Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix tokenizer serialization

This commit is contained in:
Matthew Honnibal 2017-05-31 14:12:38 +02:00
parent 4a398c15b7
commit 0561df2a9d
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/tokenizer.pyx
View File

@ -357,7 +357,7 @@ cdef class Tokenizer:
""" """
serializers = { serializers = {
'vocab': lambda: self.vocab.to_bytes(), 'vocab': lambda: self.vocab.to_bytes(),
'prefix': lambda: self.prefix_search.__self__.pattern, 'prefix_search': lambda: self.prefix_search.__self__.pattern,
'suffix_search': lambda: self.suffix_search.__self__.pattern, 'suffix_search': lambda: self.suffix_search.__self__.pattern,
'infix_finditer': lambda: self.infix_finditer.__self__.pattern, 'infix_finditer': lambda: self.infix_finditer.__self__.pattern,
'token_match': lambda: self.token_match.__self__.pattern, 'token_match': lambda: self.token_match.__self__.pattern,
@ -375,19 +375,19 @@ cdef class Tokenizer:
data = {} data = {}
deserializers = { deserializers = {
'vocab': lambda b: self.vocab.from_bytes(b), 'vocab': lambda b: self.vocab.from_bytes(b),
'prefix': lambda b: data.setdefault('prefix', b), 'prefix_search': lambda b: data.setdefault('prefix', b),
'suffix_search': lambda b: data.setdefault('suffix_search', b), 'suffix_search': lambda b: data.setdefault('suffix_search', b),
'infix_finditer': lambda b: data.setdefault('infix_finditer', b), 'infix_finditer': lambda b: data.setdefault('infix_finditer', b),
'token_match': lambda b: data.setdefault('token_match', b), 'token_match': lambda b: data.setdefault('token_match', b),
'exceptions': lambda b: data.setdefault('rules', b) 'exceptions': lambda b: data.setdefault('rules', b)
} }
msg = util.from_bytes(bytes_data, deserializers, exclude) msg = util.from_bytes(bytes_data, deserializers, exclude)
if 'prefix' in data: if 'prefix_search' in data:
self.prefix_search = re.compile(data['prefix']).search self.prefix_search = re.compile(data['prefix_search']).search
if 'suffix' in data: if 'suffix_search' in data:
self.suffix_search = re.compile(data['suffix']).search self.suffix_search = re.compile(data['suffix_search']).search
if 'infix' in data: if 'infix_finditer' in data:
self.infix_finditer = re.compile(data['infix']).finditer self.infix_finditer = re.compile(data['infix_finditer']).finditer
if 'token_match' in data: if 'token_match' in data:
self.token_match = re.compile(data['token_match']).search self.token_match = re.compile(data['token_match']).search
for string, substrings in data.get('rules', {}).items(): for string, substrings in data.get('rules', {}).items():