def generate(self, writer):
value = self.value
# Compress whitespace if requested, with a crude heuristic to avoid
# altering preformatted whitespace.
if "<pre>" not in value:
value = filter_whitespace(self.whitespace, value)
if value:
writer.write_line('_tt_append(%r)' % escape.utf8(value), self.line)
python类utf8()的实例源码
def _format_chunk(self, chunk):
if self._expected_content_remaining is not None:
self._expected_content_remaining -= len(chunk)
if self._expected_content_remaining < 0:
# Close the stream now to stop further framing errors.
self.stream.close()
raise httputil.HTTPOutputError(
"Tried to write more data than Content-Length")
if self._chunking_output and chunk:
# Don't write out empty chunks because that means END-OF-STREAM
# with chunked encoding
return utf8("%x" % len(chunk)) + b"\r\n" + chunk + b"\r\n"
else:
return chunk
def test_comment(self):
template = Template("Hello{# TODO i18n #} {{ name }}!")
self.assertEqual(template.generate(name=utf8("Ben")),
b"Hello Ben!")
def test_unicode_template(self):
template = Template(utf8(u("\u00e9")))
self.assertEqual(template.generate(), utf8(u("\u00e9")))
def test_unicode_literal_expression(self):
# Unicode literals should be usable in templates. Note that this
# test simulates unicode characters appearing directly in the
# template file (with utf8 encoding), i.e. \u escapes would not
# be used in the template file itself.
if str is unicode_type:
# python 3 needs a different version of this test since
# 2to3 doesn't run on template internals
template = Template(utf8(u('{{ "\u00e9" }}')))
else:
template = Template(utf8(u('{{ u"\u00e9" }}')))
self.assertEqual(template.generate(), utf8(u("\u00e9")))
def test_apply(self):
def upper(s):
return s.upper()
template = Template(utf8("{% apply upper %}foo{% end %}"))
self.assertEqual(template.generate(upper=upper), b"FOO")
def test_unicode_apply(self):
def upper(s):
return to_unicode(s).upper()
template = Template(utf8(u("{% apply upper %}foo \u00e9{% end %}")))
self.assertEqual(template.generate(upper=upper), utf8(u("FOO \u00c9")))
def test_if(self):
template = Template(utf8("{% if x > 4 %}yes{% else %}no{% end %}"))
self.assertEqual(template.generate(x=5), b"yes")
self.assertEqual(template.generate(x=3), b"no")
def test_if_empty_body(self):
template = Template(utf8("{% if True %}{% else %}{% end %}"))
self.assertEqual(template.generate(), b"")
def test_try(self):
template = Template(utf8("""{% try %}
try{% set y = 1/x %}
{% except %}-except
{% else %}-else
{% finally %}-finally
{% end %}"""))
self.assertEqual(template.generate(x=1), b"\ntry\n-else\n-finally\n")
self.assertEqual(template.generate(x=0), b"\ntry-except\n-finally\n")
def test_comment_directive(self):
template = Template(utf8("{% comment blah blah %}foo"))
self.assertEqual(template.generate(), b"foo")
def test_break_continue(self):
template = Template(utf8("""\
{% for i in range(10) %}
{% if i == 2 %}
{% continue %}
{% end %}
{{ i }}
{% if i == 6 %}
{% break %}
{% end %}
{% end %}"""))
result = template.generate()
# remove extraneous whitespace
result = b''.join(result.split())
self.assertEqual(result, b"013456")
def test_break_in_apply(self):
# This test verifies current behavior, although of course it would
# be nice if apply didn't cause seemingly unrelated breakage
try:
Template(utf8("{% for i in [] %}{% apply foo %}{% break %}{% end %}{% end %}"))
raise Exception("Did not get expected exception")
except ParseError:
pass
def test_utf8_in_file(self):
tmpl = self.loader.load("utf8.html")
result = tmpl.generate()
self.assertEqual(to_unicode(result).strip(), u("H\u00e9llo"))
def test_unicode_escapes(self):
self.assertEqual(utf8(u('\u00e9')), b'\xc3\xa9')
def test_import_member(self):
self.assertIs(import_object('tornado.escape.utf8'), utf8)
def test_import_member_unicode(self):
self.assertIs(import_object(u('tornado.escape.utf8')), utf8)
def test_unicode_newlines(self):
# Ensure that only \r\n is recognized as a header separator, and not
# the other newline-like unicode characters.
# Characters that are likely to be problematic can be found in
# http://unicode.org/standard/reports/tr13/tr13-5.html
# and cpython's unicodeobject.c (which defines the implementation
# of unicode_type.splitlines(), and uses a different list than TR13).
newlines = [
u('\u001b'), # VERTICAL TAB
u('\u001c'), # FILE SEPARATOR
u('\u001d'), # GROUP SEPARATOR
u('\u001e'), # RECORD SEPARATOR
u('\u0085'), # NEXT LINE
u('\u2028'), # LINE SEPARATOR
u('\u2029'), # PARAGRAPH SEPARATOR
]
for newline in newlines:
# Try the utf8 and latin1 representations of each newline
for encoding in ['utf8', 'latin1']:
try:
try:
encoded = newline.encode(encoding)
except UnicodeEncodeError:
# Some chars cannot be represented in latin1
continue
data = b'Cookie: foo=' + encoded + b'bar'
# parse() wants a native_str, so decode through latin1
# in the same way the real parser does.
headers = HTTPHeaders.parse(
native_str(data.decode('latin1')))
expected = [('Cookie', 'foo=' +
native_str(encoded.decode('latin1')) + 'bar')]
self.assertEqual(
expected, list(headers.get_all()))
except Exception:
gen_log.warning("failed while trying %r in %s",
newline, encoding)
raise
def raw_fetch(self, headers, body, newline=b"\r\n"):
with closing(IOStream(socket.socket())) as stream:
stream.connect(('127.0.0.1', self.get_http_port()), self.stop)
self.wait()
stream.write(
newline.join(headers +
[utf8("Content-Length: %d" % len(body))]) +
newline + newline + body)
read_stream_body(stream, self.stop)
headers, body = self.wait()
return body
def test_malformed_body(self):
# parse_qs is pretty forgiving, but it will fail on python 3
# if the data is not utf8. On python 2 parse_qs will work,
# but then the recursive_unicode call in EchoHandler will
# fail.
if str is bytes:
return
with ExpectLog(gen_log, 'Invalid x-www-form-urlencoded body'):
response = self.fetch(
'/echo', method="POST",
headers={'Content-Type': 'application/x-www-form-urlencoded'},
body=b'\xe9')
self.assertEqual(200, response.code)
self.assertEqual(b'{}', response.body)
