From f5ea47488a2c59b2520b4988b7eab4d8830e3077 Mon Sep 17 00:00:00 2001
From: pukkandan
Date: Mon, 11 Jul 2022 01:17:48 +0530
Subject: [cleanup] Minor fixes
---
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 8024a8e7c..948d5d059 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -895,7 +895,7 @@ class TestUtil(unittest.TestCase):
'dynamic_range': 'HDR10',
})
self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), {
- 'vcodec': 'av01.0.12M.10',
+ 'vcodec': 'av01.0.12M.10.0.110.09.16.09.0',
'acodec': 'none',
'dynamic_range': 'HDR10',
})
--
cgit v1.2.3
From a904a7f8c6edc42046f0a78fb279739d500d4887 Mon Sep 17 00:00:00 2001
From: Lesmiscore
Date: Fri, 15 Jul 2022 20:52:14 +0900
Subject: Allow users to specify encoding in each config files (#4357)
Authored by: Lesmiscore
---
test/test_utils.py | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 948d5d059..c668ff9e4 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -39,6 +39,7 @@ from yt_dlp.utils import (
datetime_from_str,
detect_exe_version,
determine_ext,
+ determine_file_encoding,
dfxp2srt,
dict_get,
encode_base_n,
@@ -1822,6 +1823,33 @@ Line 1
with contextlib.suppress(OSError):
os.remove(FILE)
+ def test_determine_file_encoding(self):
+ self.assertEqual(determine_file_encoding(b''), (None, 0))
+ self.assertEqual(determine_file_encoding(b'--verbose -x --audio-format mkv\n'), (None, 0))
+
+ self.assertEqual(determine_file_encoding(b'\xef\xbb\xbf'), ('utf-8', 3))
+ self.assertEqual(determine_file_encoding(b'\x00\x00\xfe\xff'), ('utf-32-be', 4))
+ self.assertEqual(determine_file_encoding(b'\xff\xfe'), ('utf-16-le', 2))
+
+ self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-'), ('cp932', 0))
+ self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-\n'), ('cp932', 0))
+ self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-\r\n'), ('cp932', 0))
+
+ self.assertEqual(determine_file_encoding(b'# coding: utf-8\n--verbose'), ('utf-8', 0))
+ self.assertEqual(determine_file_encoding(b'# coding: someencodinghere-12345\n--verbose'), ('someencodinghere-12345', 0))
+
+ self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932'), ('cp932', 0))
+ self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932\n'), ('cp932', 0))
+ self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932\r\n'), ('cp932', 0))
+ self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932,euc-jp\r\n'), ('cp932', 0))
+
+ self.assertEqual(determine_file_encoding(
+ b'\0\0\0#\0\0\0 \0\0\0c\0\0\0o\0\0\0d\0\0\0i\0\0\0n\0\0\0g\0\0\0:\0\0\0 \0\0\0u\0\0\0t\0\0\0f\0\0\0-\0\0\x003\0\0\x002\0\0\0-\0\0\0b\0\0\0e'),
+ ('utf-32-be', 0))
+ self.assertEqual(determine_file_encoding(
+ b'#\0 \0c\0o\0d\0i\0n\0g\0:\0 \0u\0t\0f\0-\x001\x006\0-\0l\0e\0'),
+ ('utf-16-le', 0))
+
if __name__ == '__main__':
unittest.main()
--
cgit v1.2.3
From 88f60feb32614c723f997b2cba20c8c10fbe9bd3 Mon Sep 17 00:00:00 2001
From: pukkandan
Date: Fri, 15 Jul 2022 21:44:07 +0530
Subject: Fix a904a7f8c6edc42046f0a78fb279739d500d4887
---
test/test_utils.py | 20 ++++++--------------
1 file changed, 6 insertions(+), 14 deletions(-)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index c668ff9e4..bf46bdc61 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1831,24 +1831,16 @@ Line 1
self.assertEqual(determine_file_encoding(b'\x00\x00\xfe\xff'), ('utf-32-be', 4))
self.assertEqual(determine_file_encoding(b'\xff\xfe'), ('utf-16-le', 2))
- self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-'), ('cp932', 0))
- self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-\n'), ('cp932', 0))
- self.assertEqual(determine_file_encoding(b'# -*- coding: cp932 -*-\r\n'), ('cp932', 0))
+ self.assertEqual(determine_file_encoding(b'\xff\xfe# coding: utf-8\n--verbose'), ('utf-16-le', 2))
self.assertEqual(determine_file_encoding(b'# coding: utf-8\n--verbose'), ('utf-8', 0))
self.assertEqual(determine_file_encoding(b'# coding: someencodinghere-12345\n--verbose'), ('someencodinghere-12345', 0))
