Index: graphspell-js/tokenizer.js ================================================================== --- graphspell-js/tokenizer.js +++ graphspell-js/tokenizer.js @@ -39,11 +39,11 @@ [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯff-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯff-st]+ *>/, 'HTML'], [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯff-st]+\]/, 'PSEUDOHTML'], [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'], [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'WORD_ELIDED'], [/^\d\d?[h:]\d\d(?:[m:]\d\ds?|)\b/, 'HOUR'], - [/^\d+(?:ers?\b|nds?\b|es?\b|des?\b|ièmes?\b|èmes?\b|emes?\b|ᵉʳˢ?|ⁿᵈˢ?|ᵉˢ?|ᵈᵉˢ?)/, 'WORD_ORDINAL'], + [/^\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'], [/^[&%‰€$+±=*/<>⩾⩽#|×¥£§¢¬÷@-]/, 'SIGN'], [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯff-stᴀ-ᶿᵉʳˢⁿᵈ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯff-stᴀ-ᶿᵉʳˢⁿᵈ_]+)*/, 'WORD'] ] }; Index: graphspell/tokenizer.py ================================================================== --- graphspell/tokenizer.py +++ graphspell/tokenizer.py @@ -30,11 +30,11 @@ r'(?P(?:https?://|www[.]|\w+[@.]\w\w+[@.])\w[\w./?&!%=+*"\'@$#-]+)', r'(?P[#@][\w-]+)', r'(?P<\w+.*?>|)', r'(?P\[/?\w+\])', r"(?P(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`])", - r'(?P\d+(?:ers?|nds?|es?|des?|ièmes?|èmes?|emes?|ᵉʳˢ?|ⁿᵈˢ?|ᵉˢ?|ᵈᵉˢ?)\b)', + r'(?P\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\d\d?[h:]\d\d(?:[m:]\d\ds?|)\b)', r'(?P\d+(?:[.,]\d+|))', r'(?P[&%‰€$+±=*/<>⩾⩽#|×¥£¢§¬÷@-])', r"(?P\w+(?:[’'`-]\w+)*)" )