explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update lex_attrs.py for Spanish with ordinals (#10038)

Browse Source 
* Update lex_attrs.py

Add ordinal words

* black formatting

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
This commit is contained in:
pepemedigu 2022-01-20 15:44:13 +01:00 committed by GitHub
parent d2afdfefc2
commit 2abd380f2d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 40 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
spacy/lang/es/lex_attrs.py
View File

@ -47,6 +47,41 @@ _num_words = [
]
_ordinal_words = [
"primero",
"segundo",
"tercero",
"cuarto",
"quinto",
"sexto",
"séptimo",
"octavo",
"noveno",
"décimo",
"undécimo",
"duodécimo",
"decimotercero",
"decimocuarto",
"decimoquinto",
"decimosexto",
"decimoséptimo",
"decimoctavo",
"decimonoveno",
"vigésimo",
"trigésimo",
"cuadragésimo",
"quincuagésimo",
"sexagésimo",
"septuagésimo",
"octogésima",
"nonagésima",
"centésima",
"milésima",
"millonésima",
"billonésima",
]
def like_num(text):
if text.startswith(("+", "-", "±", "~")):
text = text[1:]
@ -57,7 +92,11 @@ def like_num(text):
num, denom = text.split("/")
if num.isdigit() and denom.isdigit():
return True
if text.lower() in _num_words:
text_lower = text.lower()
if text_lower in _num_words:
return True
# Check ordinal number
if text_lower in _ordinal_words:
return True
return False