Mercurial > genshi > mirror
annotate genshi/filters/html.py @ 576:b00765a115a5 trunk
Improve docs on `Stream.select()` for #135.
author | cmlenz |
---|---|
date | Mon, 23 Jul 2007 09:50:44 +0000 |
parents | f0461dc3939a |
children | 94f719af686d |
rev | line source |
---|---|
1 | 1 # -*- coding: utf-8 -*- |
2 # | |
408 | 3 # Copyright (C) 2006-2007 Edgewall Software |
1 | 4 # All rights reserved. |
5 # | |
6 # This software is licensed as described in the file COPYING, which | |
7 # you should have received as part of this distribution. The terms | |
230 | 8 # are also available at http://genshi.edgewall.org/wiki/License. |
1 | 9 # |
10 # This software consists of voluntary contributions made by many | |
11 # individuals. For the exact contribution history, see the revision | |
230 | 12 # history and logs, available at http://genshi.edgewall.org/log/. |
1 | 13 |
14 """Implementation of a number of stream filters.""" | |
15 | |
16 try: | |
17 frozenset | |
18 except NameError: | |
19 from sets import ImmutableSet as frozenset | |
20 import re | |
21 | |
403
228907abb726
Remove some magic/overhead from `Attrs` creation and manipulation by not automatically wrapping attribute names in `QName`.
cmlenz
parents:
363
diff
changeset
|
22 from genshi.core import Attrs, QName, stripentities |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
23 from genshi.core import END, START, TEXT, COMMENT |
1 | 24 |
363
37e4b4bb0b53
Parse template includes at parse time to avoid some runtime overhead.
cmlenz
parents:
345
diff
changeset
|
25 __all__ = ['HTMLFormFiller', 'HTMLSanitizer'] |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
26 __docformat__ = 'restructuredtext en' |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
27 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
28 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
29 class HTMLFormFiller(object): |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
30 """A stream filter that can populate HTML forms from a dictionary of values. |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
31 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
32 >>> from genshi.input import HTML |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
33 >>> html = HTML('''<form> |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
34 ... <p><input type="text" name="foo" /></p> |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
35 ... </form>''') |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
36 >>> filler = HTMLFormFiller(data={'foo': 'bar'}) |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
37 >>> print html | filler |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
38 <form> |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
39 <p><input type="text" name="foo" value="bar"/></p> |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
40 </form> |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
41 """ |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
42 # TODO: only select the first radio button, and the first select option |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
43 # (if not in a multiple-select) |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
44 # TODO: only apply to elements in the XHTML namespace (or no namespace)? |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
45 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
46 def __init__(self, name=None, id=None, data=None): |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
47 """Create the filter. |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
48 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
49 :param name: The name of the form that should be populated. If this |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
50 parameter is given, only forms where the ``name`` attribute |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
51 value matches the parameter are processed. |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
52 :param id: The ID of the form that should be populated. If this |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
53 parameter is given, only forms where the ``id`` attribute |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
54 value matches the parameter are processed. |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
55 :param data: The dictionary of form values, where the keys are the names |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
56 of the form fields, and the values are the values to fill |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
57 in. |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
58 """ |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
59 self.name = name |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
60 self.id = id |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
61 if data is None: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
62 data = {} |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
63 self.data = data |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
64 |
439
9f11c745fac9
Add support for adding custom template filters by passing a custom callback function to the `TemplateLoader`. Closes #89 (see added unit test).
cmlenz
parents:
431
diff
changeset
|
65 def __call__(self, stream): |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
66 """Apply the filter to the given stream. |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
67 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
68 :param stream: the markup event stream to filter |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
69 """ |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
70 in_form = in_select = in_option = in_textarea = False |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
71 select_value = option_value = textarea_value = None |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
72 option_start = option_text = None |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
73 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
74 for kind, data, pos in stream: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
75 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
76 if kind is START: |
345 | 77 tag, attrs = data |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
78 tagname = tag.localname |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
79 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
80 if tagname == 'form' and ( |
345 | 81 self.name and attrs.get('name') == self.name or |
82 self.id and attrs.get('id') == self.id or | |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
83 not (self.id or self.name)): |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
84 in_form = True |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
85 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
86 elif in_form: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
87 if tagname == 'input': |
345 | 88 type = attrs.get('type') |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
89 if type in ('checkbox', 'radio'): |
345 | 90 name = attrs.get('name') |
471
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
91 if name and name in self.data: |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
92 value = self.data[name] |
345 | 93 declval = attrs.get('value') |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
94 checked = False |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
95 if isinstance(value, (list, tuple)): |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
96 if declval: |
415
b9f9a22484f0
`HTMLFormFiller` now correctly deals with non-string values in the data dictionary for select/checkbox/radio controls.
