explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-07 21:33:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix missing n_patterns property in Matcher class. Fix from_dir method

Browse Source
This commit is contained in:
Matthew Honnibal 2015-08-26 19:17:02 +02:00
parent 3acf60df06
commit 430affc347
1 changed files with 14 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
spacy/matcher.pyx
View File

@ -99,7 +99,7 @@ def map_attr_name(attr):
cdef class Matcher: cdef class Matcher:
cdef Pool mem cdef Pool mem
cdef vector[Pattern*] patterns cdef vector[Pattern*] patterns
cdef readonly int n_patterns cdef readonly Vocab vocab
def __init__(self, vocab, patterns): def __init__(self, vocab, patterns):
self.mem = Pool() self.mem = Pool()
@ -107,6 +107,19 @@ cdef class Matcher:
for entity_key, (etype, attrs, specs) in sorted(patterns.items()): for entity_key, (etype, attrs, specs) in sorted(patterns.items()):
self.add(entity_key, etype, attrs, specs) self.add(entity_key, etype, attrs, specs)
@classmethod
def from_dir(cls, data_dir, Vocab vocab):
patterns_loc = path.join(data_dir, 'vocab', 'gazetteer.json')
if path.exists(patterns_loc):
patterns_data = open(patterns_loc).read()
patterns = json.loads(patterns_data)
return cls(vocab, patterns)
else:
return cls(vocab, {})
property n_patterns:
def __get__(self): return self.patterns.size()
def add(self, entity_key, etype, attrs, specs): def add(self, entity_key, etype, attrs, specs):
if isinstance(entity_key, basestring): if isinstance(entity_key, basestring):
entity_key = self.vocab.strings[entity_key] entity_key = self.vocab.strings[entity_key]
@ -120,16 +133,6 @@ cdef class Matcher:
spec = _convert_strings(spec, self.vocab.strings) spec = _convert_strings(spec, self.vocab.strings)
self.patterns.push_back(init_pattern(self.mem, spec, etype)) self.patterns.push_back(init_pattern(self.mem, spec, etype))
@classmethod
def from_dir(cls, vocab, data_dir):
patterns_loc = path.join(data_dir, 'vocab', 'gazetteer.json')
if path.exists(patterns_loc):
patterns_data = open(patterns_loc).read()
patterns = json.loads(patterns_data)
return cls(vocab, patterns)
else:
return cls(vocab, {})
def __call__(self, Doc doc): def __call__(self, Doc doc):
cdef vector[Pattern*] partials cdef vector[Pattern*] partials
cdef int n_partials = 0 cdef int n_partials = 0