From 8670b2d9944e822a8f440278c1bf49415d3bf421 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Thu, 15 Aug 2024 11:26:25 -0700
Subject: [PATCH] utils: add match_endofsentence and use it in processors

---
 .../processors/aggregators/sentence.py        | 13 ++++------
 src/pipecat/services/ai_services.py           | 20 +---------------
 src/pipecat/utils/string.py                   | 24 +++++++++++++++++++
 3 files changed, 30 insertions(+), 27 deletions(-)
 create mode 100644 src/pipecat/utils/string.py

diff --git a/src/pipecat/processors/aggregators/sentence.py b/src/pipecat/processors/aggregators/sentence.py
index a7992eace..7ee641826 100644
--- a/src/pipecat/processors/aggregators/sentence.py
+++ b/src/pipecat/processors/aggregators/sentence.py
@@ -4,10 +4,9 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import re
-
 from pipecat.frames.frames import EndFrame, Frame, InterimTranscriptionFrame, TextFrame
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.utils.string import match_endofsentence
 
 
 class SentenceAggregator(FrameProcessor):
@@ -40,12 +39,10 @@ class SentenceAggregator(FrameProcessor):
             return
 
         if isinstance(frame, TextFrame):
-            m = re.search("(.*[?.!])(.*)", frame.text)
-            if m:
-                await self.push_frame(TextFrame(self._aggregation + m.group(1)))
-                self._aggregation = m.group(2)
-            else:
-                self._aggregation += frame.text
+            self._aggregation += frame.text
+            if match_endofsentence(self._aggregation):
+                await self.push_frame(TextFrame(self._aggregation))
+                self._aggregation = ""
         elif isinstance(frame, EndFrame):
             if self._aggregation:
                 await self.push_frame(TextFrame(self._aggregation))
diff --git a/src/pipecat/services/ai_services.py b/src/pipecat/services/ai_services.py
index 485ae85a4..33abf4e15 100644
--- a/src/pipecat/services/ai_services.py
+++ b/src/pipecat/services/ai_services.py
@@ -27,28 +27,10 @@ from pipecat.frames.frames import (
 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.string import match_endofsentence
 from pipecat.utils.utils import exp_smoothing
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 
-import re
-
-
-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|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
-    $                # End of string
-"""
-ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)
-
-
-def match_endofsentence(text: str) -> bool:
-    return ENDOFSENTENCE_PATTERN.search(text.rstrip()) is not None
-
 
 class AIService(FrameProcessor):
     def __init__(self, **kwargs):
diff --git a/src/pipecat/utils/string.py b/src/pipecat/utils/string.py
new file mode 100644
index 000000000..a47db6c5c
--- /dev/null
+++ b/src/pipecat/utils/string.py
@@ -0,0 +1,24 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import re
+
+
+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|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
+    $                # End of string
+"""
+ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)
+
+
+def match_endofsentence(text: str) -> bool:
+    return ENDOFSENTENCE_PATTERN.search(text.rstrip()) is not None