cmlenz
parents:
408
diff
changeset
|
97 checked = declval in [str(v) for v |
b9f9a22484f0
`HTMLFormFiller` now correctly deals with non-string values in the data dictionary for select/checkbox/radio controls.
cmlenz
parents:
408
diff
changeset
|
98 in value] |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
99 else: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
100 checked = bool(filter(None, value)) |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
101 else: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
102 if declval: |
415
b9f9a22484f0
`HTMLFormFiller` now correctly deals with non-string values in the data dictionary for select/checkbox/radio controls.
cmlenz
parents:
408
diff
changeset
|
103 checked = declval == str(value) |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
104 elif type == 'checkbox': |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
105 checked = bool(value) |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
106 if checked: |
403
228907abb726
Remove some magic/overhead from `Attrs` creation and manipulation by not automatically wrapping attribute names in `QName`.
cmlenz
parents:
363
diff
changeset
|
107 attrs |= [(QName('checked'), 'checked')] |
345 | 108 elif 'checked' in attrs: |
109 attrs -= 'checked' | |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
110 elif type in (None, 'hidden', 'text'): |
345 | 111 name = attrs.get('name') |
471
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
112 if name and name in self.data: |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
113 value = self.data[name] |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
114 if isinstance(value, (list, tuple)): |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
115 value = value[0] |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
116 if value is not None: |
403
228907abb726
Remove some magic/overhead from `Attrs` creation and manipulation by not automatically wrapping attribute names in `QName`.
cmlenz
parents:
363
diff
changeset
|
117 attrs |= [(QName('value'), unicode(value))] |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
118 elif tagname == 'select': |
345 | 119 name = attrs.get('name') |
471
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
120 if name in self.data: |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
121 select_value = self.data[name] |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
122 in_select = True |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
123 elif tagname == 'textarea': |
345 | 124 name = attrs.get('name') |
471
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
125 if name in self.data: |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
126 textarea_value = self.data.get(name) |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
127 if isinstance(textarea_value, (list, tuple)): |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
128 textarea_value = textarea_value[0] |
76a0ec32835d
The `HTMLFormFiller` stream filter no longer alters form elements for which the data element contains no corresponding item.
cmlenz
parents:
446
diff
changeset
|
129 in_textarea = True |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
130 elif in_select and tagname == 'option': |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
131 option_start = kind, data, pos |
345 | 132 option_value = attrs.get('value') |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
133 in_option = True |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
134 continue |
345 | 135 yield kind, (tag, attrs), pos |
136 | |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
137 elif in_form and kind is TEXT: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
138 if in_select and in_option: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
139 if option_value is None: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
140 option_value = data |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
141 option_text = kind, data, pos |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
142 continue |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
143 elif in_textarea: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
144 continue |
345 | 145 yield kind, data, pos |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
146 |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
147 elif in_form and kind is END: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
148 tagname = data.localname |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
149 if tagname == 'form': |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
150 in_form = False |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
151 elif tagname == 'select': |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
152 in_select = False |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
153 select_value = None |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
154 elif in_select and tagname == 'option': |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
155 if isinstance(select_value, (tuple, list)): |
415
b9f9a22484f0
`HTMLFormFiller` now correctly deals with non-string values in the data dictionary for select/checkbox/radio controls.
cmlenz
parents:
408
diff
changeset
|
156 selected = option_value in [str(v) for v |
b9f9a22484f0
`HTMLFormFiller` now correctly deals with non-string values in the data dictionary for select/checkbox/radio controls.
