From d0bd3f5ee43e976990fc562ce412537ef4f3b23f Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Fri, 24 Mar 2023 16:26:40 +0100
Subject: [PATCH] Update Serbian tokenization for UD Serbian SET (#12442)

---
 spacy/lang/sr/__init__.py    |  3 +++
 spacy/lang/sr/punctuation.py | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)
 create mode 100644 spacy/lang/sr/punctuation.py

diff --git a/spacy/lang/sr/__init__.py b/spacy/lang/sr/__init__.py
index fd0c8c832..b99ce96ec 100644
--- a/spacy/lang/sr/__init__.py
+++ b/spacy/lang/sr/__init__.py
@@ -1,11 +1,14 @@
 from .stop_words import STOP_WORDS
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .lex_attrs import LEX_ATTRS
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
 from ...language import Language, BaseDefaults
 
 
 class SerbianDefaults(BaseDefaults):
     tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
     lex_attr_getters = LEX_ATTRS
     stop_words = STOP_WORDS
 
diff --git a/spacy/lang/sr/punctuation.py b/spacy/lang/sr/punctuation.py
new file mode 100644
index 000000000..793a20ec2
--- /dev/null
+++ b/spacy/lang/sr/punctuation.py
@@ -0,0 +1,36 @@
+from ..char_classes import LIST_ELLIPSES, LIST_ICONS, LIST_PUNCT, LIST_QUOTES
+from ..char_classes import CURRENCY, UNITS, PUNCT
+from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
+
+
+_infixes = (
+    LIST_ELLIPSES
+    + LIST_ICONS
+    + [
+        r"(?<=[0-9])[+\-\*^](?=[0-9-])",
+        r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
+            al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
+        ),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
+    ]
+)
+
+_suffixes = (
+    LIST_PUNCT
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_ICONS
+    + [
+        r"(?<=[0-9])\+",
+        r"(?<=°[FfCcKk])\.",
+        r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
+        r"(?<=[0-9])(?:{u})".format(u=UNITS),
+        r"(?<=[{a}{e}{p}(?:{q})])\.".format(
+            a=ALPHA, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
+        ),
+    ]
+)
+
+TOKENIZER_INFIXES = _infixes
+TOKENIZER_SUFFIXES = _suffixes