From d1a36004ab3f88dc7381bebdf432055a9cd5b2e7 Mon Sep 17 00:00:00 2001
From: TomTom101 <thobra@gmail.com>
Date: Sat, 6 Jul 2024 11:01:32 +0200
Subject: [PATCH 1/4] fix: No more falsely detect a sentence end on "U.S.A",
 "3:00 a.m." and more

---
 src/pipecat/services/ai_services.py | 13 ++++++++++---
 tests/test_ai_services.py           | 20 ++++++++++++++++++--
 2 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/src/pipecat/services/ai_services.py b/src/pipecat/services/ai_services.py
index 06e4b3ebe..e5ab88258 100644
--- a/src/pipecat/services/ai_services.py
+++ b/src/pipecat/services/ai_services.py
@@ -28,6 +28,15 @@ from pipecat.processors.async_frame_processor import AsyncFrameProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.utils.audio import calculate_audio_volume
 from pipecat.utils.utils import exp_smoothing
+import re
+
+
+endofsentence_pattern = r"(?<![A-Z])(?<!\d)(?<!\d\s[ap])(?<!Mr|Ms|Dr)(?<!Mrs)(?<!Prof)[\.\?\!:]$"
+endofsentence_re = re.compile(endofsentence_pattern)
+
+
+def match_endofsentence(text: str) -> bool:
+    return endofsentence_re.search(text.rstrip()) is not None
 
 
 class AIService(FrameProcessor):
@@ -137,9 +146,7 @@ class TTSService(AIService):
             text = frame.text
         else:
             self._current_sentence += frame.text
-            if self._current_sentence.strip().endswith(
-                    (".", "?", "!")) and not self._current_sentence.strip().endswith(
-                    ("Mr,", "Mrs.", "Ms.", "Dr.")):
+            if match_endofsentence(self._current_sentence):
                 text = self._current_sentence
                 self._current_sentence = ""
 
diff --git a/tests/test_ai_services.py b/tests/test_ai_services.py
index ec44d5625..fb00fc893 100644
--- a/tests/test_ai_services.py
+++ b/tests/test_ai_services.py
@@ -2,8 +2,8 @@ import unittest
 
 from typing import AsyncGenerator
 
-from pipecat.services.ai_services import AIService
-from pipecat.pipeline.frames import EndFrame, Frame, TextFrame
+from pipecat.services.ai_services import AIService, match_endofsentence
+from pipecat.frames.frames import EndFrame, Frame, TextFrame
 
 
 class SimpleAIService(AIService):
@@ -27,6 +27,22 @@ class TestBaseAIService(unittest.IsolatedAsyncioTestCase):
 
         self.assertEqual(input_frames, output_frames)
 
+    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 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, ")
+        assert not match_endofsentence("Ok, Mr. Smith let's ")
+        assert not match_endofsentence("Dr. Walker, I presume ")
+        assert not match_endofsentence("Prof. Walker, I presume ")
+        assert not match_endofsentence("zweitens, und 3.")
+        assert not match_endofsentence("Heute ist Dienstag, der 3.")  # 3. Juli 2024
+        assert not match_endofsentence("America, or the U.")  # U.S.A.
+        assert not match_endofsentence("It still early, it's 3:00 a.")  # 3:00 a.m.
+
 
 if __name__ == "__main__":
     unittest.main()

From b23db4a20255731067632d3d35ee213e43ea423d Mon Sep 17 00:00:00 2001
From: TomTom101 <thobra@gmail.com>
Date: Sat, 6 Jul 2024 11:06:52 +0200
Subject: [PATCH 2/4] chore: commented regex

---
 src/pipecat/services/ai_services.py | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/src/pipecat/services/ai_services.py b/src/pipecat/services/ai_services.py
index e5ab88258..4482d2b50 100644
--- a/src/pipecat/services/ai_services.py
+++ b/src/pipecat/services/ai_services.py
@@ -31,8 +31,19 @@ from pipecat.utils.utils import exp_smoothing
 import re
 
