Mercurial > genshi > genshi-test
annotate markup/core.py @ 140:a2edde90ad24
Fix bug in HTML serializer, plus some other minor tweaks.
author | cmlenz |
---|---|
date | Wed, 09 Aug 2006 21:00:15 +0000 |
parents | 636e0100fcaf |
children | b3ceaa35fb6b |
rev | line source |
---|---|
1 | 1 # -*- coding: utf-8 -*- |
2 # | |
66
822089ae65ce
Switch copyright to Edgewall and URLs to markup.edgewall.org.
cmlenz
parents:
54
diff
changeset
|
3 # Copyright (C) 2006 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 | |
66
822089ae65ce
Switch copyright to Edgewall and URLs to markup.edgewall.org.
cmlenz
parents:
54
diff
changeset
|
8 # are also available at http://markup.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 | |
66
822089ae65ce
Switch copyright to Edgewall and URLs to markup.edgewall.org.
cmlenz
parents:
54
diff
changeset
|
12 # history and logs, available at http://markup.edgewall.org/log/. |
1 | 13 |
14 """Core classes for markup processing.""" | |
15 | |
16 import htmlentitydefs | |
17 import re | |
18 from StringIO import StringIO | |
19 | |
20 __all__ = ['Stream', 'Markup', 'escape', 'unescape', 'Namespace', 'QName'] | |
21 | |
22 | |
17
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
23 class StreamEventKind(str): |
1 | 24 """A kind of event on an XML stream.""" |
25 | |
26 | |
27 class Stream(object): | |
28 """Represents a stream of markup events. | |
29 | |
30 This class is basically an iterator over the events. | |
31 | |
32 Also provided are ways to serialize the stream to text. The `serialize()` | |
33 method will return an iterator over generated strings, while `render()` | |
34 returns the complete generated text at once. Both accept various parameters | |
35 that impact the way the stream is serialized. | |
36 | |
37 Stream events are tuples of the form: | |
38 | |
39 (kind, data, position) | |
40 | |
41 where `kind` is the event kind (such as `START`, `END`, `TEXT`, etc), `data` | |
42 depends on the kind of event, and `position` is a `(line, offset)` tuple | |
43 that contains the location of the original element or text in the input. | |
44 """ | |
45 __slots__ = ['events'] | |
46 | |
17
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
47 START = StreamEventKind('START') # a start tag |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
48 END = StreamEventKind('END') # an end tag |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
49 TEXT = StreamEventKind('TEXT') # literal text |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
50 DOCTYPE = StreamEventKind('DOCTYPE') # doctype declaration |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
51 START_NS = StreamEventKind('START-NS') # start namespace mapping |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
52 END_NS = StreamEventKind('END-NS') # end namespace mapping |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
53 PI = StreamEventKind('PI') # processing instruction |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
54 COMMENT = StreamEventKind('COMMENT') # comment |
1 | 55 |
56 def __init__(self, events): | |
57 """Initialize the stream with a sequence of markup events. | |
58 | |
27 | 59 @param events: a sequence or iterable providing the events |
1 | 60 """ |
61 self.events = events | |
62 | |
63 def __iter__(self): | |
64 return iter(self.events) | |
65 | |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
66 def filter(self, *filters): |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
67 """Apply filters to the stream. |
113
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
68 |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
69 This method returns a new stream with the given filters applied. The |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
70 filters must be callables that accept the stream object as parameter, |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
71 and return the filtered stream. |
113
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
72 """ |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
73 stream = self |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
74 for filter_ in filters: |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
75 stream = filter_(iter(stream)) |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
76 return Stream(stream) |
113
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
77 |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
78 def render(self, method='xml', encoding='utf-8', **kwargs): |
1 | 79 """Return a string representation of the stream. |
80 | |
81 @param method: determines how the stream is serialized; can be either | |
96
35d681a94763
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
91
diff
changeset
|
82 "xml", "xhtml", or "html", or a custom `Serializer` |
35d681a94763
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
91
diff
changeset
|
83 subclass |
1 | 84 @param encoding: how the output string should be encoded; if set to |
85 `None`, this method returns a `unicode` object | |
86 | |
87 Any additional keyword arguments are passed to the serializer, and thus | |
88 depend on the `method` parameter value. | |
89 """ | |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
90 generator = self.serialize(method=method, **kwargs) |
17
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
91 output = u''.join(list(generator)) |
1 | 92 if encoding is not None: |
9
3dc28e165273
Actually use the specified encoding in `Stream.render()`.
cmlenz
parents:
8
diff
changeset
|
93 return output.encode(encoding) |
8
ea47069a901c
`Stream.render()` was masking `TypeError`s (fix based on suggestion by Matt Good).
