iemejia commented on code in PR #3861:
URL: https://github.com/apache/avro/pull/3861#discussion_r3570744997
##########
lang/py/avro/io.py:
##########
@@ -599,6 +665,99 @@ def write_timestamp_micros_long(self, datum:
datetime.datetime) -> None:
#
# DatumReader/Writer
#
+#: Environment variable overriding the collection element limits. When set to a
+#: non-negative integer it caps both the number of zero-byte-encoded collection
+#: elements (e.g. an array of nulls) and the structural cap on the total
number of
+#: elements in any collection, allocated from a single decode.
+MAX_COLLECTION_ITEMS_ENV = "AVRO_MAX_COLLECTION_ITEMS"
+
+#: Default maximum number of zero-byte-encoded collection elements to allocate.
+#: Elements whose schema encodes to zero bytes (``null``, a zero-length
``fixed``,
+#: or a record with only zero-byte fields) consume no input, so the
bytes-remaining
+#: check cannot bound their count; without a cap a tiny payload can declare a
huge
+#: block count and exhaust memory. A legitimate collection of zero-byte
elements is
+#: small, so this default is generous while still rejecting pathological
input. It
+#: can be raised (or lowered) with the ``AVRO_MAX_COLLECTION_ITEMS``
environment
+#: variable.
+DEFAULT_MAX_COLLECTION_ITEMS = 10_000_000
+
+#: Default structural cap on the number of elements in any array or map (a
+#: collection larger than this is treated as malformed regardless of element
+#: type). Matches the historical ``Integer.MAX_VALUE - 8`` limit. Elements
with a
+#: positive on-wire size are also bounded by the bytes remaining; this cap is
an
+#: additional overflow/defense-in-depth guard. ``AVRO_MAX_COLLECTION_ITEMS``,
when
+#: set, overrides both this and :data:`DEFAULT_MAX_COLLECTION_ITEMS`.
+DEFAULT_MAX_COLLECTION_STRUCTURAL = (1 << 31) - 1 - 8 # Integer.MAX_VALUE - 8
+
+
+def _collection_limits() -> Tuple[int, int]:
+ """Return ``(zero_byte_limit, structural_limit)``.
+
+ ``AVRO_MAX_COLLECTION_ITEMS``, when set to a non-negative integer, caps
both
+ zero-byte-element collections and all other collections at that value.
+ Otherwise zero-byte elements use the tighter
:data:`DEFAULT_MAX_COLLECTION_ITEMS`
+ and all collections use :data:`DEFAULT_MAX_COLLECTION_STRUCTURAL`.
+ """
+ value = os.environ.get(MAX_COLLECTION_ITEMS_ENV)
+ if value is None:
+ return DEFAULT_MAX_COLLECTION_ITEMS, DEFAULT_MAX_COLLECTION_STRUCTURAL
+ try:
+ parsed = int(value)
+ except ValueError:
+ warnings.warn(avro.errors.AvroWarning(f"Ignoring invalid
{MAX_COLLECTION_ITEMS_ENV} value: {value!r}"))
+ return DEFAULT_MAX_COLLECTION_ITEMS, DEFAULT_MAX_COLLECTION_STRUCTURAL
+ if parsed < 0:
+ warnings.warn(avro.errors.AvroWarning(f"Ignoring negative
{MAX_COLLECTION_ITEMS_ENV} value: {value!r}"))
+ return DEFAULT_MAX_COLLECTION_ITEMS, DEFAULT_MAX_COLLECTION_STRUCTURAL
+ return parsed, parsed
+
+
+def _max_collection_items() -> int:
+ """Return the configured zero-byte-element collection limit."""
+ return _collection_limits()[0]
+
+
+def _min_bytes_per_element(schema: avro.schema.Schema, visited:
Optional[Set[int]] = None) -> int:
+ """
+ Return the minimum number of bytes a single value of ``schema`` can occupy
+ on the wire. Used to reject an array/map block count that could not
possibly
+ be backed by the bytes remaining. A type that can encode to zero bytes
+ (``null``) returns 0, which disables the collection check for it (avoiding
a
+ false positive on, e.g., an array of nulls).
+ """
+ if visited is None:
+ visited = set()
+ schema_type = schema.type
+ if schema_type == "null":
+ return 0
+ if schema_type == "float":
+ return 4
+ if schema_type == "double":
+ return 8
+ if schema_type == "fixed":
+ return getattr(schema, "size", 1)
+ if schema_type in ("record", "error"):
+ # Guard against self-referencing records (recursion would not
terminate).
+ if id(schema) in visited:
+ return 0
Review Comment:
Fixed in a1920ee: `_min_bytes_per_element()` now returns 1 (not 0) when it
detects a recursive record/error reference. A recursive value must terminate
through a union (>= 1 byte branch index) or an empty array/map (>= 1 byte block
count), so 1 is a safe conservative lower bound — recursive records are no
longer treated as zero-byte elements, and unions containing them are not
underestimated. Added a regression test covering the recursive record and a
union containing it.
--
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]