- self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932'), ('cp932', 0))
- self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932\n'), ('cp932', 0))
- self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932\r\n'), ('cp932', 0))
- self.assertEqual(determine_file_encoding(b'# vi: set fileencoding=cp932,euc-jp\r\n'), ('cp932', 0))
-
- self.assertEqual(determine_file_encoding(
- b'\0\0\0#\0\0\0 \0\0\0c\0\0\0o\0\0\0d\0\0\0i\0\0\0n\0\0\0g\0\0\0:\0\0\0 \0\0\0u\0\0\0t\0\0\0f\0\0\0-\0\0\x003\0\0\x002\0\0\0-\0\0\0b\0\0\0e'),
- ('utf-32-be', 0))
- self.assertEqual(determine_file_encoding(
- b'#\0 \0c\0o\0d\0i\0n\0g\0:\0 \0u\0t\0f\0-\x001\x006\0-\0l\0e\0'),
- ('utf-16-le', 0))
+ self.assertEqual(determine_file_encoding(b'#coding:utf-8\n--verbose'), ('utf-8', 0))
+ self.assertEqual(determine_file_encoding(b'# coding: utf-8 \r\n--verbose'), ('utf-8', 0))
+
+ self.assertEqual(determine_file_encoding('# coding: utf-32-be'.encode('utf-32-be')), ('utf-32-be', 0))
+ self.assertEqual(determine_file_encoding('# coding: utf-16-le'.encode('utf-16-le')), ('utf-16-le', 0))
if __name__ == '__main__':
--
cgit v1.2.3
From 47304e07dc4a044242f7d5a14c3f6c3e5f3ad8ba Mon Sep 17 00:00:00 2001
From: nixxo
Date: Mon, 1 Aug 2022 21:25:48 +0200
Subject: [extractor/rai] Add raisudtirol extractor (#4524)
Closes #4206
Authored by: nixxo
---
test/test_utils.py | 1 +
1 file changed, 1 insertion(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index bf46bdc61..8ec1413b8 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -368,6 +368,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
self.assertEqual(unified_strdate('1968 12 10'), '19681210')
self.assertEqual(unified_strdate('1968-12-10'), '19681210')
+ self.assertEqual(unified_strdate('31-07-2022 20:00'), '20220731')
self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
self.assertEqual(
unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
--
cgit v1.2.3
From fc61aff41beae0063b306dd9d74cc4ff27f0eff7 Mon Sep 17 00:00:00 2001
From: "Lauren N. Liberda"
Date: Thu, 4 Aug 2022 02:42:12 +0200
Subject: Determine merge container better (See desc) (#1482)
* Determine the container early. Closes #4069
* Use codecs instead of just file extensions
* Obey `--prefer-free-formats`
* Allow fallbacks in `--merge-output`
Authored by: pukkandan, selfisekai
---
test/test_utils.py | 26 ++++++++++++++++++++++++++
1 file changed, 26 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 8ec1413b8..989a99ea3 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -53,6 +53,7 @@ from yt_dlp.utils import (
fix_xml_ampersands,
float_or_none,
format_bytes,
+ get_compatible_ext,
get_element_by_attribute,
get_element_by_class,
get_element_html_by_attribute,
@@ -1843,6 +1844,31 @@ Line 1
self.assertEqual(determine_file_encoding('# coding: utf-32-be'.encode('utf-32-be')), ('utf-32-be', 0))
self.assertEqual(determine_file_encoding('# coding: utf-16-le'.encode('utf-16-le')), ('utf-16-le', 0))
+ def test_get_compatible_ext(self):
+ self.assertEqual(get_compatible_ext(
+ vcodecs=[None], acodecs=[None, None], vexts=['mp4'], aexts=['m4a', 'm4a']), 'mkv')
+ self.assertEqual(get_compatible_ext(
+ vcodecs=[None], acodecs=[None], vexts=['flv'], aexts=['flv']), 'flv')
+
+ self.assertEqual(get_compatible_ext(
+ vcodecs=[None], acodecs=[None], vexts=['mp4'], aexts=['m4a']), 'mp4')
+ self.assertEqual(get_compatible_ext(
+ vcodecs=[None], acodecs=[None], vexts=['mp4'], aexts=['webm']), 'mkv')
+ self.assertEqual(get_compatible_ext(
+ vcodecs=[None], acodecs=[None], vexts=['webm'], aexts=['m4a']), 'mkv')
+ self.assertEqual(get_compatible_ext(
+ vcodecs=[None], acodecs=[None], vexts=['webm'], aexts=['webm']), 'webm')
+
+ self.assertEqual(get_compatible_ext(
+ vcodecs=['h264'], acodecs=['mp4a'], vexts=['mov'], aexts=['m4a']), 'mp4')
+ self.assertEqual(get_compatible_ext(
+ vcodecs=['av01.0.12M.08'], acodecs=['opus'], vexts=['mp4'], aexts=['webm']), 'webm')
+
