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

fix: Add support for pyarrow type large_string #2663

Merged
merged 2 commits into from
Feb 9, 2024
Merged

fix: Add support for pyarrow type large_string #2663

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6ec081f
Add support for pyarrow type large_string
joakibo Feb 8, 2024
b807a1e
Update _data_types.py
joakibo Feb 8, 2024
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
16 changes: 8 additions & 8 deletions awswrangler/_data_types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ def pyarrow2athena( # noqa: PLR0911,PLR0912
return "double"
if pa.types.is_boolean(dtype):
return "boolean"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return "string"
if pa.types.is_timestamp(dtype):
return "timestamp"
Expand Down Expand Up @@ -87,7 +87,7 @@ def pyarrow2redshift( # noqa: PLR0911,PLR0912
return "FLOAT8"
if pa.types.is_boolean(dtype):
return "BOOL"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return string_type
if pa.types.is_timestamp(dtype):
return "TIMESTAMP"
Expand Down Expand Up @@ -132,7 +132,7 @@ def pyarrow2mysql( # noqa: PLR0911,PLR0912
return "DOUBLE PRECISION"
if pa.types.is_boolean(dtype):
return "BOOLEAN"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return string_type
if pa.types.is_timestamp(dtype):
return "TIMESTAMP"
Expand Down Expand Up @@ -167,7 +167,7 @@ def pyarrow2oracle( # noqa: PLR0911
return "BINARY_DOUBLE"
if pa.types.is_boolean(dtype):
return "NUMBER(3)"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return string_type
if pa.types.is_timestamp(dtype):
return "TIMESTAMP"
Expand Down Expand Up @@ -202,7 +202,7 @@ def pyarrow2postgresql( # noqa: PLR0911
return "FLOAT8"
if pa.types.is_boolean(dtype):
return "BOOL"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return string_type
if pa.types.is_timestamp(dtype):
return "TIMESTAMP"
Expand Down Expand Up @@ -237,7 +237,7 @@ def pyarrow2sqlserver( # noqa: PLR0911
return "FLOAT"
if pa.types.is_boolean(dtype):
return "BIT"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return string_type
if pa.types.is_timestamp(dtype):
return "DATETIME2"
Expand Down Expand Up @@ -270,7 +270,7 @@ def pyarrow2timestream(dtype: pa.DataType) -> str: # noqa: PLR0911
return "DOUBLE"
if pa.types.is_boolean(dtype):
return "BOOLEAN"
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return "VARCHAR"
if pa.types.is_date(dtype):
return "DATE"
Expand Down Expand Up @@ -470,7 +470,7 @@ def pyarrow2pandas_extension( # noqa: PLR0911
return pd.UInt64Dtype()
if pa.types.is_boolean(dtype):
return pd.BooleanDtype()
if pa.types.is_string(dtype):
if pa.types.is_string(dtype) or pa.types.is_large_string(dtype):
return pd.StringDtype()
return None

Expand Down
Loading