Skip to content
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

UDPipe Lemmatizer: remove self.model from pickle #722

Merged
merged 1 commit into from
Oct 8, 2021
Merged

UDPipe Lemmatizer: remove self.model from pickle #722

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
25 changes: 17 additions & 8 deletions orangecontrib/text/preprocess/normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,6 @@ def __init__(self, language='English', use_tokenizer=False):
self.__use_tokenizer = use_tokenizer
self.models = UDPipeModels()
self.__model = None
self.__output_format = None

@property
def use_tokenizer(self):
Expand All @@ -153,7 +152,6 @@ def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:
except StopIteration:
raise UDPipeStopIteration

self.__output_format = udpipe.OutputFormat.newOutputFormat('epe')
if self.__use_tokenizer:
corpus = Preprocessor.__call__(self, corpus)
if callback is None:
Expand Down Expand Up @@ -184,17 +182,28 @@ def __normalize_document(self, document: str) -> List[str]:

def __getstate__(self):
"""
This function remove udpipe.Model that cannot be pickled

Note: __setstate__ is not required since we do not make any harm if
model is not restored. It will be loaded on __call__
This function remove udpipe.Model that cannot be pickled and models that
include absolute paths on computer -- so it is not transferable between
computers.
"""
state = super().__getstate__()
# Remove the unpicklable Model and output format.
# Remove the nonpicklable Model.
state['_UDPipeLemmatizer__model'] = None
state['_UDPipeLemmatizer__output_format'] = None
# models object together with serverfiles store absolute paths to models
# on computers -- we will init it on when unpickling -- setstate
state.pop('models')
return state

def __setstate__(self, state):
"""
Called on unpickling the object. It init new models object which was
deleted from the dictionary in __getstate__.

Note: __model will be loaded on __call__
"""
self.__dict__.update(state)
self.models = UDPipeModels()


class LemmagenLemmatizer(BaseNormalizer):
name = 'Lemmagen Lemmatizer'
Expand Down