How to use test_encoding method in Molotov

Best Python code snippet using molotov_python

process.py

Source:process.py

1import os2import torch3from transformers import BertTokenizer4from sklearn.model_selection import train_test_split5from src.utils.config import config6from src.utils.util import save_pkl, load_pkl7def process_text(question1, question2, label):8    """9    å¤çè®ç»çæ°æ®10    :param question1:11    :param question2:12    :param label:13    :return:14    """15    tokenizer = BertTokenizer.from_pretrained(config.bert_base_path)16    train, test = [], []17    if os.path.exists(config.train_path):18        train = load_pkl(config.train_path, 'train_data')19        test = load_pkl(config.test_path, 'test_data')20    else:21        q1_train, q1_val, q2_train, q2_val, train_label, test_label = train_test_split(question1, question2, label,22                                                                                       test_size=0.2, stratify=label)23        # train_data = tokenizer.batch_encode_plus(q1_train, q2_train, truncation=True, padding=True, max_length=375)24        # train_encoding.append(train_data['input_ids'])25        # train_encoding.append(train_data['token_type_ids'])26        # train_encoding.append(train_data['attention_mask'])27        #28        # test_data = tokenizer.batch_encode_plus(q1_val, q2_val, truncation=True, padding=True, max_length=375)29        # test_encoding.append(test_data['input_ids'])30        # test_encoding.append(test_data['token_type_ids'])31        # test_encoding.append(test_data['attention_mask'])32        for i in range(len(q1_train)):33            train_encoding = []34            train_data = tokenizer.encode_plus(str(q1_train[i]), str(q2_train[i]), truncation=True,35                                               padding=True, max_length=200)36            train_encoding.append(train_data['input_ids'])37            train_encoding.append(train_data['token_type_ids'])38            train_encoding.append(train_data['attention_mask'])39            train_encoding.append(int(train_label[i]))40            train.append(train_encoding)41        for i in range(len(q1_val)):42            test_encoding = []43            test_data = tokenizer.encode_plus(str(q1_val[i]), str(q2_val[i]), truncation=True,44                                              padding=True, max_length=200)45            test_encoding.append(test_data['input_ids'])46            test_encoding.append(test_data['token_type_ids'])47            test_encoding.append(test_data['attention_mask'])48            test_encoding.append(int(test_label[i]))49            test.append(test_encoding)50        save_pkl(config.train_path, train, 'train_data', use_bert=True)51        save_pkl(config.test_path, test, 'test_data', use_bert=True)52    return train, test53def process_pre_text(question1, question2):54    """55    å¤çé¢æµæ°æ®56    :param question1:57    :param question2:58    :return:59    """60    tokenizer = BertTokenizer.from_pretrained(config.bert_base_path)61    train_encoding = []62    train_data = tokenizer.encode_plus(question1, question2, truncation=True, padding=True, max_length=200)63    train_encoding.append(train_data['input_ids'])64    train_encoding.append(train_data['token_type_ids'])65    train_encoding.append(train_data['attention_mask'])66    return [train_encoding]67def process_batch_pre_text(question1, question2):68    """69    å¤çæ¹éæ°æ®70    """71    tokenizer = BertTokenizer.from_pretrained(config.bert_base_path)72    all_data = []73    for i in range(len(question1)):74        train_encoding = []75        train_data = tokenizer.encode_plus(str(question1[i]), str(question2[i]), truncation=True, padding=True,76                                           max_length=200)77        train_encoding.append(train_data['input_ids'])78        train_encoding.append(train_data['token_type_ids'])79        train_encoding.append(train_data['attention_mask'])80        all_data.append(train_encoding)...

