X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=test%2Ftest_utils.py;h=8d89979775c75db9f54c041716f5bfc92a77150a;hb=cc7fec5818254f4679896823c7de9d17f50201ca;hp=fd8190f510d5ae69c83ba7cb188810077ab162e0;hpb=3cd69a54b20b690d570e7c7ae5a9bba26f30b897;p=youtube-dl
diff --git a/test/test_utils.py b/test/test_utils.py
index fd8190f51..8d8997977 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1,22 +1,46 @@
-# Various small unit tests
+#!/usr/bin/env python
+# coding: utf-8
-import sys
-import unittest
+from __future__ import unicode_literals
# Allow direct execution
import os
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import sys
+import unittest
+sys.path.insert(0, 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
+# 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,
+ 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,
+)
class TestUtil(unittest.TestCase):
@@ -39,9 +63,9 @@ 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\\/'
@@ -63,9 +87,9 @@ 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:
@@ -73,12 +97,17 @@ 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) != '')
+ def test_sanitize_ids(self):
+ 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])
self.assertEqual(orderedSet([]), [])
@@ -87,7 +116,175 @@ 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")
+ 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 = '''