Index: graphspell-js/tokenizer.js
==================================================================
--- graphspell-js/tokenizer.js
+++ graphspell-js/tokenizer.js
@@ -23,11 +23,12 @@
             [/^\[\/?[a-zA-Z]+\]/, 'PSEUDOHTML'],
             [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
             [/^\d\d?[h:]\d\d(?:[m:]\d\ds?|)\b/, 'HOUR'],
             [/^\d+(?:[.,]\d+|)/, 'NUM'],
             [/^[&%‰€$+±=*/<>⩾⩽#|×¥£§¢¬÷@-]/, 'SIGN'],
-            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ_]+)*/, 'WORD']
+            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ_]+)*/, 'WORD'],
+            [/^\S/, 'OTHER']
         ],
     "fr":
         [
             [/^[   \t]+/, 'SPACE'],
             [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆ_.()-]+)*/, 'FOLDERUNIX'],
@@ -42,11 +43,12 @@
             [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu|presqu|quelqu)['’ʼ‘‛´`′‵՚ꞌꞋ]/i, 'WORD_ELIDED'],
             [/^\d\d?[h:]\d\d(?:[m:]\d\ds?|)\b/, 'HOUR'],
             [/^\d+(?:ers?\b|res?\b|è[rm]es?\b|i[èe][mr]es?\b|de?s?\b|nde?s?\b|ès?\b|es?\b|ᵉʳˢ?|ʳᵉˢ?|ᵈᵉ?ˢ?|ⁿᵈᵉ?ˢ?|ᵉˢ?)/, 'WORD_ORDINAL'],
             [/^\d+(?:[.,]\d+|)/, 'NUM'],
             [/^[&%‰€$+±=*/<>⩾⩽#|×¥£§¢¬÷@-]/, 'SIGN'],
-            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ\u0300-\u036fᵉʳˢⁿᵈ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ\u0300-\u036fᵉʳˢⁿᵈ_]+)*/, 'WORD']
+            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ\u0300-\u036fᵉʳˢⁿᵈ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯﬀ-ﬆᴀ-ᶿ\u0300-\u036fᵉʳˢⁿᵈ_]+)*/, 'WORD'],
+            [/^\S/, 'OTHER'],
         ]
 };
 
 
 class Tokenizer {

Index: graphspell/tokenizer.py
==================================================================
--- graphspell/tokenizer.py
+++ graphspell/tokenizer.py
@@ -19,11 +19,12 @@
             r'(?P<HTML><\w+.*?>|</\w+ *>)',
             r'(?P<PSEUDOHTML>\[/?\w+\])',
             r'(?P<HOUR>\d\d?[h:]\d\d(?:[m:]\d\ds?|)\b)',
             r'(?P<NUM>\d+(?:[.,]\d+))',
             r'(?P<SIGN>[&%‰€$+±=*/<>⩾⩽#|×¥£§¢¬÷@-])',
-            r"(?P<WORD>\w+(?:[’'`-]\w+)*)"
+            r"(?P<WORD>[\w\u0300-\u036f]+(?:[’'`-][\w\u0300-\u036f]+)*)",        # with combining diacritics
+            r"(?P<OTHER>\S)"
         ),
     "fr":
         (
             r'(?P<FOLDERUNIX>/(?:bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:/[\w.()-]+)*)',
             r'(?P<FOLDERWIN>[a-zA-Z]:\\(?:Program Files(?: [(]x86[)]|)|[\w.()]+)(?:\\[\w.()-]+)*)',
@@ -36,11 +37,12 @@
             r"(?P<WORD_ELIDED>(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu|presqu|quelqu)['’ʼ‘‛´`′‵՚ꞌꞋ])",
             r'(?P<WORD_ORDINAL>\d+(?:ers?|res?|è[rm]es?|i[èe][mr]es?|de?s?|nde?s?|ès?|es?|ᵉʳˢ?|ʳᵉˢ?|ᵈᵉ?ˢ?|ⁿᵈᵉ?ˢ?|ᵉˢ?)\b)',
             r'(?P<HOUR>\d\d?[h:]\d\d(?:[m:]\d\ds?|)\b)',
             r'(?P<NUM>\d+(?:[.,]\d+|))',
             r'(?P<SIGN>[&%‰€$+±=*/<>⩾⩽#|×¥£¢§¬÷@-])',
-            r"(?P<WORD>[\w\u0300-\u036f]+(?:[’'`-][\w\u0300-\u036f]+)*)"
+            r"(?P<WORD>[\w\u0300-\u036f]+(?:[’'`-][\w\u0300-\u036f]+)*)",        # with combining diacritics
+            r"(?P<OTHER>\S)"
         )
 }
 
 
 class Tokenizer:

