def test_basic_prefix_stripper(self):
obj = RemovePrefix()
#பேரின்பம் -> இன்பம்,
#u"":u"",u"":u"",u"":u"",u"":u"",u"":u"",u"":u"",
prefix_removal_map = {u"எக்காலம்":u"காலம்",u"இக்காலம்":u"காலம்",u"அக்காலம்":u"காலம்",\
u"மாமனிதன்":u"மனிதன்",u"சின்னஜமீன்":u"ஜமீன்",u"அதிவேகம்":u"வேகம்",\
u"சிறுகுன்றம்":u"குன்றம்",u"மாமரம்":u"மரம்"}
no_removal_map = {}
# update no-prefix-to-be-removed / no-change values
for v in prefix_removal_map.values():
no_removal_map[v] = v
# prefix removal does not happen for these words
words_list = list(no_removal_map.keys())
for idx,w in enumerate(words_list):
rval = obj.removePrefix(w)
self.assertFalse(rval[1])
expected = no_removal_map[w]
self.assertEqual(rval[0], expected)
# prefix removal to happen as expected
words_list = list(prefix_removal_map.keys())
for idx,w in enumerate(words_list):
rval = obj.removePrefix(w)
self.assertTrue(rval[1])
expected = prefix_removal_map[w]
self.assertEqual(rval[0], expected)
return
def test_basic_prefix_stripper(self):
obj = RemovePrefix()
#பேரின்பம் -> இன்பம்,
#u"":u"",u"":u"",u"":u"",u"":u"",u"":u"",u"":u"",
prefix_removal_map = {u"எக்காலம்":u"காலம்",u"இக்காலம்":u"காலம்",u"அக்காலம்":u"காலம்",\
u"மாமனிதன்":u"மனிதன்",u"சின்னஜமீன்":u"ஜமீன்",u"அதிவேகம்":u"வேகம்",\
u"சிறுகுன்றம்":u"குன்றம்",u"மாமரம்":u"மரம்"}
no_removal_map = {}
# update no-prefix-to-be-removed / no-change values
for v in prefix_removal_map.values():
no_removal_map[v] = v
# prefix removal does not happen for these words
words_list = list(no_removal_map.keys())
for idx,w in enumerate(words_list):
rval = obj.removePrefix(w)
self.assertFalse(rval[1])
expected = no_removal_map[w]
self.assertEqual(rval[0], expected)
# prefix removal to happen as expected
words_list = list(prefix_removal_map.keys())
for idx,w in enumerate(words_list):
rval = obj.removePrefix(w)
self.assertTrue(rval[1])
expected = prefix_removal_map[w]
self.assertEqual(rval[0], expected)
return
def __init__(self, filename=None, lang="ta", mode="non-web"):
object.__init__(self)
self.lang = lang.lower()
self.filename = filename
self.user_dict = set()
self.case_filter = CaseFilter(RemovePluralSuffix(),
RemoveVerbSuffixTense(),
RemoveCaseSuffix(), RemovePrefix())
if self.lang == u"en":
self.alphabets = [a for a in string.ascii_lowercase]
else:
self.alphabets = None
if mode != "web":
if not self.filename:
self.interactive()
else:
self.spellcheck(self.filename)
pass