diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/markupsafe/__init__.py | 144 | ||||
| -rw-r--r-- | src/markupsafe/_compat.py | 11 | ||||
| -rw-r--r-- | src/markupsafe/_constants.py | 506 | ||||
| -rw-r--r-- | src/markupsafe/_native.py | 19 |
4 files changed, 359 insertions, 321 deletions
diff --git a/src/markupsafe/__init__.py b/src/markupsafe/__init__.py index 29fe1bd..e02c15d 100644 --- a/src/markupsafe/__init__.py +++ b/src/markupsafe/__init__.py @@ -12,16 +12,20 @@ special characters with safe representations. import re import string -from markupsafe._compat import ( - PY2, int_types, iteritems, string_types, text_type, unichr, Mapping -) +from ._compat import int_types +from ._compat import iteritems +from ._compat import Mapping +from ._compat import PY2 +from ._compat import string_types +from ._compat import text_type +from ._compat import unichr -__version__ = '1.1.dev' +__version__ = "1.1.dev" -__all__ = ['Markup', 'soft_unicode', 'escape', 'escape_silent'] +__all__ = ["Markup", "soft_unicode", "escape", "escape_silent"] -_striptags_re = re.compile(r'(<!--.*?-->|<[^>]*>)') -_entity_re = re.compile(r'&([^& ;]+);') +_striptags_re = re.compile(r"(<!--.*?-->|<[^>]*>)") +_entity_re = re.compile(r"&([^& ;]+);") class Markup(text_type): @@ -60,10 +64,11 @@ class Markup(text_type): >>> Markup('<em>Hello</em> ') + '<foo>' Markup('<em>Hello</em> <foo>') """ + __slots__ = () - def __new__(cls, base=u'', encoding=None, errors='strict'): - if hasattr(base, '__html__'): + def __new__(cls, base=u"", encoding=None, errors="strict"): + if hasattr(base, "__html__"): base = base.__html__() if encoding is None: return text_type.__new__(cls, base) @@ -73,12 +78,12 @@ class Markup(text_type): return self def __add__(self, other): - if isinstance(other, string_types) or hasattr(other, '__html__'): + if isinstance(other, string_types) or hasattr(other, "__html__"): return self.__class__(super(Markup, self).__add__(self.escape(other))) return NotImplemented def __radd__(self, other): - if hasattr(other, '__html__') or isinstance(other, string_types): + if hasattr(other, "__html__") or isinstance(other, string_types): return self.escape(other).__add__(self) return NotImplemented @@ -86,6 +91,7 @@ class Markup(text_type): if isinstance(num, int_types): return self.__class__(text_type.__mul__(self, num)) return NotImplemented + __rmul__ = __mul__ def __mod__(self, arg): @@ -96,26 +102,26 @@ class Markup(text_type): return self.__class__(text_type.__mod__(self, arg)) def __repr__(self): - return '%s(%s)' % ( - self.__class__.__name__, - text_type.__repr__(self) - ) + return "%s(%s)" % (self.__class__.__name__, text_type.__repr__(self)) def join(self, seq): return self.__class__(text_type.join(self, map(self.escape, seq))) + join.__doc__ = text_type.join.__doc__ def split(self, *args, **kwargs): return list(map(self.__class__, text_type.split(self, *args, **kwargs))) + split.__doc__ = text_type.split.__doc__ def rsplit(self, *args, **kwargs): return list(map(self.__class__, text_type.rsplit(self, *args, **kwargs))) + rsplit.__doc__ = text_type.rsplit.__doc__ def splitlines(self, *args, **kwargs): - return list(map(self.