From 1c469a9480e9d8bea45950898eb46e07b0c58290 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 26 Nov 2012 23:58:46 +0100 Subject: New optoin --restrict-filenames --- test/test_utils.py | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index e7c6d5b3d..0a435ddc5 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -30,11 +30,34 @@ class TestUtil(unittest.TestCase): self.assertEqual(u'yes no', sanitize_filename(u'yes? no')) self.assertEqual(u'this - that', sanitize_filename(u'this: that')) + self.assertEqual(sanitize_filename(u'AT&T'), u'AT&T') self.assertEqual(sanitize_filename(u'ä'), u'ä') self.assertEqual(sanitize_filename(u'кириллица'), u'кириллица') - for forbidden in u'"\0\\/': - self.assertTrue(forbidden not in sanitize_filename(forbidden)) + forbidden = u'"\0\\/' + for fc in forbidden: + for fbc in forbidden: + self.assertTrue(fbc not in sanitize_filename(fc)) + + def test_sanitize_filename_restricted(self): + self.assertEqual(sanitize_filename(u'abc', restricted=True), u'abc') + self.assertEqual(sanitize_filename(u'abc_d-e', restricted=True), u'abc_d-e') + + self.assertEqual(sanitize_filename(u'123', restricted=True), u'123') + + self.assertEqual(u'abc-de', sanitize_filename(u'abc/de', restricted=True)) + self.assertFalse(u'/' in sanitize_filename(u'abc/de///', restricted=True)) + + self.assertEqual(u'abc-de', sanitize_filename(u'abc/<>\\*|de', restricted=True)) + self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|', restricted=True)) + self.assertEqual(u'yes_no', sanitize_filename(u'yes? no', restricted=True)) + self.assertEqual(u'this_-_that', sanitize_filename(u'this: that', restricted=True)) + + forbidden = u'"\0\\/&: \'\t\n' + for fc in forbidden: + print('input: ' + fc + ', result: ' + repr(sanitize_filename(fc, restricted=True))) + for fbc in forbidden: + self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) 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]) -- cgit v1.2.3 From 56781d3d2e476e2e109d0907d89548fd4da05058 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 12:46:09 +0100 Subject: Switch back to underline for invalid characters, and make restricted ASCII-only --- test/test_utils.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index 0a435ddc5..0b57e016c 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -22,10 +22,10 @@ class TestUtil(unittest.TestCase): self.assertEqual(sanitize_filename(u'123'), u'123') - self.assertEqual(u'abc-de', sanitize_filename(u'abc/de')) + self.assertEqual(u'abc_de', sanitize_filename(u'abc/de')) self.assertFalse(u'/' in sanitize_filename(u'abc/de///')) - self.assertEqual(u'abc-de', sanitize_filename(u'abc/<>\\*|de')) + self.assertEqual(u'abc_de', sanitize_filename(u'abc/<>\\*|de')) self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|')) self.assertEqual(u'yes no', sanitize_filename(u'yes? no')) self.assertEqual(u'this - that', sanitize_filename(u'this: that')) @@ -45,14 +45,17 @@ class TestUtil(unittest.TestCase): self.assertEqual(sanitize_filename(u'123', restricted=True), u'123') - self.assertEqual(u'abc-de', sanitize_filename(u'abc/de', restricted=True)) + self.assertEqual(u'abc_de', sanitize_filename(u'abc/de', restricted=True)) self.assertFalse(u'/' in sanitize_filename(u'abc/de///', restricted=True)) - self.assertEqual(u'abc-de', sanitize_filename(u'abc/<>\\*|de', restricted=True)) + self.assertEqual(u'abc_de', sanitize_filename(u'abc/<>\\*|de', restricted=True)) self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|', restricted=True)) self.assertEqual(u'yes_no', sanitize_filename(u'yes? no', restricted=True)) self.assertEqual(u'this_-_that', sanitize_filename(u'this: that', restricted=True)) + self.assertEqual(sanitize_filename(u'aäb', restricted=True), u'a_b') + self.assertTrue(sanitize_filename(u'ö', restricted=True) != u'') # No empty filename + forbidden = u'"\0\\/&: \'\t\n' for fc in forbidden: print('input: ' + fc + ', result: ' + repr(sanitize_filename(fc, restricted=True))) -- cgit v1.2.3 From c7032546f1f0536f594fe741274b2aae84a9d365 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 12:46:27 +0100 Subject: Clean up test --- test/test_utils.py | 1 - 1 file changed, 1 deletion(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index 0b57e016c..4208ee653 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -58,7 +58,6 @@ class TestUtil(unittest.TestCase): forbidden = u'"\0\\/&: \'\t\n' for fc in forbidden: - print('input: ' + fc + ', result: ' + repr(sanitize_filename(fc, restricted=True))) for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) -- cgit v1.2.3 From 46cbda0be4bed00122a5cf43e640808e6c32222d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 15:07:10 +0100 Subject: Minor filename encoding improvement in a common case --- test/test_utils.