Skip to content

[py] reject negative enum and union index in binary decoder #3876

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

Open
arib06 wants to merge 1 commit into
base: main
Choose a base branch
from
+19 −3
Open

[py] reject negative enum and union index in binary decoder #3876

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions lang/py/avro/io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -765,7 +765,7 @@ def read_enum(self, writers_schema: avro.schema.EnumSchema, readers_schema: avro
"""
# read data
index_of_symbol = decoder.read_int()
if index_of_symbol >= len(writers_schema.symbols):
if not 0 <= index_of_symbol < len(writers_schema.symbols):
raise avro.errors.SchemaResolutionException(
f"Can't access enum index {index_of_symbol} for enum with {len(writers_schema.symbols)} symbols", writers_schema, readers_schema
)
Expand Down Expand Up @@ -864,7 +864,7 @@ def read_union(self, writers_schema: avro.schema.UnionSchema, readers_schema: av
"""
# schema resolution
index_of_schema = int(decoder.read_long())
if index_of_schema >= len(writers_schema.schemas):
if not 0 <= index_of_schema < len(writers_schema.schemas):
raise avro.errors.SchemaResolutionException(
f"Can't access branch index {index_of_schema} for union with {len(writers_schema.schemas)} branches", writers_schema, readers_schema
)
Expand All @@ -875,7 +875,7 @@ def read_union(self, writers_schema: avro.schema.UnionSchema, readers_schema: av

def skip_union(self, writers_schema: avro.schema.UnionSchema, decoder: BinaryDecoder) -> None:
index_of_schema = int(decoder.read_long())
if index_of_schema >= len(writers_schema.schemas):
if not 0 <= index_of_schema < len(writers_schema.schemas):
raise avro.errors.SchemaResolutionException(
f"Can't access branch index {index_of_schema} for union with {len(writers_schema.schemas)} branches", writers_schema
)
Expand Down
16 changes: 16 additions & 0 deletions lang/py/avro/test/test_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -598,6 +598,22 @@ def test_unknown_symbol(self) -> None:
datum_reader = avro.io.DatumReader(writers_schema, readers_schema)
self.assertRaises(avro.errors.SchemaResolutionException, datum_reader.read, decoder)

def test_negative_enum_index(self) -> None:
# A negative zigzag-encoded index (0x01 -> -1) must be rejected rather than
# silently wrapping to symbols[-1] via Python negative indexing.
writers_schema = avro.schema.parse(json.dumps({"type": "enum", "name": "Test", "symbols": ["FOO", "BAR"]}))
decoder = avro.io.BinaryDecoder(io.BytesIO(b"\x01"))
datum_reader = avro.io.DatumReader(writers_schema, writers_schema)
self.assertRaises(avro.errors.SchemaResolutionException, datum_reader.read, decoder)

def test_negative_union_index(self) -> None:
# A negative branch index must be rejected rather than selecting schemas[-1]
# and decoding the payload with the wrong branch schema.
writers_schema = avro.schema.parse(json.dumps(["null", "string", "long"]))
decoder = avro.io.BinaryDecoder(io.BytesIO(b"\x01\x08"))
datum_reader = avro.io.DatumReader(writers_schema, writers_schema)
self.assertRaises(avro.errors.SchemaResolutionException, datum_reader.read, decoder)

def test_no_default_value(self) -> None:
writers_schema = LONG_RECORD_SCHEMA
datum_to_write = LONG_RECORD_DATUM
Expand Down
Loading