cmlenz
parents:
408
diff
changeset
|
157 in select_value] |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
158 else: |
415
b9f9a22484f0
`HTMLFormFiller` now correctly deals with non-string values in the data dictionary for select/checkbox/radio controls.
cmlenz
parents:
408
diff
changeset
|
159 selected = option_value == str(select_value) |
345 | 160 okind, (tag, attrs), opos = option_start |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
161 if selected: |
403
228907abb726
Remove some magic/overhead from `Attrs` creation and manipulation by not automatically wrapping attribute names in `QName`.
cmlenz
parents:
363
diff
changeset
|
162 attrs |= [(QName('selected'), 'selected')] |
345 | 163 elif 'selected' in attrs: |
164 attrs -= 'selected' | |
165 yield okind, (tag, attrs), opos | |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
166 if option_text: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
167 yield option_text |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
168 in_option = False |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
169 option_start = option_text = option_value = None |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
170 elif tagname == 'textarea': |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
171 if textarea_value: |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
172 yield TEXT, unicode(textarea_value), pos |
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
173 in_textarea = False |
345 | 174 yield kind, data, pos |
275
d91cbdeb75e9
Integrated `HTMLFormFiller` filter initially presented as a [wiki:FormFilling#Usingatemplatefilter recipe].
cmlenz
parents:
230
diff
changeset
|
175 |
345 | 176 else: |
177 yield kind, data, pos | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
178 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
179 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
180 class HTMLSanitizer(object): |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
181 """A filter that removes potentially dangerous HTML tags and attributes |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
182 from the stream. |
431
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
183 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
184 >>> from genshi import HTML |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
185 >>> html = HTML('<div><script>alert(document.cookie)</script></div>') |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
186 >>> print html | HTMLSanitizer() |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
187 <div/> |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
188 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
189 The default set of safe tags and attributes can be modified when the filter |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
190 is instantiated. For example, to allow inline ``style`` attributes, the |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
191 following instantation would work: |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
192 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
193 >>> html = HTML('<div style="background: #000"></div>') |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
194 >>> sanitizer = HTMLSanitizer(safe_attrs=HTMLSanitizer.SAFE_ATTRS | set(['style'])) |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
195 >>> print html | sanitizer |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
196 <div style="background: #000"/> |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
197 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
198 Note that even in this case, the filter *does* attempt to remove dangerous |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
199 constructs from style attributes: |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
200 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
201 >>> html = HTML('<div style="background: url(javascript:void); color: #000"></div>') |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
202 >>> print html | sanitizer |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
203 <div style="color: #000"/> |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
204 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
205 This handles HTML entities, unicode escapes in CSS and Javascript text, as |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
206 well as a lot of other things. However, the style tag is still excluded by |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
207 default because it is very hard for such sanitizing to be completely safe, |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
208 especially considering how much error recovery current web browsers perform. |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
209 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
210 :warn: Note that this special processing of CSS is currently only applied to |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
211 style attributes, **not** style elements. |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
212 """ |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
213 |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
214 SAFE_TAGS = frozenset(['a', 'abbr', 'acronym', 'address', 'area', 'b', |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
215 'big', 'blockquote', 'br', 'button', 'caption', 'center', 'cite', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
216 'code', 'col', 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
217 'em', 'fieldset', 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
218 'hr', 'i', 'img', 'input', 'ins', 'kbd', 'label', 'legend', 'li', 'map', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
219 'menu', 'ol', 'optgroup', 'option', 'p', 'pre', 'q', 's', 'samp', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
220 'select', 'small', 'span', 'strike', 'strong', 'sub', 'sup', 'table', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
221 'tbody', 'td', 'textarea', 'tfoot', 'th', 'thead', 'tr', 'tt', 'u', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
222 'ul', 'var']) |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
223 |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
224 SAFE_ATTRS = frozenset(['abbr', 'accept', 'accept-charset', 'accesskey', |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
225 'action', 'align', 'alt', 'axis', 'bgcolor', 'border', 'cellpadding', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
226 'cellspacing', 'char', 'charoff', 'charset', 'checked', 'cite', 'class', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
227 'clear', 'cols', 'colspan', 'color', 'compact', 'coords', 'datetime', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
228 'dir', 'disabled', 'enctype', 'for', 'frame', 'headers', 'height', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
229 'href', 'hreflang', 'hspace', 'id', 'ismap', 'label', 'lang', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
230 'longdesc', 'maxlength', 'media', 'method', 'multiple', 'name', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
