Merge pull request #1269 from pipecat-ai/aleix/endofsentence-support-ellipses

utils: add support for ellipses in match_endofsentence()

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.

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)

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, ")