From 2abd380f2d17010fe22fe52e8aab529d70cbeec6 Mon Sep 17 00:00:00 2001
From: pepemedigu <pepe.medina@uca.es>
Date: Thu, 20 Jan 2022 15:44:13 +0100
Subject: [PATCH] Update lex_attrs.py for Spanish with ordinals (#10038)

* Update lex_attrs.py

Add ordinal words

* black formatting

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
---
 spacy/lang/es/lex_attrs.py | 41 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/spacy/lang/es/lex_attrs.py b/spacy/lang/es/lex_attrs.py
index 988dbaba1..9d1fa93b8 100644
--- a/spacy/lang/es/lex_attrs.py
+++ b/spacy/lang/es/lex_attrs.py
@@ -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