231 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', 'rel', 'rev', |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
232 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', |
431
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
233 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
234 'type', 'usemap', 'valign', 'value', 'vspace', 'width']) |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
235 |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
236 SAFE_SCHEMES = frozenset(['file', 'ftp', 'http', 'https', 'mailto', None]) |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
237 |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
238 URI_ATTRS = frozenset(['action', 'background', 'dynsrc', 'href', 'lowsrc', |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
239 'src']) |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
240 |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
241 def __init__(self, safe_tags=SAFE_TAGS, safe_attrs=SAFE_ATTRS, |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
242 safe_schemes=SAFE_SCHEMES, uri_attrs=URI_ATTRS): |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
243 """Create the sanitizer. |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
244 |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
245 The exact set of allowed elements and attributes can be configured. |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
246 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
247 :param safe_tags: a set of tag names that are considered safe |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
248 :param safe_attrs: a set of attribute names that are considered safe |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
249 :param safe_schemes: a set of URI schemes that are considered safe |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
250 :param uri_attrs: a set of names of attributes that contain URIs |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
251 """ |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
252 self.safe_tags = safe_tags |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
253 "The set of tag names that are considered safe." |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
254 self.safe_attrs = safe_attrs |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
255 "The set of attribute names that are considered safe." |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
256 self.uri_attrs = uri_attrs |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
257 "The set of names of attributes that may contain URIs." |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
258 self.safe_schemes = safe_schemes |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
259 "The set of URI schemes that are considered safe." |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
260 |
439
9f11c745fac9
Add support for adding custom template filters by passing a custom callback function to the `TemplateLoader`. Closes #89 (see added unit test).
cmlenz
parents:
431
diff
changeset
|
261 def __call__(self, stream): |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
262 """Apply the filter to the given stream. |
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
263 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
415
diff
changeset
|
264 :param stream: the markup event stream to filter |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
265 """ |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
266 waiting_for = None |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
267 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
268 for kind, data, pos in stream: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
269 if kind is START: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
270 if waiting_for: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
271 continue |
345 | 272 tag, attrs = data |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
273 if tag not in self.safe_tags: |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
274 waiting_for = tag |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
275 continue |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
276 |
345 | 277 new_attrs = [] |
278 for attr, value in attrs: | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
279 value = stripentities(value) |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
280 if attr not in self.safe_attrs: |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
281 continue |
277
7e30bfa966ab
The `HTMLSanitizer` now lets you override the default set of tag and attribute names that are considered safe.
cmlenz
parents:
275
diff
changeset
|
282 elif attr in self.uri_attrs: |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
283 # Don't allow URI schemes such as "javascript:" |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
284 if not self.is_safe_uri(value): |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
285 continue |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
286 elif attr == 'style': |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
287 # Remove dangerous CSS declarations from inline styles |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
288 decls = self.sanitize_css(value) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
289 if not decls: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
290 continue |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
291 value = '; '.join(decls) |
345 | 292 new_attrs.append((attr, value)) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
293 |
345 | 294 yield kind, (tag, Attrs(new_attrs)), pos |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
295 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
296 elif kind is END: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
297 tag = data |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
298 if waiting_for: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
299 if waiting_for == tag: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
300 waiting_for = None |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
301 else: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
302 yield kind, data, pos |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
303 |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
304 elif kind is not COMMENT: |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
305 if not waiting_for: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
113
diff
changeset
|
306 yield kind, data, pos |
431
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
307 |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
308 def is_safe_uri(self, uri): |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
309 """Determine whether the given URI is to be considered safe for |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
310 inclusion in the output. |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
311 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
312 The default implementation checks whether the scheme of the URI is in |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
313 the set of allowed URIs (`safe_schemes`). |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
