def pinyinify():
if request.method == 'POST':
print 'POST'
# print request.data
data = request.form
titlePairs = []
paragraphsPairs = []
html_doc = data['data']
html_doc = u''+html_doc
soup = BeautifulSoup(html_doc, 'html.parser')
print soup.h1.text
# print soup.get_text()
title = u'' + soup.h1.text
paragraphs = soup.find_all('p')
# print 'Reaching'
for ch in title:
titlePairs.append((ch, hanzi.to_pinyin(ch)))
for p in paragraphs:
paraPairs = []
print p
for ch in p.text:
paraPairs.append((ch, hanzi.to_pinyin(ch)))
paragraphsPairs.append(paraPairs)
return jsonify(title=titlePairs, paragraphs=paragraphsPairs)
else:
return "Error wrong method"
def test_accented_pinyin(self):
self.assertEqual(hanzi.to_pinyin(self.chinese), self.apinyin)
self.assertEqual(hanzi.to_pinyin(self.chinese, all_readings=True),
self.apinyin_readings)
self.assertEqual(hanzi.to_pinyin(self.chinese_segmented),
self.apinyin_segmented)
self.assertEqual(hanzi.to_pinyin(self.chinese_segmented,
all_readings=True),
self.apinyin_segmented_readings)
def test_accented_pinyin(self):
self.assertEqual(hanzi.to_pinyin(self.chinese), self.apinyin)
self.assertEqual(hanzi.to_pinyin(self.chinese, all_readings=True),
self.apinyin_readings)
self.assertEqual(hanzi.to_pinyin(self.chinese_segmented),
self.apinyin_segmented)
self.assertEqual(hanzi.to_pinyin(self.chinese_segmented,
all_readings=True),
self.apinyin_segmented_readings)
def get_pinyin(chinese_phrase):
# first, query pinyin for complete phrase
pinyin_phrase = hanzi.to_pinyin(chinese_phrase)
# split by syllable and add relevant html container elements
# e.g. "niǔdài" -> ['niǔ', 'dài']
pinyin_parts = re.findall(pinyin.syllable, pinyin_phrase)
pinyin_html = "".join([add_pinyin_tone_html(x) for x in pinyin_parts])
return (pinyin_phrase, pinyin_html)
def do_make(self, arg):
'make a custom flashcard: make 什么什么'
if not hanzi.has_chinese(arg):
print('input is not well formed chinese characters')
return # don't transition state
simplified = t2s.convert(arg)
traditional = s2t.convert(arg)
pinyin = hanzi.to_pinyin(arg)
zhuyin = hanzi.to_zhuyin(arg)
english = input('english definition: ')
self.save_to_file(
ChineseRecognitionOnly(simplified, traditional, pinyin, zhuyin,
english, '', '', '', self.tags))
self.transition_to(State.BEGIN)
def test_issue_10(self):
"""Incorrect readings for 女."""
reading = hanzi.to_pinyin('女')
self.assertEqual('nǚ', reading)
def test_issue_7(self):
reading = hanzi.to_pinyin('手')
self.assertEqual('shǒu', reading)
reading = hanzi.to_pinyin('收')
self.assertEqual('shōu', reading)
def test_custom_container(self):
apinyin = self.apinyin_readings.replace('[', '(').replace(']', ')')
self.assertEqual(hanzi.to_pinyin(self.chinese, all_readings=True,
container='()'), apinyin)
def test_word_readings(self):
self.assertEqual(hanzi.to_pinyin('便宜'), 'piànyi')
self.assertEqual(hanzi.to_pinyin('便宜', all_readings=True),
'[piànyi/biànyí]')
def test_custom_container(self):
apinyin = self.apinyin_readings.replace('[', '(').replace(']', ')')
self.assertEqual(hanzi.to_pinyin(self.chinese, all_readings=True,
container='()'), apinyin)
def test_word_readings(self):
self.assertEqual(hanzi.to_pinyin('便宜'), 'piànyi')
self.assertEqual(hanzi.to_pinyin('便宜', all_readings=True),
'[piànyi/biànyí]')
locale: Locale
def romanize(self, locale: Locale) -> Markup:
r = super().romanize(locale)
return Markup(r.capitalize()) if self.loan[0].isupper() else r
hangul_romanize_transliter = Transliter(academic)
romanizers: Mapping[Locale, Callable[[str], Markup]] = {
Locale.parse('ja'):
lambda t: Markup(to_roma(t.replace(' ', ''))),
Locale.parse('ko'):
lambda t: Markup(hangul_romanize_transliter.translit(t.replace(' ', ''))),
Locale.parse('zh_CN'):
lambda t: Markup(to_pinyin(t).replace(' ', '')),
Locale.parse('zh_HK'):
lambda t: Markup(
re.sub(
r'(\d) ?', r'<sup>\1</sup>', t if re.match(r'^[A-Za-z0-9 ]+$', t)
else pinyin_jyutping_sentence.jyutping(t, True, True))),
Locale.parse('zh_TW'):
lambda t: Markup(zhuyin_to_pinyin(to_zhuyin(t)).replace(' ', '')),
}
def romanize(term: str, locale: Locale) -> Markup:
global romanizers
try:
f = romanizers[locale]
except KeyError:
def test_issue_10(self):
"""Incorrect readings for 女."""
reading = hanzi.to_pinyin('女')
self.assertEqual('nǚ', reading)
def test_issue_7(self):
reading = hanzi.to_pinyin('手')
self.assertEqual('shǒu', reading)
reading = hanzi.to_pinyin('收')
self.assertEqual('shōu', reading)
g = NeoGraph()
db = Db()
eng = db.create_engine()
df = pd.read_sql("""select * from words""", eng)
df['len'] = df['characters'].apply(lambda x: len(list(x)))
df['c1'] = df['characters'].apply(lambda x: list(x)[0])
df['c2'] = df['characters'].apply(lambda x: list(x)[1]
if len(x) >= 2 else None)
df['p1'] = df['pinyin'].apply(lambda x: x.split(' ')[0])
df['p2'] = df['pinyin'].apply(lambda x: x.split(' ')[1] if ' ' in x else None)
df['english'] = df['english'].apply(lambda x: x.replace("'", "\\'"))
# df['english_short'] = df['english'].apply(lambda x: x.split(';')[0])
# df['descr'] = df.apply(lambda x: f"""{x['pinyin']} | {x['english_short']}""",axis = 1)
df['pinyin_num'] = df['pinyin'].copy()
df['pinyin'] = df['characters'].apply(lambda x: hanzi.to_pinyin(x))
helper = []
chars = []
for i, c in df.iterrows():
for h, p in zip(list(c['characters']), c['pinyin'].split(' ')):
helper.append(f'{h} : {p}')
chars.append(h)
truncate = True
if truncate:
g.truncate()
g.add_characters(list(set(chars)), df)
g.create_links(df[df['len'] == 2])
def to_pinyin(sent):
return hanzi.to_pinyin(sent, accented=False)