 
-endofsentence_pattern = r"(?<![A-Z])(?<!\d)(?<!\d\s[ap])(?<!Mr|Ms|Dr)(?<!Mrs)(?<!Prof)[\.\?\!:]$"
-endofsentence_re = re.compile(endofsentence_pattern)
+endofsentence_pattern = r"""
+    (?<![A-Z])       # Negative lookbehind: not preceded by an uppercase letter (e.g., "U.S.A.")
+    (?<!\d)          # Negative lookbehind: not preceded by a digit (e.g., "1. Let's start")
+    (?<!\d\s[ap])    # Negative lookbehind: not preceded by time (e.g., "3:00 a.m.")
+    (?<!Mr)          # Negative lookbehind: not preceded by "Mr"
+    (?<!Ms)          # Negative lookbehind: not preceded by "Ms"
+    (?<!Dr)          # Negative lookbehind: not preceded by "Dr"
+    (?<!Mrs)         # Negative lookbehind: not preceded by "Mrs"
+    (?<!Prof)        # Negative lookbehind: not preceded by "Prof"
+    [\.\?\!:]        # Match a period, question mark, exclamation point, or colon
+    $                # End of string
+"""
+endofsentence_re = re.compile(endofsentence_pattern, re.VERBOSE)
 
 
 def match_endofsentence(text: str) -> bool:

From 327ea9d547303f2b2f3cafd0abc13bb63d867639 Mon Sep 17 00:00:00 2001
From: TomTom101 <thobra@gmail.com>
Date: Sat, 6 Jul 2024 11:08:51 +0200
Subject: [PATCH 3/4] chore: Make it a const

---
 src/pipecat/services/ai_services.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/pipecat/services/ai_services.py b/src/pipecat/services/ai_services.py
index 4482d2b50..9e28889c4 100644
--- a/src/pipecat/services/ai_services.py
+++ b/src/pipecat/services/ai_services.py
@@ -31,7 +31,7 @@ from pipecat.utils.utils import exp_smoothing
 import re
 
 
-endofsentence_pattern = r"""
+ENDOFSENTENCE_PATTERN_STR = r"""
     (?<![A-Z])       # Negative lookbehind: not preceded by an uppercase letter (e.g., "U.S.A.")
     (?<!\d)          # Negative lookbehind: not preceded by a digit (e.g., "1. Let's start")
     (?<!\d\s[ap])    # Negative lookbehind: not preceded by time (e.g., "3:00 a.m.")
@@ -43,11 +43,11 @@ endofsentence_pattern = r"""
     [\.\?\!:]        # Match a period, question mark, exclamation point, or colon
     $                # End of string
 """
-endofsentence_re = re.compile(endofsentence_pattern, re.VERBOSE)
+ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)
 
 
 def match_endofsentence(text: str) -> bool:
-    return endofsentence_re.search(text.rstrip()) is not None
+    return ENDOFSENTENCE_PATTERN.search(text.rstrip()) is not None
 
 
 class AIService(FrameProcessor):

From da2082b02527b2641caaff15b715797aaadf508f Mon Sep 17 00:00:00 2001
From: TomTom101 <thobra@gmail.com>
Date: Sat, 6 Jul 2024 11:11:40 +0200
Subject: [PATCH 4/4] chore: Combined combinable lookaheads

---
 src/pipecat/services/ai_services.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/pipecat/services/ai_services.py b/src/pipecat/services/ai_services.py
index 9e28889c4..46bba673e 100644
--- a/src/pipecat/services/ai_services.py
+++ b/src/pipecat/services/ai_services.py
@@ -35,9 +35,7 @@ ENDOFSENTENCE_PATTERN_STR = r"""
     (?<![A-Z])       # Negative lookbehind: not preceded by an uppercase letter (e.g., "U.S.A.")
     (?<!\d)          # Negative lookbehind: not preceded by a digit (e.g., "1. Let's start")
     (?<!\d\s[ap])    # Negative lookbehind: not preceded by time (e.g., "3:00 a.m.")
-    (?<!Mr)          # Negative lookbehind: not preceded by "Mr"
-    (?<!Ms)          # Negative lookbehind: not preceded by "Ms"
-    (?<!Dr)          # Negative lookbehind: not preceded by "Dr"
+    (?<!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 colon