+ self.assertEqual(get_compatible_ext(
+ vcodecs=['vp9'], acodecs=['opus'], vexts=['webm'], aexts=['webm'], preferences=['flv', 'mp4']), 'mp4')
+ self.assertEqual(get_compatible_ext(
+ vcodecs=['av1'], acodecs=['mp4a'], vexts=['webm'], aexts=['m4a'], preferences=('webm', 'mkv')), 'mkv')
+
if __name__ == '__main__':
unittest.main()
--
cgit v1.2.3
From 97d9c79e926197dcf277635d2582f882df4290ac Mon Sep 17 00:00:00 2001
From: pukkandan
Date: Thu, 4 Aug 2022 23:47:55 +0530
Subject: Fix tests for 989a01c2610832193c268d072ada8814bfd4c00d
---
test/test_utils.py | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 989a99ea3..659b071d3 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -140,13 +140,13 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_filename('123'), '123')
- self.assertEqual('abc_de', sanitize_filename('abc/de'))
+ 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('abc_de', sanitize_filename('abc/<>\\*|de', is_id=False))
+ self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', is_id=False))
+ self.assertEqual('yes no', sanitize_filename('yes? no', is_id=False))
+ self.assertEqual('this - that', sanitize_filename('this: that', is_id=False))
self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
aumlaut = 'ä'
--
cgit v1.2.3
From 8f53dc44a0cc1c2d98c35740b9293462c080f5d0 Mon Sep 17 00:00:00 2001
From: pukkandan
Date: Sun, 14 Aug 2022 04:51:54 +0530
Subject: [jsinterp] Handle new youtube signature functions
Closes #4635
---
test/test_utils.py | 4 ++++
1 file changed, 4 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 659b071d3..67cd966d8 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -413,6 +413,10 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
+ self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
+ self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
+ self.assertEqual(unified_timestamp('12/31/1969 20:01:18 EDT', False), 78)
+
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
--
cgit v1.2.3
From 7657ec7ed6318dd66dd72cc100ba7bc5b911366e Mon Sep 17 00:00:00 2001
From: Elyse <26639800+elyse0@users.noreply.github.com>
Date: Sat, 3 Sep 2022 22:09:45 -0500
Subject: [utils] `base_url`: URL paths can contain `&` (#4841)
Authored by: elyse0
Closes #4187
---
test/test_utils.py | 1 +
1 file changed, 1 insertion(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 67cd966d8..96477c53f 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -566,6 +566,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
+ self.assertEqual(base_url('http://foo.de/bar/baz&x=z&w=y/x/c'), 'http://foo.de/bar/baz&x=z&w=y/x/')
def test_urljoin(self):
self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
--
cgit v1.2.3
From ab029d7e9200a273d7204be68c0735b16971ff44 Mon Sep 17 00:00:00 2001
From: Simon Sawicki <37424085+Grub4K@users.noreply.github.com>
Date: Sun, 25 Sep 2022 23:03:19 +0200
Subject: [utils] `traverse_obj`: Rewrite, document and add tests (#5024)
Authored by: Grub4K
---
test/test_utils.py | 187 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 187 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 96477c53f..69313564a 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -109,6 +109,7 @@ from yt_dlp.utils import (
strip_or_none,
subtitles_filename,
timeconvert,
+ traverse_obj,
unescapeHTML,
unified_strdate,
unified_timestamp,
@@ -1874,6 +1875,192 @@ Line 1
self.assertEqual(get_compatible_ext(
vcodecs=['av1'], acodecs=['mp4a'], vexts=['webm'], aexts=['m4a'], preferences=('webm', 'mkv')), 'mkv')
+ def test_traverse_obj(self):
+ _TEST_DATA = {
+ 100: 100,
+ 1.2: 1.2,
+ 'str': 'str',
+ 'None': None,
+ '...': ...,
+ 'urls': [
+ {'index': 0, 'url': 'https://www.example.com/0'},
+ {'index': 1, 'url': 'https://www.example.com/1'},
+ ],
+ 'data': (
+ {'index': 2},
+ {'index': 3},
+ ),
+ }
+
+ # Test base functionality
+ self.assertEqual(traverse_obj(_TEST_DATA, ('str',)), 'str',
+ msg='allow tuple path')
+ self.assertEqual(traverse_obj(_TEST_DATA, ['str']), 'str',
