From 2179079a9173b33b81e1084fc1e8e181c19ef8e9 Mon Sep 17 00:00:00 2001 From: Alexandre Flament Date: Fri, 2 Aug 2019 13:37:13 +0200 Subject: [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). --- tests/unit/test_utils.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tests/unit/test_utils.py') diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index fbaed2bd1..b09b9d414 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -90,6 +90,13 @@ class TestUtils(SearxTestCase): 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): -- cgit v1.2.3