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index 4208ee653..e806a10c5 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -61,6 +61,13 @@ class TestUtil(unittest.TestCase): for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) + # Handle a common case more neatly + self.assertEqual(sanitize_filename(u'大声带 - Song', restricted=True), u'Song') + self.assertEqual(sanitize_filename(u'总统: Speech', restricted=True), u'Speech') + # .. but make sure the file name is never empty + self.assertTrue(sanitize_filename(u'-', restricted=True) != u'') + self.assertTrue(sanitize_filename(u':', restricted=True) != u'') + 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]) self.assertEqual(orderedSet([]), []) -- cgit v1.2.3 From 1a911e60a4c2e15182a4c08683863a86a722b43f Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 16:07:52 +0100 Subject: Add test for asian characters (#551) --- test/test_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index e806a10c5..e7d4e0330 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -53,7 +53,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(u'yes_no', sanitize_filename(u'yes? no', restricted=True)) self.assertEqual(u'this_-_that', sanitize_filename(u'this: that', restricted=True)) - self.assertEqual(sanitize_filename(u'aäb', restricted=True), u'a_b') + self.assertEqual(sanitize_filename(u'aäb中国的c', restricted=True), u'a_b_c') self.assertTrue(sanitize_filename(u'ö', restricted=True) != u'') # No empty filename forbidden = u'"\0\\/&: \'\t\n' -- cgit v1.2.3 From dffe658bac71531dc6aa72088c4d98f6a556bfbf Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 17:15:33 +0100 Subject: Remove exclamation mark in --restrict-filenames mode --- test/test_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index e7d4e0330..a3a23fbb4 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -56,7 +56,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(sanitize_filename(u'aäb中国的c', restricted=True), u'a_b_c') self.assertTrue(sanitize_filename(u'ö', restricted=True) != u'') # No empty filename - forbidden = u'"\0\\/&: \'\t\n' + forbidden = u'"\0\\/&!: \'\t\n' for fc in forbidden: for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) -- cgit v1.2.3 From dae7c920f633605167aed534a000c85b3096ba56 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 27 Nov 2012 23:20:29 +0100 Subject: Make test_utils.py run on Python 3 --- test/test_utils.py | 77 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 45 insertions(+), 32 deletions(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index a3a23fbb4..b8fc13aef 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1,15 +1,22 @@ -# -*- coding: utf-8 -*- - # Various small unit tests +import sys import unittest +# 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 +if sys.version < (3,0): + _compat_str = lambda b: b.decode('unicode-escape') +else: + _compat_str = lambda s: s class TestUtil(unittest.TestCase): def test_timeconvert(self): @@ -17,56 +24,59 @@ class TestUtil(unittest.TestCase): self.assertTrue(timeconvert('bougrg') is None) def test_sanitize_filename(self): - self.assertEqual(sanitize_filename(u'abc'), u'abc') - self.assertEqual(sanitize_filename(u'abc_d-e'), u'abc_d-e') + self.assertEqual(sanitize_filename('abc'), 'abc') + self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') - self.assertEqual(sanitize_filename(u'123'), u'123') + self.assertEqual(sanitize_filename('123'), '123') - self.assertEqual(u'abc_de', sanitize_filename(u'abc/de')) - self.assertFalse(u'/' in sanitize_filename(u'abc/de///')) + self.assertEqual('abc_de', sanitize_filename('abc/de')) + self.assertFalse('/' in sanitize_filename('abc/de///')) - self.assertEqual(u'abc_de', sanitize_filename(u'abc/<>\\*|de')) - self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|')) - self.assertEqual(u'yes