本文整理汇总了Python中tokenization.BasicTokenizer方法的典型用法代码示例。如果您正苦于以下问题：Python tokenization.BasicTokenizer方法的具体用法？Python tokenization.BasicTokenizer怎么用？Python tokenization.BasicTokenizer使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tokenization的用法示例。
在下文中一共展示了tokenization.BasicTokenizer方法的7个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_basic_tokenizer_lower
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def test_basic_tokenizer_lower(self):
tokenizer = tokenization.BasicTokenizer(do_lower_case=True)
self.assertAllEqual(
tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "),
["hello", "!", "how", "are", "you", "?"])
self.assertAllEqual(tokenizer.tokenize(u"H\u00E9llo"), ["hello"]) 示例2: test_basic_tokenizer_no_lower
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def test_basic_tokenizer_no_lower(self):
tokenizer = tokenization.BasicTokenizer(do_lower_case=False)
self.assertAllEqual(
tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "),
["HeLLo", "!", "how", "Are", "yoU", "?"]) 示例3: test_chinese
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def test_chinese(self):
tokenizer = tokenization.BasicTokenizer()
self.assertAllEqual(
tokenizer.tokenize(u"ah\u535A\u63A8zz"),
[u"ah", u"\u535A", u"\u63A8", u"zz"]) 开发者ID:Nagakiran1，项目名称:Extending-Google-BERT-as-Question-and-Answering-model-and-Chatbot，代码行数:8，代码来源:tokenization_test.py
示例4: test_basic_tokenizer_lower
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def test_basic_tokenizer_lower(self):
tokenizer = tokenization.BasicTokenizer(do_lower_case=True)
self.assertAllEqual(
tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "),
["hello", "!", "how", "are", "you", "?"])
self.assertAllEqual(tokenizer.tokenize(u"H\u00E9llo"), ["hello"]) 开发者ID:Nagakiran1，项目名称:Extending-Google-BERT-as-Question-and-Answering-model-and-Chatbot，代码行数:9，代码来源:tokenization_test.py
示例5: test_basic_tokenizer_no_lower
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def test_basic_tokenizer_no_lower(self):
tokenizer = tokenization.BasicTokenizer(do_lower_case=False)
self.assertAllEqual(
tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "),
["HeLLo", "!", "how", "Are", "yoU", "?"]) 开发者ID:Nagakiran1，项目名称:Extending-Google-BERT-as-Question-and-Answering-model-and-Chatbot，代码行数:8，代码来源:tokenization_test.py
示例6: customize_tokenizer
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def customize_tokenizer(text, do_lower_case=False):
tokenizer = tokenization.BasicTokenizer(do_lower_case=do_lower_case)
temp_x = ""
text = tokenization.convert_to_unicode(text)
for c in text:
if tokenizer._is_chinese_char(ord(c)) or tokenization._is_punctuation(c) or tokenization._is_whitespace(c) or tokenization._is_control(c):
temp_x += " " + c + " "
else:
temp_x += c
if do_lower_case:
temp_x = temp_x.lower()
return temp_x.split()
# 示例7: test_chinese
# 需要导入模块: import tokenization [as 别名]
# 或者: from tokenization import BasicTokenizer [as 别名]
def test_chinese(self):
tokenizer = tokenization.BasicTokenizer()
self.assertAllEqual(
tokenizer.tokenize(u"ah\u535A\u63A8zz"),
[u"ah", u"\u535A", u"\u63A8", u"zz"])