explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-22 01:51:58 +03:00
Code Issues Packages Projects Releases Wiki Activity

Minor updates based on review

Browse Source
This commit is contained in:
Patrick J. Burns 2023-04-20 09:34:48 -04:00
parent cc238c83e8
commit eb544903ec
3 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/la/lex_attrs.py
View File

@ -10,10 +10,12 @@ _num_words = """unus una unum duo duae tres tria quattuor quinque sex septem oct
""".split()
_num_words += [item.replace("v", "u") for item in _num_words]
_num_words = set(_num_words)
_ordinal_words = """primus prima primum secundus secunda secundum tertius tertia tertium quartus quarta quartum quintus quinta quintum sextus sexta sextum septimus septima septimum octavus octava octavum nonus nona nonum decimus decima decimum undecimus undecima undecimum duodecimus duodecima duodecimum duodevicesimus duodevicesima duodevicesimum undevicesimus undevicesima undevicesimum vicesimus vicesima vicesimum tricesimus tricesima tricesimum quadragesimus quadragesima quadragesimum quinquagesimus quinquagesima quinquagesimum sexagesimus sexagesima sexagesimum septuagesimus septuagesima septuagesimum octogesimus octogesima octogesimum nonagesimus nonagesima nonagesimum centesimus centesima centesimum ducentesimus ducentesima ducentesimum trecentesimus trecentesima trecentesimum quadringentesimus quadringentesima quadringentesimum quingentesimus quingentesima quingentesimum sescentesimus sescentesima sescentesimum septingentesimus septingentesima septingentesimum octingentesimus octingentesima octingentesimum nongentesimus nongentesima nongentesimum millesimus millesima millesimum""".split()
_ordinal_words += [item.replace("v", "u") for item in _ordinal_words]
_ordinal_words = set(_ordinal_words)
def like_num(text):

4
spacy/lang/la/syntax_iterators.py
View File

@ -4,11 +4,13 @@ from ...symbols import NOUN, PROPN, PRON, VERB, AUX
from ...errors import Errors
# NB: Modified from da on suggestion from https://github.com/explosion/spaCy/issues/7457#issuecomment-800349751 [PJB]
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:
def is_verb_token(tok):
return tok.pos in [VERB, AUX]
def get_left_bound(doc, root):
def get_left_bound(root):
left_bound = root
for tok in reversed(list(root.lefts)):
if tok.dep in np_left_deps:

2
spacy/lang/la/tokenizer_exceptions.py
View File

@ -20,7 +20,7 @@ _abbrev_exc += [item.replace("v", "u").replace("V", "U") for item in _abbrev_exc
_abbrev_exc += ["d.N."]
for orth in _abbrev_exc:
for orth in set(_abbrev_exc):
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)