no', sanitize_filename(u'yes? no')) - self.assertEqual(u'this - that', sanitize_filename(u'this: that')) + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) + self.assertEqual('yes no', sanitize_filename('yes? no')) + self.assertEqual('this - that', sanitize_filename('this: that')) - self.assertEqual(sanitize_filename(u'AT&T'), u'AT&T') - self.assertEqual(sanitize_filename(u'ä'), u'ä') - self.assertEqual(sanitize_filename(u'кириллица'), u'кириллица') + self.assertEqual(sanitize_filename('AT&T'), 'AT&T') + aumlaut = _compat_str('\xe4') + self.assertEqual(sanitize_filename(aumlaut), aumlaut) + tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') + self.assertEqual(sanitize_filename(tests), tests) - forbidden = u'"\0\\/' + forbidden = '"\0\\/' for fc in forbidden: for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc)) def test_sanitize_filename_restricted(self): - self.assertEqual(sanitize_filename(u'abc', restricted=True), u'abc') - self.assertEqual(sanitize_filename(u'abc_d-e', restricted=True), u'abc_d-e') + self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') + self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') - self.assertEqual(sanitize_filename(u'123', restricted=True), u'123') + self.assertEqual(sanitize_filename('123', restricted=True), '123') - self.assertEqual(u'abc_de', sanitize_filename(u'abc/de', restricted=True)) - self.assertFalse(u'/' in sanitize_filename(u'abc/de///', restricted=True)) + self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) + self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) - self.assertEqual(u'abc_de', sanitize_filename(u'abc/<>\\*|de', restricted=True)) - self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|', restricted=True)) - self.assertEqual(u'yes_no', sanitize_filename(u'yes? no', restricted=True)) - self.assertEqual(u'this_-_that', sanitize_filename(u'this: that', restricted=True)) + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) + self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) + self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) - self.assertEqual(sanitize_filename(u'aäb中国的c', restricted=True), u'a_b_c') - self.assertTrue(sanitize_filename(u'ö', restricted=True) != u'') # No empty filename + tests =_compat_str('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 - forbidden = u'"\0\\/&!: \'\t\n' + forbidden = '"\0\\/&!: \'\t\n' for fc in forbidden: for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) # Handle a common case more neatly - self.assertEqual(sanitize_filename(u'大声带 - Song', restricted=True), u'Song') - self.assertEqual(sanitize_filename(u'总统: Speech', restricted=True), u'Speech') + 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') # .. but make sure the file name is never empty - self.assertTrue(sanitize_filename(u'-', restricted=True) != u'') - self.assertTrue(sanitize_filename(u':', restricted=True) != u'') + self.assertTrue(sanitize_filename('-', restricted=True) != '') + self.assertTrue(sanitize_filename(':', restricted=True) != '') 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]) @@ -76,4 +86,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(orderedSet([135,1,1,1]), [135,1]) def test_unescape_html(self): - self.assertEqual(unescapeHTML(u"%20;"), u"%20;") + self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + +if __name__ == '__main__': + unittest.main() -- cgit v1.2.3 From 8cd10ac4efb5168f3ceb18ec94338bce73e166a7 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 00:46:21 +0100 Subject: Fix printing title etc. --- test/test_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index b8fc13aef..e2f226bf1 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -13,7 +13,7 @@ from youtube_dl.utils import sanitize_filename from youtube_dl.utils import unescapeHTML from youtube_dl.utils import orderedSet -if sys.version < (3,0): +if sys.version_info < (3,0): _compat_str = lambda b: b.decode('unicode-escape') else: _compat_str = lambda s: s -- cgit v1.2.3 From 59ae15a507cbf93de13f8fda8444d2d9a251747a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 02:04:46 +0100 Subject: Convert all tabs to 4 spaces (PEP8) --- test/test_utils.py | 142 ++++++++++++++++++++++++++--------------------------- 1 file changed, 71 insertions(+), 71 deletions(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index