Permalink
Browse files

Added initial commit from Jinja2. TODO: check copyrights!

  • Loading branch information...
0 parents commit 115ba3726e42da36f2aa04857283a5ebb856b354 @mitsuhiko mitsuhiko committed Jun 22, 2010
Showing with 832 additions and 0 deletions.
  1. +7 −0 .gitignore
  2. +32 −0 LICENSE
  3. +2 −0 MANIFEST.in
  4. +225 −0 markupsafe/__init__.py
  5. +267 −0 markupsafe/_constants.py
  6. +36 −0 markupsafe/_native.py
  7. +227 −0 markupsafe/_speedups.c
  8. +36 −0 setup.py
@@ -0,0 +1,7 @@
+.DS_Store
+*.pyc
+*.pyo
+env
+dist
+build
+*.egg-info
32 LICENSE
@@ -0,0 +1,32 @@
+Copyright (c) 2010 by Armin Ronacher.
+
+Some rights reserved.
+
+Redistribution and use in source and binary forms of the software as well
+as documentation, with or without modification, are permitted provided
+that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above
+ copyright notice, this list of conditions and the following
+ disclaimer in the documentation and/or other materials provided
+ with the distribution.
+
+* The names of the contributors may not be used to endorse or
+ promote products derived from this software without specific
+ prior written permission.
+
+THIS SOFTWARE AND DOCUMENTATION IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT
+NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
+OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE AND DOCUMENTATION, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGE.
@@ -0,0 +1,2 @@
+include LICENSE
+recursive-include markupsafe *.c
@@ -0,0 +1,225 @@
+# -*- coding: utf-8 -*-
+"""
+ markupsafe
+ ~~~~~~~~~~
+
+ Implements a Markup string.
+
+ :copyright: (c) 2010 by Armin Ronacher.
+ :license: BSD, see LICENSE for more details.
+"""
+import re
+from itertools import imap
+
+
+__all__ = ['Module', 'soft_unicode']
+
+
+_striptags_re = re.compile(r'(<!--.*?-->|<[^>]*>)')
+_entity_re = re.compile(r'&([^;]+);')
+
+
+class Markup(unicode):
+ r"""Marks a string as being safe for inclusion in HTML/XML output without
+ needing to be escaped. This implements the `__html__` interface a couple
+ of frameworks and web applications use. :class:`Markup` is a direct
+ subclass of `unicode` and provides all the methods of `unicode` just that
+ it escapes arguments passed and always returns `Markup`.
+
+ The `escape` function returns markup objects so that double escaping can't
+ happen.
+
+ The constructor of the :class:`Markup` class can be used for three
+ different things: When passed an unicode object it's assumed to be safe,
+ when passed an object with an HTML representation (has an `__html__`
+ method) that representation is used, otherwise the object passed is
+ converted into a unicode string and then assumed to be safe:
+
+ >>> Markup("Hello <em>World</em>!")
+ Markup(u'Hello <em>World</em>!')
+ >>> class Foo(object):
+ ... def __html__(self):
+ ... return '<a href="#">foo</a>'
+ ...
+ >>> Markup(Foo())
+ Markup(u'<a href="#">foo</a>')
+
+ If you want object passed being always treated as unsafe you can use the
+ :meth:`escape` classmethod to create a :class:`Markup` object:
+
+ >>> Markup.escape("Hello <em>World</em>!")
+ Markup(u'Hello &lt;em&gt;World&lt;/em&gt;!')
+
+ Operations on a markup string are markup aware which means that all
+ arguments are passed through the :func:`escape` function:
+
+ >>> em = Markup("<em>%s</em>")
+ >>> em % "foo & bar"
+ Markup(u'<em>foo &amp; bar</em>')
+ >>> strong = Markup("<strong>%(text)s</strong>")
+ >>> strong % {'text': '<blink>hacker here</blink>'}
+ Markup(u'<strong>&lt;blink&gt;hacker here&lt;/blink&gt;</strong>')
+ >>> Markup("<em>Hello</em> ") + "<foo>"
+ Markup(u'<em>Hello</em> &lt;foo&gt;')
+ """
+ __slots__ = ()
+
+ def __new__(cls, base=u'', encoding=None, errors='strict'):
+ if hasattr(base, '__html__'):
+ base = base.__html__()
+ if encoding is None:
+ return unicode.__new__(cls, base)
+ return unicode.__new__(cls, base, encoding, errors)
+
+ def __html__(self):
+ return self
+
+ def __add__(self, other):
+ if hasattr(other, '__html__') or isinstance(other, basestring):
+ return self.__class__(unicode(self) + unicode(escape(other)))
+ return NotImplemented
+
+ def __radd__(self, other):
+ if hasattr(other, '__html__') or isinstance(other, basestring):
