explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-15 02:32:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix tokenizer serialization

Browse Source
This commit is contained in:
Matthew Honnibal 2018-07-06 12:23:04 +02:00
parent f5703b7a91
commit 1a2f61725c
1 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/tokenizer.pyx
View File

@ -375,11 +375,10 @@ cdef class Tokenizer:
""" """
serializers = OrderedDict(( serializers = OrderedDict((
('vocab', lambda: self.vocab.to_bytes()), ('vocab', lambda: self.vocab.to_bytes()),
('prefix_search', lambda: self.prefix_search.__self__.pattern), ('prefix_search', _get_regex_pattern(self.prefix_search)),
('suffix_search', lambda: self.suffix_search.__self__.pattern), ('suffix_search', _get_regex_pattern(self.suffix_search)),
('infix_finditer', lambda: self.infix_finditer.__self__.pattern), ('infix_finditer', _get_regex_pattern(self.infix_finditer)),
('token_match', lambda: ('token_match', _get_regex_pattern(self.token_match)),
self.token_match.__self__.pattern if self.token_match else None),
('exceptions', lambda: OrderedDict(sorted(self._rules.items()))) ('exceptions', lambda: OrderedDict(sorted(self._rules.items())))
)) ))
return util.to_bytes(serializers, exclude) return util.to_bytes(serializers, exclude)
@ -412,3 +411,7 @@ cdef class Tokenizer:
for string, substrings in data.get('rules', {}).items(): for string, substrings in data.get('rules', {}).items():
self.add_special_case(string, substrings) self.add_special_case(string, substrings)
return self return self
def _get_regex_pattern(regex):
'''Get a pattern string for a regex, or None if the pattern is None.'''
return None if regex is None else regex.__self__.pattern