kamp/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-11-17 18:00:12 +01:00
Code
69a61ce333
searxng/tests/unit/test_utils.py

157 lines
6.2 KiB
Python
Raw Normal View History

[enh] test utils.prettify_url
2015-09-07 19:22:01 +02:00
# -*- coding: utf-8 -*-
Cover searx.utils
2014-07-12 15:46:55 +02:00
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'))
A bit of utils unit tests
2015-01-27 20:03:33 +01:00
def test_searx_useragent(self):
self.assertIsInstance(utils.searx_useragent(), str)
self.assertIsNotNone(utils.searx_useragent())
self.assertTrue(utils.searx_useragent().startswith('searx'))
Cover searx.utils
2014-07-12 15:46:55 +02:00
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'
Drop Python 2 (4/n): SearchQuery.query is a str instead of bytes
2020-08-11 16:25:03 +02:00
query = 'test'
Cover searx.utils
2014-07-12 15:46:55 +02:00
self.assertEqual(utils.highlight_content(content, query), content)
Drop Python 2 (4/n): SearchQuery.query is a str instead of bytes
2020-08-11 16:25:03 +02:00
query = 'a test'
Cover searx.utils
2014-07-12 15:46:55 +02:00
self.assertEqual(utils.highlight_content(content, query), content)
A bit of utils unit tests
2015-01-27 20:03:33 +01:00
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>
"""
Drop Python 2 (1/n): remove unicode string and url_utils
2020-08-06 17:42:46 +02:00
self.assertIsInstance(utils.html_to_text(html), str)
A bit of utils unit tests
2015-01-27 20:03:33 +01:00
self.assertIsNotNone(utils.html_to_text(html))
self.assertEqual(utils.html_to_text(html), "Test text")
[fix] searx.utils.HTMLTextExtractor: invalid HTML don't raise an Exception Close #2188
2020-09-11 10:23:56 +02:00
def test_html_to_text_invalid(self):
html = '<p><b>Lorem ipsum</i>dolor sit amet</p>'
self.assertEqual(utils.html_to_text(html), "Lorem ipsum")
[enh] test utils.prettify_url
2015-09-07 19:22:01 +02:00
def test_prettify_url(self):
data = (('https://searx.me/', 'https://searx.me/'),
Drop Python 2 (1/n): remove unicode string and url_utils
2020-08-06 17:42:46 +02:00
('https://searx.me/ű', 'https://searx.me/ű'),
[enh] test utils.prettify_url
2015-09-07 19:22:01 +02:00
('https://searx.me/' + (100 * 'a'), 'https://searx.me/[...]aaaaaaaaaaaaaaaaa'),
Drop Python 2 (1/n): remove unicode string and url_utils
2020-08-06 17:42:46 +02:00
('https://searx.me/' + (100 * 'ű'), 'https://searx.me/[...]űűűűűűűűűűűűűűűűű'))
[enh] test utils.prettify_url
2015-09-07 19:22:01 +02:00
for test_url, expected in data:
self.assertEqual(utils.prettify_url(test_url, max_length=32), expected)
refactor engine's search language handling Add match_language function in utils to match any user given language code with a list of engine's supported languages. Also add language_aliases dict on each engine to translate standard language codes into the custom codes used by the engine.
2018-03-01 05:30:48 +01:00
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')
[fix] fix flickr_noapi decoding (#1655) Characters that were not ASCII were incorrectly decoded. Add an helper function: searx.utils.ecma_unescape (Python implementation of unescape Javascript function).
2019-08-02 13:37:13 +02:00
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')
Cover searx.utils
2014-07-12 15:46:55 +02:00
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')
Drop Python 2 (1/n): remove unicode string and url_utils
2020-08-06 17:42:46 +02:00
self.assertIn('\x0f', self.html_text_extractor.result)
Cover searx.utils
2014-07-12 15:46:55 +02:00
self.html_text_extractor.handle_charref('XF')
Drop Python 2 (1/n): remove unicode string and url_utils
2020-08-06 17:42:46 +02:00
self.assertIn('\x0f', self.html_text_extractor.result)
Cover searx.utils
2014-07-12 15:46:55 +02:00
self.html_text_extractor.handle_charref('97')
Drop Python 2 (1/n): remove unicode string and url_utils
2020-08-06 17:42:46 +02:00
self.assertIn('a', self.html_text_extractor.result)
Cover searx.utils
2014-07-12 15:46:55 +02:00
def test_handle_entityref(self):
entity = 'test'
self.html_text_extractor.handle_entityref(entity)
self.assertIn(entity, self.html_text_extractor.result)
[fix] searx.utils.HTMLTextExtractor: invalid HTML don't raise an Exception Close #2188
2020-09-11 10:23:56 +02:00
def test_invalid_html(self):
text = '<p><b>Lorem ipsum</i>dolor sit amet</p>'
with self.assertRaises(utils.HTMLTextExtractorException):
self.html_text_extractor.feed(text)
Cover searx.utils
2014-07-12 15:46:55 +02:00
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))
[fix] secret_key can be bytes instead of a string (#1602) Fix #1600 In settings.yml, the secret_key can be written as string or as base64 encoded data using !!binary notation.
2019-07-17 10:09:09 +02:00
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')
Copy Permalink