AlenkaF commented on code in PR #47663:
URL: https://github.com/apache/arrow/pull/47663#discussion_r3180256853
##########
python/pyarrow/tests/test_csv.py:
##########
@@ -1381,6 +1393,58 @@ def test_column_types_with_column_names(self):
'y': ['b', 'd', 'f'],
}
+ def test_default_column_type(self):
+ rows = b"a,b,c,d\n001,2.5,hello,true\n4,3.14,world,false\n"
+
+ # Test with default_column_type only -
+ # all columns should use the specified type.
+ opts = ConvertOptions(default_column_type=pa.string())
+ table = self.read_bytes(rows, convert_options=opts)
+ schema = pa.schema([('a', pa.string()),
+ ('b', pa.string()),
+ ('c', pa.string()),
+ ('d', pa.string())])
+ assert table.schema == schema
+ assert table.to_pydict() == {
+ 'a': ["001", "4"],
+ 'b': ["2.5", "3.14"],
+ 'c': ["hello", "world"],
+ 'd': ["true", "false"],
+ }
+
+ # Test with both column_types and default_column_type
+ # Columns specified in column_types should override default_column_type
+ opts = ConvertOptions(
+ column_types={'b': pa.float64(), 'd': pa.bool_()},
+ default_column_type=pa.string()
+ )
+ table = self.read_bytes(rows, convert_options=opts)
+ schema = pa.schema([('a', pa.string()),
+ ('b', pa.float64()),
+ ('c', pa.string()),
+ ('d', pa.bool_())])
+ assert table.schema == schema
+ assert table.to_pydict() == {
+ 'a': ["001", "4"],
+ 'b': [2.5, 3.14],
+ 'c': ["hello", "world"],
+ 'd': [True, False],
+ }
+
+ # Test that default_column_type disables type inference
+ opts_no_default = ConvertOptions(column_types={'b': pa.float64()})
+ table_no_default = self.read_bytes(rows,
convert_options=opts_no_default)
+
+ opts_with_default = ConvertOptions(
+ column_types={'b': pa.float64()},
+ default_column_type=pa.string()
+ )
+ table_with_default = self.read_bytes(rows,
convert_options=opts_with_default)
+
+ # Column 'a' should be int64 without default, string with default
+ assert table_no_default.schema.field('a').type == pa.int64()
+ assert table_with_default.schema.field('a').type == pa.string()
Review Comment:
Could we add an assert for `b` column also? (being `float` in both cases)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
