Skip to content

[PYTHON-4803] Big endian fix for binary bson vectors #1885

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

Merged
merged 2 commits into from
Oct 1, 2024
Merged

[PYTHON-4803] Big endian fix for binary bson vectors #1885

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d6ac0c4
Fix for ZSeries
caseyclements Oct 1, 2024
70d7a41
Endianness take II
caseyclements Oct 1, 2024
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
11 changes: 7 additions & 4 deletions bson/binary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,7 +432,7 @@ def from_vector(
raise NotImplementedError("%s not yet supported" % dtype)

metadata = struct.pack("<sB", dtype.value, padding)
data = struct.pack(f"{len(vector)}{format_str}", *vector)
data = struct.pack(f"<{len(vector)}{format_str}", *vector)
return cls(metadata + data, subtype=VECTOR_SUBTYPE)

def as_vector(self) -> BinaryVector:
Expand All @@ -454,7 +454,7 @@ def as_vector(self) -> BinaryVector:

if dtype == BinaryVectorDtype.INT8:
dtype_format = "b"
format_string = f"{n_values}{dtype_format}"
format_string = f"<{n_values}{dtype_format}"
vector = list(struct.unpack_from(format_string, self, position))
return BinaryVector(vector, dtype, padding)

Expand All @@ -465,13 +465,16 @@ def as_vector(self) -> BinaryVector:
raise ValueError(
"Corrupt data. N bytes for a float32 vector must be a multiple of 4."
)
vector = list(struct.unpack_from(f"{n_values}f", self, position))
dtype_format = "f"
format_string = f"<{n_values}{dtype_format}"
vector = list(struct.unpack_from(format_string, self, position))
return BinaryVector(vector, dtype, padding)

elif dtype == BinaryVectorDtype.PACKED_BIT:
# data packed as uint8
dtype_format = "B"
unpacked_uint8s = list(struct.unpack_from(f"{n_values}{dtype_format}", self, position))
format_string = f"<{n_values}{dtype_format}"
unpacked_uint8s = list(struct.unpack_from(format_string, self, position))
return BinaryVector(unpacked_uint8s, dtype, padding)

else:
Expand Down
Loading