From 12bce2e8c0ad5766ff2ce278c7727ffaf7e9d44c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Fri, 21 Feb 2025 09:54:11 -0800
Subject: [PATCH] utils: add support for ellipses in match_endofsentence()

---
 CHANGELOG.md                |  2 ++
 src/pipecat/utils/string.py |  4 ++--
 tests/test_utils_string.py  | 10 ++++++----
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 760c79cee..f2375c8e5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -36,6 +36,8 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 
 ### Fixed
 
+- Fixed `match_endofsentence` support for ellipses.
+
 - Fixed an issue that would cause undesired interruptions via
   `EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no
   final transcriptions) where received.
diff --git a/src/pipecat/utils/string.py b/src/pipecat/utils/string.py
index 916dfad41..154d03174 100644
--- a/src/pipecat/utils/string.py
+++ b/src/pipecat/utils/string.py
@@ -13,8 +13,8 @@ ENDOFSENTENCE_PATTERN_STR = r"""
     (?<!Mr|Ms|Dr)    # Negative lookbehind: not preceded by Mr, Ms, Dr (combined bc. length is the same)
     (?<!Mrs)         # Negative lookbehind: not preceded by "Mrs"
     (?<!Prof)        # Negative lookbehind: not preceded by "Prof"
-    [\.\?\!;]|       # Match a period, question mark, exclamation point, or semicolon
-    [。？！；।]        # the full-width version (mainly used in East Asian languages such as Chinese, Hindi)
+    (\.\s*\.\s*\.|[\.\?\!;])|   # Match a period, question mark, exclamation point, or semicolon
+    (\。\s*\。\s*\。|[。？！；।])  # the full-width version (mainly used in East Asian languages such as Chinese, Hindi)
     $                # End of string
 """
 ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)
diff --git a/tests/test_utils_string.py b/tests/test_utils_string.py
index 660397f3c..4b08bd411 100644
--- a/tests/test_utils_string.py
+++ b/tests/test_utils_string.py
@@ -11,10 +11,12 @@ from pipecat.utils.string import match_endofsentence
 
 class TestUtilsString(unittest.IsolatedAsyncioTestCase):
     async def test_endofsentence(self):
-        assert match_endofsentence("This is a sentence.")
-        assert match_endofsentence("This is a sentence! ")
-        assert match_endofsentence("This is a sentence?")
-        assert match_endofsentence("This is a sentence;")
+        assert match_endofsentence("This is a sentence.") == 19
+        assert match_endofsentence("This is a sentence!") == 19
+        assert match_endofsentence("This is a sentence?") == 19
+        assert match_endofsentence("This is a sentence;") == 19
+        assert match_endofsentence("This is a sentence...") == 21
+        assert match_endofsentence("This is a sentence . . .") == 24
         assert not match_endofsentence("This is not a sentence")
         assert not match_endofsentence("This is not a sentence,")
         assert not match_endofsentence("This is not a sentence, ")