def en_to_kana(msg_src):
msg_list = re.split(r'([(a-z)(A-Z)]+)', msg_src)
msg_list_fmt = []
for word in msg_list:
if alkana.get_kana(word) is None:
msg_list_fmt.append(word)
else:
msg_list_fmt.append(alkana.get_kana(word))
msg_fmt = ''.join(msg_list_fmt)
return msg_fmt
def countMora(m_token):
mora = 0
yomi = ''
if m_token[-1] == '*':
if alkana.get_kana(m_token[0]):
yomi = alkana.get_kana(m_token[0])
else:
yomi = m_token[-1]
if yomi == '':
if m_token[1] == '記号' or m_token[1] == '補助記号':
mora = 0
else:
mora = len(re.sub(r'[ゃゅょ]+?', '', m_token[0]))
elif m_token[1] == '記号' or m_token[1] == '補助記号':
mora = 0
else:
mora = len(re.sub(r'[ャュョ]+?', '', yomi))
return mora
def replace_eng_to_kana(cls, msg: str) -> str:
'''
英語をかな読み文字に置換する
例）wood→うっど
'''
_msg = msg
# 英語かな読み対応辞書の作成
for word in cls.re_eng.findall(_msg):
# alkanaは小文字検索
read = alkana.get_kana(word.lower())
if read is not None:
_msg = _msg.replace(word, read, 1)
return _msg
def test_add_external_data(self):
self.assertEqual(None, alkana.get_kana('mmmmm'))
file_path = os.path.join(os.path.dirname(__file__), 'sample_external_data.csv')
alkana.add_external_data(file_path)
self.assertEqual('テスト', alkana.get_kana('mmmmm'))
def test_get_kana_upper_case(self):
self.assertEqual('ワールド', alkana.get_kana("World"))
def test_get_kana(self):
self.assertEqual('ハロー', alkana.get_kana('hello'))
def test_get_kana_none_case(self):
self.assertEqual(None, alkana.get_kana("abcdefg"))
def search_synonym(word, criteria_vowel_r):
synonym_data = {}
synonym_data['original'] = word
word_yomi = mecab_get_yomi(word)
word_phoneme = g2p(word_yomi)
rhyme_pt = 0
word_phoneme.reverse()
word_vowel_r = [x for x in word_phoneme if x in vowel]
for index, p in enumerate(criteria_vowel_r):
if p == word_vowel_r[index]:
rhyme_pt += 1
else:
break
synonym_best = {
'word': word,
'rhyme_pt': rhyme_pt
}
# 問い合わせしたい単語がWordnetに存在するか確認する
cur = conn.execute("select wordid from word where lemma='%s'" % word)
word_id = 99999999 #temp
for row in cur:
word_id = row[0]
# Wordnetに存在する語であるかの判定
if word_id==99999999:
synonym_data['synonym'] = synonym_best
return synonym_data
# 入力された単語を含む概念を検索する
cur = conn.execute("select synset from sense where wordid='%s'" % word_id)
synsets = []
for row in cur:
synsets.append(row[0])
# 概念に含まれる単語を検索して画面出力する
for synset in synsets:
cur3 = conn.execute("select wordid from sense where (synset='%s' and wordid!=%s)" % (synset,word_id))
for row3 in cur3:
target_word_id = row3[0]
cur3_1 = conn.execute("select lemma from word where wordid=%s" % target_word_id)
for row3_1 in cur3_1:
synonym = row3_1[0]
if '_' in synonym:
continue
else:
if isalpha(synonym):
synonym = alkana.get_kana(synonym)
if synonym != None:
synonym_yomi = mecab_get_yomi(synonym)
synonym_phoneme = g2p(synonym_yomi)
if '<unk>' in synonym_phoneme:
continue
else:
rhyme_pt = 0
# 音素を逆順にする
synonym_phoneme.reverse()
synonym_vowel_r = [x for x in synonym_phoneme if x in vowel]
for index in range(min(len(criteria_vowel_r), len(synonym_vowel_r))):
if criteria_vowel_r[index] == synonym_vowel_r[index]:
rhyme_pt += 1
else:
break
if rhyme_pt > synonym_best['rhyme_pt']:
synonym_best = {
'word': synonym,
'rhyme_pt': rhyme_pt
}
synonym_data['synonym'] = synonym_best
return synonym_data