314 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
315 >>> sanitizer = HTMLSanitizer() |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
316 >>> sanitizer.is_safe_uri('http://example.org/') |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
317 True |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
318 >>> sanitizer.is_safe_uri('javascript:alert(document.cookie)') |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
319 False |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
320 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
321 :param uri: the URI to check |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
322 :return: `True` if the URI can be considered safe, `False` otherwise |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
323 :rtype: `bool` |
576 | 324 :since: version 0.4.3 |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
325 """ |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
326 if ':' not in uri: |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
327 return True # This is a relative URI |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
328 chars = [char for char in uri.split(':', 1)[0] if char.isalnum()] |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
329 return ''.join(chars).lower() in self.safe_schemes |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
330 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
331 def sanitize_css(self, text): |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
332 """Remove potentially dangerous property declarations from CSS code. |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
333 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
334 In particular, properties using the CSS ``url()`` function with a scheme |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
335 that is not considered safe are removed: |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
336 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
337 >>> sanitizer = HTMLSanitizer() |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
338 >>> sanitizer.sanitize_css(u''' |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
339 ... background: url(javascript:alert("foo")); |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
340 ... color: #000; |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
341 ... ''') |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
342 [u'color: #000'] |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
343 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
344 Also, the proprietary Internet Explorer function ``expression()`` is |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
345 always stripped: |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
346 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
347 >>> sanitizer.sanitize_css(u''' |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
348 ... background: #fff; |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
349 ... color: #000; |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
350 ... width: e/**/xpression(alert("foo")); |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
351 ... ''') |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
352 [u'background: #fff', u'color: #000'] |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
353 |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
354 :param text: the CSS text; this is expected to be `unicode` and to not |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
355 contain any character or numeric references |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
356 :return: a list of declarations that are considered safe |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
357 :rtype: `list` |
576 | 358 :since: version 0.4.3 |
571
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
359 """ |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
360 decls = [] |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
361 text = self._strip_css_comments(self._replace_unicode_escapes(text)) |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
362 for decl in filter(None, text.split(';')): |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
363 decl = decl.strip() |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
364 if not decl: |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
365 continue |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
366 is_evil = False |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
367 if 'expression' in decl: |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
368 is_evil = True |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
369 for match in re.finditer(r'url\s*\(([^)]+)', decl): |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
370 if not self.is_safe_uri(match.group(1)): |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
371 is_evil = True |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
372 break |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
373 if not is_evil: |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
374 decls.append(decl.strip()) |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
375 return decls |
f0461dc3939a
* Cleaned up the implementation of the `HTMLSanitizer`.
cmlenz
parents:
556
diff
changeset
|
376 |
431
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
377 _NORMALIZE_NEWLINES = re.compile(r'\r\n').sub |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
378 _UNICODE_ESCAPE = re.compile(r'\\([0-9a-fA-F]{1,6})\s?').sub |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
379 |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
380 def _replace_unicode_escapes(self, text): |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
381 def _repl(match): |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
382 return unichr(int(match.group(1), 16)) |
ad01564e87f2
* Don't allow `style` attributes by default in the `HTMLSanitizer`. Closes #97.
cmlenz
parents:
425
diff
changeset
|
383 return self._UNICODE_ESCAPE(_repl, self._NORMALIZE_NEWLINES('\n', text)) |
556
0d98569eaced
The HTML sanitizer now strips any CSS comments in style attributes, which could previously be used to hide malicious property values.
cmlenz
parents:
471
diff
changeset
|
384 |
0d98569eaced
The HTML sanitizer now strips any CSS comments in style attributes, which could previously be used to hide malicious property values.
cmlenz
parents:
471
diff
changeset
|
385 _CSS_COMMENTS = re.compile(r'/\*.*?\*/').sub |
0d98569eaced
The HTML sanitizer now strips any CSS comments in style attributes, which could previously be used to hide malicious property values.
cmlenz
parents:
471
diff
changeset
|
386 |
0d98569eaced
The HTML sanitizer now strips any CSS comments in style attributes, which could previously be used to hide malicious property values.
cmlenz
parents:
471
diff
changeset
|
387 def _strip_css_comments(self, text): |
0d98569eaced
The HTML sanitizer now strips any CSS comments in style attributes, which could previously be used to hide malicious property values.
cmlenz
parents:
471
diff
changeset
|
388 return self._CSS_COMMENTS('', text) |