def test_protobuf():
c = ColumnProfile("col")
for val in [1, 2, 3]:
c.track(val)
msg = c.to_protobuf()
c1 = ColumnProfile.from_protobuf(msg)
assert c1.column_name == c.column_name == "col"
assert hasattr(c1, "number_tracker")
assert hasattr(c1, "string_tracker")
assert c1.string_tracker.length is not None
assert c1.string_tracker.length.count == 0
assert len(c1.string_tracker.char_pos_tracker.character_list) == 56
c1.to_protobuf()
def test_copy_counters_null_count_in_schema_tracker():
col = ColumnProfile("test")
vals = ["a", "b", None, "d", pd.NA, "f", 1.0, 2.0]
for v in vals:
col.track(v)
assert col.schema_tracker.get_count(InferredType.Type.NULL) == 2
# ensuring we can still access the value in summary mode
assert col.to_summary().counters.null_count.value == 2
# Mimic a legal protobuf with null_count set
msg: ColumnMessage = col.to_protobuf()
msg.counters.null_count.value = 2
roundtrip = ColumnProfile.from_protobuf(msg)
assert roundtrip.schema_tracker.get_count(InferredType.Type.NULL) == 4
def test_protobuf():
c = ColumnProfile("col")
for val in [1, 2, 3]:
c.track(val)
msg = c.to_protobuf()
c1 = ColumnProfile.from_protobuf(msg)
assert c1.column_name == c.column_name == "col"
assert hasattr(c1, "number_tracker")
msg2 = c1.to_protobuf()
# We cannot do a straight equality comparison for serialized frequent
# strings objects
compare_frequent_items(
c1.number_tracker.frequent_numbers.get_frequent_items(),
c.number_tracker.frequent_numbers.get_frequent_items(),
)
msg.numbers.frequent_numbers.sketch = bytes()
msg2.numbers.frequent_numbers.sketch = bytes()
