From 64b22be76e5e9e6fa4e375e395fbd732cf6c2958 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Wed, 4 Sep 2024 14:22:13 +0200
Subject: [PATCH] Fix apparent bug in Spanish lemmatizer. Not sure why this
 emerges in v4 not in v3

---
 spacy/lang/es/lemmatizer.py | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/spacy/lang/es/lemmatizer.py b/spacy/lang/es/lemmatizer.py
index ee5d38e84..8989000e0 100644
--- a/spacy/lang/es/lemmatizer.py
+++ b/spacy/lang/es/lemmatizer.py
@@ -53,12 +53,15 @@ class SpanishLemmatizer(Lemmatizer):
             else:
                 rule_pos = pos
             rule = self.select_rule(rule_pos, list(features))
-            index = self.lookups.get_table("lemma_index").get(rule_pos, [])
-            lemmas = getattr(self, "lemmatize_" + rule_pos)(
-                string, features, rule, index
-            )
-            # Remove duplicates but preserve the ordering
-            lemmas = list(dict.fromkeys(lemmas))
+            if rule is None:
+                lemmas = [string]
+            else:
+                index = self.lookups.get_table("lemma_index").get(rule_pos, [])
+                lemmas = getattr(self, "lemmatize_" + rule_pos)(
+                    string, features, rule, index
+                )
+                # Remove duplicates but preserve the ordering
+                lemmas = list(dict.fromkeys(lemmas))
 
         self.cache[cache_key] = lemmas
         return lemmas
@@ -203,6 +206,7 @@ class SpanishLemmatizer(Lemmatizer):
         word (str): The word to lemmatize.
         features (List[str]): The morphological features as a list of Feat=Val
             pairs.
+        rule (str): The rule ID to use
         index (List[str]): The POS-specific lookup list.
 
         RETURNS (List[str]): The list of lemmas.