def apply_T1(word):
'''There is a syllable boundary in front of every CV-sequence.'''
T1 = ' T1'
WORD = _split_consonants_and_vowels(word)
CONTINUE_VV = 0
CONTINUE_VVV = 0
for i, v in enumerate(WORD):
if i == 0 and is_consonant(v[0][0]):
continue
elif is_consonant(v[0]) and i + 1 != len(WORD):
WORD[i] = v[:-1] + '.' + v[-1]
elif is_vowel(v[0]):
if len(v) > 2:
CONTINUE_VVV += 1
elif len(v) > 1:
CONTINUE_VV += 1
word = ''.join(WORD)
return word, CONTINUE_VV, CONTINUE_VVV, T1
def apply_T6(word):
'''If a VVV-sequence contains a long vowel, there is a syllable boundary
between it and the third vowel, e.g. [kor.ke.aa], [yh.ti.öön], [ruu.an],
[mää.yt.te].'''
T6 = ''
WORD = word.split('.')
for i, v in enumerate(WORD):
if contains_VVV(v):
VV = [v.find(j) for j in LONG_VOWELS if v.find(j) > 0]
if VV:
I = VV[0]
T6 = ' T6'
if I + 2 == len(v) or is_vowel(v[I + 2]):
WORD[i] = v[:I + 2] + '.' + v[I + 2:] # TODO
else:
WORD[i] = v[:I] + '.' + v[I:]
word = '.'.join(WORD)
word = word.strip('.') # TODO
return word, T6
def apply_T7(word):
'''If a VVV-sequence does not contain a potential /i/-final diphthong,
there is a syllable boundary between the second and third vowels, e.g.
[kau.an], [leu.an], [kiu.as].'''
WORD = _split_consonants_and_vowels(word)
for k, v in WORD.iteritems():
if len(v) == 3 and is_vowel(v[0]):
WORD[k] = v[:2] + '.' + v[2:]
word = _compile_dict_into_word(WORD)
return word
def apply_T2(word):
'''There is a syllable boundary within a sequence VV of two nonidentical
that are not a genuine diphthong, e.g., [ta.e], [ko.et.taa].'''
WORD = _split_consonants_and_vowels(word)
for k, v in WORD.iteritems():
if is_diphthong(v):
continue
if len(v) == 2 and is_vowel(v[0]):
if v[0] != v[1]:
WORD[k] = v[0] + '.' + v[1]
word = _compile_dict_into_word(WORD)
return word
def apply_T7(word):
'''If a VVV-sequence does not contain a potential /i/-final diphthong,
there is a syllable boundary between the second and third vowels, e.g.
[kau.an], [leu.an], [kiu.as].'''
T7 = ''
WORD = word.split('.')
for i, v in enumerate(WORD):
if contains_VVV(v):
for I, V in enumerate(v[::-1]):
if is_vowel(V):
WORD[i] = v[:I] + '.' + v[I:]
T7 = ' T7'
word = '.'.join(WORD)
return word, T7
def apply_T5(word):
'''If a (V)VVV sequence contains a VV sequence that could be an /i/-final
diphthong, there is a syllable boundary between it and the third vowel,
e.g., [raa.ois.sa], [huo.uim.me], [la.eis.sa], [sel.vi.äi.si], [tai.an],
[säi.e], [oi.om.me].'''
WORD = word
offset = 0
for vi in i_final_diphthong_vvv_sequences(WORD):
s = max(vi.start(1), vi.start(2))
i = 2 if s + 2 < len(word) and is_vowel(word[s + 2]) else 0
if not (s == i == 0):
i += s + offset
WORD = WORD[:i] + '.' + WORD[i:]
offset += 1
RULE = ' T5' if word != WORD else ''
return WORD, RULE
def apply_T6(word):
'''If a VVV-sequence contains a long vowel, there is a syllable boundary
between it and the third vowel, e.g. [kor.ke.aa], [yh.ti.öön], [ruu.an],
[mää.yt.te].'''
WORD = _split_consonants_and_vowels(word)
for k, v in WORD.iteritems():
if len(v) == 3 and is_vowel(v[0]):
vv = [v.find(i) for i in LONG_VOWELS if v.find(i) > 0]
if any(vv):
vv = vv[0]
if vv == v[0]:
WORD[k] = v[:2] + '.' + v[2:]
else:
WORD[k] = v[:vv] + '.' + v[vv:]
word = _compile_dict_into_word(WORD)
return word
def apply_T5(word):
'''If a (V)VVV-sequence contains a VV-sequence that could be an /i/-final
diphthong, there is a syllable boundary between it and the third vowel,
e.g., [raa.ois.sa], [huo.uim.me], [la.eis.sa], [sel.vi.äi.si], [tai.an],
[säi.e], [oi.om.me].'''
WORD = _split_consonants_and_vowels(word)
for k, v in WORD.iteritems():
if len(v) >= 3 and is_vowel(v[0]):
vv = [v.find(i) for i in i_DIPHTHONGS if v.find(i) > 0]
if any(vv):
vv = vv[0]
if vv == v[0]:
WORD[k] = v[:2] + '.' + v[2:]
else:
WORD[k] = v[:vv] + '.' + v[vv:]
word = _compile_dict_into_word(WORD)
return word