From fd759a881b02a7bc3488b1d9c005d5849cfc05f9 Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Mon, 11 Oct 2021 09:38:45 +0000
Subject: [PATCH] Fix inconsistent lemmas (#9405)

* Add util function to unique lists and preserve order

* Use unique function instead of list(set())

list(set()) has the issue that it's not consistent between runs of the
Python interpreter, so order can vary.

list(set()) calls were left in a few places where they were behind calls
to sorted(). I think in this case the calls to list() can be removed,
but this commit doesn't do that.

* Use the existing pattern for this
---
 spacy/lang/ca/lemmatizer.py | 2 +-
 spacy/lang/fr/lemmatizer.py | 2 +-
 spacy/lang/nl/lemmatizer.py | 2 +-
 spacy/lang/ru/lemmatizer.py | 4 ++--
 spacy/util.py               | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/spacy/lang/ca/lemmatizer.py b/spacy/lang/ca/lemmatizer.py
index 2518eb720..2fd012912 100644
--- a/spacy/lang/ca/lemmatizer.py
+++ b/spacy/lang/ca/lemmatizer.py
@@ -76,6 +76,6 @@ class CatalanLemmatizer(Lemmatizer):
             forms.append(self.lookup_lemmatize(token)[0])
         if not forms:
             forms.append(string)
-        forms = list(set(forms))
+        forms = list(dict.fromkeys(forms))
         self.cache[cache_key] = forms
         return forms
diff --git a/spacy/lang/fr/lemmatizer.py b/spacy/lang/fr/lemmatizer.py
index bb5a270ab..c6422cf96 100644
--- a/spacy/lang/fr/lemmatizer.py
+++ b/spacy/lang/fr/lemmatizer.py
@@ -75,6 +75,6 @@ class FrenchLemmatizer(Lemmatizer):
             forms.append(self.lookup_lemmatize(token)[0])
         if not forms:
             forms.append(string)
-        forms = list(set(forms))
+        forms = list(dict.fromkeys(forms))
         self.cache[cache_key] = forms
         return forms
diff --git a/spacy/lang/nl/lemmatizer.py b/spacy/lang/nl/lemmatizer.py
index 6c025dcf6..4f6b2ef30 100644
--- a/spacy/lang/nl/lemmatizer.py
+++ b/spacy/lang/nl/lemmatizer.py
@@ -97,7 +97,7 @@ class DutchLemmatizer(Lemmatizer):
                     return forms
                 else:
                     oov_forms.append(form)
-        forms = list(set(oov_forms))
+        forms = list(dict.fromkeys(oov_forms))
         # Back-off through remaining return value candidates.
         if forms:
             for form in forms:
diff --git a/spacy/lang/ru/lemmatizer.py b/spacy/lang/ru/lemmatizer.py
index 399cd174c..92bec4c8c 100644
--- a/spacy/lang/ru/lemmatizer.py
+++ b/spacy/lang/ru/lemmatizer.py
@@ -56,7 +56,7 @@ class RussianLemmatizer(Lemmatizer):
         if not len(filtered_analyses):
             return [string.lower()]
         if morphology is None or (len(morphology) == 1 and POS in morphology):
-            return list(set([analysis.normal_form for analysis in filtered_analyses]))
+            return list(dict.fromkeys([analysis.normal_form for analysis in filtered_analyses]))
         if univ_pos in ("ADJ", "DET", "NOUN", "PROPN"):
             features_to_compare = ["Case", "Number", "Gender"]
         elif univ_pos == "NUM":
@@ -87,7 +87,7 @@ class RussianLemmatizer(Lemmatizer):
                 filtered_analyses.append(analysis)
         if not len(filtered_analyses):
             return [string.lower()]
-        return list(set([analysis.normal_form for analysis in filtered_analyses]))
+        return list(dict.fromkeys([analysis.normal_form for analysis in filtered_analyses]))
 
     def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]:
         string = token.text
diff --git a/spacy/util.py b/spacy/util.py
index b49bd096f..0aa7c4c17 100644
--- a/spacy/util.py
+++ b/spacy/util.py
@@ -1403,7 +1403,7 @@ def get_arg_names(func: Callable) -> List[str]:
     RETURNS (List[str]): The argument names.
     """
     argspec = inspect.getfullargspec(func)
-    return list(set([*argspec.args, *argspec.kwonlyargs]))
+    return list(dict.fromkeys([*argspec.args, *argspec.kwonlyargs]))
 
 
 def combine_score_weights(