Handle more UTF-8 wackiness gracefully in the spellchecker.

This commit is contained in:
Eric S. Raymond 2010-06-17 21:41:45 +00:00
parent cdf9ee9222
commit f23be008f1

View file

@ -1896,6 +1896,10 @@ def inner_spellcheck(nav, value, spelldict):
value = value.replace("\xe2\x80\x94", " ") # UTF-8 em dash
value = value.replace("\xe2\x80\x93", " ") # UTF-8 en dash
value = value.replace("\xe2\x80\x95", " ") # UTF-8 horizontal dash
value = value.replace("\xe2\x80\x99", "'") # UTF-8 right single quote
value = value.replace("\xe2\x80\x98", "'") # UTF-8 left single quote
value = value.replace("\xe2\x80\x9d", " ") # UTF-8 right double quote
value = value.replace("\xe2\x80\x9c", " ") # UTF-8 left double quote
value = value.replace("''", "")
value = value.replace("female^", " ")
value = value.replace("male^", " ")