python-myghty 1.1-5 / usr / share / pyshared / myghty / escapes.py

This file is indexed.

/usr/share/pyshared/myghty/escapes.py is in python-myghty 1.1-5.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below. 

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
# $Id: escapes.py 2133 2006-09-06 18:52:56Z dairiki $
# escapes.py - string escaping functions for Myghty
# Copyright (C) 2004, 2005 Michael Bayer mike_mp@zzzcomputing.com
# Original Perl code and documentation copyright (c) 1998-2003 by Jonathan Swartz. 
#
# This module is part of Myghty and is released under
# the MIT License: http://www.opensource.org/licenses/mit-license.php
#


import re, cgi, urllib, htmlentitydefs, codecs
from StringIO import StringIO

xml_escapes = {
    '&' : '&',
    '>' : '>', 
    '<' : '&lt;', 
    '"' : '&#34;',   # also &quot; in html-only
    "'" : '&#39;'    # also &apos; in html-only    
}
# XXX: &quot; is valid in HTML and XML
#      &apos; is not valid HTML, but is valid XML

def html_escape(string):
    return cgi.escape(string, True)

def xml_escape(string):
    return re.sub(r'([&<"\'>])', lambda m: xml_escapes[m.group()], string)

def url_escape(string):
    # convert into a list of octets
    string = string.encode("utf8")
    return urllib.quote_plus(string)

def url_unescape(string):
    text = urllib.unquote_plus(string)
    if not is_ascii_str(text):
        text = text.decode("utf8")
    return text

_ASCII_re = re.compile(r'\A[\x00-\x7f]*\Z')

def is_ascii_str(text):
    return isinstance(text, str) and _ASCII_re.match(text)

################################################################    

class XMLEntityEscaper(object):
    def __init__(self, codepoint2name, name2codepoint):
        self.codepoint2entity = dict([(c, u'&%s;' % n)
                                      for c,n in codepoint2name.iteritems()])
        self.name2codepoint = name2codepoint

    def escape_entities(self, text):
        """Replace characters with their character entity references.

        Only characters corresponding to a named entity are replaced.
        """
        return unicode(text).translate(self.codepoint2entity)

    def __escape(self, m):
        codepoint = ord(m.group())
        try:
            return self.codepoint2entity[codepoint]
        except (KeyError, IndexError):
            return '&#x%X;' % codepoint


    __escapable = re.compile(r'["&<>]|[^\x00-\x7f]')

    def escape(self, text):
        """Replace characters with their character references.

        Replace characters by their named entity references.
        Non-ASCII characters, if they do not have a named entity reference,
        are replaced by numerical character references.

        The return value is guaranteed to be ASCII.
        """
        return self.__escapable.sub(self.__escape, unicode(text)
                                    ).encode('ascii')

    # XXX: This regexp will not match all valid XML entity names__.
    # (It punts on details involving involving CombiningChars and Extenders.)
    #
    # .. __: http://www.w3.org/TR/2000/REC-xml-20001006#NT-EntityRef
    __characterrefs = re.compile(r'''& (?:
                                          \#(\d+)
                                          | \#x([\da-f]+)
                                          | ( (?!\d) [:\w] [-.:\w]+ )
                                          ) ;''',
                                 re.X | re.UNICODE)
    
    def __unescape(self, m):
        dval, hval, name = m.groups()
        if dval:
            codepoint = int(dval)
        elif hval:
            codepoint = int(hval, 16)
        else:
            codepoint = self.name2codepoint.get(name, 0xfffd)
            # U+FFFD = "REPLACEMENT CHARACTER"
        if codepoint < 128:
            return chr(codepoint)
        return unichr(codepoint)
    
    def unescape(self, text):
        """Unescape character references.

        All character references (both entity references and numerical
        character references) are unescaped.
        """
        return self.__characterrefs.sub(self.__unescape, text)


_html_entities_escaper = XMLEntityEscaper(htmlentitydefs.codepoint2name,
                                          htmlentitydefs.name2codepoint)

html_entities_escape = _html_entities_escaper.escape_entities
html_entities_unescape = _html_entities_escaper.unescape


def htmlentityreplace_errors(ex):
    """An encoding error handler.

    This python `codecs`_ error handler replaces unencodable
    characters with HTML entities, or, if no HTML entity exists for
    the character, XML character references.

    >>> u'The cost was \u20ac12.'.encode('latin1', 'htmlentityreplace')
    'The cost was &euro;12.'
    """
    if isinstance(ex, UnicodeEncodeError):
        # Handle encoding errors
        bad_text = ex.object[ex.start:ex.end]
        text = _html_entities_escaper.escape(bad_text)
        return (unicode(text), ex.end)
    raise ex

codecs.register_error('htmlentityreplace', htmlentityreplace_errors)

APT Browse - Built by Thomas Orozco.