+ msg='allow list path')
+ self.assertEqual(traverse_obj(_TEST_DATA, (value for value in ("str",))), 'str',
+ msg='allow iterable path')
+ self.assertEqual(traverse_obj(_TEST_DATA, 'str'), 'str',
+ msg='single items should be treated as a path')
+ self.assertEqual(traverse_obj(_TEST_DATA, None), _TEST_DATA)
+ self.assertEqual(traverse_obj(_TEST_DATA, 100), 100)
+ self.assertEqual(traverse_obj(_TEST_DATA, 1.2), 1.2)
+
+ # Test Ellipsis behavior
+ self.assertCountEqual(traverse_obj(_TEST_DATA, ...),
+ (item for item in _TEST_DATA.values() if item is not None),
+ msg='`...` should give all values except `None`')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, ('urls', 0, ...)), _TEST_DATA['urls'][0].values(),
+ msg='`...` selection for dicts should select all values')
+ self.assertEqual(traverse_obj(_TEST_DATA, (..., ..., 'url')),
+ ['https://www.example.com/0', 'https://www.example.com/1'],
+ msg='nested `...` queries should work')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, (..., ..., 'index')), range(4),
+ msg='`...` query result should be flattened')
+
+ # Test function as key
+ self.assertEqual(traverse_obj(_TEST_DATA, lambda x, y: x == 'urls' and isinstance(y, list)),
+ [_TEST_DATA['urls']],
+ msg='function as query key should perform a filter based on (key, value)')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, lambda _, x: isinstance(x[0], str)), {'str'},
+ msg='exceptions in the query function should be catched')
+
+ # Test alternative paths
+ self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'str'), 'str',
+ msg='multiple `path_list` should be treated as alternative paths')
+ self.assertEqual(traverse_obj(_TEST_DATA, 'str', 100), 'str',
+ msg='alternatives should exit early')
+ self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'fail'), None,
+ msg='alternatives should return `default` if exhausted')
+
+ # Test branch and path nesting
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', (3, 0), 'url')), ['https://www.example.com/0'],
+ msg='tuple as key should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', [3, 0], 'url')), ['https://www.example.com/0'],
+ msg='list as key should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', ((1, 'fail'), (0, 'url')))), ['https://www.example.com/0'],
+ msg='double nesting in path should be treated as paths')
+ self.assertEqual(traverse_obj(['0', [1, 2]], [(0, 1), 0]), [1],
+ msg='do not fail early on branching')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, ('urls', ((1, ('fail', 'url')), (0, 'url')))),
+ ['https://www.example.com/0', 'https://www.example.com/1'],
+ msg='tripple nesting in path should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', ('fail', (..., 'url')))),
+ ['https://www.example.com/0', 'https://www.example.com/1'],
+ msg='ellipsis as branch path start gets flattened')
+
+ # Test dictionary as key
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 100, 1: 1.2}), {0: 100, 1: 1.2},
+ msg='dict key should result in a dict with the same keys')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', 0, 'url')}),
+ {0: 'https://www.example.com/0'},
+ msg='dict key should allow paths')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', (3, 0), 'url')}),
+ {0: ['https://www.example.com/0']},
+ msg='tuple in dict path should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, 'fail'), (0, 'url')))}),
+ {0: ['https://www.example.com/0']},
+ msg='double nesting in dict path should be treated as paths')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, ('fail', 'url')), (0, 'url')))}),
+ {0: ['https://www.example.com/1', 'https://www.example.com/0']},
+ msg='tripple nesting in dict path should be treated as branches')
+ self.assertEqual(traverse_obj({}, {0: 1}, default=...), {0: ...},
+ msg='do not remove `None` values when dict key')
+
+ # Testing default parameter behavior
+ _DEFAULT_DATA = {'None': None, 'int': 0, 'list': []}
