| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147 |
- # -*- coding: utf-8 -*-
- import mock
- from searx.testing import SearxTestCase
- from searx import utils
- class TestUtils(SearxTestCase):
- def test_gen_useragent(self):
- self.assertIsInstance(utils.gen_useragent(), str)
- self.assertIsNotNone(utils.gen_useragent())
- self.assertTrue(utils.gen_useragent().startswith('Mozilla'))
- def test_searx_useragent(self):
- self.assertIsInstance(utils.searx_useragent(), str)
- self.assertIsNotNone(utils.searx_useragent())
- self.assertTrue(utils.searx_useragent().startswith('searx'))
- def test_highlight_content(self):
- self.assertEqual(utils.highlight_content(0, None), None)
- self.assertEqual(utils.highlight_content(None, None), None)
- self.assertEqual(utils.highlight_content('', None), None)
- self.assertEqual(utils.highlight_content(False, None), None)
- contents = [
- '<html></html>'
- 'not<'
- ]
- for content in contents:
- self.assertEqual(utils.highlight_content(content, None), content)
- content = 'a'
- query = 'test'
- self.assertEqual(utils.highlight_content(content, query), content)
- query = 'a test'
- self.assertEqual(utils.highlight_content(content, query), content)
- def test_html_to_text(self):
- html = """
- <a href="/testlink" class="link_access_account">
- <span class="toto">
- <span>
- <img src="test.jpg" />
- </span>
- </span>
- <span class="titi">
- Test text
- </span>
- </a>
- """
- self.assertIsInstance(utils.html_to_text(html), str)
- self.assertIsNotNone(utils.html_to_text(html))
- self.assertEqual(utils.html_to_text(html), "Test text")
- def test_prettify_url(self):
- data = (('https://searx.me/', 'https://searx.me/'),
- ('https://searx.me/ű', 'https://searx.me/ű'),
- ('https://searx.me/' + (100 * 'a'), 'https://searx.me/[...]aaaaaaaaaaaaaaaaa'),
- ('https://searx.me/' + (100 * 'ű'), 'https://searx.me/[...]űűűűűűűűűűűűűűűűű'))
- for test_url, expected in data:
- self.assertEqual(utils.prettify_url(test_url, max_length=32), expected)
- def test_match_language(self):
- self.assertEqual(utils.match_language('es', ['es']), 'es')
- self.assertEqual(utils.match_language('es', [], fallback='fallback'), 'fallback')
- self.assertEqual(utils.match_language('ja', ['jp'], {'ja': 'jp'}), 'jp')
- aliases = {'en-GB': 'en-UK', 'he': 'iw'}
- # guess country
- self.assertEqual(utils.match_language('de-DE', ['de']), 'de')
- self.assertEqual(utils.match_language('de', ['de-DE']), 'de-DE')
- self.assertEqual(utils.match_language('es-CO', ['es-AR', 'es-ES', 'es-MX']), 'es-ES')
- self.assertEqual(utils.match_language('es-CO', ['es-MX']), 'es-MX')
- self.assertEqual(utils.match_language('en-UK', ['en-AU', 'en-GB', 'en-US']), 'en-GB')
- self.assertEqual(utils.match_language('en-GB', ['en-AU', 'en-UK', 'en-US'], aliases), 'en-UK')
- # language aliases
- self.assertEqual(utils.match_language('iw', ['he']), 'he')
- self.assertEqual(utils.match_language('he', ['iw'], aliases), 'iw')
- self.assertEqual(utils.match_language('iw-IL', ['he']), 'he')
- self.assertEqual(utils.match_language('he-IL', ['iw'], aliases), 'iw')
- self.assertEqual(utils.match_language('iw', ['he-IL']), 'he-IL')
- self.assertEqual(utils.match_language('he', ['iw-IL'], aliases), 'iw-IL')
- self.assertEqual(utils.match_language('iw-IL', ['he-IL']), 'he-IL')
- self.assertEqual(utils.match_language('he-IL', ['iw-IL'], aliases), 'iw-IL')
- def test_ecma_unscape(self):
- self.assertEqual(utils.ecma_unescape('text%20with%20space'), 'text with space')
- self.assertEqual(utils.ecma_unescape('text using %xx: %F3'),
- u'text using %xx: ó')
- self.assertEqual(utils.ecma_unescape('text using %u: %u5409, %u4E16%u754c'),
- u'text using %u: 吉, 世界')
- class TestHTMLTextExtractor(SearxTestCase):
- def setUp(self):
- self.html_text_extractor = utils.HTMLTextExtractor()
- def test__init__(self):
- self.assertEqual(self.html_text_extractor.result, [])
- def test_handle_charref(self):
- self.html_text_extractor.handle_charref('xF')
- self.assertIn('\x0f', self.html_text_extractor.result)
- self.html_text_extractor.handle_charref('XF')
- self.assertIn('\x0f', self.html_text_extractor.result)
- self.html_text_extractor.handle_charref('97')
- self.assertIn('a', self.html_text_extractor.result)
- def test_handle_entityref(self):
- entity = 'test'
- self.html_text_extractor.handle_entityref(entity)
- self.assertIn(entity, self.html_text_extractor.result)
- class TestUnicodeWriter(SearxTestCase):
- def setUp(self):
- self.unicode_writer = utils.UnicodeWriter(mock.MagicMock())
- def test_write_row(self):
- row = [1, 2, 3]
- self.assertEqual(self.unicode_writer.writerow(row), None)
- def test_write_rows(self):
- self.unicode_writer.writerow = mock.MagicMock()
- rows = [1, 2, 3]
- self.unicode_writer.writerows(rows)
- self.assertEqual(self.unicode_writer.writerow.call_count, len(rows))
- class TestNewHmac(SearxTestCase):
- def test_bytes(self):
- for secret_key in ['secret', b'secret', 1]:
- if secret_key == 1:
- with self.assertRaises(TypeError):
- utils.new_hmac(secret_key, b'http://example.com')
- continue
- res = utils.new_hmac(secret_key, b'http://example.com')
- self.assertEqual(
- res,
- '23e2baa2404012a5cc8e4a18b4aabf0dde4cb9b56f679ddc0fd6d7c24339d819')
|
