Skip to content

Feat json array #2

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
RStar2022 wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Feat json array #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
fc34e94
add len on DocIndex
RStar2022 Apr 25, 2023
509e918
Merge branch 'main' into feat-len
RStar2022 Apr 25, 2023
a7b0df0
add json-array
RStar2022 Apr 26, 2023
776427d
Merge branch 'main' into feat-json-array
RStar2022 Apr 26, 2023
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
15 changes: 12 additions & 3 deletions docarray/array/doc_list/io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,8 +46,8 @@
T = TypeVar('T', bound='IOMixinArray')
T_doc = TypeVar('T_doc', bound=BaseDoc)

ARRAY_PROTOCOLS = {'protobuf-array', 'pickle-array'}
SINGLE_PROTOCOLS = {'pickle', 'protobuf'}
ARRAY_PROTOCOLS = {'protobuf-array', 'pickle-array', 'json-array'}
SINGLE_PROTOCOLS = {'pickle', 'protobuf', 'json'}
ALLOWED_PROTOCOLS = ARRAY_PROTOCOLS.union(SINGLE_PROTOCOLS)
ALLOWED_COMPRESSIONS = {'lz4', 'bz2', 'lzma', 'zlib', 'gzip'}

Expand Down Expand Up @@ -180,6 +180,8 @@ def _write_bytes(
f.write(self.to_protobuf().SerializePartialToString())
elif protocol == 'pickle-array':
f.write(pickle.dumps(self))
elif protocol == 'json-array':
f.write(self.to_json())
elif protocol in SINGLE_PROTOCOLS:
f.write(
b''.join(
Expand Down Expand Up @@ -575,7 +577,11 @@ def _load_binary_all(
else:
d = fp.read()

if protocol is not None and protocol in ('pickle-array', 'protobuf-array'):
if protocol is not None and protocol in (
'pickle-array',
'protobuf-array',
'json-array',
):
if _get_compress_ctx(algorithm=compress) is not None:
d = _decompress_bytes(d, algorithm=compress)
compress = None
Expand All @@ -590,6 +596,9 @@ def _load_binary_all(
elif protocol is not None and protocol == 'pickle-array':
return pickle.loads(d)

elif protocol is not None and protocol == 'json-array':
return cls.from_json(d)

# Binary format for streaming case
else:
from rich import filesize
Expand Down
4 changes: 2 additions & 2 deletions tests/units/array/test_array_save_load.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ class MyDoc(BaseDoc):

@pytest.mark.slow
@pytest.mark.parametrize(
'protocol', ['pickle-array', 'protobuf-array', 'protobuf', 'pickle']
'protocol', ['pickle-array', 'protobuf-array', 'protobuf', 'pickle', 'json-array']
)
@pytest.mark.parametrize('compress', ['lz4', 'bz2', 'lzma', 'zlib', 'gzip', None])
@pytest.mark.parametrize('show_progress', [False, True])
Expand Down Expand Up @@ -52,7 +52,7 @@ def test_array_save_load_binary(protocol, compress, tmp_path, show_progress):

@pytest.mark.slow
@pytest.mark.parametrize(
'protocol', ['pickle-array', 'protobuf-array', 'protobuf', 'pickle']
'protocol', ['pickle-array', 'protobuf-array', 'protobuf', 'pickle', 'json-array']
)
@pytest.mark.parametrize('compress', ['lz4', 'bz2', 'lzma', 'zlib', 'gzip', None])
@pytest.mark.parametrize('show_progress', [False, True])
Expand Down