class Mock_thai_name():
female_names = list(pc.thai_female_names())
male_names = list(pc.thai_male_names())
family_names = list(pc.thai_family_names())
def __init__(self,
female_n: int = 1,
male_n: int = 1,
output_csv_filename=None):
"""สุ่มชื่อภาษาไทยโดยระบุจำนวนชื่อผู้หญิงและผู้ชาย
Args:
female_n (int, optional): จำนวนชื่อผู้หญิง. Defaults to 1.
male_n (int, optional): จำนวนชื่อผู้ชาย. Defaults to 1.
output_csv_filename ([type], optional): save ผลลัพธ์เป็น csv file. Defaults to None.
"""
females = random.sample(self.female_names, female_n)
females_family = random.sample(self.family_names, female_n)
males = random.sample(self.male_names, male_n)
males_family = random.sample(self.family_names, male_n)
dict_female = {
'fname': females,
'lname': females_family,
'gender': 'f'
}
dict_male = {'fname': males, 'lname': males_family, 'gender': 'm'}
self.df = pd.concat(
[pd.DataFrame(dict_female),
pd.DataFrame(dict_male)])
if output_csv_filename:
self.df.to_csv(output_csv_filename, index=False)
def test_corpus(self):
self.assertIsInstance(thai_negations(), frozenset)
self.assertIsInstance(thai_stopwords(), frozenset)
self.assertIsInstance(thai_syllables(), frozenset)
self.assertIsInstance(thai_words(), frozenset)
self.assertIsInstance(countries(), frozenset)
self.assertIsInstance(provinces(), frozenset)
self.assertIsInstance(thai_female_names(), frozenset)
self.assertIsInstance(thai_male_names(), frozenset)
self.assertEqual(get_corpus_db_detail("XXX"),
{}) # corpus does not exist
self.assertTrue(download("test")) # download the first time
self.assertTrue(download(name="test", force=True)) # force download
self.assertTrue(download(name="test")) # try download existing
self.assertFalse(download(name="test",
url="wrongurl")) # URL not exist
self.assertFalse(
download(name="XxxXXxxx817d37sf")) # corpus name not exist
self.assertIsNotNone(get_corpus_db_detail("test")) # corpus exists
self.assertTrue(remove("test")) # remove existing
self.assertFalse(remove("test")) # remove non-existing
self.assertTrue(download(name="test", version="0.1"))
self.assertTrue(remove("test"))
def test_corpus(self):
self.assertIsInstance(thai_negations(), frozenset)
self.assertIsInstance(thai_stopwords(), frozenset)
self.assertIsInstance(thai_syllables(), frozenset)
self.assertIsInstance(thai_words(), frozenset)
self.assertIsInstance(countries(), frozenset)
self.assertIsInstance(provinces(), frozenset)
self.assertIsInstance(provinces(details=True), list)
self.assertEqual(len(provinces(details=False)),
len(provinces(details=True)))
self.assertIsInstance(thai_family_names(), frozenset)
self.assertIsInstance(list(thai_family_names())[0], str)
self.assertIsInstance(thai_female_names(), frozenset)
self.assertIsInstance(thai_male_names(), frozenset)
self.assertIsInstance(
get_corpus_db("https://example.com/XXXXXX0lkjasd/SXfmskdjKKXXX"),
Response,
) # URL does not exist, should get 404 response
self.assertIsNone(get_corpus_db("XXXlkja3sfdXX")) # Invalid URL
self.assertEqual(get_corpus_db_detail("XXXmx3KSXX"),
{}) # corpus does not exist
self.assertEqual(get_corpus_db_detail("XXXmx3KSXX", version="0.2"),
{}) # corpus does not exist
self.assertTrue(download("test")) # download the first time
self.assertTrue(download(name="test", force=True)) # force download
self.assertTrue(download(name="test")) # try download existing
self.assertFalse(download(name="test",
url="wrongurl")) # URL not exist
self.assertFalse(
download(name="XxxXXxxx817d37sf")) # corpus name not exist
self.assertIsNotNone(get_corpus_db_detail("test")) # corpus exists
self.assertIsNotNone(get_corpus_path("test")) # corpus exists
self.assertTrue(remove("test")) # remove existing
self.assertFalse(remove("test")) # remove non-existing
self.assertIsNone(get_corpus_path("XXXkdjfBzc")) # query non-existing
self.assertFalse(download(name="test", version="0.0"))
self.assertFalse(download(name="test", version="0.0.0"))
self.assertFalse(download(name="test", version="0.0.1"))
self.assertFalse(download(name="test", version="0.0.2"))
self.assertFalse(download(name="test", version="0.0.3"))
self.assertFalse(download(name="test", version="0.0.4"))
self.assertIsNotNone(download(name="test", version="0.0.5"))
self.assertTrue(download("test"))
self.assertIsNotNone(remove("test")) # remove existing
self.assertIsNotNone(download(name="test", version="0.0.6"))
self.assertIsNotNone(download(name="test", version="0.0.7"))
self.assertIsNotNone(download(name="test", version="0.0.8"))
self.assertIsNotNone(download(name="test", version="0.0.9"))
self.assertIsNotNone(download(name="test", version="0.0.10"))
with self.assertRaises(Exception) as context:
self.assertIsNotNone(download(name="test", version="0.0.11"))
self.assertTrue(
"Hash does not match expected." in str(context.exception))
self.assertIsNotNone(download(name="test", version="0.1"))
self.assertIsNotNone(remove("test"))
def test_corpus(self):
self.assertIsNotNone(countries())
self.assertIsNotNone(provinces())
self.assertIsNotNone(thai_negations())
self.assertIsNotNone(thai_stopwords())
self.assertIsNotNone(thai_syllables())
self.assertIsNotNone(thai_words())
self.assertIsNotNone(thai_female_names())
self.assertIsNotNone(thai_male_names())
self.assertEqual(get_corpus_db_detail("XXX"), {})
self.assertIsNone(download("test"))
self.assertIsNone(download("test", force=True))
self.assertIsNotNone(get_corpus_db_detail("test"))
self.assertIsNotNone(remove("test"))
self.assertFalse(remove("test"))
# -*- coding: utf-8 -*-
import random
from pythainlp.corpus import thai_female_names, thai_male_names, thai_words
from faker import Faker
fake = Faker()
list_name = list(thai_female_names()) + list(thai_male_names())
list_domain_thai = [
".go.th", ".co.th", ".or.th", ".in.th", ".ac.th", ".net.th", ".mi.th",
".ไทย"
]
list_thai_word = [i for i in list(thai_words()) if ' ' not in i]
def gen_name(full_name: bool = False) -> str:
name = random.choice(list_name)
if full_name:
name += " " + random.choice(list_name)
return name
def gen_thai_phone_number(mobile: bool = True) -> str:
num = "0"
last_i = 7
if mobile:
last_i = 8
num += str(random.randint(1, 9))
for i in range(0, last_i):
num += str(random.randint(0, 9))
return num