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail'), None,
+ msg='default value should be `None`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail', 'fail', default=...), ...,
+ msg='chained fails should result in default')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'None', 'int'), 0,
+ msg='should not short cirquit on `None`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail', default=1), 1,
+ msg='invalid dict key should result in `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'None', default=1), 1,
+ msg='`None` is a deliberate sentinel and should become `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', 10)), None,
+ msg='`IndexError` should result in `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, (..., 'fail'), default=1), 1,
+ msg='if branched but not successfull return `default`, not `[]`')
+
+ # Testing expected_type behavior
+ _EXPECTED_TYPE_DATA = {'str': 'str', 'int': 0}
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=str), 'str',
+ msg='accept matching `expected_type` type')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=int), None,
+ msg='reject non matching `expected_type` type')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'int', expected_type=lambda x: str(x)), '0',
+ msg='transform type using type function')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str',
+ expected_type=lambda _: 1 / 0), None,
+ msg='wrap expected_type fuction in try_call')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, ..., expected_type=str), ['str'],
+ msg='eliminate items that expected_type fails on')
+
+ # Test get_all behavior
+ _GET_ALL_DATA = {'key': [0, 1, 2]}
+ self.assertEqual(traverse_obj(_GET_ALL_DATA, ('key', ...), get_all=False), 0,
+ msg='if not `get_all`, return only first matching value')
+ self.assertEqual(traverse_obj(_GET_ALL_DATA, ..., get_all=False), [0, 1, 2],
+ msg='do not overflatten if not `get_all`')
+
+ # Test casesense behavior
+ _CASESENSE_DATA = {
+ 'KeY': 'value0',
+ 0: {
+ 'KeY': 'value1',
+ 0: {'KeY': 'value2'},
+ },
+ }
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, 'key'), None,
+ msg='dict keys should be case sensitive unless `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, 'keY',
+ casesense=False), 'value0',
+ msg='allow non matching key case if `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, (0, ('keY',)),
+ casesense=False), ['value1'],
+ msg='allow non matching key case in branch if `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, (0, ((0, 'keY'),)),
+ casesense=False), ['value2'],
+ msg='allow non matching key case in branch path if `casesense`')
+
+ # Test traverse_string behavior
+ _TRAVERSE_STRING_DATA = {'str': 'str', 1.2: 1.2}
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', 0)), None,
+ msg='do not traverse into string if not `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', 0),
+ traverse_string=True), 's',
+ msg='traverse into string if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, (1.2, 1),
+ traverse_string=True), '.',
+ msg='traverse into converted data if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', ...),
+ traverse_string=True), list('str'),
+ msg='`...` branching into string should result in list')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', (0, 2)),
+ traverse_string=True), ['s', 'r'],
+ msg='branching into string should result in list')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', lambda _, x: x),
+ traverse_string=True), list('str'),
+ msg='function branching into string should result in list')
+
+ # Test is_user_input behavior
+ _IS_USER_INPUT_DATA = {'range8': list(range(8))}
+ self.assertEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', '3'),
+ is_user_input=True), 3,
+ msg='allow for string indexing if `is_user_input`')
+ self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', '3:'),
+ is_user_input=True), tuple(range(8))[3:],