e2f226bf1..ceefabefc 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -14,79 +14,79 @@ from youtube_dl.utils import unescapeHTML from youtube_dl.utils import orderedSet if sys.version_info < (3,0): - _compat_str = lambda b: b.decode('unicode-escape') + _compat_str = lambda b: b.decode('unicode-escape') else: - _compat_str = lambda s: s + _compat_str = lambda s: s class TestUtil(unittest.TestCase): - def test_timeconvert(self): - self.assertTrue(timeconvert('') is None) - self.assertTrue(timeconvert('bougrg') is None) - - def test_sanitize_filename(self): - self.assertEqual(sanitize_filename('abc'), 'abc') - self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') - - self.assertEqual(sanitize_filename('123'), '123') - - self.assertEqual('abc_de', sanitize_filename('abc/de')) - self.assertFalse('/' in sanitize_filename('abc/de///')) - - self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) - self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) - self.assertEqual('yes no', sanitize_filename('yes? no')) - self.assertEqual('this - that', sanitize_filename('this: that')) - - self.assertEqual(sanitize_filename('AT&T'), 'AT&T') - aumlaut = _compat_str('\xe4') - self.assertEqual(sanitize_filename(aumlaut), aumlaut) - tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') - self.assertEqual(sanitize_filename(tests), tests) - - forbidden = '"\0\\/' - for fc in forbidden: - for fbc in forbidden: - self.assertTrue(fbc not in sanitize_filename(fc)) - - def test_sanitize_filename_restricted(self): - self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') - self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') - - self.assertEqual(sanitize_filename('123', restricted=True), '123') - - self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) - self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) - - self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) - self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) - 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') - self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') - self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename - - forbidden = '"\0\\/&!: \'\t\n' - for fc in forbidden: - for fbc in forbidden: - 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') - # .. but make sure the file name is never empty - self.assertTrue(sanitize_filename('-', restricted=True) != '') - self.assertTrue(sanitize_filename(':', restricted=True) != '') - - 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]) - self.assertEqual(orderedSet([]), []) - self.assertEqual(orderedSet([1]), [1]) - #keep the list ordered - self.assertEqual(orderedSet([135,1,1,1]), [135,1]) - - def test_unescape_html(self): - self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) + def test_timeconvert(self): + self.assertTrue(timeconvert('') is None) + self.assertTrue(timeconvert('bougrg') is None) + + def test_sanitize_filename(self): + self.assertEqual(sanitize_filename('abc'), 'abc') + self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e') + + self.assertEqual(sanitize_filename('123'), '123') + + self.assertEqual('abc_de', sanitize_filename('abc/de')) + self.assertFalse('/' in sanitize_filename('abc/de///')) + + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de')) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|')) + self.assertEqual('yes no', sanitize_filename('yes? no')) + self.assertEqual('this - that', sanitize_filename('this: that')) + + self.assertEqual(sanitize_filename('AT&T'), 'AT&T') + aumlaut = _compat_str('\xe4') + self.assertEqual(sanitize_filename(aumlaut), aumlaut) + tests = _compat_str('\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430') + self.assertEqual(sanitize_filename(tests), tests) + + forbidden = '"\0\\/' + for fc in forbidden: + for fbc in forbidden: + self.assertTrue(fbc not in sanitize_filename(fc)) + + def test_sanitize_filename_restricted(self): + self.assertEqual(sanitize_filename('abc', restricted=True), 'abc') + self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e') + + self.assertEqual(sanitize_filename('123', restricted=True), '123') + + self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True)) + self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True)) + + self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True)) + self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True)) + 