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

Fix tokenizer serialization if token_match is None

This commit is contained in:
Matthew Honnibal 2018-06-29 14:24:46 +02:00
parent e0860bcfb3
commit 46d8a66fef
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/tokenizer.pyx
View File

@ -378,7 +378,8 @@ cdef class Tokenizer:
('prefix_search', lambda: self.prefix_search.__self__.pattern),
('suffix_search', lambda: self.suffix_search.__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 if self.token_match else None),
('exceptions', lambda: OrderedDict(sorted(self._rules.items())))
))
return util.to_bytes(serializers, exclude)
@ -406,7 +407,7 @@ cdef class Tokenizer:
self.suffix_search = re.compile(data['suffix_search']).search
if 'infix_finditer' in data:
self.infix_finditer = re.compile(data['infix_finditer']).finditer
if 'token_match' in data:
if data.get('token_match'):
self.token_match = re.compile(data['token_match']).search
for string, substrings in data.get('rules', {}).items():
self.add_special_case(string, substrings)