From b843703134a166013518c707fa5a77373f1bf0bf Mon Sep 17 00:00:00 2001
From: Scott Gasch <scott@gasch.org>
Date: Thu, 5 Aug 2021 14:56:34 -0700
Subject: Adds profanity filter, fixes bugs.

---
 string_utils.py | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

(limited to 'string_utils.py')

diff --git a/string_utils.py b/string_utils.py
index 6fc257d..45cf5aa 100644
--- a/string_utils.py
+++ b/string_utils.py
@@ -9,7 +9,7 @@ import logging
 import random
 import re
 import string
-from typing import Any, Callable, List, Optional
+from typing import Any, Callable, Iterable, List, Optional
 import unicodedata
 from uuid import uuid4
 
@@ -963,3 +963,21 @@ def thify(n: int) -> str:
         return "rd"
     else:
         return "th"
+
+
+def ngrams(txt: str, n: int):
+    words = txt.split()
+    return ngrams_presplit(words, n)
+
+
+def ngrams_presplit(words: Iterable[str], n: int):
+    for ngram in zip(*[words[i:] for i in range(n)]):
+        yield(' '.join(ngram))
+
+
+def bigrams(txt: str):
+    return ngrams(txt, 2)
+
+
+def trigrams(txt: str):
+    return ngrams(txt, 3)
-- 
cgit v1.3