__class__, text_type.splitlines( - self, *args, **kwargs))) + return list(map(self.__class__, text_type.splitlines(self, *args, **kwargs))) + splitlines.__doc__ = text_type.splitlines.__doc__ def unescape(self): @@ -125,20 +131,22 @@ class Markup(text_type): >>> Markup('Main » <em>About</em>').unescape() 'Main » <em>About</em>' """ - from markupsafe._constants import HTML_ENTITIES + from ._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'): + if name[:2] in ("#x", "#X"): return unichr(int(name[2:], 16)) - elif name.startswith('#'): + elif name.startswith("#"): return unichr(int(name[1:])) except ValueError: pass # Don't modify unexpected input. return m.group() + return _entity_re.sub(handle_match, text_type(self)) def striptags(self): @@ -148,7 +156,7 @@ class Markup(text_type): >>> Markup('Main »\t<em>About</em>').striptags() 'Main » About' """ - stripped = u' '.join(_striptags_re.sub('', self).split()) + stripped = u" ".join(_striptags_re.sub("", self).split()) return Markup(stripped).unescape() @classmethod @@ -161,45 +169,57 @@ class Markup(text_type): return cls(rv) return rv - def make_simple_escaping_wrapper(name): + def make_simple_escaping_wrapper(name): # noqa: B902 orig = getattr(text_type, name) + def func(self, *args, **kwargs): args = _escape_argspec(list(args), enumerate(args), self.escape) _escape_argspec(kwargs, iteritems(kwargs), self.escape) 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': + for method in ( + "__getitem__", + "capitalize", + "title", + "lower", + "upper", + "replace", + "ljust", + "rjust", + "lstrip", + "rstrip", + "center", + "strip", + "translate", + "expandtabs", + "swapcase", + "zfill", + ): locals()[method] = make_simple_escaping_wrapper(method) def partition(self, sep): - return tuple(map(self.__class__, - text_type.partition(self, self.escape(sep)))) + return tuple(map(self.__class__, text_type.partition(self, self.escape(sep)))) def rpartition(self, sep): - return tuple(map(self.__class__, - text_type.rpartition(self, self.escape(sep)))) + return tuple(map(self.__class__, text_type.rpartition(self, self.escape(sep)))) - def format(*args, **kwargs): - self, args = args[0], args[1:] + def format(self, *args, **kwargs): formatter = EscapeFormatter(self.escape) kwargs = _MagicFormatMapping(args, kwargs) return self.__class__(formatter.vformat(self, args, kwargs)) def __html_format__(self, format_spec): if format_spec: - raise ValueError('Unsupported format specification ' - 'for Markup.') + raise ValueError("Unsupported format specification " "for Markup.") return self # not in python 3 - if hasattr(text_type, '__getslice__'): - __getslice__ = make_simple_escaping_wrapper('__getslice__') + if hasattr(text_type, "__getslice__"): + __getslice__ = make_simple_escaping_wrapper("__getslice__") del method, make_simple_escaping_wrapper @@ -218,7 +238,7 @@ class _MagicFormatMapping(Mapping): self._last_index = 0 def __getitem__(self, key): - if key == '': + if key == "": idx = self._last_index self._last_index += 1 try: @@ -235,38 +255,37 @@ class _MagicFormatMapping(Mapping): return len(self._kwargs) -if hasattr(text_type, 'format'): - class EscapeFormatter(string.Formatter): +if hasattr(text_type, "format"): + class EscapeFormatter(string.Formatter): def __init__(self, escape): self.escape = escape def format_field(self, value, format_spec): - if hasattr(value, '__html_format__'): + if hasattr(value, "__html_format__"): rv = value.