explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 01:16:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix merge errors

Browse Source
This commit is contained in:
Ines Montani 2020-06-20 16:02:42 +02:00
parent 52728d8fa3
commit 0cdb631e6c
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/pipeline/pipes.pyx
View File

@ -1337,7 +1337,7 @@ class EntityLinker(Pipe):
final_kb_ids.append(self.NIL)
final_tensors.append(sentence_encoding)
sent_doc = doc[start_token:end_token].as_doc()
sent_doc = doc[sent.start:sent.end].as_doc()
# currently, the context is the same for each entity in a sentence (should be refined)
sentence_encoding = self.model([sent_doc])[0]

4
spacy/tokenizer.pyx
View File

@ -782,7 +782,7 @@ cdef class Tokenizer:
"suffix_search": lambda b: data.setdefault("suffix_search", b),
"infix_finditer": lambda b: data.setdefault("infix_finditer", b),
"token_match": lambda b: data.setdefault("token_match", b),
"url_match": lambda b: data.setdefault("url_match", b)
"url_match": lambda b: data.setdefault("url_match", b),
"exceptions": lambda b: data.setdefault("rules", b)
}
exclude = util.get_serialization_exclude(deserializers, exclude, kwargs)
@ -795,7 +795,7 @@ cdef class Tokenizer:
self.infix_finditer = re.compile(data["infix_finditer"]).finditer
if "token_match" in data and isinstance(data["token_match"], str):
self.token_match = re.compile(data["token_match"]).match
if "url_match" in data and isinstance(data["url_match"], basestring_):
if "url_match" in data and isinstance(data["url_match"], str):
self.url_match = re.compile(data["url_match"]).match
if "rules" in data and isinstance(data["rules"], dict):
# make sure to hard reset the cache to remove data from the default exceptions