Skip to content

perf: only check if field is set #519

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
alaeddine-13 merged 3 commits into from
Sep 5, 2022
Merged

perf: only check if field is set #519

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d365266
perf: only check if field is set
alaeddine-13 Sep 2, 2022
c7af65c
fix: correct _is_not_empty implementation
alaeddine-13 Sep 2, 2022
09fa4fe
Merge branch 'main' into perf-filter-exists
alaeddine-13 Sep 5, 2022
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
4 changes: 3 additions & 1 deletion docarray/array/queryset/lookup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,8 @@
"""
from typing import TYPE_CHECKING

from docarray.document.data import _is_not_empty

if TYPE_CHECKING:
from docarray import Document
import re
Expand Down Expand Up @@ -121,7 +123,7 @@ def lookup(key, val, doc: 'Document') -> bool:

return is_empty != val
else:
return (get_key in doc.non_empty_fields) == val
return (_is_not_empty(get_key, value)) == val
else:
# return value == val
raise ValueError(
Expand Down
40 changes: 23 additions & 17 deletions docarray/document/data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,27 @@
_all_mime_types = set(mimetypes.types_map.values())


def _is_not_empty(attribute, value):
if value is not None:
if attribute not in default_values:
return True
else:
dv = default_values[attribute]
if dv in (
'ChunkArray',
'MatchArray',
'DocumentArray',
list,
dict,
'Dict[str, NamedScore]',
):
if value:
return True
elif value != dv:
return True
return False


@dataclass(unsafe_hash=True, eq=False)
class DocumentData:
_reference_doc: 'Document' = field(hash=False, compare=False)
Expand Down Expand Up @@ -67,23 +88,8 @@ def _non_empty_fields(self) -> Tuple[str]:
f_name = f.name
if not f_name.startswith('_') or f_name == '_metadata':
v = getattr(self, f_name)
if v is not None:
if f_name not in default_values:
r.append(f_name)
else:
dv = default_values[f_name]
if dv in (
'ChunkArray',
'MatchArray',
'DocumentArray',
list,
dict,
'Dict[str, NamedScore]',
):
if v:
r.append(f_name)
elif v != dv:
r.append(f_name)
if _is_not_empty(f_name, v):
r.append(f_name)

return tuple(r)

Expand Down