X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=test%2Ftest_utils.py;h=f3fbff042ccc8193d8d08527fdc04421c9832305;hb=4ed3e51080dea651b3db8889b0c8f2e40d261075;hp=ceefabefc83151d8590e1cf355b14d4d3567a0e7;hpb=59ae15a507cbf93de13f8fda8444d2d9a251747a;p=youtube-dl

diff --git a/test/test_utils.py b/test/test_utils.py
index ceefabefc..f3fbff042 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1,23 +1,37 @@
-# Various small unit tests
+#!/usr/bin/env python
+# coding: utf-8
 
+# 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
+# Various small unit tests
+import xml.etree.ElementTree
 
-if sys.version_info < (3,0):
+#from youtube_dl.utils import htmlentity_transform
+from youtube_dl.utils import (
+    timeconvert,
+    sanitize_filename,
+    unescapeHTML,
+    orderedSet,
+    DateRange,
+    unified_strdate,
+    find_xpath_attr,
+    get_meta_content,
+    xpath_with_ns,
+    smuggle_url,
+    unsmuggle_url,
+)
+
+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 +76,11 @@ 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))
@@ -78,15 +92,84 @@ class TestUtil(unittest.TestCase):
         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([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;'))
+        
+    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')
+
+    def test_find_xpath_attr(self):
+        testxml = u'''<root>
+            <node/>
+            <node x="a"/>
+            <node x="a" y="c" />
+            <node x="b" y="d" />
+        </root>'''
+        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'''
+        <head>
+            <meta name="description" content="foo &amp; bar">
+            <meta content='Plato' name='author'/>
+        </head>
+        '''
+        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'''<root xmlns:media="http://example.com/">
+            <media:song>
+                <media:author>The Author</media:author>
+                <url>http://server.com/download.mp3</url>
+            </media:song>
+        </root>'''
+        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)
+
 
 if __name__ == '__main__':
     unittest.main()