Source Code for Module lxml.tests.test_unicode

  1  # -*- coding: utf-8 -*- 
  2  import unittest 
  3  import sys 
  4  import os.path 
  5   
  6  this_dir = os.path.dirname(__file__) 
  7  if this_dir not in sys.path: 
  8      sys.path.insert(0, this_dir)  # needed for Py3 
  9   
 10  from common_imports import StringIO, etree, SillyFileLike, HelperTestCase 
 11  from common_imports import _str, _bytes 
 12   
 13  try: 
 14      unicode 
 15  except NameError: 
 16      unicode = str 
 17   
 18  ascii_uni = _bytes('a').decode('utf8') 
 19   
 20  klingon = _bytes("\\uF8D2").decode("unicode_escape") # not valid for XML names 
 21   
 22  invalid_tag = _bytes("test").decode('utf8') + klingon 
 23   
 24  uni = _bytes('\\xc3\\u0680\\u3120').decode("unicode_escape") # some non-ASCII characters 
 25   
 26  uxml = _bytes("<test><title>test \\xc3\\xa1\\u3120</title><h1>page \\xc3\\xa1\\u3120 title</h1></test>" 
 27                ).decode("unicode_escape") 
 28   
 29   
 30 -class UnicodeTestCase(HelperTestCase): 
 31 -    def test_unicode_xml(self): 
 32          tree = etree.XML('<p>%s</p>' % uni) 
 33          self.assertEqual(uni, tree.text) 
 34   
 35 -    def test_wide_unicode_xml(self): 
 36          if sys.maxunicode < 1114111: 
 37              return  # skip test 
 38          tree = etree.XML(_bytes('<p>\\U00026007</p>').decode('unicode_escape')) 
 39          self.assertEqual(1, len(tree.text)) 
 40          self.assertEqual(_bytes('\\U00026007').decode('unicode_escape'), 
 41                           tree.text) 
 42   
 43 -    def test_unicode_xml_broken(self): 
 44          uxml = ('<?xml version="1.0" encoding="UTF-8"?>' + 
 45                  '<p>%s</p>' % uni) 
 46          self.assertRaises(ValueError, etree.XML, uxml) 
 47   
 48 -    def test_unicode_tag(self): 
 49          el = etree.Element(uni) 
 50          self.assertEqual(uni, el.tag) 
 51   
 52 -    def test_unicode_tag_invalid(self): 
 53          # sadly, Klingon is not well-formed 
 54          self.assertRaises(ValueError, etree.Element, invalid_tag) 
 55   
 56 -    def test_unicode_nstag(self): 
 57          tag = "{http://abc/}%s" % uni 
 58          el = etree.Element(tag) 
 59          self.assertEqual(tag, el.tag) 
 60   
 61 -    def test_unicode_ns_invalid(self): 
 62          # namespace URIs must conform to RFC 3986 
 63          tag = "{http://%s/}abc" % uni 
 64          self.assertRaises(ValueError, etree.Element, tag) 
 65   
 66 -    def test_unicode_nstag_invalid(self): 
 67          # sadly, Klingon is not well-formed 
 68          tag = "{http://abc/}%s" % invalid_tag 
 69          self.assertRaises(ValueError, etree.Element, tag) 
 70   
 71 -    def test_unicode_qname(self): 
 72          qname = etree.QName(uni, uni) 
 73          tag = "{%s}%s" % (uni, uni) 
 74          self.assertEqual(qname.text, tag) 
 75          self.assertEqual(unicode(qname), tag) 
 76   
 77 -    def test_unicode_qname_invalid(self): 
 78          self.assertRaises(ValueError, etree.QName, invalid_tag) 
 79   
 80 -    def test_unicode_attr(self): 
 81          el = etree.Element('foo', {'bar': uni}) 
 82          self.assertEqual(uni, el.attrib['bar']) 
 83   
 84 -    def test_unicode_comment(self): 
 85          el = etree.Comment(uni) 
 86          self.assertEqual(uni, el.text) 
 87   
 88 -    def test_unicode_parse_stringio(self): 
 89          el = etree.parse(StringIO('<p>%s</p>' % uni)).getroot() 
 90          self.assertEqual(uni, el.text) 
 91   
 92  ##     def test_parse_fileobject_unicode(self): 
 93  ##         # parse unicode from unamed file object (not support by ElementTree) 
 94  ##         f = SillyFileLike(uxml) 
 95  ##         root = etree.parse(f).getroot() 
 96  ##         self.assertEqual(unicode(etree.tostring(root, 'UTF-8'), 'UTF-8'), 
 97  ##                           uxml) 
 98   
 99   
100 -class EncodingsTestCase(HelperTestCase): 
101 -    def test_illegal_utf8(self): 
102          data = _bytes('<test>\x80\x80\x80</test>', encoding='iso8859-1') 
103          self.assertRaises(etree.XMLSyntaxError, etree.fromstring, data) 
104   
105 -    def test_illegal_utf8_recover(self): 
106          data = _bytes('<test>\x80\x80\x80</test>', encoding='iso8859-1') 
107          parser = etree.XMLParser(recover=True) 
108          self.assertRaises(etree.XMLSyntaxError, etree.fromstring, data, parser) 
109   
110   
111 -def test_suite(): 
112      suite = unittest.TestSuite() 
113      suite.addTests([unittest.makeSuite(UnicodeTestCase)]) 
114      suite.addTests([unittest.makeSuite(EncodingsTestCase)]) 
115      return suite 
116