Skip to content

SNOW-1853347: Add mechanism to allow changing type strs when printing schema #2819

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
sfc-gh-jrose merged 2 commits into from
Jan 6, 2025
Merged

SNOW-1853347: Add mechanism to allow changing type strs when printing schema #2819

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
beb70ea
SNOW-1853347: Add mechanism to allow changing type strs when printing…
sfc-gh-jrose Jan 2, 2025
ff1e514
Merge branch 'main' into jrose_snow_1853347_print_schema_type_map
sfc-gh-jrose Jan 4, 2025
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
11 changes: 9 additions & 2 deletions src/snowflake/snowpark/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5655,7 +5655,10 @@ def convert(col: ColumnOrName) -> Expression:
return exprs

def _format_schema(
self, level: Optional[int] = None, translate_columns: Optional[dict] = None
self,
level: Optional[int] = None,
translate_columns: Optional[dict] = None,
translate_types: Optional[dict] = None,
) -> str:
def _format_datatype(name, dtype, nullable=None, depth=0):
if level is not None and depth >= level:
Expand All @@ -5669,6 +5672,10 @@ def _format_datatype(name, dtype, nullable=None, depth=0):
extra_lines = []
type_str = dtype.__class__.__name__

translated = None
if translate_types:
translated = translate_types.get(type_str, type_str)

# Structured Type format their parameters on multiple lines.
if isinstance(dtype, ArrayType):
extra_lines = [
Expand All @@ -5695,7 +5702,7 @@ def _format_datatype(name, dtype, nullable=None, depth=0):

return "\n".join(
[
f"{prefix} |-- {name}: {type_str}{nullable_str}",
f"{prefix} |-- {name}: {translated or type_str}{nullable_str}",
]
+ [f"{line}" for line in extra_lines if line]
)
Expand Down
13 changes: 13 additions & 0 deletions tests/integ/scala/test_datatype_suite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1077,6 +1077,19 @@ def test_structured_type_print_schema(
== 'root\n |-- "map": MapType (nullable = True)'
)

# Check that column types can be translated
assert (
df._format_schema(
2,
translate_types={
"MapType": "dict",
"StringType": "str",
"ArrayType": "list",
},
)
== 'root\n |-- "MAP": dict (nullable = True)\n | |-- key: str\n | |-- value: list'
)


@pytest.mark.skipif(
"config.getoption('local_testing_mode', default=False)",
Expand Down
Loading