__html_format__(format_spec) - elif hasattr(value, '__html__'): + elif hasattr(value, "__html__"): if format_spec: raise ValueError( - 'Format specifier {0} given, but {1} does not' - ' define __html_format__. A class that defines' - ' __html__ must define __html_format__ to work' - ' with format specifiers.'.format( - format_spec, type(value))) + "Format specifier {0} given, but {1} does not" + " define __html_format__. A class that defines" + " __html__ must define __html_format__ to work" + " with format specifiers.".format(format_spec, type(value)) + ) rv = value.__html__() else: # We need to make sure the format spec is unicode here as # otherwise the wrong callback methods are invoked. For # instance a byte string there would invoke __str__ and # not __unicode__. - rv = string.Formatter.format_field( - self, value, text_type(format_spec)) + rv = string.Formatter.format_field(self, value, text_type(format_spec)) return text_type(self.escape(rv)) def _escape_argspec(obj, iterable, escape): """Helper for various string-wrapped functions.""" for key, value in iterable: - if hasattr(value, '__html__') or isinstance(value, string_types): + if hasattr(value, "__html__") or isinstance(value, string_types): obj[key] = escape(value) return obj @@ -278,20 +297,31 @@ class _MarkupEscapeHelper(object): self.obj = obj self.escape = escape - __getitem__ = lambda s, x: _MarkupEscapeHelper(s.obj[x], s.escape) - __unicode__ = __str__ = lambda s: text_type(s.escape(s.obj)) - __repr__ = lambda s: str(s.escape(repr(s.obj))) - __int__ = lambda s: int(s.obj) - __float__ = lambda s: float(s.obj) + def __getitem__(self, item): + return _MarkupEscapeHelper(self.obj[item], self.escape) + + def __str__(self): + return text_type(self.escape(self.obj)) + + __unicode__ = __str__ + + def __repr__(self): + return str(self.escape(repr(self.obj))) + + def __int__(self): + return int(self.obj) + + def __float__(self): + return float(self.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, escape_silent, soft_unicode + from ._speedups import escape, escape_silent, soft_unicode except ImportError: - from markupsafe._native import escape, escape_silent, soft_unicode + from ._native import escape, escape_silent, soft_unicode if not PY2: soft_str = soft_unicode - __all__.append('soft_str') + __all__.append("soft_str") diff --git a/src/markupsafe/_compat.py b/src/markupsafe/_compat.py index 4d2e2cd..e51d57d 100644 --- a/src/markupsafe/_compat.py +++ b/src/markupsafe/_compat.py @@ -15,12 +15,19 @@ if not PY2: string_types = (str,) unichr = chr int_types = (int,) - iteritems = lambda x: iter(x.items()) + + def iteritems(x): + return iter(x.items()) + from collections.abc import Mapping + else: text_type = unicode string_types = (str, unicode) unichr = unichr int_types = (int, long) - iteritems = lambda x: x.iteritems() + + def iteritems(x): + return x.iteritems() + from collections import Mapping diff --git a/src/markupsafe/_constants.py b/src/markupsafe/_constants.py index ea6ac2f..83670cb 100644 --- a/src/markupsafe/_constants.py +++ b/src/markupsafe/_constants.py @@ -8,257 +8,257 @@ markupsafe._constants """ HTML_ENTITIES = { - 'AElig': 198, - 'Aacute': 193, - 'Acirc': 194, - 'Agrave': 192, - 'Alpha': 913, - 'Aring': 197, - 'Atilde': 195, - 'Auml': 196, - 'Beta': 914, - 'Ccedil': 199, - 'Chi': 935, - 'Dagger': 8225, - 'Delta': 916, - 'ETH': 208, - 'Eacute': 201, - 'Ecirc': 202, - 'Egrave': 200, - 'Epsilon': 917, - 'Eta': 919, - 'Euml': 203, - 'Gamma': 915, - 'Iacute': 205, - 'Icirc': 206, - 'Igrave': 204, - 'Iota': 921, - 'Iuml': 207, - 'Kappa': 922, - 'Lambda': 923, - 'Mu': 924, - 'Ntilde': 209, - 'Nu': 925, - 'OElig': 338, - 'Oacute': 211, - 'Ocirc': 212, - 'Ograve': 210, - 'Omega': 937, - 'Omicron': 927, - 'Oslash': 216, - 'Otilde': 213, - 'Ouml': 214, - 'Phi': 934, - 'Pi': 928, - 'Prime': 8243, - 'Psi': 936, - 'Rho': 929, - 'Scaron': 352, - 'Sigma': 931, - 'THORN': 222, - 'Tau': 932, - 'Theta': 920, - 'Uacute': 218, - 'Ucirc': 219, - 'Ugrave': 217, - 'Upsilon': 933, - 'Uuml': 220, - 'Xi': 926, - 'Yacute': 221, - 'Yuml': 376, - 'Zeta': 918, - 'aacute': 225, - 'acirc': 226, - 'acute': 180, - 'aelig': 230, - 'agrave': 224, - 'alefsym': 8501, - 'alpha': 945, - 'amp': 38, - 'and': 8743, - 'ang': 8736, - 'apos': 39, - 'aring': 229, - 'asymp': 8776, - 'atilde': 227, - 'auml': 228, - 'bdquo': 8222, - 'beta': 946, - 'brvbar': 166, - 'bull': 8226, - 'cap': 8745, - 'ccedil': 231, - 'cedil': 184, - 'cent': 162, - 'chi': 967, - 'circ': 710, - 'clubs': 9827, - 'cong': 8773, - 'copy': 169, - 'crarr': 8629, - 'cup': 8746, - 'curren': 164, - 'dArr': 8659, - 'dagger': 8224, - 'darr': 8595, - 'deg': 176, - 'delta': 948, - 'diams': 9830, - 'divide': 247, - 'eacute': 233, - 'ecirc': 234, - 'egrave': 232, - 'empty': 8709, - 'emsp': 8195, - 'ensp': 8194, - 'epsilon': 949, - 'equiv': 8801, - 'eta': 951, - 'eth': 240, - 'euml': 235, - 'euro': 8364, - 'exist': 8707, - 'fnof': 402, - 'forall': 8704, - 'frac12': 189, - 'frac14': 188, - 'frac34': 190, - 'frasl': 8260, - 'gamma': 947, - 'ge': 8805, - 'gt': 62, - 'hArr': 8660, - 'harr': 8596, - 'hearts': 9829, - 'hellip': 8230, - 'iacute': 237, - 'icirc': 238, - 'iexcl': 161, - 'igrave': 236, - 'image': 8465, - 'infin': 8734, - 'int': 8747, - 'iota': 953, - 'iquest': 191, - 'isin': 8712, - 'iuml': 239, - 'kappa': 954, - 'lArr': 8656, - 'lambda': 955, - 'lang': 9001, - 'laquo': 171, - 'larr': 8592, - 'lceil': 8968, - 'ldquo': 8220, - 'le': 8804, - 'lfloor': 8970, - 'lowast': 8727, - 'loz': 9674, - 'lrm': 8206, - 'lsaquo': 8249, - 'lsquo': 8216, - 'lt': 60, - 'macr': 175, - 'mdash': 8212, - 'micro': 181, - 'middot': 183, - 'minus': 8722, - 'mu': 956, - 'nabla': 8711, - 'nbsp': 160, - 'ndash': 8211, - 'ne': 8800, - 'ni': 8715, - 'not': 172, - 'notin': 8713, - 'nsub': 8836, - 'ntilde': 241, - 'nu': 957, - 'oacute': 243, - 'ocirc': 244, - 'oelig': 339, - 'ograve': 242, - 'oline': 8254, - 'omega': 969, - 'omicron': 959, - 'oplus': 8853, - 'or': 