[SPARK-53355][PYTHON][SQL] fix numpy 1.x repr in type tests

### What changes were proposed in this pull request?

- this is a minor followup to #52105, we noticed that the test breaks in two spark master runs with a different env
- the root cause was that numpy 1.x implements `__repr__` differently

### Why are the changes needed?

- fix `Build / Python-only (master, Minimum dependencies of PySpark)`

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?

ran tests locally with numpy 1.22.4

### Was this patch authored or co-authored using generative AI tooling?

No

Closes #52247 from benrobby/SPARK-53355-fix-numpy-repr.

Authored-by: Ben Hurdelhey <[email protected]>
Signed-off-by: Ruifeng Zheng <[email protected]>

Author: benhurdelhey

python/pyspark/sql/tests/udf_type_tests/test_udf_input_types.py

@@ -115,7 +115,38 @@ def value_udf(x):
                     return x
 
                 def value_str(x):
-                    return str(x)
+                    class NpPrintable:
+                        def __init__(self, x):
+                            self.x = x
+
+                        def __repr__(self):
+                            return f"np.{self.x.dtype}({self.x.item()})"
+
+                    # Numpy 1.x __repr__ returns a different format, see
+                    # https://numpy.org/doc/stable/release/2.0.0-notes.html#representation-of-numpy-scalars-changed # noqa: E501
+                    # We only care about types and values of the elements,
+                    # so we accept this difference and implement our own repr to make
+                    # tests with numpy 1 return the same format as numpy 2.
+                    def convert_to_numpy_printable(x):
+                        import numpy as np
+
+                        if isinstance(x, Row):
+                            converted_values = tuple(convert_to_numpy_printable(v) for v in x)
+                            new_row = Row(*converted_values)
+                            new_row.__fields__ = x.__fields__
+                            return new_row
+                        elif isinstance(x, (list)):
+                            return [convert_to_numpy_printable(elem) for elem in x]
+                        elif isinstance(x, tuple):
+                            return tuple(convert_to_numpy_printable(elem) for elem in x)
+                        elif isinstance(x, dict):
+                            return {k: convert_to_numpy_printable(v) for k, v in x.items()}
+                        elif isinstance(x, np.generic):
+                            return NpPrintable(x)
+                        else:
+                            return x
+
+                    return str(convert_to_numpy_printable(x))
 
                 type_test_udf = udf(type_udf, returnType=StringType(), useArrow=use_arrow)
                 value_test_udf = udf(value_udf, returnType=spark_type, useArrow=use_arrow)