mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
Remove trailing whitespace
This commit is contained in:
parent
5f0f940a1f
commit
3a8d9b37a6
|
@ -30,5 +30,3 @@ def main(text_loc):
|
|||
|
||||
if __name__ == '__main__':
|
||||
plac.call(main)
|
||||
|
||||
|
||||
|
|
|
@ -11,5 +11,3 @@ The CLA must be signed on your first pull request. To do this, simply fill in th
|
|||
$ git add -A spaCy/contributors/<your GitHub username>.md
|
||||
|
||||
Now finish your pull request, and you're done.
|
||||
|
||||
|
||||
|
|
|
@ -75,4 +75,3 @@ Boolean features
|
|||
+-------------+--------------------------------------------------------------+
|
||||
| IN_LIST | Facility for loading arbitrary run-time word lists? |
|
||||
+-------------+--------------------------------------------------------------+
|
||||
|
||||
|
|
|
@ -68,4 +68,3 @@ Cons:
|
|||
- Higher memory usage (up to 1gb)
|
||||
- More conceptually complicated
|
||||
- Tokenization rules expressed in code, not as data
|
||||
|
||||
|
|
|
@ -260,5 +260,3 @@ these models is really all about the data structures. We want to stay small,
|
|||
and stay contiguous. Minimize redundancy and minimize pointer chasing.
|
||||
That's why Cython is so well suited to this: we get to lay out our data
|
||||
structures, and manage the memory ourselves, with full C-level control.
|
||||
|
||||
|
||||
|
|
|
@ -278,6 +278,3 @@ sentence represents the document as a whole.
|
|||
|
||||
Document Model
|
||||
--------------
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -234,4 +234,3 @@ Features
|
|||
+---------+-----------------------------------------------------------+
|
||||
| prob | Log probability of word, smoothed with Simple Good-Turing |
|
||||
+---------+-----------------------------------------------------------+
|
||||
|
||||
|
|
|
@ -79,5 +79,3 @@ cpdef enum attr_id_t:
|
|||
POS
|
||||
TAG
|
||||
DEP
|
||||
|
||||
|
||||
|
|
|
@ -22,4 +22,3 @@ cdef class EnPosTagger:
|
|||
|
||||
cdef int set_morph(self, const int i, const PosTag* tag, TokenC* tokens) except -1
|
||||
cdef int lemmatize(self, const univ_pos_t pos, const LexemeC* lex) except -1
|
||||
|
||||
|
|
|
@ -381,4 +381,3 @@ cdef inline void _fill_from_token(atom_t* context, const TokenC* t) nogil:
|
|||
context[7] = 4
|
||||
else:
|
||||
context[7] = 0
|
||||
|
||||
|
|
|
@ -149,5 +149,3 @@ cpdef enum:
|
|||
|
||||
|
||||
cdef int fill_context(atom_t* context, State* s, Tokens tokens) except -1
|
||||
|
||||
|
||||
|
|
|
@ -15,4 +15,3 @@ cdef class Span:
|
|||
cdef public Span head
|
||||
cdef public list rights
|
||||
cdef public list lefts
|
||||
|
||||
|
|
|
@ -280,5 +280,3 @@ class OracleError(Exception):
|
|||
|
||||
class UnknownMove(Exception):
|
||||
pass
|
||||
|
||||
|
||||
|
|
|
@ -13,5 +13,3 @@ class Config(object):
|
|||
@classmethod
|
||||
def read(cls, model_dir, name):
|
||||
return cls(**json.load(open(path.join(model_dir, '%s.json' % name))))
|
||||
|
||||
|
||||
|
|
|
@ -608,4 +608,3 @@ _parse_unset_error = """Text has not been parsed, so cannot be accessed.
|
|||
Check that the parser data is installed. Run "python -m spacy.en.download" if not.
|
||||
Check whether parse=False in the call to English.__call__
|
||||
"""
|
||||
|
||||
|
|
|
@ -94,5 +94,3 @@ ctypedef uint64_t flags_t
|
|||
ctypedef uint32_t id_t
|
||||
ctypedef uint16_t len_t
|
||||
ctypedef uint16_t tag_t
|
||||
|
||||
|
||||
|
|
|
@ -33,4 +33,3 @@ cdef class Vocab:
|
|||
cdef int _add_lex_to_vocab(self, hash_t key, const LexemeC* lex) except -1
|
||||
|
||||
cdef PreshMap _map
|
||||
|
||||
|
|
|
@ -30,6 +30,3 @@ def test_align_continue():
|
|||
assert aligned[2] == ('re-align', [(5, 7), (7, 8), (8, 13)])
|
||||
assert aligned[3] == ('and', [(13, 16)])
|
||||
assert aligned[4] == ('continue', [(16, 24)])
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -37,5 +37,3 @@ def test_dep():
|
|||
assert feats_array[1][1] == tokens[1].dep
|
||||
assert feats_array[2][1] == tokens[2].dep
|
||||
assert feats_array[3][1] == tokens[3].dep
|
||||
|
||||
|
||||
|
|
|
@ -35,4 +35,3 @@ def test_merge_heads():
|
|||
def test_issue_54():
|
||||
text = u'Talks given by women had a slightly higher number of questions asked (3.2$\pm$0.2) than talks given by men (2.6$\pm$0.1).'
|
||||
tokens = NLU(text, merge_mwes=True)
|
||||
|
||||
|
|
|
@ -33,4 +33,3 @@ def test_word():
|
|||
def test_not_number():
|
||||
assert not like_number('dog')
|
||||
assert not like_number(',')
|
||||
|
||||
|
|
|
@ -58,4 +58,3 @@ def test_child_consistency(nlp, sun_text):
|
|||
assert not children
|
||||
for head_index, children in rights.items():
|
||||
assert not children
|
||||
|
||||
|
|
|
@ -49,4 +49,3 @@ def test_three_same_close(close_puncts, EN):
|
|||
def test_double_end_quote(EN):
|
||||
assert len(EN("Hello''")) == 2
|
||||
assert len(EN("''")) == 1
|
||||
|
||||
|
|
|
@ -16,6 +16,3 @@ def test_one(EN):
|
|||
assert tokens[0].orth_ == 'Betty'
|
||||
tokens2 = EN('Betty also bought a pound of butter.')
|
||||
assert tokens2[0].orth_ == 'Betty'
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -16,4 +16,3 @@ def test_subtrees():
|
|||
assert len(list(bus.children)) == 1
|
||||
|
||||
assert len(list(wheels.subtree)) == 6
|
||||
|
||||
|
|
|
@ -35,5 +35,3 @@ def test_single_token_string():
|
|||
nlp = English()
|
||||
tokens = nlp(u'foobar')
|
||||
assert tokens[0].string == 'foobar'
|
||||
|
||||
|
||||
|
|
|
@ -39,5 +39,3 @@ def test_newline_double_space(EN):
|
|||
def test_newline_space_wrap(EN):
|
||||
tokens = EN('hello \n possums')
|
||||
assert len(tokens) == 3
|
||||
|
||||
|
||||
|
|
Loading…
Reference in New Issue
Block a user