run.py

Source:run.py

1# -*- coding: latin-1 -*-2from pysys.constants import *3from pysys.basetest import BaseTest4import io, locale5# contains a non-ascii ï¿½ character that is different in utf-8 vs latin-16TEST_STR = u'Hello ï¿½ world' 7# use a different encoding to the default/local encoding8TEST_ENCODING = 'latin-1' if PREFERRED_ENCODING.lower() == 'utf-8' else 'utf-8'9class PySysTest(BaseTest):10	def execute(self):11		self.log.info('Python local/default/preferred encoding is %s; will test with non-local encoding %s', PREFERRED_ENCODING, TEST_ENCODING)12		if PREFERRED_ENCODING in ['ANSI_X3.4-1968', 'ascii']: self.skipTest('cannot run in ASCII locale')13		self.__myDefaultEncoding = None14		self.write_text('test-nonlocal.txt', os.linesep.join([TEST_STR, TEST_STR, 'otherstring']), encoding=TEST_ENCODING)15	def validate(self):16		if TEST_ENCODING == 'utf-8': # can't even read the file without an exception on utf8 systems17			self.assertGrep('test-nonlocal.txt', expr=TEST_STR, contains=False) # without encoding arg, won't work18		self.assertLineCount('test-nonlocal.txt', expr=TEST_STR, condition='==2', encoding=TEST_ENCODING)19		self.assertGrep('test-nonlocal.txt', expr=TEST_STR, contains=True, encoding=TEST_ENCODING)20		self.waitForGrep('test-nonlocal.txt', expr=TEST_STR, condition='==2', timeout=2, abortOnError=True, encoding=TEST_ENCODING)21		self.assertLastGrep('test-nonlocal.txt', expr=TEST_STR, contains=True, ignores=['^$', 'otherstring'], encoding=TEST_ENCODING)22		self.assertOrderedGrep('test-nonlocal.txt', exprList=[TEST_STR, TEST_STR], encoding=TEST_ENCODING)23		self.assertTrue(self.logFileContents('test-nonlocal.txt', encoding=TEST_ENCODING))24		self.assertDiff('test-nonlocal.txt', 'test-nonlocal.txt', filedir1=self.output, filedir2=self.output, encoding=TEST_ENCODING)25		self.assertThat('%s==%s', repr(TEST_STR), repr(self.getExprFromFile('test-nonlocal.txt', TEST_STR, encoding=TEST_ENCODING)))26		27		self.log.info('')28		self.log.info('now testing using getDefaultFileEncoding:')29		self.__myDefaultEncoding = TEST_ENCODING30		self.assertLineCount('test-nonlocal.txt', expr=TEST_STR, condition='==2')31		self.assertGrep('test-nonlocal.txt', expr=TEST_STR, contains=True)32		self.waitForGrep('test-nonlocal.txt', expr=TEST_STR, condition='==2', timeout=2, abortOnError=True)33		self.assertLastGrep('test-nonlocal.txt', expr=TEST_STR, contains=True, ignores=['^$', 'otherstring'])34		self.assertOrderedGrep('test-nonlocal.txt', exprList=[TEST_STR, TEST_STR])35		self.assertTrue(self.logFileContents('test-nonlocal.txt'))36		self.assertDiff('test-nonlocal.txt', 'test-nonlocal.txt', filedir1=self.output, filedir2=self.output)37		self.assertThat('%s==%s', repr(TEST_STR), repr(self.getExprFromFile('test-nonlocal.txt', TEST_STR)))38		39	40	def getDefaultFileEncoding(self, file, **xargs):41		if self.__myDefaultEncoding != None:42			self.log.info('  called getDefaultFileEncoding for %s with %s', file, xargs)43		return self.__myDefaultEncoding44	...

test_encoding.py

Source:test_encoding.py

...41    client = TestClient(run_panini)42    client.start()43    yield client44    client.stop()45def test_encoding(client):46    response = client.request("test_encoding.foo", {"data": "some correct data"})47    assert response["len"] == 1748    response = client.request("test_encoding.foo", {"data": "Ð½Ðµ Ð»Ð°ÑÐ¸Ð½ÑÐºÐ¸Ðµ ÑÐ¸Ð¼Ð²Ð¾Ð»Ñ"})49    assert response["len"] == 2050def test_correct_message_format(client):51    response = client.request("test_encoding.correct", {"data": "some data"})52    assert response["success"] is True53def test_incorrect_message_format(client):54    with pytest.raises(OSError):55        client.request("test_encoding.message.correct", {"data": "some data"})56    with pytest.raises(OSError):...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.