def checkFormErrors(word, errmsg=None):
r1 = BadIME()
r2 = AdjacentConsonants()
r2.freq_threshold = 4
r3 = AdjacentVowels()
item0 = operator.itemgetter(0)
if errmsg and r1.apply(word)[0]:
errmsg.append(u"BadIME")
print("Bad IME")
return any(list(map(lambda obj: not item0(obj.apply(word)), [r1, r2, r3])))
def checkFormErrors(word,errmsg=None):
r1=BadIME()
r2=AdjacentConsonants()
r2.freq_threshold=4
r3=AdjacentVowels()
item0 = operator.itemgetter(0)
if errmsg and r1.apply(word)[0]:
errmsg.append(u"BadIME")
print("Bad IME")
return any(list(map(lambda obj: not item0(obj.apply(word)),[r1,r2,r3])))
def test_all_valid(self):
data,DEBUG = [],False
with codecs.open("data/project_madurai_utf8.txt","r","utf-8") as f:
data = filter(lambda x: len(x)>2, f.readlines())
obj = BadIME()
for idx,line in enumerate(data):
for col,word in enumerate( re.split(u'\s+',line) ):
if DEBUG:
print(idx,col)
print(utf8.get_letters(word))
self.assertEqual(obj.apply(word),(True,None))
pass
pass
def test_all_valid(self):
data, DEBUG = [], False
with codecs.open("data/project_madurai_utf8.txt", "r", "utf-8") as f:
data = filter(lambda x: len(x) > 2, f.readlines())
obj = BadIME()
for idx, line in enumerate(data):
for col, word in enumerate(re.split(u'\s+', line)):
if DEBUG:
print(idx, col)
print(utf8.get_letters(word))
self.assertEqual(obj.apply(word), (True, None))
pass
pass
def test_invalid_pulli_seq(self):
not_a_word = u"ஆள்்ஆ"
#from tamil import utf8
#print(utf8.get_letters(not_a_word))
obj = BadIME()
self.assertEqual(obj.apply(not_a_word), (False, BadIME.reason))
def test_valid_word_det(self):
for a_word in [u"ஆள்", u"ஏனையோருக்கும்"]:
obj = BadIME()
#print(utf8.get_letters(a_word))
self.assertEqual(obj.apply(a_word), (True, None))
return
def test_invalid_word3(self):
obj = BadIME()
not_a_word = u"தூூக்"
self.assertEqual(obj.apply(not_a_word), (False, BadIME.reason))
not_a_word = u"ஏூூளா"
self.assertEqual(obj.apply(not_a_word), (False, BadIME.reason))
def test_invalid_word_det(self):
not_a_word = u"ஆாள்"
#print(utf8.get_letters(not_a_word))
obj = BadIME()
self.assertEqual(obj.apply(not_a_word), (False, BadIME.reason))
def test_invalid_pulli_seq(self):
not_a_word = u"ஆள்்ஆ"
#from tamil import utf8
#print(utf8.get_letters(not_a_word))
obj = BadIME()
self.assertEqual( obj.apply(not_a_word), (False,BadIME.reason) )
def test_valid_word_det(self):
for a_word in [u"ஆள்",u"ஏனையோருக்கும்"]:
obj = BadIME()
#print(utf8.get_letters(a_word))
self.assertEqual( obj.apply(a_word), (True,None) )
return
def test_invalid_word3(self):
obj = BadIME()
not_a_word = u"தூூக்"
self.assertEqual( obj.apply(not_a_word),(False,BadIME.reason) )
not_a_word = u"ஏூூளா"
self.assertEqual( obj.apply(not_a_word),(False,BadIME.reason) )
def test_invalid_word_det(self):
not_a_word = u"ஆாள்"
#print(utf8.get_letters(not_a_word))
obj = BadIME()
self.assertEqual( obj.apply(not_a_word),(False,BadIME.reason) )