explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix tag set serialisation

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-29 17:52:36 -05:00
parent 2a061e2777
commit 9bf22a94aa
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
spacy/vocab.pyx
View File

@ -292,10 +292,11 @@ cdef class Vocab:
**exclude: Named attributes to prevent from being serialized. **exclude: Named attributes to prevent from being serialized.
RETURNS (bytes): The serialized form of the `Vocab` object. RETURNS (bytes): The serialized form of the `Vocab` object.
""" """
getters = { getters = OrderedDict((
'strings': lambda: self.strings.to_bytes(), ('strings', lambda: self.strings.to_bytes()),
'lexemes': lambda: self.lexemes_to_bytes() ('lexemes', lambda: self.lexemes_to_bytes()),
} ('tag_map', lambda: self.morphology.tag_map),
))
return util.to_bytes(getters, exclude) return util.to_bytes(getters, exclude)
def from_bytes(self, bytes_data, **exclude): def from_bytes(self, bytes_data, **exclude):
@ -305,9 +306,13 @@ cdef class Vocab:
**exclude: Named attributes to prevent from being loaded. **exclude: Named attributes to prevent from being loaded.
RETURNS (Vocab): The `Vocab` object. RETURNS (Vocab): The `Vocab` object.
""" """
def set_tag_map(tag_map):
self.morphology = Morphology(self.strings, tag_map,
self.morphology.lemmatizer)
setters = OrderedDict(( setters = OrderedDict((
('strings', lambda b: self.strings.from_bytes(b)), ('strings', lambda b: self.strings.from_bytes(b)),
('lexemes', lambda b: self.lexemes_from_bytes(b)) ('lexemes', lambda b: self.lexemes_from_bytes(b)),
('tag_map', lambda b: set_tag_map(b))
)) ))
return util.from_bytes(bytes_data, setters, exclude) return util.from_bytes(bytes_data, setters, exclude)