def test_constructor(self):
e = structures.XMLEntity(b"<hello>")
self.assertTrue(e.line_num == 1)
self.assertTrue(e.line_pos == 1)
self.assertTrue(is_unicode(e.the_char) and e.the_char == '<')
e = structures.XMLEntity(ul("<hello>"))
self.assertTrue(is_unicode(e.the_char) and e.the_char == '<')
e = structures.XMLEntity(StringIO(ul("<hello>")))
self.assertTrue(e.line_num == 1)
self.assertTrue(e.line_pos == 1)
self.assertTrue(is_unicode(e.the_char) and e.the_char == '<')
def test_chars(self):
e = structures.XMLEntity(b"<hello>")
for c in "<hello>":
self.assertTrue(e.the_char == c)
e.next_char()
self.assertTrue(e.the_char is None)
e.reset()
self.assertTrue(e.the_char == '<')
def test_codecs(self):
m = ul('Caf\xe9')
e = structures.XMLEntity(b'Caf\xc3\xa9')
self.assertTrue(e.bom is False, 'defaulted utf-8 BOM detection')
for c in m:
self.assertTrue(
e.the_char == c, "Print: parsing utf-8 got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
e = structures.XMLEntity(b'Caf\xe9', 'latin_1')
self.assertTrue(e.bom is False, 'latin_1 BOM detection')
for c in m:
self.assertTrue(
e.the_char == c,
"Print: parsing latin-1 got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
# This string should be automatically detected
e = structures.XMLEntity(b'\xff\xfeC\x00a\x00f\x00\xe9\x00')
self.assertTrue(e.bom is True, 'utf-16-le BOM detection')
for c in m:
self.assertTrue(
e.the_char == c,
"Print: parsing utf-16LE got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
e = structures.XMLEntity(b'\xfe\xff\x00C\x00a\x00f\x00\xe9')
self.assertTrue(e.bom is True, 'utf-16-be BOM detection')
for c in m:
self.assertTrue(
e.the_char == c,
"Print: parsing utf-16BE got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
e = structures.XMLEntity(b'\xef\xbb\xbfCaf\xc3\xa9', 'utf-8')
self.assertTrue(e.bom is False, 'utf-8 BOM detection')
for c in m:
self.assertTrue(
e.the_char == c,
"Print: parsing utf-8 with BOM got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
e = structures.XMLEntity(b'Caf\xe9')
for c in 'Ca':
e.next_char()
e.change_encoding('ISO-8859-1')
self.assertTrue(e.the_char == 'f', "Bad encoding change")
e.next_char()
self.assertTrue(
e.the_char == character(0xE9),
"Print: change encoding got %s instead of %s" %
(repr(e.the_char), repr(character(0xE9))))
e = structures.XMLEntity(b'C\x00a\x00f\x00\xe9\x00', 'utf-16-le')
self.assertTrue(e.bom is False, 'utf-16-le no BOM detection error')
for c in m:
self.assertTrue(
e.the_char == c,
"Print: parsing utf-16LE no BOM got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
# add <? to trigger auto-detection
e = structures.XMLEntity(b'\x00<\x00?\x00C\x00a\x00f\x00\xe9')
self.assertTrue(e.bom is False, 'utf-16-be no BOM detection error')
for c in ul("<?") + m:
self.assertTrue(
e.the_char == c,
"Print: parsing utf-16BE no BOM got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
e = structures.XMLEntity(b'\xfe\xff\xfe\xff\x00C\x00a\x00f\x00\xe9')
for c in character(0xfeff) + m:
self.assertTrue(
e.the_char == c,
"Print: parsing double BOM got %s instead of %s" %
(repr(e.the_char), repr(c)))
e.next_char()
def test_lines(self):
e = structures.XMLEntity(b"Hello\nWorld\n!")
while e.the_char is not None:
e.next_char()
self.assertTrue(e.line_num == 3)
self.assertTrue(e.line_pos == 2)
