explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/explosion/spaCy

Browse Source
This commit is contained in:
Ines Montani 2019-09-29 17:30:46 +02:00
commit 8489ec08ba
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/matcher/phrasematcher.pyx
View File

@ -49,7 +49,7 @@ cdef class PhraseMatcher:
self._terminal_hash = 826361138722620965 self._terminal_hash = 826361138722620965
map_init(self.mem, self.c_map, 8) map_init(self.mem, self.c_map, 8)
if isinstance(attr, long): if isinstance(attr, (int, long)):
self.attr = attr self.attr = attr
else: else:
attr = attr.upper() attr = attr.upper()
@ -79,7 +79,7 @@ cdef class PhraseMatcher:
return key in self._callbacks return key in self._callbacks
def __reduce__(self): def __reduce__(self):
data = (self.vocab, self._docs, self._callbacks) data = (self.vocab, self._docs, self._callbacks, self.attr)
return (unpickle_matcher, data, None, None) return (unpickle_matcher, data, None, None)
def remove(self, key): def remove(self, key):
@ -171,6 +171,7 @@ cdef class PhraseMatcher:
for doc in docs: for doc in docs:
if len(doc) == 0: if len(doc) == 0:
continue continue
if isinstance(doc, Doc):
if self.attr in (POS, TAG, LEMMA) and not doc.is_tagged: if self.attr in (POS, TAG, LEMMA) and not doc.is_tagged:
raise ValueError(Errors.E155.format()) raise ValueError(Errors.E155.format())
if self.attr == DEP and not doc.is_parsed: if self.attr == DEP and not doc.is_parsed:
@ -179,7 +180,6 @@ cdef class PhraseMatcher:
and self.attr not in (DEP, POS, TAG, LEMMA): and self.attr not in (DEP, POS, TAG, LEMMA):
string_attr = self.vocab.strings[self.attr] string_attr = self.vocab.strings[self.attr]
user_warning(Warnings.W012.format(key=key, attr=string_attr)) user_warning(Warnings.W012.format(key=key, attr=string_attr))
if isinstance(doc, Doc):
keyword = self._convert_to_array(doc) keyword = self._convert_to_array(doc)
else: else:
keyword = doc keyword = doc
@ -310,8 +310,8 @@ cdef class PhraseMatcher:
return [Token.get_struct_attr(&doc.c[i], self.attr) for i in range(len(doc))] return [Token.get_struct_attr(&doc.c[i], self.attr) for i in range(len(doc))]
def unpickle_matcher(vocab, docs, callbacks): def unpickle_matcher(vocab, docs, callbacks, attr):
matcher = PhraseMatcher(vocab) matcher = PhraseMatcher(vocab, attr=attr)
for key, specs in docs.items(): for key, specs in docs.items():
callback = callbacks.get(key, None) callback = callbacks.get(key, None)
matcher.add(key, callback, *specs) matcher.add(key, callback, *specs)