explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 16:22:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add morph rules in Language

Browse Source
This commit is contained in:
Matthew Honnibal 2017-03-15 09:24:40 -05:00
parent 8dbff4f5f4
commit b382dc902c
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/language.py
View File

@ -51,11 +51,15 @@ class BaseDefaults(object):
# This is very messy, but it's the minimal working fix to Issue #639. # This is very messy, but it's the minimal working fix to Issue #639.
# This defaults stuff needs to be refactored (again) # This defaults stuff needs to be refactored (again)
lex_attr_getters[IS_STOP] = lambda string: string.lower() in cls.stop_words lex_attr_getters[IS_STOP] = lambda string: string.lower() in cls.stop_words
return Vocab(lex_attr_getters=lex_attr_getters, tag_map=cls.tag_map, vocab = Vocab(lex_attr_getters=lex_attr_getters, tag_map=cls.tag_map,
lemmatizer=lemmatizer) lemmatizer=lemmatizer)
else: else:
return Vocab.load(nlp.path, lex_attr_getters=cls.lex_attr_getters, vocab = Vocab.load(nlp.path, lex_attr_getters=cls.lex_attr_getters,
tag_map=cls.tag_map, lemmatizer=lemmatizer) tag_map=cls.tag_map, lemmatizer=lemmatizer)
for tag_str, exc in cls.morph_rules.items():
for orth_str, attrs in exc.items():
vocab.morphology.add_special_case(tag_str, orth_str, attrs)
return vocab
@classmethod @classmethod
def add_vectors(cls, nlp=None): def add_vectors(cls, nlp=None):
@ -169,6 +173,7 @@ class BaseDefaults(object):
lemma_rules = {} lemma_rules = {}
lemma_exc = {} lemma_exc = {}
lemma_index = {} lemma_index = {}
morph_rules = {}
lex_attr_getters = { lex_attr_getters = {
attrs.LOWER: lambda string: string.lower(), attrs.LOWER: lambda string: string.lower(),