diff options
author | Marc Abramowitz <marc@marc-abramowitz.com> | 2015-04-30 17:39:24 -0700 |
---|---|---|
committer | Marc Abramowitz <marc@marc-abramowitz.com> | 2015-04-30 17:39:24 -0700 |
commit | fa100c92c06d3a8a61a0dda1a2e06018437b09c6 (patch) | |
tree | a1cc50f93fbf257685c3849e03496c5e33949281 /paste/util/looper.py | |
download | paste-git-test_wsgirequest_charset_use_UTF-8_instead_of_iso-8859-1.tar.gz |
test_wsgirequest_charset: Use UTF-8 instead of iso-8859-1test_wsgirequest_charset_use_UTF-8_instead_of_iso-8859-1
because it seems that the defacto standard for encoding URIs is to use UTF-8.
I've been reading about url encoding and it seems like perhaps using an
encoding other than UTF-8 is very non-standard and not well-supported (this
test is trying to use `iso-8859-1`).
From http://en.wikipedia.org/wiki/Percent-encoding
> For a non-ASCII character, it is typically converted to its byte sequence in
> UTF-8, and then each byte value is represented as above.
> The generic URI syntax mandates that new URI schemes that provide for the
> representation of character data in a URI must, in effect, represent
> characters from the unreserved set without translation, and should convert
> all other characters to bytes according to UTF-8, and then percent-encode
> those values. This requirement was introduced in January 2005 with the
> publication of RFC 3986
From http://tools.ietf.org/html/rfc3986:
> Non-ASCII characters must first be encoded according to UTF-8 [STD63], and
> then each octet of the corresponding UTF-8 sequence must be percent-encoded
> to be represented as URI characters. URI producing applications must not use
> percent-encoding in host unless it is used to represent a UTF-8 character
> sequence.
From http://tools.ietf.org/html/rfc3987:
> Conversions from URIs to IRIs MUST NOT use any character encoding other than
> UTF-8 in steps 3 and 4, even if it might be possible to guess from the
> context that another character encoding than UTF-8 was used in the URI. For
> example, the URI "http://www.example.org/r%E9sum%E9.html" might with some
> guessing be interpreted to contain two e-acute characters encoded as
> iso-8859-1. It must not be converted to an IRI containing these e-acute
> characters. Otherwise, in the future the IRI will be mapped to
> "http://www.example.org/r%C3%A9sum%C3%A9.html", which is a different URI from
> "http://www.example.org/r%E9sum%E9.html".
See issue #7, which I think this at least partially fixes.
Diffstat (limited to 'paste/util/looper.py')
-rw-r--r-- | paste/util/looper.py | 156 |
1 files changed, 156 insertions, 0 deletions
diff --git a/paste/util/looper.py b/paste/util/looper.py new file mode 100644 index 0000000..b56358a --- /dev/null +++ b/paste/util/looper.py @@ -0,0 +1,156 @@ +""" +Helper for looping over sequences, particular in templates. + +Often in a loop in a template it's handy to know what's next up, +previously up, if this is the first or last item in the sequence, etc. +These can be awkward to manage in a normal Python loop, but using the +looper you can get a better sense of the context. Use like:: + + >>> for loop, item in looper(['a', 'b', 'c']): + ... print("%s %s" % (loop.number, item)) + ... if not loop.last: + ... print('---') + 1 a + --- + 2 b + --- + 3 c + +""" + +__all__ = ['looper'] + +import six + + +class looper(object): + """ + Helper for looping (particularly in templates) + + Use this like:: + + for loop, item in looper(seq): + if loop.first: + ... + """ + + def __init__(self, seq): + self.seq = seq + + def __iter__(self): + return looper_iter(self.seq) + + def __repr__(self): + return '<%s for %r>' % ( + self.__class__.__name__, self.seq) + +class looper_iter(object): + + def __init__(self, seq): + self.seq = list(seq) + self.pos = 0 + + def __iter__(self): + return self + + def next(self): + if self.pos >= len(self.seq): + raise StopIteration + result = loop_pos(self.seq, self.pos), self.seq[self.pos] + self.pos += 1 + return result + __next__ = next + +class loop_pos(object): + + def __init__(self, seq, pos): + self.seq = seq + self.pos = pos + + def __repr__(self): + return '<loop pos=%r at %r>' % ( + self.seq[self.pos], self.pos) + + def index(self): + return self.pos + index = property(index) + + def number(self): + return self.pos + 1 + number = property(number) + + def item(self): + return self.seq[self.pos] + item = property(item) + + def next(self): + try: + return self.seq[self.pos+1] + except IndexError: + return None + next = property(next) + + def previous(self): + if self.pos == 0: + return None + return self.seq[self.pos-1] + previous = property(previous) + + def odd(self): + return not self.pos % 2 + odd = property(odd) + + def even(self): + return self.pos % 2 + even = property(even) + + def first(self): + return self.pos == 0 + first = property(first) + + def last(self): + return self.pos == len(self.seq)-1 + last = property(last) + + def length(self): + return len(self.seq) + length = property(length) + + def first_group(self, getter=None): + """ + Returns true if this item is the start of a new group, + where groups mean that some attribute has changed. The getter + can be None (the item itself changes), an attribute name like + ``'.attr'``, a function, or a dict key or list index. + """ + if self.first: + return True + return self._compare_group(self.item, self.previous, getter) + + def last_group(self, getter=None): + """ + Returns true if this item is the end of a new group, + where groups mean that some attribute has changed. The getter + can be None (the item itself changes), an attribute name like + ``'.attr'``, a function, or a dict key or list index. + """ + if self.last: + return True + return self._compare_group(self.item, self.next, getter) + + def _compare_group(self, item, other, getter): + if getter is None: + return item != other + elif (isinstance(getter, (six.binary_type, six.text_type)) + and getter.startswith('.')): + getter = getter[1:] + if getter.endswith('()'): + getter = getter[:-2] + return getattr(item, getter)() != getattr(other, getter)() + else: + return getattr(item, getter) != getattr(other, getter) + elif callable(getter): + return getter(item) != getter(other) + else: + return item[getter] != other[getter] + |