explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-06 06:30:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Serialize all attrs by default

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-20 15:59:39 +02:00
parent 3241acbe0b
commit f5780cb160
1 changed files with 14 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/tokens/_serialize.py
View File

@ -9,6 +9,19 @@ from ..attrs import SPACY, ORTH, intify_attr
from ..errors import Errors from ..errors import Errors
ALL_ATTRS = (
"ORTH",
"TAG",
"HEAD",
"DEP",
"SENT_START",
"ENT_IOB",
"ENT_TYPE",
"LEMMA",
"MORPH"
)
class DocBin(object): class DocBin(object):
"""Pack Doc objects for binary serialization. """Pack Doc objects for binary serialization.
@ -39,7 +52,7 @@ class DocBin(object):
document from the DocBin. document from the DocBin.
""" """
def __init__(self, attrs=None, store_user_data=False, docs=[]): def __init__(self, attrs=ALL_ATTRS, store_user_data=False, docs=[]):
"""Create a DocBin object to hold serialized annotations. """Create a DocBin object to hold serialized annotations.
attrs (list): List of attributes to serialize. 'orth' and 'spacy' are attrs (list): List of attributes to serialize. 'orth' and 'spacy' are
@ -49,7 +62,6 @@ class DocBin(object):
DOCS: https://spacy.io/api/docbin#init DOCS: https://spacy.io/api/docbin#init
""" """
attrs = attrs or []
attrs = sorted([intify_attr(attr) for attr in attrs]) attrs = sorted([intify_attr(attr) for attr in attrs])
self.attrs = [attr for attr in attrs if attr != ORTH and attr != SPACY] self.attrs = [attr for attr in attrs if attr != ORTH and attr != SPACY]
self.attrs.insert(0, ORTH) # Ensure ORTH is always attrs[0] self.attrs.insert(0, ORTH) # Ensure ORTH is always attrs[0]