def preprocess(self, source, name=None, filename=None):
"""Preprocesses the source with all extensions. This is automatically
called for all parsing and compiling methods but *not* for :meth:`lex`
because there you usually only want the actual source tokenized.
"""
return reduce(lambda s, e: e.preprocess(s, name, filename),
self.iter_extensions(), text_type(source))
def urlize(text, trim_url_limit=None, rel=None, target=None):
"""Converts any URLs in text into clickable links. Works on http://,
https:// and www. links. Links can have trailing punctuation (periods,
commas, close-parens) and leading punctuation (opening parens) and
it'll still do the right thing.
If trim_url_limit is not None, the URLs in link text will be limited
to trim_url_limit characters.
If nofollow is True, the URLs in link text will get a rel="nofollow"
attribute.
If target is not None, a target attribute will be added to the link.
"""
trim_url = lambda x, limit=trim_url_limit: limit is not None \
and (x[:limit] + (len(x) >=limit and '...'
or '')) or x
words = _word_split_re.split(text_type(escape(text)))
rel_attr = rel and ' rel="%s"' % text_type(escape(rel)) or ''
target_attr = target and ' target="%s"' % escape(target) or ''
for i, word in enumerate(words):
match = _punctuation_re.match(word)
if match:
lead, middle, trail = match.groups()
if middle.startswith('www.') or (
'@' not in middle and
not middle.startswith('http://') and
not middle.startswith('https://') and
len(middle) > 0 and
middle[0] in _letters + _digits and (
middle.endswith('.org') or
middle.endswith('.net') or
middle.endswith('.com')
)):
middle = '<a href="http://%s"%s%s>%s</a>' % (middle,
rel_attr, target_attr, trim_url(middle))
if middle.startswith('http://') or \
middle.startswith('https://'):
middle = '<a href="%s"%s%s>%s</a>' % (middle,
rel_attr, target_attr, trim_url(middle))
if '@' in middle and not middle.startswith('www.') and \
not ':' in middle and _simple_email_re.match(middle):
middle = '<a href="mailto:%s">%s</a>' % (middle, middle)
if lead + middle + trail != word:
words[i] = lead + middle + trail
return u''.join(words)
def unicode_urlencode(obj, charset='utf-8', for_qs=False):
"""URL escapes a single bytestring or unicode string with the
given charset if applicable to URL safe quoting under all rules
that need to be considered under all supported Python versions.
If non strings are provided they are converted to their unicode
representation first.
"""
if not isinstance(obj, string_types):
obj = text_type(obj)
if isinstance(obj, text_type):
obj = obj.encode(charset)
safe = not for_qs and b'/' or b''
rv = text_type(url_quote(obj, safe))
if for_qs:
rv = rv.replace('%20', '+')
return rv
def lex(self, source, name=None, filename=None):
"""Lex the given sourcecode and return a generator that yields
tokens as tuples in the form ``(lineno, token_type, value)``.
This can be useful for :ref:`extension development <writing-extensions>`
and debugging templates.
This does not perform preprocessing. If you want the preprocessing
of the extensions to be applied you have to filter source through
the :meth:`preprocess` method.
"""
source = text_type(source)
try:
return self.lexer.tokeniter(source, name, filename)
except TemplateSyntaxError:
exc_info = sys.exc_info()
self.handle_exception(exc_info, source_hint=source)
def native_concat(nodes):
"""Return a native Python type from the list of compiled nodes. If the
result is a single node, its value is returned. Otherwise, the nodes are
concatenated as strings. If the result can be parsed with
:func:`ast.literal_eval`, the parsed value is returned. Otherwise, the
string is returned.
"""
head = list(islice(nodes, 2))
if not head:
return None
if len(head) == 1:
out = head[0]
else:
out = u''.join([text_type(v) for v in chain(head, nodes)])
try:
return literal_eval(out)
except (ValueError, SyntaxError, MemoryError):
return out
def test_upper(value):
"""Return true if the variable is uppercased."""
return text_type(value).isupper()
def tokeniter(self, source, name, filename=None, state=None):
"""This method tokenizes the text and returns the tokens in a
generator. Use this method if you just want to tokenize a template.
