func(data_gen)


@pytest.mark.parametrize('data_gen', orderable_gens, ids=idfn)
Expand All @@ -160,18 +185,24 @@ def test_gt(data_gen):

@pytest.mark.skipif(is_before_spark_330(), reason='DayTimeInterval is not supported before Pyspark 3.3.0')
def test_gt_interval():
data_gen = DayTimeIntervalGen()
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') > s1,
s2 > f.col('b'),
f.lit(None).cast(data_type) > f.col('a'),
f.col('b') > f.lit(None).cast(data_type),
f.col('a') > f.col('b')))
def test_func(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') > s1,
s2 > f.col('b'),
f.lit(None).cast(data_type) > f.col('a'),
f.col('b') > f.lit(None).cast(data_type),
f.col('a') > f.col('b')))
# DayTimeIntervalType not supported inside Structs -- issue #6184
# data_gens = [DayTimeIntervalGen(),
# StructGen([['child0', StructGen([['child2', DayTimeIntervalGen()]])], ['child1', short_gen]])]
data_gens = [DayTimeIntervalGen()]
for data_gen in data_gens:
test_func(data_gen)

@pytest.mark.parametrize('data_gen', orderable_gens, ids=idfn)
@pytest.mark.parametrize('data_gen', orderable_gens + struct_gens_sample_with_decimal128_no_list, ids=idfn)
def test_gte(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
Expand All @@ -185,16 +216,22 @@ def test_gte(data_gen):

@pytest.mark.skipif(is_before_spark_330(), reason='DayTimeInterval is not supported before Pyspark 3.3.0')
def test_gte_for_interval():
data_gen = DayTimeIntervalGen()
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') >= s1,
s2 >= f.col('b'),
f.lit(None).cast(data_type) >= f.col('a'),
f.col('b') >= f.lit(None).cast(data_type),
f.col('a') >= f.col('b')))
def test_func(data_gen):
(s1, s2) = gen_scalars(data_gen, 2, force_no_nulls=not isinstance(data_gen, NullGen))
data_type = data_gen.data_type
assert_gpu_and_cpu_are_equal_collect(
lambda spark : binary_op_df(spark, data_gen).select(
f.col('a') >= s1,
s2 >= f.col('b'),
f.lit(None).cast(data_type) >= f.col('a'),
f.col('b') >= f.lit(None).cast(data_type),
f.col('a') >= f.col('b')))
# DayTimeIntervalType not supported inside Structs -- issue #6184
# data_gens = [DayTimeIntervalGen(),
# StructGen([['child0', StructGen([['child2', DayTimeIntervalGen()]])], ['child1', short_gen]])]
data_gens = [DayTimeIntervalGen()]
for data_gen in data_gens:
test_func(data_gen)

@pytest.mark.parametrize('data_gen', eq_gens_with_decimal_gen + array_gens_sample + struct_gens_sample + map_gens_sample, ids=idfn)
def test_isnull(data_gen):
Expand Down
5 changes: 5 additions & 0 deletions integration_tests/src/main/python/data_gen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -953,11 +953,16 @@ def gen_scalars_for_sql(data_gen, count, seed=0, force_no_nulls=False):
nonempty_struct_gens_sample = [all_basic_struct_gen,
StructGen([['child0', byte_gen], ['child1', all_basic_struct_gen]]),
StructGen([['child0', ArrayGen(short_gen)], ['child1', double_gen]])]
nonempty_struct_gens_sample_no_list = [all_basic_struct_gen,
StructGen([['child0', byte_gen], ['child1', all_basic_struct_gen]]),
StructGen([['child0', short_gen], ['child1', double_gen]])]

struct_gens_sample = nonempty_struct_gens_sample + [StructGen([])]
struct_gens_sample_no_list = nonempty_struct_gens_sample_no_list + [StructGen([])]
struct_gen_decimal128 = StructGen(
[['child' + str(ind), sub_gen] for ind, sub_gen in enumerate([decimal_gen_128bit])])
struct_gens_sample_with_decimal128 = struct_gens_sample + [struct_gen_decimal128]
struct_gens_sample_with_decimal128_no_list = struct_gens_sample_no_list + [struct_gen_decimal128]

simple_string_to_string_map_gen = MapGen(StringGen(pattern='key_[0-9]', nullable=False),
StringGen(), max_length=10)
Expand Down
Loading