+ return self.__class__(unicode(escape(other)) + unicode(self))
+ return NotImplemented
+
+ def __mul__(self, num):
+ if isinstance(num, (int, long)):
+ return self.__class__(unicode.__mul__(self, num))
+ return NotImplemented
+ __rmul__ = __mul__
+
+ def __mod__(self, arg):
+ if isinstance(arg, tuple):
+ arg = tuple(imap(_MarkupEscapeHelper, arg))
+ else:
+ arg = _MarkupEscapeHelper(arg)
+ return self.__class__(unicode.__mod__(self, arg))
+
+ def __repr__(self):
+ return '%s(%s)' % (
+ self.__class__.__name__,
+ unicode.__repr__(self)
+ )
+
+ def join(self, seq):
+ return self.__class__(unicode.join(self, imap(escape, seq)))
+ join.__doc__ = unicode.join.__doc__
+
+ def split(self, *args, **kwargs):
+ return map(self.__class__, unicode.split(self, *args, **kwargs))
+ split.__doc__ = unicode.split.__doc__
+
+ def rsplit(self, *args, **kwargs):
+ return map(self.__class__, unicode.rsplit(self, *args, **kwargs))
+ rsplit.__doc__ = unicode.rsplit.__doc__
+
+ def splitlines(self, *args, **kwargs):
+ return map(self.__class__, unicode.splitlines(self, *args, **kwargs))
+ splitlines.__doc__ = unicode.splitlines.__doc__
+
+ def unescape(self):
+ r"""Unescape markup again into an unicode string. This also resolves
+ known HTML4 and XHTML entities:
+
+ >>> Markup("Main &raquo; <em>About</em>").unescape()
+ u'Main \xbb <em>About</em>'
+ """
+ from markupsafe._constants import HTML_ENTITIES
+ def handle_match(m):
+ name = m.group(1)
+ if name in HTML_ENTITIES:
+ return unichr(HTML_ENTITIES[name])
+ try:
+ if name[:2] in ('#x', '#X'):
+ return unichr(int(name[2:], 16))
+ elif name.startswith('#'):
+ return unichr(int(name[1:]))
+ except ValueError:
+ pass
+ return u''
+ return _entity_re.sub(handle_match, unicode(self))
+
+ def striptags(self):
+ r"""Unescape markup into an unicode string and strip all tags. This
+ also resolves known HTML4 and XHTML entities. Whitespace is
+ normalized to one:
+
+ >>> Markup("Main &raquo; <em>About</em>").striptags()
+ u'Main \xbb About'
+ """
+ stripped = u' '.join(_striptags_re.sub('', self).split())
+ return Markup(stripped).unescape()
+
+ @classmethod
+ def escape(cls, s):
+ """Escape the string. Works like :func:`escape` with the difference
+ that for subclasses of :class:`Markup` this function would return the
+ correct subclass.
+ """
+ rv = escape(s)
+ if rv.__class__ is not cls:
+ return cls(rv)
+ return rv
+
+ def make_wrapper(name):
+ orig = getattr(unicode, name)
+ def func(self, *args, **kwargs):
+ args = _escape_argspec(list(args), enumerate(args))
+ _escape_argspec(kwargs, kwargs.iteritems())
+ return self.__class__(orig(self, *args, **kwargs))
+ func.__name__ = orig.__name__
+ func.__doc__ = orig.__doc__
+ return func
+
+ for method in '__getitem__', 'capitalize', \
+ 'title', 'lower', 'upper', 'replace', 'ljust', \
+ 'rjust', 'lstrip', 'rstrip', 'center', 'strip', \
+ 'translate', 'expandtabs', 'swapcase', 'zfill':
+ locals()[method] = make_wrapper(method)
+
+ # new in python 2.5
+ if hasattr(unicode, 'partition'):
+ partition = make_wrapper('partition'),
+ rpartition = make_wrapper('rpartition')
+
+ # new in python 2.6
+ if hasattr(unicode, 'format'):
+ format = make_wrapper('format')
+
+ # not in python 3
+ if hasattr(unicode, '__getslice__'):
+ __getslice__ = make_wrapper('__getslice__')
+
+ del method, make_wrapper
+
+
+def _escape_argspec(obj, iterable):
+ """Helper for various string-wrapped functions."""
+ for key, value in iterable:
+ if hasattr(value, '__html__') or isinstance(value, basestring):
+ obj[key] = escape(value)
+ return obj
+
+
+class _MarkupEscapeHelper(object):
+ """Helper for Markup.__mod__"""
+
+ def __init__(self, obj):
+ self.obj = obj
+
+ __getitem__ = lambda s, x: _MarkupEscapeHelper(s.obj[x])
+ __str__ = lambda s: str(escape(s.obj))
+ __unicode__ = lambda s: unicode(escape(s.obj))
+ __repr__ = lambda s: str(escape(repr(s.obj)))
+ __int__ = lambda s: int(s.obj)
+ __float__ = lambda s: float(s.obj)
+
+
+# we have to import it down here as the speedups and native
+# modules imports the markup type which is define above.
+try:
+ from markupsafe._speedups import escape, soft_unicode
+except ImportError:
+ from markupsafe._native import escape, soft_unicode
Oops, something went wrong.

0 comments on commit 115ba37

Please sign in to comment.