cmlenz
parents:
6
diff
changeset
|
94 return output |
1 | 95 |
96 def select(self, path): | |
97 """Return a new stream that contains the events matching the given | |
98 XPath expression. | |
99 | |
100 @param path: a string containing the XPath expression | |
101 """ | |
102 from markup.path import Path | |
17
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
103 return Path(path).select(self) |
1 | 104 |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
105 def serialize(self, method='xml', **kwargs): |
1 | 106 """Generate strings corresponding to a specific serialization of the |
107 stream. | |
108 | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
109 Unlike the `render()` method, this method is a generator that returns |
1 | 110 the serialized output incrementally, as opposed to returning a single |
111 string. | |
112 | |
113 @param method: determines how the stream is serialized; can be either | |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
114 "xml", "xhtml", or "html", or a custom serializer class |
1 | 115 """ |
116 from markup import output | |
117 cls = method | |
118 if isinstance(method, basestring): | |
96
35d681a94763
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
91
diff
changeset
|
119 cls = {'xml': output.XMLSerializer, |
35d681a94763
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
91
diff
changeset
|
120 'xhtml': output.XHTMLSerializer, |
35d681a94763
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
91
diff
changeset
|
121 'html': output.HTMLSerializer}[method] |
123
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
122 serialize = cls(**kwargs) |
93bbdcf9428b
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
116
diff
changeset
|
123 return serialize(_ensure(self)) |
1 | 124 |
125 def __str__(self): | |
126 return self.render() | |
127 | |
128 def __unicode__(self): | |
129 return self.render(encoding=None) | |
130 | |
131 | |
69 | 132 START = Stream.START |
133 END = Stream.END | |
134 TEXT = Stream.TEXT | |
135 DOCTYPE = Stream.DOCTYPE | |
136 START_NS = Stream.START_NS | |
137 END_NS = Stream.END_NS | |
138 PI = Stream.PI | |
139 COMMENT = Stream.COMMENT | |
140 | |
111
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
141 def _ensure(stream): |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
142 """Ensure that every item on the stream is actually a markup event.""" |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
143 for event in stream: |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
144 try: |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
145 kind, data, pos = event |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
146 except ValueError: |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
147 kind, data, pos = event.totuple() |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
148 yield kind, data, pos |
8a4d9064f363
Some fixes and more unit tests for the XPath engine.
cmlenz
parents:
100
diff
changeset
|
149 |
69 | 150 |
1 | 151 class Attributes(list): |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
152 """Sequence type that stores the attributes of an element. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
153 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
154 The order of the attributes is preserved, while accessing and manipulating |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
155 attributes by name is also supported. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
156 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
157 >>> attrs = Attributes([('href', '#'), ('title', 'Foo')]) |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
158 >>> attrs |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
159 [(u'href', '#'), (u'title', 'Foo')] |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
160 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
161 >>> 'href' in attrs |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
162 True |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
163 >>> 'tabindex' in attrs |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
164 False |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
165 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
166 >>> attrs.get(u'title') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
167 'Foo' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
168 >>> attrs.set(u'title', 'Bar') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
169 >>> attrs |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
170 [(u'href', '#'), (u'title', 'Bar')] |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
171 >>> attrs.remove(u'title') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
172 >>> attrs |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
173 [(u'href', '#')] |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
174 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
175 New attributes added using the `set()` method are appended to the end of |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
176 the list: |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
177 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
178 >>> attrs.set(u'accesskey', 'k') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
179 >>> attrs |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
180 [(u'href', '#'), (u'accesskey', 'k')] |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
181 """ |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
182 __slots__ = [] |
1 | 183 |
184 def __init__(self, attrib=None): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
185 """Create the `Attributes` instance. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
186 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
187 If the `attrib` parameter is provided, it is expected to be a sequence |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
188 of `(name, value)` tuples. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
189 """ |
27 | 190 if attrib is None: |
191 attrib = [] | |
192 list.__init__(self, [(QName(name), value) for name, value in attrib]) | |
1 | 193 |
194 def __contains__(self, name): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
195 """Return whether the list includes an attribute with the specified |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
196 name. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
197 """ |
133
b9a0031d4bbb
Minor cleanup and performance improvement for the builder module.
cmlenz
parents:
123
diff
changeset
|
198 for attr, _ in self: |
b9a0031d4bbb
Minor cleanup and performance improvement for the builder module.
cmlenz
parents:
123
diff
changeset
|
199 if attr == name: |
b9a0031d4bbb
Minor cleanup and performance improvement for the builder module.
