X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c4994c6aff3e03c7848b0a9d4ff9a1873412d31f..b167626f0befcfaa9c2e0f16d2c70a75b56f76e9:/test/test_utils.py?ds=sidebyside diff --git a/test/test_utils.py b/test/test_utils.py index 796ed4a..51eb0b6 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1,19 +1,45 @@ #!/usr/bin/env python +# coding: utf-8 -# Various small unit tests - +# Allow direct execution +import os import sys import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -# Allow direct execution -import os -sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +# Various small unit tests +import io +import json +import xml.etree.ElementTree #from youtube_dl.utils import htmlentity_transform -from youtube_dl.utils import timeconvert -from youtube_dl.utils import sanitize_filename -from youtube_dl.utils import unescapeHTML -from youtube_dl.utils import orderedSet +from youtube_dl.utils import ( + DateRange, + encodeFilename, + find_xpath_attr, + fix_xml_ampersands, + get_meta_content, + orderedSet, + PagedList, + parse_duration, + read_batch_urls, + sanitize_filename, + shell_quote, + smuggle_url, + str_to_int, + struct_unpack, + timeconvert, + unescapeHTML, + unified_strdate, + unsmuggle_url, + url_basename, + urlencode_postdata, + xpath_with_ns, + parse_iso8601, + strip_jsonp, + uppercase_escape, +) if sys.version_info < (3, 0): _compat_str = lambda b: b.decode('unicode-escape') @@ -82,9 +108,9 @@ class TestUtil(unittest.TestCase): self.assertTrue(sanitize_filename(':', restricted=True) != '') def test_sanitize_ids(self): - self.assertEquals(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') - self.assertEquals(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw') - self.assertEquals(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI') + self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') + self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw') + self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI') def test_ordered_set(self): self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) @@ -95,6 +121,168 @@ class TestUtil(unittest.TestCase): def test_unescape_html(self): self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + + def test_daterange(self): + _20century = DateRange("19000101","20000101") + self.assertFalse("17890714" in _20century) + _ac = DateRange("00010101") + self.assertTrue("19690721" in _ac) + _firstmilenium = DateRange(end="10000101") + self.assertTrue("07110427" in _firstmilenium) + + def test_unified_dates(self): + self.assertEqual(unified_strdate('December 21, 2010'), '20101221') + self.assertEqual(unified_strdate('8/7/2009'), '20090708') + self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214') + self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011') + self.assertEqual(unified_strdate('1968-12-10'), '19681210') + + def test_find_xpath_attr(self): + testxml = u''' + + + + + ''' + doc = xml.etree.ElementTree.fromstring(testxml) + + self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None) + self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1]) + self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2]) + + def test_meta_parser(self): + testhtml = u''' + + + + + ''' + get_meta = lambda name: get_meta_content(name, testhtml) + self.assertEqual(get_meta('description'), u'foo & bar') + self.assertEqual(get_meta('author'), 'Plato') + + def test_xpath_with_ns(self): + testxml = u''' + + The Author + http://server.com/download.mp3 + + ''' + doc = xml.etree.ElementTree.fromstring(testxml) + find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'})) + self.assertTrue(find('media:song') is not None) + self.assertEqual(find('media:song/media:author').text, u'The Author') + self.assertEqual(find('media:song/url').text, u'http://server.com/download.mp3') + + def test_smuggle_url(self): + data = {u"ö": u"ö", u"abc": [3]} + url = 'https://foo.bar/baz?x=y#a' + smug_url = smuggle_url(url, data) + unsmug_url, unsmug_data = unsmuggle_url(smug_url) + self.assertEqual(url, unsmug_url) + self.assertEqual(data, unsmug_data) + + res_url, res_data = unsmuggle_url(url) + self.assertEqual(res_url, url) + self.assertEqual(res_data, None) + + def test_shell_quote(self): + args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')] + self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""") + + def test_str_to_int(self): + self.assertEqual(str_to_int('123,456'), 123456) + self.assertEqual(str_to_int('123.456'), 123456) + + def test_url_basename(self): + self.assertEqual(url_basename(u'http://foo.de/'), u'') + self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz') + self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz') + self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz') + self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz') + self.assertEqual( + url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'), + u'trailer.mp4') + + def test_parse_duration(self): + self.assertEqual(parse_duration(None), None) + self.assertEqual(parse_duration('1'), 1) + self.assertEqual(parse_duration('1337:12'), 80232) + self.assertEqual(parse_duration('9:12:43'), 33163) + self.assertEqual(parse_duration('12:00'), 720) + self.assertEqual(parse_duration('00:01:01'), 61) + self.assertEqual(parse_duration('x:y'), None) + self.assertEqual(parse_duration('3h11m53s'), 11513) + self.assertEqual(parse_duration('62m45s'), 3765) + self.assertEqual(parse_duration('6m59s'), 419) + self.assertEqual(parse_duration('49s'), 49) + self.assertEqual(parse_duration('0h0m0s'), 0) + self.assertEqual(parse_duration('0m0s'), 0) + self.assertEqual(parse_duration('0s'), 0) + + def test_fix_xml_ampersands(self): + self.assertEqual( + fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a') + self.assertEqual( + fix_xml_ampersands('"&x=y&wrong;&z=a'), + '"&x=y&wrong;&z=a') + self.assertEqual( + fix_xml_ampersands('&'><"'), + '&'><"') + self.assertEqual( + fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼') + self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#') + + def test_paged_list(self): + def testPL(size, pagesize, sliceargs, expected): + def get_page(pagenum): + firstid = pagenum * pagesize + upto = min(size, pagenum * pagesize + pagesize) + for i in range(firstid, upto): + yield i + + pl = PagedList(get_page, pagesize) + got = pl.getslice(*sliceargs) + self.assertEqual(got, expected) + + testPL(5, 2, (), [0, 1, 2, 3, 4]) + testPL(5, 2, (1,), [1, 2, 3, 4]) + testPL(5, 2, (2,), [2, 3, 4]) + testPL(5, 2, (4,), [4]) + testPL(5, 2, (0, 3), [0, 1, 2]) + testPL(5, 2, (1, 4), [1, 2, 3]) + testPL(5, 2, (2, 99), [2, 3, 4]) + testPL(5, 2, (20, 99), []) + + def test_struct_unpack(self): + self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,)) + + def test_read_batch_urls(self): + f = io.StringIO(u'''\xef\xbb\xbf foo + bar\r + baz + # More after this line\r + ; or after this + bam''') + self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam']) + + def test_urlencode_postdata(self): + data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}) + self.assertTrue(isinstance(data, bytes)) + + def test_parse_iso8601(self): + self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266) + self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266) + self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266) + + def test_strip_jsonp(self): + stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);') + d = json.loads(stripped) + self.assertEqual(d, [{"id": "532cb", "x": 3}]) + + def test_uppercase_escpae(self): + self.assertEqual(uppercase_escape(u'aä'), u'aä') + self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐') if __name__ == '__main__': unittest.main()