From 8fc2a5f13bdff33e3d6f7a3eff951a0276249602 Mon Sep 17 00:00:00 2001
From: Lise Brinck <lise.brinck@vitecsoftware.com>
Date: Wed, 22 Feb 2023 14:55:26 +0100
Subject: [PATCH] create punctuation.py for swedish

---
 spacy/lang/sv/__init__.py    |  5 +----
 spacy/lang/sv/punctuation.py | 31 +++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 4 deletions(-)
 create mode 100644 spacy/lang/sv/punctuation.py

diff --git a/spacy/lang/sv/__init__.py b/spacy/lang/sv/__init__.py
index 6963e8b79..28e5085a8 100644
--- a/spacy/lang/sv/__init__.py
+++ b/spacy/lang/sv/__init__.py
@@ -6,10 +6,7 @@ from .lex_attrs import LEX_ATTRS
 from .syntax_iterators import SYNTAX_ITERATORS
 from ...language import Language, BaseDefaults
 from ...pipeline import Lemmatizer
-
-
-# Punctuation stolen from Danish
-from ..da.punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
 
 
 class SwedishDefaults(BaseDefaults):
diff --git a/spacy/lang/sv/punctuation.py b/spacy/lang/sv/punctuation.py
new file mode 100644
index 000000000..e050ab7aa
--- /dev/null
+++ b/spacy/lang/sv/punctuation.py
@@ -0,0 +1,31 @@
+from ..char_classes import LIST_ELLIPSES, LIST_ICONS
+from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
+from ..punctuation import TOKENIZER_SUFFIXES
+
+
+_quotes = CONCAT_QUOTES.replace("'", "")
+
+_infixes = (
+    LIST_ELLIPSES
+    + LIST_ICONS
+    + [
+        r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
+        r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
+        r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
+    ]
+)
+
+_suffixes = [
+    suffix
+    for suffix in TOKENIZER_SUFFIXES
+    if suffix not in ["'s", "'S", "’s", "’S", r"\'"]
+]
+_suffixes += [r"(?<=[^sSxXzZ])\'"]
+
+
+TOKENIZER_INFIXES = _infixes
+TOKENIZER_SUFFIXES = _suffixes