def generate_key(self, ingr):
"""Generate a generic-looking key from a string."""
timer = TimeAction('keymanager.generate_key 1',3)
debug("Start generate_key(self,%s)"%ingr,10)
ingr = ingr.strip()
# language specific here - turn off the strip().lower() for German, 'cos:
# i) german Nouns always start with an uppercase Letter.
# ii) the function 'lower()' doesn't appear to work correctly with umlauts.
if (not langProperties['capitalisedNouns']):
# We want to use unicode's lower() method
if not isinstance(ingr,unicode):
ingr = unicode(ingr.decode('utf8'))
ingr = ingr.lower()
timer.end()
timer = TimeAction('keymanager.generate_key 2',3)
debug("verbless string=%s"%ingr,10)
if ingr.find(',') == -1:
# if there are no commas, we see if it makes sense
# to turn, e.g. whole-wheat bread into bread, whole-wheat
words = ingr.split()
if len(words) >= 2:
if self.cats.__contains__(words[-1]):
ingr = "%s, %s" %(words[-1],string.join(words[0:-1]))
#if len(str) > 32:
# str = str[0:32]
debug("End generate_key",10)
timer.end()
return ingr
def remove_verbs (self,words):
"""Handed a list of words, we remove anything from the
list that matches a regexp in self.ignored"""
debug("Start remove_verbs",10)
t=TimeAction('remove_verbs',0)
stringp=True
if type(words)==type([]):
stringp=False
words = string.join(words," ")
words = words.split(';')[0] #we ignore everything after semicolon
words = words.split("--")[0] # we ignore everything after double dashes too!
m = self.ignored_regexp.match(words)
while m:
words = words[0:m.start()] + words[m.end():]
m = self.ignored_regexp.match(words)
t.end()
if stringp:
return words
else:
return words.split()