cmlenz
parents:
123
diff
changeset
|
200 return True |
1 | 201 |
202 def get(self, name, default=None): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
203 """Return the value of the attribute with the specified name, or the |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
204 value of the `default` parameter if no such attribute is found. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
205 """ |
1 | 206 for attr, value in self: |
207 if attr == name: | |
208 return value | |
209 return default | |
210 | |
5
1add946decb8
Improved `py:attrs` directive so that it removes existing attributes if they evaluate to `None` (AFAICT matching Kid behavior).
cmlenz
parents:
1
diff
changeset
|
211 def remove(self, name): |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
212 """Removes the attribute with the specified name. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
213 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
214 If no such attribute is found, this method does nothing. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
215 """ |
5
1add946decb8
Improved `py:attrs` directive so that it removes existing attributes if they evaluate to `None` (AFAICT matching Kid behavior).
cmlenz
parents:
1
diff
changeset
|
216 for idx, (attr, _) in enumerate(self): |
1add946decb8
Improved `py:attrs` directive so that it removes existing attributes if they evaluate to `None` (AFAICT matching Kid behavior).
cmlenz
parents:
1
diff
changeset
|
217 if attr == name: |
1add946decb8
Improved `py:attrs` directive so that it removes existing attributes if they evaluate to `None` (AFAICT matching Kid behavior).
cmlenz
parents:
1
diff
changeset
|
218 del self[idx] |
1add946decb8
Improved `py:attrs` directive so that it removes existing attributes if they evaluate to `None` (AFAICT matching Kid behavior).
cmlenz
parents:
1
diff
changeset
|
219 break |
1add946decb8
Improved `py:attrs` directive so that it removes existing attributes if they evaluate to `None` (AFAICT matching Kid behavior).
cmlenz
parents:
1
diff
changeset
|
220 |
1 | 221 def set(self, name, value): |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
222 """Sets the specified attribute to the given value. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
223 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
224 If an attribute with the specified name is already in the list, the |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
225 value of the existing entry is updated. Otherwise, a new attribute is |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
226 appended to the end of the list. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
227 """ |
1 | 228 for idx, (attr, _) in enumerate(self): |
229 if attr == name: | |
230 self[idx] = (attr, value) | |
231 break | |
232 else: | |
233 self.append((QName(name), value)) | |
234 | |
77
f1aa49c759b2
* Simplify implementation of the individual XPath tests (use closures instead of callable classes)
cmlenz
parents:
73
diff
changeset
|
235 def totuple(self): |
f1aa49c759b2
* Simplify implementation of the individual XPath tests (use closures instead of callable classes)
cmlenz
parents:
73
diff
changeset
|
236 return TEXT, u''.join([x[1] for x in self]), (None, -1, -1) |
f1aa49c759b2
* Simplify implementation of the individual XPath tests (use closures instead of callable classes)
cmlenz
parents:
73
diff
changeset
|
237 |
1 | 238 |
116 | 239 def plaintext(text, keeplinebreaks=True): |
240 """Returns the text as a `unicode` string with all entities and tags | |
241 removed. | |
242 """ | |
243 text = stripentities(striptags(text)) | |
244 if not keeplinebreaks: | |
245 text = text.replace(u'\n', u' ') | |
246 return text | |
247 | |
113
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
248 def stripentities(text, keepxmlentities=False): |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
249 """Return a copy of the given text with any character or numeric entities |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
250 replaced by the equivalent UTF-8 characters. |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
251 |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
252 If the `keepxmlentities` parameter is provided and evaluates to `True`, |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
253 the core XML entities (&, ', >, < and ") are not |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
254 stripped. |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
255 """ |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
256 def _replace_entity(match): |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
257 if match.group(1): # numeric entity |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
258 ref = match.group(1) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
259 if ref.startswith('x'): |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
260 ref = int(ref[1:], 16) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
261 else: |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
262 ref = int(ref, 10) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
263 return unichr(ref) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
264 else: # character entity |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
265 ref = match.group(2) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
266 if keepxmlentities and ref in ('amp', 'apos', 'gt', 'lt', |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
267 'quot'): |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
268 return '&%s;' % ref |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
269 try: |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
270 codepoint = htmlentitydefs.name2codepoint[ref] |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
271 return unichr(codepoint) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
272 except KeyError: |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
273 if keepxmlentities: |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
274 return '&%s;' % ref |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
275 else: |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
276 return ref |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
277 return re.sub(r'&(?:#((?:\d+)|(?:[xX][0-9a-fA-F]+));?|(\w+);)', |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
278 _replace_entity, text) |
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
279 |
116 | 280 def striptags(text): |
281 """Return a copy of the text with all XML/HTML tags removed.""" | |
282 return re.sub(r'<[^>]*?>', '', text) | |
283 | |
113
e815c2c07572
Removed the `sanitize()` method from the `Markup` class, and migrate the existing unit tests to `markup.tests.filters`. Provide a `Stream.filter()` method instead which can be used to conveniently apply a filter to a stream.