"""
source = text_type(source)
lines = source.splitlines()
if self.keep_trailing_newline and source:
for newline in ('\r\n', '\r', '\n'):
if source.endswith(newline):
lines.append('')
break
source = '\n'.join(lines)
pos = 0
lineno = 1
stack = ['root']
if state is not None and state != 'root':
assert state in ('variable', 'block'), 'invalid state'
stack.append(state + '_begin')
else:
state = 'root'
statetokens = self.rules[stack[-1]]
source_length = len(source)
balancing_stack = []
while 1:
# tokenizer loop
for regex, tokens, new_state in statetokens:
m = regex.match(source, pos)
# if no match we try again with the next rule
if m is None:
continue
# we only match blocks and variables if braces / parentheses
# are balanced. continue parsing with the lower rule which
# is the operator rule. do this only if the end tags look
# like operators
if balancing_stack and \
tokens in ('variable_end', 'block_end',
'linestatement_end'):
continue
# tuples support more options
if isinstance(tokens, tuple):
for idx, token in enumerate(tokens):
# failure group
if token.__class__ is Failure:
raise token(lineno, filename)
# bygroup is a bit more complex, in that case we
# yield for the current token the first named
# group that matched
elif token == '#bygroup':
for key, value in iteritems(m.groupdict()):
if value is not None:
yield lineno, key, value
lineno += value.count('\n')
break
else:
raise RuntimeError('%r wanted to resolve '
'the token dynamically'
' but no group matched' %
regex)
# normal group
else:
data = m.group(idx + 1)
if data or token not in ignore_if_empty:
yield lineno, token, data
lineno += data.count('\n')
# strings as token just are yielded as it.
else:
data = m.group()
# update brace/parentheses balance
if tokens == 'operator':
if data == '{':
balancing_stack.append('}')
elif data == '(':
balancing_stack.append(')')
elif data == '[':
balancing_stack.append(']')
elif data in ('}', ')', ']'):
if not balancing_stack:
raise TemplateSyntaxError(
'unexpected \'%s\'' % data, lineno, name,
filename)
expected_op = balancing_stack.pop()
if expected_op != data:
raise TemplateSyntaxError(
'unexpected \'%s\', '
'expected \'%s\'' % (data, expected_op),
lineno, name, filename)
# yield items
if data or tokens not in ignore_if_empty:
yield lineno, tokens, data
lineno += data.count('\n')
# fetch new position into new variable so that we can check
# if there is a internal parsing error which would result
# in an infinite loop
pos2 = m.end()
# handle state changes
if new_state is not None:
# remove the uppermost state
if new_state == '#pop':
stack.pop()
# resolve the new state by group checking
elif new_state == '#bygroup':
for key, value in iteritems(m.groupdict()):
if value is not None:
stack.append(key)
break
else:
raise RuntimeError('%r wanted to resolve the '
'new state dynamically but'
' no group matched' % regex)
# direct state name given
else:
stack.append(new_state)
statetokens = self.rules[stack[-1]]
# we are still at the same position and no stack change.
# this means a loop without break condition, avoid that and
# raise error
elif pos2 == pos:
raise RuntimeError('%r yielded empty string without '
'stack change' % regex)
# publish new function and start again
pos = pos2
break
# if loop terminated without break we haven't found a single match
# either we are at the end of the file or we have a problem
else:
# end of text
if pos >= source_length:
return
# something went wrong
raise TemplateSyntaxError(
'unexpected char %r at %d' % (source[pos], pos), lineno,
name, filename)
def as_const(self, eval_ctx=None):
eval_ctx = get_eval_context(self, eval_ctx)
return ''.join(text_type(x.as_const(eval_ctx)) for x in self.nodes)
def __init__(self, message=None):
if message is not None:
message = text_type(message).encode('utf-8')
Exception.__init__(self, message)