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') + self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') + self.assertTrue(sanitize_filename(_compat_str('\xf6'), restricted=True) != '') # No empty filename + + forbidden = '"\0\\/&!: \'\t\n' + for fc in forbidden: + for fbc in forbidden: + 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') + # .. but make sure the file name is never empty + self.assertTrue(sanitize_filename('-', restricted=True) != '') + self.assertTrue(sanitize_filename(':', restricted=True) != '') + + 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]) + self.assertEqual(orderedSet([]), []) + self.assertEqual(orderedSet([1]), [1]) + #keep the list ordered + self.assertEqual(orderedSet([135,1,1,1]), [135,1]) + + def test_unescape_html(self): + self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) if __name__ == '__main__': - unittest.main() + unittest.main() -- cgit v1.2.3 From 627dcfff398b00429c8b310f1c1775f9be6f0268 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Nov 2012 12:59:27 +0100 Subject: Restrict more characters (Closes #566) --- test/test_utils.py | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index ceefabefc..fd8190f51 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -13,11 +13,12 @@ from youtube_dl.utils import sanitize_filename from youtube_dl.utils import unescapeHTML from youtube_dl.utils import orderedSet -if sys.version_info < (3,0): +if sys.version_info < (3, 0): _compat_str = lambda b: b.decode('unicode-escape') else: _compat_str = lambda s: s + class TestUtil(unittest.TestCase): def test_timeconvert(self): self.assertTrue(timeconvert('') is None) @@ -62,11 +63,11 @@ 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 = _compat_str('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(_compat_str('\xf6'), restricted=True) != '') # No empty filename - forbidden = '"\0\\/&!: \'\t\n' + forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#' for fc in forbidden: for fbc in forbidden: self.assertTrue(fbc not in sanitize_filename(fc, restricted=True)) @@ -79,11 +80,11 @@ class TestUtil(unittest.TestCase): self.assertTrue(sanitize_filename(':', restricted=True) != '') 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]) + self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) self.assertEqual(orderedSet([]), []) self.assertEqual(orderedSet([1]), [1]) #keep the list ordered - self.assertEqual(orderedSet([135,1,1,1]), [135,1]) + self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) def test_unescape_html(self): self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;')) -- cgit v1.2.3 From 796173d08b514182eedc704541eb55d5c9e1dc0d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 3 Dec 2012 15:36:24 +0100 Subject: Keep video IDs verbatim if possible (Closes #571) --- test/test_utils.py | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index fd8190f51..8afc30370 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -79,6 +79,11 @@ class TestUtil(unittest.TestCase): self.assertTrue(sanitize_filename('-', restricted=True) != '') 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') + 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]) self.assertEqual(orderedSet([]), []) -- cgit v1.2.3 From e387eb5aba241e55e38e8bd5b57cc76b082ac6b9 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 4 Dec 2012 10:59:38 +0100 Subject: Let youtube IE handle IDs starting with PL (Closes #572) --- test/test_utils.py | 2 ++ 1 file changed, 2 insertions(+) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index 8afc30370..796ed4ab2 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1,3 +1,5 @@ +#!/usr/bin/env python + # Various small unit tests import sys -- cgit v1.2.3 From 314d506b96d87a212e7e57eaa4d86514579c1c12 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 20 Dec 2012 13:26:37 +0100 Subject: Do not use deprecated method --- test/test_utils.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'test/test_utils.py') diff --git a/test/test_utils.py b/test/test_utils.py index 796ed4ab2..eeaaa7fad 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -82,9 +82,9 @@ 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]) -- cgit v1.2.3