+ msg='allow for string slice if `is_user_input`')
+ self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':4:2'),
+ is_user_input=True), tuple(range(8))[:4:2],
+ msg='allow step in string slice if `is_user_input`')
+ self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':'),
+ is_user_input=True), range(8),
+ msg='`:` should be treated as `...` if `is_user_input`')
+ with self.assertRaises(TypeError, msg='too many params should result in error'):
+ traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':::'), is_user_input=True)
+
if __name__ == '__main__':
unittest.main()
--
cgit v1.2.3
From f99bbfc9838d98d81027dddb18ace0af66acdf6d Mon Sep 17 00:00:00 2001
From: Simon Sawicki <37424085+Grub4K@users.noreply.github.com>
Date: Sun, 9 Oct 2022 03:27:32 +0200
Subject: [utils] `traverse_obj`: Always return list when branching (#5170)
Fixes #5162
Authored by: Grub4K
---
test/test_utils.py | 27 +++++++++++++++++++++++----
1 file changed, 23 insertions(+), 4 deletions(-)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 69313564a..6f3f6cb91 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1890,6 +1890,7 @@ Line 1
{'index': 2},
{'index': 3},
),
+ 'dict': {},
}
# Test base functionality
@@ -1926,11 +1927,15 @@ Line 1
# Test alternative paths
self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'str'), 'str',
- msg='multiple `path_list` should be treated as alternative paths')
+ msg='multiple `paths` should be treated as alternative paths')
self.assertEqual(traverse_obj(_TEST_DATA, 'str', 100), 'str',
msg='alternatives should exit early')
self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'fail'), None,
msg='alternatives should return `default` if exhausted')
+ self.assertEqual(traverse_obj(_TEST_DATA, (..., 'fail'), 100), 100,
+ msg='alternatives should track their own branching return')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('dict', ...), ('data', ...)), list(_TEST_DATA['data']),
+ msg='alternatives on empty objects should search further')
# Test branch and path nesting
self.assertEqual(traverse_obj(_TEST_DATA, ('urls', (3, 0), 'url')), ['https://www.example.com/0'],
@@ -1963,8 +1968,16 @@ Line 1
self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, ('fail', 'url')), (0, 'url')))}),
{0: ['https://www.example.com/1', 'https://www.example.com/0']},
msg='tripple nesting in dict path should be treated as branches')
- self.assertEqual(traverse_obj({}, {0: 1}, default=...), {0: ...},
- msg='do not remove `None` values when dict key')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'fail'}), {},
+ msg='remove `None` values when dict key')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'fail'}, default=...), {0: ...},
+ msg='do not remove `None` values if `default`')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'dict'}), {0: {}},
+ msg='do not remove empty values when dict key')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'dict'}, default=...), {0: {}},
+ msg='do not remove empty values when dict key and a default')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('dict', ...)}), {0: []},
+ msg='if branch in dict key not successful, return `[]`')
# Testing default parameter behavior
_DEFAULT_DATA = {'None': None, 'int': 0, 'list': []}
@@ -1981,7 +1994,13 @@ Line 1
self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', 10)), None,
msg='`IndexError` should result in `default`')
self.assertEqual(traverse_obj(_DEFAULT_DATA, (..., 'fail'), default=1), 1,
- msg='if branched but not successfull return `default`, not `[]`')
+ msg='if branched but not successful return `default` if defined, not `[]`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, (..., 'fail'), default=None), None,
+ msg='if branched but not successful return `default` even if `default` is `None`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, (..., 'fail')), [],
+ msg='if branched but not successful return `[]`, not `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', ...)), [],
