From f6912c0f9a45efcb9e3d375985c11618aad36a18 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Fri, 14 Feb 2025 15:44:13 -0800
Subject: [PATCH] utils: don't consider colon an end of sentence

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

diff --git a/CHANGELOG.md b/CHANGELOG.md
index c8590e665..0201fdc23 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -56,6 +56,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- We don't consider a colon `:` and end of sentence any more.
+
 - Updated `DailyTransport` to respect the `audio_in_stream_on_start` field,
   ensuring it only starts receiving the audio input if it is enabled.
 
diff --git a/src/pipecat/utils/string.py b/src/pipecat/utils/string.py
index c269c5e57..916dfad41 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, colon, or semicolon
-    [。？！：；।]       # the full-width version (mainly used in East Asian languages such as Chinese, Hindi)
+    [\.\?\!;]|       # Match a period, question mark, exclamation point, or semicolon
+    [。？！；।]        # 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 aa135a639..660397f3c 100644
--- a/tests/test_utils_string.py
+++ b/tests/test_utils_string.py
@@ -14,7 +14,6 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
         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;")
         assert not match_endofsentence("This is not a sentence")
         assert not match_endofsentence("This is not a sentence,")
@@ -33,7 +32,6 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
             "你好！",
             "吃了吗？",
             "安全第一；",
-            "他说：",
         ]
         for i in chinese_sentences:
             assert match_endofsentence(i)