explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

rely on is_empty property instead of __len__ (#12347)

Browse Source
This commit is contained in:
Sofie Van Landeghem 2023-03-01 12:06:07 +01:00 committed by GitHub
parent efbc3d37b3
commit 74cae47bf6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/errors.py
View File

@ -444,8 +444,7 @@ class Errors(metaclass=ErrorsWithCodes):
E133 = ("The sum of prior probabilities for alias '{alias}' should not " E133 = ("The sum of prior probabilities for alias '{alias}' should not "
"exceed 1, but found {sum}.") "exceed 1, but found {sum}.")
E134 = ("Entity '{entity}' is not defined in the Knowledge Base.") E134 = ("Entity '{entity}' is not defined in the Knowledge Base.")
E139 = ("Knowledge base for component '{name}' is empty. Use the methods " E139 = ("Knowledge base for component '{name}' is empty.")
"`kb.add_entity` and `kb.add_alias` to add entries.")
E140 = ("The list of entities, prior probabilities and entity vectors " E140 = ("The list of entities, prior probabilities and entity vectors "
"should be of equal length.") "should be of equal length.")
E141 = ("Entity vectors should be of length {required} instead of the " E141 = ("Entity vectors should be of length {required} instead of the "

3
spacy/kb/kb_in_memory.pyx
View File

@ -46,6 +46,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
self._alias_index = PreshMap(nr_aliases + 1) self._alias_index = PreshMap(nr_aliases + 1)
self._aliases_table = alias_vec(nr_aliases + 1) self._aliases_table = alias_vec(nr_aliases + 1)
def is_empty(self):
return len(self) == 0
def __len__(self): def __len__(self):
return self.get_size_entities() return self.get_size_entities()

2
spacy/pipeline/entity_linker.py
View File

@ -250,7 +250,7 @@ class EntityLinker(TrainablePipe):
# Raise an error if the knowledge base is not initialized. # Raise an error if the knowledge base is not initialized.
if self.kb is None: if self.kb is None:
raise ValueError(Errors.E1018.format(name=self.name)) raise ValueError(Errors.E1018.format(name=self.name))
if len(self.kb) == 0: if hasattr(self.kb, "is_empty") and self.kb.is_empty():
raise ValueError(Errors.E139.format(name=self.name)) raise ValueError(Errors.E139.format(name=self.name))
def initialize( def initialize(

3
spacy/tests/pipeline/test_entity_linker.py
View File

@ -353,6 +353,9 @@ def test_kb_default(nlp):
"""Test that the default (empty) KB is loaded upon construction""" """Test that the default (empty) KB is loaded upon construction"""
entity_linker = nlp.add_pipe("entity_linker", config={}) entity_linker = nlp.add_pipe("entity_linker", config={})
assert len(entity_linker.kb) == 0 assert len(entity_linker.kb) == 0
with pytest.raises(ValueError, match="E139"):
# this raises an error because the KB is empty
entity_linker.validate_kb()
assert entity_linker.kb.get_size_entities() == 0 assert entity_linker.kb.get_size_entities() == 0
assert entity_linker.kb.get_size_aliases() == 0 assert entity_linker.kb.get_size_aliases() == 0
# 64 is the default value from pipeline.entity_linker # 64 is the default value from pipeline.entity_linker