8744, - 'ordf': 170, - 'ordm': 186, - 'oslash': 248, - 'otilde': 245, - 'otimes': 8855, - 'ouml': 246, - 'para': 182, - 'part': 8706, - 'permil': 8240, - 'perp': 8869, - 'phi': 966, - 'pi': 960, - 'piv': 982, - 'plusmn': 177, - 'pound': 163, - 'prime': 8242, - 'prod': 8719, - 'prop': 8733, - 'psi': 968, - 'quot': 34, - 'rArr': 8658, - 'radic': 8730, - 'rang': 9002, - 'raquo': 187, - 'rarr': 8594, - 'rceil': 8969, - 'rdquo': 8221, - 'real': 8476, - 'reg': 174, - 'rfloor': 8971, - 'rho': 961, - 'rlm': 8207, - 'rsaquo': 8250, - 'rsquo': 8217, - 'sbquo': 8218, - 'scaron': 353, - 'sdot': 8901, - 'sect': 167, - 'shy': 173, - 'sigma': 963, - 'sigmaf': 962, - 'sim': 8764, - 'spades': 9824, - 'sub': 8834, - 'sube': 8838, - 'sum': 8721, - 'sup': 8835, - 'sup1': 185, - 'sup2': 178, - 'sup3': 179, - 'supe': 8839, - 'szlig': 223, - 'tau': 964, - 'there4': 8756, - 'theta': 952, - 'thetasym': 977, - 'thinsp': 8201, - 'thorn': 254, - 'tilde': 732, - 'times': 215, - 'trade': 8482, - 'uArr': 8657, - 'uacute': 250, - 'uarr': 8593, - 'ucirc': 251, - 'ugrave': 249, - 'uml': 168, - 'upsih': 978, - 'upsilon': 965, - 'uuml': 252, - 'weierp': 8472, - 'xi': 958, - 'yacute': 253, - 'yen': 165, - 'yuml': 255, - 'zeta': 950, - 'zwj': 8205, - 'zwnj': 8204 + "AElig": 198, + "Aacute": 193, + "Acirc": 194, + "Agrave": 192, + "Alpha": 913, + "Aring": 197, + "Atilde": 195, + "Auml": 196, + "Beta": 914, + "Ccedil": 199, + "Chi": 935, + "Dagger": 8225, + "Delta": 916, + "ETH": 208, + "Eacute": 201, + "Ecirc": 202, + "Egrave": 200, + "Epsilon": 917, + "Eta": 919, + "Euml": 203, + "Gamma": 915, + "Iacute": 205, + "Icirc": 206, + "Igrave": 204, + "Iota": 921, + "Iuml": 207, + "Kappa": 922, + "Lambda": 923, + "Mu": 924, + "Ntilde": 209, + "Nu": 925, + "OElig": 338, + "Oacute": 211, + "Ocirc": 212, + "Ograve": 210, + "Omega": 937, + "Omicron": 927, + "Oslash": 216, + "Otilde": 213, + "Ouml": 214, + "Phi": 934, + "Pi": 928, + "Prime": 8243, + "Psi": 936, + "Rho": 929, + "Scaron": 352, + "Sigma": 931, + "THORN": 222, + "Tau": 932, + "Theta": 920, + "Uacute": 218, + "Ucirc": 219, + "Ugrave": 217, + "Upsilon": 933, + "Uuml": 220, + "Xi": 926, + "Yacute": 221, + "Yuml": 376, + "Zeta": 918, + "aacute": 225, + "acirc": 226, + "acute": 180, + "aelig": 230, + "agrave": 224, + "alefsym": 8501, + "alpha": 945, + "amp": 38, + "and": 8743, + "ang": 8736, + "apos": 39, + "aring": 229, + "asymp": 8776, + "atilde": 227, + "auml": 228, + "bdquo": 8222, + "beta": 946, + "brvbar": 166, + "bull": 8226, + "cap": 8745, + "ccedil": 231, + "cedil": 184, + "cent": 162, + "chi": 967, + "circ": 710, + "clubs": 9827, + "cong": 8773, + "copy": 169, + "crarr": 8629, + "cup": 8746, + "curren": 164, + "dArr": 8659, + "dagger": 8224, + "darr": 8595, + "deg": 176, + "delta": 948, + "diams": 9830, + "divide": 247, + "eacute": 233, + "ecirc": 234, + "egrave": 232, + "empty": 8709, + "emsp": 8195, + "ensp": 8194, + "epsilon": 949, + "equiv": 8801, + "eta": 951, + "eth": 240, + "euml": 235, + "euro": 8364, + "exist": 8707, + "fnof": 402, + "forall": 8704, + "frac12": 189, + "frac14": 188, + "frac34": 190, + "frasl": 8260, + "gamma": 947, + "ge": 8805, + "gt": 