utils(string): support email addresses in end of sentence matching

src/pipecat/utils/string.py

@@ -17,9 +17,26 @@ ENDOFSENTENCE_PATTERN_STR = r"""
     (\。\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)
 
+EMAIL_PATTERN = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")
+
 
 def match_endofsentence(text: str) -> int:
-    match = ENDOFSENTENCE_PATTERN.search(text.rstrip())
+    text = text.rstrip()
+
+    # Find all emails.
+    emails = list(EMAIL_PATTERN.finditer(text))
+
+    # Replace email dots by ampersands so we can find the end of sentence.
+    for email_match in emails:
+        start = email_match.start()
+        end = email_match.end()
+        new_email = text[start:end].replace(".", "&")
+        text = text[:start] + new_email + text[end:]
+
+    # Match against the new text.
+    match = ENDOFSENTENCE_PATTERN.search(text)
+
     return match.end() if match else 0