def processline(s):
"""Conform the input string to the index requirements and return the conformed string
To conform the string, first LaTex diacritics like {\'{e}} are removed. Then, Unicode
is translated to ASCII
Args:
s (str): the input string
Returns:
str: the output string
Example:
>>> print(processline("\v{C}{\'{e}}pl\"o, SlavomÃr")
Ceplo, Slavomir
"""
if s.strip() == '':
return s
#find the substring used for sorting
m = p.match(s)
sortstring = ''
try:
sortstring = m.groups(1)[0]
except AttributeError:
print("%s could not be parsed" % repr(s))
tmpstring = dediacriticize(sortstring)
tmpstring = asciify(tmpstring)
if sortstring == tmpstring:
return s
else:
print("%s => %s"%(sortstring,tmpstring))
return s.replace("%s@"%sortstring,"%s@"%tmpstring)
def processline(s):
global ignoredic
"""Conform the input string to the index requirements and return the conformed string
To conform the string, first LaTex diacritics like {\'{e}} are removed. Then, Unicode
is translated to ASCII
Args:
s (str): the input string
Returns:
str: the output string
Example:
>>> print(processline("\v{C}{\'{e}}pl\"o, SlavomÃr")
Ceplo, Slavomir
"""
if s.strip() == "":
return s
# find the substring used for sorting
m = p.match(s)
try:
items = p.match(s).group(1).split("@")
sortstring = items[0]
has_at = False
if len(items) > 1:
has_at = True
except AttributeError:
print("%s could not be parsed" % repr(s))
return ""
processedstring = asciify(dediacriticize(sortstring))
if sortstring == processedstring:
return s
else:
if sortstring not in ignoredic:
print("%s => %s" % (sortstring, processedstring))
ignoredic[sortstring] = True
if has_at:
result = s.replace("%s@" % sortstring, "%s@" % processedstring)
print(result)
return result
else:
result = s.replace(sortstring,
"%s@%s" % (processedstring, sortstring))
return result