X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/28d5370e4a3ed87a622c07b81844b14420e5bcba..9670dc776f6b13b9de78941024b43021331ef0f0:/test/test_utils.py diff --git a/test/test_utils.py b/test/test_utils.py index c4b7136..0b31d1a 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1,26 +1,54 @@ #!/usr/bin/env python +# coding: utf-8 -# Various small unit tests +from __future__ import unicode_literals +# 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__)))) -#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 -from youtube_dl.utils import unified_strdate +# Various small unit tests +import io +import json +import xml.etree.ElementTree -if sys.version_info < (3, 0): - _compat_str = lambda b: b.decode('unicode-escape') -else: - _compat_str = lambda s: s +from youtube_dl.utils import ( + DateRange, + encodeFilename, + find_xpath_attr, + fix_xml_ampersands, + get_meta_content, + orderedSet, + OnDemandPagedList, + InAdvancePagedList, + 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, + limit_length, + escape_rfc3986, + escape_url, + js_to_json, + get_filesystem_encoding, + compat_getenv, + compat_expanduser, +) class TestUtil(unittest.TestCase): @@ -43,9 +71,9 @@ class TestUtil(unittest.TestCase): self.assertEqual('this - that', sanitize_filename('this: that')) self.assertEqual(sanitize_filename('AT&T'), 'AT&T') - aumlaut = _compat_str('\xe4') + aumlaut = 'ä' self.assertEqual(sanitize_filename(aumlaut), aumlaut) - tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') + tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430' self.assertEqual(sanitize_filename(tests), tests) forbidden = '"\0\\/' @@ -67,9 +95,9 @@ class TestUtil(unittest.TestCase): self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) - tests = _compat_str('a\xe4b\u4e2d\u56fd\u7684c') + tests = 'a\xe4b\u4e2d\u56fd\u7684c' self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') - self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename + self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#' for fc in forbidden: @@ -77,8 +105,8 @@ class TestUtil(unittest.TestCase): self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) # Handle a common case more neatly - self.assertEqual(sanitize_filename(_compat_str('\u5927\u58f0\u5e26 - Song'), restricted=True), 'Song') - self.assertEqual(sanitize_filename(_compat_str('\u603b\u7edf: Speech'), restricted=True), 'Speech') + self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song') + self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech') # .. but make sure the file name is never empty self.assertTrue(sanitize_filename('-', restricted=True) != '') self.assertTrue(sanitize_filename(':', restricted=True) != '') @@ -96,7 +124,9 @@ class TestUtil(unittest.TestCase): self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) def test_unescape_html(self): - self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + self.assertEqual(unescapeHTML('%20;'), '%20;') + self.assertEqual( + unescapeHTML('é'), 'é') def test_daterange(self): _20century = DateRange("19000101","20000101") @@ -111,6 +141,235 @@ class TestUtil(unittest.TestCase): 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') + self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128') + + def test_find_xpath_attr(self): + testxml = ''' + + + + + ''' + 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 = ''' + + + + + ''' + get_meta = lambda name: get_meta_content(name, testhtml) + self.assertEqual(get_meta('description'), 'foo & bar') + self.assertEqual(get_meta('author'), 'Plato') + + def test_xpath_with_ns(self): + testxml = ''' + + 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, 'The Author') + self.assertEqual(find('media:song/url').text, '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('ñ€ß\'.mp4')] + self.assertEqual(shell_quote(args), """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('http://foo.de/'), '') + self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz') + self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz') + self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz') + self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz') + self.assertEqual( + url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'), + '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('3h 11m 53s'), 11513) + self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513) + self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 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) + self.assertEqual(parse_duration('01:02:03.05'), 3723.05) + + 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 = OnDemandPagedList(get_page, pagesize) + got = pl.getslice(*sliceargs) + self.assertEqual(got, expected) + + iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize) + got = iapl.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('!B', b'\x00'), (0,)) + + def test_read_batch_urls(self): + f = io.StringIO('''\xef\xbb\xbf foo + bar\r + baz + # More after this line\r + ; or after this + bam''') + self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', '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) + self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 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_escape(self): + self.assertEqual(uppercase_escape('aä'), 'aä') + self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') + + def test_limit_length(self): + self.assertEqual(limit_length(None, 12), None) + self.assertEqual(limit_length('foo', 12), 'foo') + self.assertTrue( + limit_length('foo bar baz asd', 12).startswith('foo bar')) + self.assertTrue('...' in limit_length('foo bar baz asd', 12)) + + def test_escape_rfc3986(self): + reserved = "!*'();:@&=+$,/?#[]" + unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~' + self.assertEqual(escape_rfc3986(reserved), reserved) + self.assertEqual(escape_rfc3986(unreserved), unreserved) + self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82') + self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82') + self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar') + self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar') + + def test_escape_url(self): + self.assertEqual( + escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'), + 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4' + ) + self.assertEqual( + escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'), + 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290' + ) + self.assertEqual( + escape_url('http://тест.рф/фрагмент'), + 'http://тест.рф/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82' + ) + self.assertEqual( + escape_url('http://тест.рф/абв?абв=абв#абв'), + 'http://тест.рф/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2' + ) + self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0') + + def test_js_to_json_realworld(self): + inp = '''{ + 'clip':{'provider':'pseudo'} + }''' + self.assertEqual(js_to_json(inp), '''{ + "clip":{"provider":"pseudo"} + }''') + json.loads(js_to_json(inp)) + + inp = '''{ + 'playlist':[{'controls':{'all':null}}] + }''' + self.assertEqual(js_to_json(inp), '''{ + "playlist":[{"controls":{"all":null}}] + }''') + + def test_js_to_json_edgecases(self): + on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}") + self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"}) + + on = js_to_json('{"abc": true}') + self.assertEqual(json.loads(on), {'abc': True}) + + def test_compat_getenv(self): + test_str = 'тест' + os.environ['YOUTUBE-DL-TEST'] = (test_str if sys.version_info >= (3, 0) + else test_str.encode(get_filesystem_encoding())) + self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str) + + def test_compat_expanduser(self): + test_str = 'C:\Documents and Settings\тест\Application Data' + os.environ['HOME'] = (test_str if sys.version_info >= (3, 0) + else test_str.encode(get_filesystem_encoding())) + self.assertEqual(compat_expanduser('~'), test_str) if __name__ == '__main__': unittest.main()