62, + "hArr": 8660, + "harr": 8596, + "hearts": 9829, + "hellip": 8230, + "iacute": 237, + "icirc": 238, + "iexcl": 161, + "igrave": 236, + "image": 8465, + "infin": 8734, + "int": 8747, + "iota": 953, + "iquest": 191, + "isin": 8712, + "iuml": 239, + "kappa": 954, + "lArr": 8656, + "lambda": 955, + "lang": 9001, + "laquo": 171, + "larr": 8592, + "lceil": 8968, + "ldquo": 8220, + "le": 8804, + "lfloor": 8970, + "lowast": 8727, + "loz": 9674, + "lrm": 8206, + "lsaquo": 8249, + "lsquo": 8216, + "lt": 60, + "macr": 175, + "mdash": 8212, + "micro": 181, + "middot": 183, + "minus": 8722, + "mu": 956, + "nabla": 8711, + "nbsp": 160, + "ndash": 8211, + "ne": 8800, + "ni": 8715, + "not": 172, + "notin": 8713, + "nsub": 8836, + "ntilde": 241, + "nu": 957, + "oacute": 243, + "ocirc": 244, + "oelig": 339, + "ograve": 242, + "oline": 8254, + "omega": 969, + "omicron": 959, + "oplus": 8853, + "or": 8744, + "ordf": 170, + "ordm": 186, + "oslash": 248, + "otilde": 245, + "otimes": 8855, + "ouml": 246, + "para": 182, + "part": 8706, + "permil": 8240, + "perp": 8869, + "phi": 966, + "pi": 960, + "piv": 982, + "plusmn": 177, + "pound": 163, + "prime": 8242, + "prod": 8719, + "prop": 8733, + "psi": 968, + "quot": 34, + "rArr": 8658, + "radic": 8730, + "rang": 9002, + "raquo": 187, + "rarr": 8594, + "rceil": 8969, + "rdquo": 8221, + "real": 8476, + "reg": 174, + "rfloor": 8971, + "rho": 961, + "rlm": 8207, + "rsaquo": 8250, + "rsquo": 8217, + "sbquo": 8218, + "scaron": 353, + "sdot": 8901, + "sect": 167, + "shy": 173, + "sigma": 963, + "sigmaf": 962, + "sim": 8764, + "spades": 9824, + "sub": 8834, + "sube": 8838, + "sum": 8721, + "sup": 8835, + "sup1": 185, + "sup2": 178, + "sup3": 179, + "supe": 8839, + "szlig": 223, + "tau": 964, + "there4": 8756, + "theta": 952, + "thetasym": 977, + "thinsp": 8201, + "thorn": 254, + "tilde": 732, + "times": 215, + "trade": 8482, + "uArr": 8657, + "uacute": 250, + "uarr": 8593, + "ucirc": 251, + "ugrave": 249, + "uml": 168, + "upsih": 978, + "upsilon": 965, + "uuml": 252, + "weierp": 8472, + "xi": 958, + "yacute": 253, + "yen": 165, + "yuml": 255, + "zeta": 950, + "zwj": 8205, + "zwnj": 8204, } diff --git a/src/markupsafe/_native.py b/src/markupsafe/_native.py index 801f285..245f03a 100644 --- a/src/markupsafe/_native.py +++ b/src/markupsafe/_native.py @@ -8,8 +8,8 @@ Native Python implementation used when the C module is not compiled. :copyright: © 2010 by the Pallets team. :license: BSD, see LICENSE for more details. """ -from markupsafe import Markup -from markupsafe._compat import text_type +from . import Markup +from ._compat import text_type def escape(s): @@ -23,14 +23,15 @@ def escape(s): :param s: An object to be converted to a string and escaped. :return: A :class:`Markup` string with the escaped text. """ - if hasattr(s, '__html__'): + if hasattr(s, "__html__"): return Markup(s.__html__()) - return Markup(text_type(s) - .replace('&', '&') - .replace('>', '>') - .replace('<', '<') - .replace("'", ''') - .replace('"', '"') + return Markup( + text_type(s) + .replace("&", "&") + .replace(">", ">") + .replace("<", "<") + .replace("'", "'") + .replace('"', """) ) |