mirror of
https://github.com/simon987/hexlib.git
synced 2025-04-10 06:06:41 +00:00
247 lines
6.7 KiB
Python
247 lines
6.7 KiB
Python
from unittest import TestCase
|
|
|
|
from hexlib.text import preprocess
|
|
|
|
|
|
class TestText(TestCase):
|
|
|
|
def test_html_invalid(self):
|
|
text = ""
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
)
|
|
expected = ""
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_1(self):
|
|
text = "<div>Hello, <strong>world</strong></div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
)
|
|
expected = "Hello, world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_2(self):
|
|
text = "<div>Hello, <strong>world</strong></div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True
|
|
)
|
|
expected = "hello, world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_3(self):
|
|
text = "<div>\n Hello, \t\n<strong> world </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
)
|
|
expected = " hello, world "
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_4(self):
|
|
text = "<div>\n Hello, \t\n<strong> world </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
strip=True
|
|
)
|
|
expected = "hello, world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_5(self):
|
|
text = "<div>\n Hello, \t\n<strong> world </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
strip=True,
|
|
remove_punctuation=True
|
|
)
|
|
expected = "hello world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_6(self):
|
|
text = "<div>\n Hello, \t\n<strong>a the world </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
remove_stopwords_en=True
|
|
)
|
|
expected = "hello world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_7(self):
|
|
text = "<div>\n Hello, \t\n<strong>a the worlds </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
remove_stopwords_en=True,
|
|
lemmatize=True
|
|
)
|
|
expected = "hello world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_8(self):
|
|
text = "<div>\n Hello, \t\n<strong>a the worlds! </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
remove_stopwords_en=True,
|
|
lemmatize=True
|
|
)
|
|
expected = "hello world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_9(self):
|
|
text = "<div>\n Hello, \t\n<strong>world! it's it`s </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
lemmatize=True,
|
|
fix_single_quotes=True
|
|
)
|
|
expected = "hello world it's it's"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_10(self):
|
|
text = "<div>\n Hello, \t\n<strong>world! it's it`s https://google.ca/test/abc.pdf </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
lemmatize=True,
|
|
fix_single_quotes=True,
|
|
remove_urls=True
|
|
)
|
|
expected = "hello world it's it's"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_11(self):
|
|
text = "<div>\n Hello, \t\n<strong>world! it's it`s & | </strong>\n\t</div>"
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
lemmatize=True,
|
|
fix_single_quotes=True,
|
|
remove_stopwords_en=True,
|
|
remove_urls=True
|
|
)
|
|
expected = "hello world"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_no_root(self):
|
|
text = "<a href=\"#p217709510\" class=\"quotelink\">>>217709510</a><br>Is there a<wbr>servant that is against civilization and humanity?<br>Literally instant summon."
|
|
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
lemmatize=False,
|
|
fix_single_quotes=True,
|
|
remove_stopwords_en=False,
|
|
remove_urls=False
|
|
)
|
|
|
|
expected = "217709510 is there a servant that is against civilization and humanity literally instant summon"
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_entity(self):
|
|
text = "doesn't"
|
|
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
lemmatize=False,
|
|
fix_single_quotes=True,
|
|
remove_stopwords_en=False,
|
|
remove_urls=False
|
|
)
|
|
|
|
expected = "doesn't"
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_html_invalid_attribute(self):
|
|
text = '<root><iframe width="560" height="315" src=" " title="youtube video player" frameborder="0" allowfullscreen></iframe></root>'
|
|
|
|
cleaned = preprocess(
|
|
text,
|
|
clean_html=True,
|
|
lowercase=True,
|
|
remove_punctuation=True,
|
|
strip=True,
|
|
lemmatize=False,
|
|
fix_single_quotes=True,
|
|
remove_stopwords_en=False,
|
|
remove_urls=False
|
|
)
|
|
|
|
expected = ""
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_bigrams(self):
|
|
text = "x A b c d e f g h"
|
|
cleaned = preprocess(
|
|
text,
|
|
lowercase=True,
|
|
bigrams={
|
|
("a", "b"),
|
|
("c", "d"),
|
|
("f", "g"),
|
|
}
|
|
)
|
|
expected = "x a_b c_d e f_g h"
|
|
|
|
self.assertEqual(cleaned, expected)
|
|
|
|
def test_remove_numbers(self):
|
|
text = "Hello1 test1124test 12 1 1111111 world"
|
|
cleaned = preprocess(
|
|
text,
|
|
lowercase=True,
|
|
remove_numbers=True
|
|
)
|
|
expected = "hello1 test1124test world"
|
|
|
|
self.assertEqual(cleaned, expected)
|