Source Code for Module lxml.tests.test_unicode

  1  # -*- coding: utf-8 -*- 
  2  import unittest, doctest, sys, os.path 
  3   
  4  this_dir = os.path.dirname(__file__) 
  5  if this_dir not in sys.path: 
  6      sys.path.insert(0, this_dir) # needed for Py3 
  7   
  8  from common_imports import StringIO, etree, SillyFileLike, HelperTestCase 
  9  from common_imports import _str, _bytes 
 10   
 11  try: 
 12      unicode 
 13  except NameError: 
 14      unicode = str 
 15   
 16  ascii_uni = _bytes('a').decode('utf8') 
 17   
 18  klingon = _bytes("\\uF8D2").decode("unicode_escape") # not valid for XML names 
 19   
 20  invalid_tag = _bytes("test").decode('utf8') + klingon 
 21   
 22  uni = _bytes('\\xc3\\u0680\\u3120').decode("unicode_escape") # some non-ASCII characters 
 23   
 24  uxml = _bytes("<test><title>test \\xc3\\xa1\\u3120</title><h1>page \\xc3\\xa1\\u3120 title</h1></test>" 
 25                ).decode("unicode_escape") 
 26   
 27 -class UnicodeTestCase(HelperTestCase): 
 28 -    def test_unicode_xml(self): 
 29          tree = etree.XML('<p>%s</p>' % uni) 
 30          self.assertEqual(uni, tree.text) 
 31   
 32 -    def test_wide_unicode_xml(self): 
 33          if sys.maxunicode < 1114111: 
 34              return  # skip test 
 35          tree = etree.XML(_bytes('<p>\\U00026007</p>').decode('unicode_escape')) 
 36          self.assertEqual(1, len(tree.text)) 
 37          self.assertEqual(_bytes('\\U00026007').decode('unicode_escape'), 
 38                           tree.text) 
 39   
 40 -    def test_unicode_xml_broken(self): 
 41          uxml = ('<?xml version="1.0" encoding="UTF-8"?>' + 
 42                  '<p>%s</p>' % uni) 
 43          self.assertRaises(ValueError, etree.XML, uxml) 
 44   
 45 -    def test_unicode_tag(self): 
 46          el = etree.Element(uni) 
 47          self.assertEqual(uni, el.tag) 
 48   
 49 -    def test_unicode_tag_invalid(self): 
 50          # sadly, Klingon is not well-formed 
 51          self.assertRaises(ValueError, etree.Element, invalid_tag) 
 52   
 53 -    def test_unicode_nstag(self): 
 54          tag = "{http://abc/}%s" % uni 
 55          el = etree.Element(tag) 
 56          self.assertEqual(tag, el.tag) 
 57   
 58 -    def test_unicode_ns_invalid(self): 
 59          # namespace URIs must conform to RFC 3986 
 60          tag = "{http://%s/}abc" % uni 
 61          self.assertRaises(ValueError, etree.Element, tag) 
 62   
 63 -    def test_unicode_nstag_invalid(self): 
 64          # sadly, Klingon is not well-formed 
 65          tag = "{http://abc/}%s" % invalid_tag 
 66          self.assertRaises(ValueError, etree.Element, tag) 
 67   
 68 -    def test_unicode_qname(self): 
 69          qname = etree.QName(uni, uni) 
 70          tag = "{%s}%s" % (uni, uni) 
 71          self.assertEqual(qname.text, tag) 
 72          self.assertEqual(unicode(qname), tag) 
 73   
 74 -    def test_unicode_qname_invalid(self): 
 75          self.assertRaises(ValueError, etree.QName, invalid_tag) 
 76   
 77 -    def test_unicode_attr(self): 
 78          el = etree.Element('foo', {'bar': uni}) 
 79          self.assertEqual(uni, el.attrib['bar']) 
 80   
 81 -    def test_unicode_comment(self): 
 82          el = etree.Comment(uni) 
 83          self.assertEqual(uni, el.text) 
 84   
 85 -    def test_unicode_parse_stringio(self): 
 86          el = etree.parse(StringIO('<p>%s</p>' % uni)).getroot() 
 87          self.assertEqual(uni, el.text) 
 88   
 89  ##     def test_parse_fileobject_unicode(self): 
 90  ##         # parse unicode from unamed file object (not support by ElementTree) 
 91  ##         f = SillyFileLike(uxml) 
 92  ##         root = etree.parse(f).getroot() 
 93  ##         self.assertEqual(unicode(etree.tostring(root, 'UTF-8'), 'UTF-8'), 
 94  ##                           uxml) 
 95   
 96 -def test_suite(): 
 97      suite = unittest.TestSuite() 
 98      suite.addTests([unittest.makeSuite(UnicodeTestCase)]) 
 99      return suite 
100