[
https://issues.apache.org/jira/browse/ARROW-18411?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
&res updated ARROW-18411:
-------------------------
Description:
By default MapType value fields are nullable:
{code:java}
pa.map_(pa.string(), pa.int32()).item_field.nullable == True {code}
It is possible to mark the value field of a MapType as not-nullable:
{code:java}
pa.map_(pa.string(), pa.field("value", pa.int32(),
nullable=False)).item_field.nullable == False{code}
But comparing these two types, that are semantically different, returns True:
{code:java}
pa.map_(pa.string(), pa.int32()) == pa.map_(pa.string(), pa.field("value",
pa.int32(), nullable=False)) # Returns True {code}
So it looks like the comparison omits the nullable flag.
{code:java}
import pyarrow as pa
map_type = pa.map_(pa.string(), pa.int32())
non_null_map_type = pa.map_(pa.string(), pa.field("value", pa.int32(),
nullable=False))
nullable_map_type = pa.map_(pa.string(), pa.field("value", pa.int32(),
nullable=True))
map_type_different_field_name = pa.map_(pa.string(), pa.field("value",
pa.int32(), nullable=True))
assert nullable_map_type == map_type # Wrong
assert str(nullable_map_type) == str(map_type)
assert str(non_null_map_type) == str(map_type) # Wrong
assert non_null_map_type == map_type
assert non_null_map_type.item_type == map_type.item_type
assert non_null_map_type.item_field != map_type.item_field
assert non_null_map_type.item_field.nullable != map_type.item_field.nullable
assert non_null_map_type.item_field.name == map_type.item_field.name
assert map_type == map_type_different_field_name # This makes sense
{code}
was:
By default MapType value fields are nullable:
{code:java}
pa.map_(pa.string(), pa.int32()).item_field.nullable == True {code}
It is possible to mark the value field of a MapType as not-nullable:
{code:java}
pa.map_(pa.string(), pa.field("value", pa.int32(),
nullable=False)).item_field.nullable == False{code}
But comparing these two types, that are semantically different, returns True:
{code:java}
pa.map_(pa.string(), pa.int32()) == pa.map_(pa.string(), pa.field("value",
pa.int32(), nullable=False)) # Returns True {code}
So it looks like the comparison omits the nullable flag.
{code:java}
import pyarrow as pa
import pytest
print(pa.__version__)
map_type = pa.map_(pa.string(), pa.int32())
pa.array(
[[("one", 1), ("two", 2), ("null", None)]],
map_type
)
with pytest.raises(pa.ArrowInvalid, match=r"Invalid Map: key field can not
contain null values"):
pa.array(
[[("one", 1), ("two", 2), (None, None)]],
map_type
)
map_type = pa.map_(pa.string(), pa.int32())
pa.array(
[[("one", 1), ("two", 2), ("null", None)]],
map_type
)
non_null_map_type = pa.map_(pa.string(), pa.field("value", pa.int32(),
nullable=False))
nullable_map_type = pa.map_(pa.string(), pa.field("value", pa.int32(),
nullable=True))
pa.array(
[[("one", 1), ("two", 2), ("null", None)]],
map_type
)
assert nullable_map_type == map_type # Should be different
assert str(nullable_map_type) == str(map_type)
assert non_null_map_type == map_type
assert non_null_map_type.item_type == map_type.item_type
assert non_null_map_type.item_field != map_type.item_field
assert non_null_map_type.item_field.nullable != map_type.item_field.nullable
assert non_null_map_type.item_field.name == map_type.item_field.name
assert str(non_null_map_type) != str(map_type.item_field.name){code}
> [Python] MapType comparison ignores nullable flag of item_field
> ---------------------------------------------------------------
>
> Key: ARROW-18411
> URL: https://issues.apache.org/jira/browse/ARROW-18411
> Project: Apache Arrow
> Issue Type: Bug
> Components: Python
> Environment: pyarrow==10.0.1
> Reporter: &res
> Priority: Minor
>
> By default MapType value fields are nullable:
> {code:java}
> pa.map_(pa.string(), pa.int32()).item_field.nullable == True {code}
> It is possible to mark the value field of a MapType as not-nullable:
> {code:java}
> pa.map_(pa.string(), pa.field("value", pa.int32(),
> nullable=False)).item_field.nullable == False{code}
> But comparing these two types, that are semantically different, returns True:
> {code:java}
> pa.map_(pa.string(), pa.int32()) == pa.map_(pa.string(), pa.field("value",
> pa.int32(), nullable=False)) # Returns True {code}
> So it looks like the comparison omits the nullable flag.
> {code:java}
> import pyarrow as pa
> map_type = pa.map_(pa.string(), pa.int32())
> non_null_map_type = pa.map_(pa.string(), pa.field("value", pa.int32(),
> nullable=False))
> nullable_map_type = pa.map_(pa.string(), pa.field("value", pa.int32(),
> nullable=True))
> map_type_different_field_name = pa.map_(pa.string(), pa.field("value",
> pa.int32(), nullable=True))
> assert nullable_map_type == map_type # Wrong
> assert str(nullable_map_type) == str(map_type)
> assert str(non_null_map_type) == str(map_type) # Wrong
> assert non_null_map_type == map_type
> assert non_null_map_type.item_type == map_type.item_type
> assert non_null_map_type.item_field != map_type.item_field
> assert non_null_map_type.item_field.nullable != map_type.item_field.nullable
> assert non_null_map_type.item_field.name == map_type.item_field.name
> assert map_type == map_type_different_field_name # This makes sense
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
