Python romanization 예제들

예제 #1

 def test_romanization_royin(self):
     engine = 'royin'
     self.assertEqual(romanization('แมว', engine=engine), 'maeo')
     self.assertEqual(romanization('เดือน', engine=engine), 'duean')
     self.assertEqual(romanization('ดู', engine=engine), 'du')
     self.assertEqual(romanization('ดำ', engine=engine), 'dam')
     self.assertEqual(romanization('บัว', engine=engine), 'bua')

예제 #2

def word_tokenize_to_g2p(text):
    wordall = dict_word_tokenize(text, custom_dict_trie=DEFAULT_DICT_TRIE)
    list = []
    for a in wordall:
        try:
            list.append(data[a])  #romanization(a,engine='pyicu'))
        except:
            word_list_icu = word_tokenize(a, engine="icu")
            for b in word_list_icu:
                list.append(romanization(b, engine='pyicu'))
    return '|'.join(list)

예제 #3

파일: name_extractor.py 프로젝트: GeoffroyDeMeyer/cv_mtl_die

    def romanize(value):
        name = ''
        try:
            name = romanization(value)
        except:
            try:
                name = self.google_tha_to_eng(value)
            except:
                pass

        return utils.keep_english_letters(name.title())

예제 #4

파일: thai_transcript.py 프로젝트: Phyks/osml10n

def thai_transcript(inpstr):
    from pythainlp.romanization import romanization
    from pythainlp.tokenize import word_tokenize

    stlist = split_by_alphabet(inpstr)

    latin = ''
    for st in stlist:
        if (unicodedata.name(st[0]).split(' ')[0] == 'THAI'):
            transcript = []
            for w in word_tokenize(st):
                transcript.append(romanization(w, engine='royin'))
            latin = latin + ' '.join(transcript)
        else:
            latin = latin + st
    return (latin)

예제 #5

# -*- coding: utf-8 -*-
from pythainlp.romanization import romanization
print(romanization("แมว"))

예제 #6

파일: __init__.py 프로젝트: gain9999/pythainlp

	def testRomanization(self):
		self.assertEqual(romanization("แมว"),'mæw')

예제 #7

파일: test.py 프로젝트: nlsntcs/pythainlp

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from pythainlp.segment import segment
a = 'ฉันรักภาษาไทยเพราะฉันเป็นคนไทย'
b = segment(a)
print(b)
from pythainlp.segment.dict import segment
print(segment(a))
print(type(b))
from pythainlp.rank import rank
aa = rank(b)
print(aa)
from pythainlp.romanization import romanization
b=romanization("แมว")
print(b)
from pythainlp.change import *
a="l;ylfu8iy["
a=texttothai(a)
b="นามรสนอำันี"
b=texttoeng(b)
print(a)
print(b)
from pythainlp.segment.dict import segment
print(segment('ปีคริสต์ศักราช'))
from pythainlp.number import numtowords
print("5611116.50")
print(numtowords(5611116.50))

from pythainlp.postaggers import tag

예제 #8

파일: test.py 프로젝트: magma2/pythainlp

from pythainlp.segment import segment
a = 'ฉันรักภาษาไทยเพราะฉันเป็นคนไทย'
b = segment(a)
print(b)
from pythainlp.segment.dict import segment
print(segment(a))
print(type(b))
from pythainlp.rank import rank
aa = rank(a)
print(aa)
from pythainlp.romanization import romanization
b=romanization("ต้นกก")
print(b)
from pythainlp.change import *
a="l;ylfu8iy["
a=texttothai(a)
b="นามรสนอำันี"
b=texttoeng(b)
print(a)
print(b)
from pythainlp.segment.dict import segment
print(segment('ฉันรักคุณ'))
from pythainlp.number import numtowords
print("5611116.50")
print(numtowords(5611116.50))

예제 #9

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from pythainlp.segment import segment
a = 'ฉันรักภาษาไทยเพราะฉันเป็นคนไทย'
b = segment(a)
print(b)
from pythainlp.segment.dict import segment
print(segment(a))
print(type(b))
from pythainlp.rank import rank
aa = rank(b)
print(aa)
from pythainlp.romanization import romanization
b = romanization("แมว")
print(b)
from pythainlp.change import *
a = "l;ylfu8iy["
a = texttothai(a)
b = "นามรสนอำันี"
b = texttoeng(b)
print(a)
print(b)
from pythainlp.segment.dict import segment
print(segment('ปีคริสต์ศักราช'))
from pythainlp.number import numtowords
print("5611116.50")
print(numtowords(5611116.50))

from pythainlp.postaggers import tag

예제 #10

파일: __init__.py 프로젝트: somjeat/pythainlp

	def test_romanization2(self):
		self.assertEqual(romanization("แมว",engine="royin"),'maeo')

예제 #11

 def test_romanization_royin(self):
     self.assertEqual(romanization("แมว", engine="royin"), 'maeo')
     self.assertEqual(romanization("เดือน", engine="royin"), 'duean')
     self.assertEqual(romanization("ดู", engine="royin"), 'du')
     self.assertEqual(romanization("ดำ", engine="royin"), 'dam')
     self.assertEqual(romanization("บัว", engine="royin"), 'bua')

예제 #12

 def test_romanization(self):
     self.assertEqual(romanization("แมว"), 'maeo')
     self.assertEqual(romanization("แมว", "pyicu"), 'mæw')

예제 #13

 def test_romanization(self):
     self.assertEqual(romanization('แมว'), 'maeo')
     self.assertEqual(romanization('แมว', 'pyicu'), 'mæw')

예제 #14

파일: __init__.py 프로젝트: zkan/pythainlp

	def test_romanization_royin(self):
		self.assertEqual(romanization("แมว",engine="royin"),'maeo')
		self.assertEqual(romanization("เดือน",engine="royin"),'duean')
		self.assertEqual(romanization("ดู",engine="royin"),'du')
		self.assertEqual(romanization("ดำ",engine="royin"),'dam')
		self.assertEqual(romanization("บัว",engine="royin"),'bua')

예제 #15

파일: __init__.py 프로젝트: zkan/pythainlp

	def test_romanization(self):
		self.assertEqual(romanization("แมว"),'maeo')
		self.assertEqual(romanization("แมว","pyicu"),'mæw')