utils(string): add support for floating point numbers

CHANGELOG.md

@@ -138,6 +138,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Fixed a `match_endofsentence` issue that would result in floating point
+  numbers to be considered an end of sentence.
+
 - Fixed a `match_endofsentence` issue that would result in emails to be
   considered an end of sentence.
 

src/pipecat/utils/string.py

@@ -8,7 +8,8 @@ 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\.\d)      # Not preceded by a decimal number (e.g., "3.14159")
+    (?<!^\d\.)       # Not preceded by a numbered list item (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"
@@ -22,19 +23,30 @@ 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,}")
 
+NUMBER_PATTERN = re.compile(r"[+-]?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?")
+
+
+def replace_match(text: str, match: re.Match, old: str, new: str) -> str:
+    start = match.start()
+    end = match.end()
+    replacement = text[start:end].replace(old, new)
+    text = text[:start] + replacement + text[end:]
+    return text
+
 
 def match_endofsentence(text: str) -> int:
     text = text.rstrip()
 
-    # Find all emails.
+    # Replace email dots by ampersands so we can find the end of sentence. For
+    # example, first.last@email.com becomes first&last@email&com.
     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()
+        text = replace_match(text, email_match, ".", "&")
-        end = email_match.end()
+
-        new_email = text[start:end].replace(".", "&")
+    # Replace number dots by ampersands so we can find the end of sentence.
-        text = text[:start] + new_email + text[end:]
+    numbers = list(NUMBER_PATTERN.finditer(text))
+    for number_match in numbers:
+        text = replace_match(text, number_match, ".", "&")
 
     # Match against the new text.
     match = ENDOFSENTENCE_PATTERN.search(text)

tests/test_utils_string.py

@@ -21,6 +21,11 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
         assert match_endofsentence("This is for Mr. and Mrs. Jones.") == 31
         assert match_endofsentence("U.S.A and U.S.A..") == 17
         assert match_endofsentence("My emails are foo@pipecat.ai and bar@pipecat.ai.") == 48
+        assert match_endofsentence("My email is foo.bar@pipecat.ai.") == 31
+        assert match_endofsentence("My email is spell(foo.bar@pipecat.ai).") == 38
+        assert match_endofsentence("The number pi is 3.14159.") == 25
+        assert match_endofsentence("Valid scientific notation 1.23e4.") == 33
+        assert match_endofsentence("Valid scientific notation 0.e4.") == 31
         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, ")
@@ -32,6 +37,7 @@ class TestUtilsString(unittest.IsolatedAsyncioTestCase):
         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.
         assert not match_endofsentence("My emails are foo@pipecat.ai and bar@pipecat.ai")
+        assert not match_endofsentence("The number pi is 3.14159")
 
     async def test_endofsentence_zh(self):
         chinese_sentences = [