+ msg='if branched but object is empty return `[]`, not `default`')
# Testing expected_type behavior
_EXPECTED_TYPE_DATA = {'str': 'str', 'int': 0}
--
cgit v1.2.3
From 7b0127e1e11186bcbb80a18b1b530d864a5dbada Mon Sep 17 00:00:00 2001
From: Simon Sawicki <37424085+Grub4K@users.noreply.github.com>
Date: Sun, 9 Oct 2022 03:31:37 +0200
Subject: [utils] `traverse_obj`: Allow `re.Match` objects (#5174)
Authored by: Grub4K
---
test/test_utils.py | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 6f3f6cb91..90085a9c0 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -2,6 +2,7 @@
# Allow direct execution
import os
+import re
import sys
import unittest
@@ -2080,6 +2081,25 @@ Line 1
with self.assertRaises(TypeError, msg='too many params should result in error'):
traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':::'), is_user_input=True)
+ # Test re.Match as input obj
+ mobj = re.fullmatch(r'0(12)(?P3)(4)?', '0123')
+ self.assertEqual(traverse_obj(mobj, ...), [x for x in mobj.groups() if x is not None],
+ msg='`...` on a `re.Match` should give its `groups()`')
+ self.assertEqual(traverse_obj(mobj, lambda k, _: k in (0, 2)), ['0123', '3'],
+ msg='function on a `re.Match` should give groupno, value starting at 0')
+ self.assertEqual(traverse_obj(mobj, 'group'), '3',
+ msg='str key on a `re.Match` should give group with that name')
+ self.assertEqual(traverse_obj(mobj, 2), '3',
+ msg='int key on a `re.Match` should give group with that name')
+ self.assertEqual(traverse_obj(mobj, 'gRoUp', casesense=False), '3',
+ msg='str key on a `re.Match` should respect casesense')
+ self.assertEqual(traverse_obj(mobj, 'fail'), None,
+ msg='failing str key on a `re.Match` should return `default`')
+ self.assertEqual(traverse_obj(mobj, 'gRoUpS', casesense=False), None,
+ msg='failing str key on a `re.Match` should return `default`')
+ self.assertEqual(traverse_obj(mobj, 8), None,
+ msg='failing int key on a `re.Match` should return `default`')
+
if __name__ == '__main__':
unittest.main()
--
cgit v1.2.3
From 4c9a1a3ba56c2906f9ef8d768de7f8e5a2361144 Mon Sep 17 00:00:00 2001
From: Matthew
Date: Sun, 9 Oct 2022 18:55:26 +1300
Subject: [extractor/wordpress:mb.miniAudioPlayer] Add embed extractor (#5087)
Closes https://github.com/yt-dlp/yt-dlp/issues/4994
Authored by: coletdjnz
---
test/test_utils.py | 3 +++
1 file changed, 3 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index 90085a9c0..df23f1f47 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1679,6 +1679,9 @@ Line 1
self.assertEqual(list(get_elements_text_and_html_by_attribute('class', 'foo', html)), [])
self.assertEqual(list(get_elements_text_and_html_by_attribute('class', 'no-such-foo', html)), [])
+ self.assertEqual(list(get_elements_text_and_html_by_attribute(
+ 'class', 'foo', 'nicenice', tag='a')), [('nice', 'nice')])
+
GET_ELEMENT_BY_TAG_TEST_STRING = '''
random text lorem ipsum
--
cgit v1.2.3
From a71b812f53a5f678e4c9467858e721dcd4953a16 Mon Sep 17 00:00:00 2001
From: Simon Sawicki <37424085+Grub4K@users.noreply.github.com>
Date: Wed, 12 Oct 2022 22:22:17 +0200
Subject: [utils] `js_to_json`: Improve escape handling (#5217)
Authored by: Grub4K
---
test/test_utils.py | 6 ++++++
1 file changed, 6 insertions(+)
(limited to 'test/test_utils.py')
diff --git a/test/test_utils.py b/test/test_utils.py
index df23f1f47..49ab3796b 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1100,6 +1100,12 @@ class TestUtil(unittest.TestCase):
on = js_to_json('[1,//{},\n2]')
self.assertEqual(json.loads(on), [1, 2])
+ on = js_to_json(R'"\^\$\#"')
+ self.assertEqual(json.loads(on), R'^$#', msg='Unnecessary escapes should be stripped')
+
+ on = js_to_json('\'"\\""\'')
+ self.assertEqual(json.loads(on), '"""', msg='Unnecessary quote escape should be escaped')
+
def test_js_to_json_malformed(self):
self.assertEqual(js_to_json('42a1'), '42"a1"')
self.assertEqual(js_to_json('42a-1'), '42"a"-1')
--
cgit v1.2.3