Adding a new "Replace" normalizer that takes a string and replaces it

with another String (for now).

bindings/python/py_src/tokenizers/normalizers/__init__.py

@@ -12,6 +12,7 @@ Strip = normalizers.Strip
 StripAccents = normalizers.StripAccents
 Nmt = normalizers.Nmt
 Precompiled = normalizers.Precompiled
+Replace = normalizers.Replace
 
 
 NORMALIZERS = {"nfc": NFC, "nfd": NFD, "nfkc": NFKC, "nfkd": NFKD}

bindings/python/py_src/tokenizers/normalizers/__init__.pyi

@@ -112,11 +112,17 @@ class Nmt(Normalizer):
         pass
 
 class Precompiled(Normalizer):
-    """ SpmNmtNfkc normalizer """
+    """ Precompiled normalizer """
 
     def __init__(self, precompiled_charsmap: bytes) -> Normalizer:
         pass
 
+class Replace(Normalizer):
+    """ Replace normalizer """
+
+    def __init__(self, pattern: str, content: str) -> Normalizer:
+        pass
+
 def unicode_normalizer_from_str(normalizer: str) -> Normalizer:
     """
     Instanciate unicode normalizer from the normalizer name