Reject invalid record sizes and return malformed-input errors

Validate payload sizes before record/header writes and make header packing
return io::Result when the total size overflows the format limit.

Return located parse errors for invalid UTF-8 and timestamp year overflow.
Validate cell timestamps consistently in full reads, selected reads, and
hierarchy scans while retaining scan behavior for skipped text geometry.

Add regression coverage for preserved writer outputs, padded metadata sizes,
malformed strings, timestamp boundaries, bounded errors, and Python bindings.
Document the fallible header packing API.

Validation: all 97 Rust tests pass in debug and release; all 16 Python tests
pass against the rebuilt native library.
This commit is contained in:
Jan Petykiewicz 2026-11-16 21:28:54 -08:00
commit 31afef0529

View file

@ -85,6 +85,31 @@ class ArrowTests(unittest.TestCase):
with self.assertRaises(TypeError):
arrow.read_cells_bytes(layout(), [[1.5, 2.5]])
def test_malformed_strings_and_years_raise_located_parse_errors(self):
data = layout()
cell = arrow.scan_bytes(data).field("cells")[0].as_py()[0]
start = cell["struct_start_offset"]
ranges = [[start, cell["struct_end_offset"]]]
cases = [
(38, b"\xff", "Invalid UTF-8"),
(start + 32, b"\xff", "Invalid UTF-8"),
]
cases += [
(offset, b"\x7f\xff", "Timestamp year")
for offset in (10, 22, start + 4, start + 16)
]
for offset, value, message in cases:
malformed = bytearray(data)
malformed[offset:offset + len(value)] = value
for read in (
arrow.read_bytes,
arrow.scan_bytes,
lambda payload: arrow.read_cells_bytes(payload, ranges),
):
with self.subTest(offset=offset, reader=read):
with self.assertRaisesRegex(PheonError, rf"at byte \d+: {message}"):
read(malformed)
def test_import_failure_releases_both_native_outputs(self):
releases = []