def test_Text_clean_nwn(text_nwn):
res = Text(text_nwn, 'nwn').clean
assert res == "你好这是非词或word数字number测试"
def test_Text_clean_whi(text_whi):
res = Text(text_whi, 'whi').clean
assert res == "你好，这是空白符号测试。"
def test_Text_clean_nwh(text_nwh):
res = Text(text_nwh, 'nwh').clean
assert res == " \t\n"
def test_Text_clean_chi(text_chi):
res = Text(text_chi, 'chi').clean
assert res == "。jefj*(&-1)！"
def test_Text_clean_pun(text_pun):
res = Text(text_pun, 'nwn').clean
assert res == "你好这是标点符号测试"
def test_Text_len_num(text_len):
res = Text(text_len).len_num
assert res == 3
def test_Text_clean(get_patten):
text = "这是，测试fdsf234*(&( 返回类型的文本。"
res = Text(text, get_patten).clean
assert isinstance(res, str) == True
def test_Text_clean_pic(text_pic):
res = Text(text_pic, 'pic').clean
assert res == "你好，这#￥是图片测试。"
def test_Text_extract_lnk(text_lnk):
res = Text(text_lnk, 'lnk').extract
assert "".join(res.mats) == "[link](https://yam.gift)http://yam.gift"
def test_Text_clean_num(text_num):
res = Text(text_num, 'num').clean
assert res == "你好，这#￥是数字, , , , , , , , , 测试。"
def test_Text_extract_pic(text_pic):
res = Text(text_pic, 'pic').extract
assert "".join(res.mats) == "https://z.jpg"
def test_Text_extract_num(text_num):
res = Text(text_num, 'num').extract
assert "".join(res.mats) == "2+2-22.1-2.21/52:3-2/52%2.5%"
def test_Text_clean_eng(text_eng):
res = Text(text_eng, 'eng').clean
assert res == "你好，这#￥是英文测试。"
def test_Text_extract_eng(text_eng):
res = Text(text_eng, 'eng').extract
assert "".join(res.mats) == "English"
def test_Text_len_pun(text_len):
res = Text(text_len).len_pun
assert res == 14
def test_Text_clean_lnk(text_lnk):
res = Text(text_lnk, 'lnk').clean
assert res == "你好，这#￥是链接测试。"
def test_Text_len_eng(text_len):
res = Text(text_len).len_eng
assert res == 32
def test_Text_extract_emj(text_emj):
res = Text(text_emj, 'emj').extract
assert "".join(res.mats) == "😁😜🌹"
def test_Text_extract(get_patten):
text = "这是，测试fdsf234*(&( 返回类型的文本。"
res = Text(text, get_patten).extract
assert isinstance(res, dict) == True
assert isinstance(res.mats, list) == True
assert isinstance(res.locs, list) == True
def test_Text_clean_emj(text_emj):
res = Text(text_emj, 'emj').clean
assert res == "你好，这#￥是表情测试。"
def test_Text_extract_chi(text_chi):
res = Text(text_chi, 'chi').extract
assert "".join(res.mats) == "你好这是中文测试"
def test_Text_len_all(text_len):
res = Text(text_len).len_all
assert res == 64
def test_Text_extract_pun(text_pun):
res = Text(text_pun, 'nwn').extract
assert "".join(res.mats) == "，,.!;<>()。"
def test_Text_len_nwh(text_len):
res = Text(text_len).len_nwh
assert res == 63
def test_Text_extract_whi(text_whi):
res = Text(text_whi, 'whi').extract
assert "".join(res.mats) == " \t\n"
def test_Text_len_chi(text_len):
res = Text(text_len).len_chi
assert res == 6
def test_Text_extract_nwh(text_nwh):
res = Text(text_nwh, 'nwh').extract
assert "".join(res.mats) == "你好，这是非空白符号测试。"
def test_Text_len_wnb(text_len):
res = Text(text_len).len_wnb
assert res == 41
def test_Text_extract_wnb(text_wnb):
res = Text(text_wnb, 'wnb').extract
assert "".join(res.mats) == "你好这是词与word数字number测试"
def test_Text_extract_nwn(text_nwn):
res = Text(text_nwn, 'nwn').extract
assert "".join(res.mats) == "，。"