Make Vocab.__contains__ work with ints. Fixes #1868

This commit is contained in:
Matthew Honnibal 2018-01-23 23:26:47 +01:00
parent f3753c2453
commit 43f381ce36
1 changed files with 10 additions and 4 deletions

View File

@ -179,14 +179,20 @@ cdef class Vocab:
self._by_orth.set(lex.orth, <void*>lex)
self.length += 1
def __contains__(self, unicode string):
"""Check whether the string has an entry in the vocabulary.
def __contains__(self, key):
"""Check whether the string or int key has an entry in the vocabulary.
string (unicode): The ID string.
RETURNS (bool) Whether the string has an entry in the vocabulary.
"""
key = hash_string(string)
lex = self._by_hash.get(key)
cdef hash_t int_key
if isinstance(key, bytes):
int_key = hash_string(key.decode('utf8'))
elif isinstance(key, unicode):
int_key = hash_string(key)
else:
int_key = key
lex = self._by_hash.get(int_key)
return lex is not NULL
def __iter__(self):