cmlenz
parents:
111
diff
changeset
|
284 |
1 | 285 class Markup(unicode): |
286 """Marks a string as being safe for inclusion in HTML/XML output without | |
287 needing to be escaped. | |
288 """ | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
289 __slots__ = [] |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
290 |
27 | 291 def __new__(cls, text='', *args): |
1 | 292 if args: |
136 | 293 text %= tuple(map(escape, args)) |
27 | 294 return unicode.__new__(cls, text) |
1 | 295 |
296 def __add__(self, other): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
297 return Markup(unicode(self) + escape(other)) |
1 | 298 |
299 def __mod__(self, args): | |
300 if not isinstance(args, (list, tuple)): | |
301 args = [args] | |
136 | 302 return Markup(unicode.__mod__(self, tuple(map(escape, args)))) |
1 | 303 |
304 def __mul__(self, num): | |
305 return Markup(unicode(self) * num) | |
306 | |
17
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
307 def __repr__(self): |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
308 return '<%s "%s">' % (self.__class__.__name__, self) |
ad63ad459524
Refactoring to address #6: all match templates are now processed by a single filter, which means that match templates added by included templates are properly applied. A side effect of this refactoring is that `Context` objects may not be reused across multiple template processing runs.
cmlenz
parents:
10
diff
changeset
|
309 |
54 | 310 def join(self, seq, escape_quotes=True): |
311 return Markup(unicode(self).join([escape(item, quotes=escape_quotes) | |
34 | 312 for item in seq])) |
1 | 313 |
314 def escape(cls, text, quotes=True): | |
315 """Create a Markup instance from a string and escape special characters | |
316 it may contain (<, >, & and \"). | |
317 | |
318 If the `quotes` parameter is set to `False`, the \" character is left | |
319 as is. Escaping quotes is generally only required for strings that are | |
320 to be used in attribute values. | |
321 """ | |
73 | 322 if not text: |
323 return cls() | |
324 if type(text) is cls: | |
1 | 325 return text |
73 | 326 text = unicode(text).replace('&', '&') \ |
327 .replace('<', '<') \ | |
328 .replace('>', '>') | |
1 | 329 if quotes: |
330 text = text.replace('"', '"') | |
331 return cls(text) | |
332 escape = classmethod(escape) | |
333 | |
334 def unescape(self): | |
335 """Reverse-escapes &, <, > and \" and returns a `unicode` object.""" | |
336 if not self: | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
337 return u'' |
1 | 338 return unicode(self).replace('"', '"') \ |
339 .replace('>', '>') \ | |
340 .replace('<', '<') \ | |
341 .replace('&', '&') | |
342 | |
116 | 343 def stripentities(self, keepxmlentities=False): |
344 """Return a copy of the text with any character or numeric entities | |
345 replaced by the equivalent UTF-8 characters. | |
346 | |
347 If the `keepxmlentities` parameter is provided and evaluates to `True`, | |
348 the core XML entities (&, ', >, < and ") are not | |
349 stripped. | |
6 | 350 """ |
116 | 351 return Markup(stripentities(self, keepxmlentities=keepxmlentities)) |
352 | |
353 def striptags(self): | |
354 """Return a copy of the text with all XML/HTML tags removed.""" | |
355 return Markup(striptags(self)) | |
1 | 356 |
357 | |
358 escape = Markup.escape | |
359 | |
360 def unescape(text): | |
361 """Reverse-escapes &, <, > and \" and returns a `unicode` object.""" | |
362 if not isinstance(text, Markup): | |
363 return text | |
364 return text.unescape() | |
365 | |
366 | |
367 class Namespace(object): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
368 """Utility class creating and testing elements with a namespace. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
369 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
370 Internally, namespace URIs are encoded in the `QName` of any element or |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
371 attribute, the namespace URI being enclosed in curly braces. This class |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
372 helps create and test these strings. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
373 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
374 A `Namespace` object is instantiated with the namespace URI. |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
375 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
376 >>> html = Namespace('http://www.w3.org/1999/xhtml') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
377 >>> html |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
378 <Namespace "http://www.w3.org/1999/xhtml"> |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
379 >>> html.uri |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
380 u'http://www.w3.org/1999/xhtml' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
381 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
382 The `Namespace` object can than be used to generate `QName` objects with |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
383 that namespace: |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
384 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
385 >>> html.body |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
386 u'{http://www.w3.org/1999/xhtml}body' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
387 >>> html.body.localname |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
388 u'body' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
389 >>> html.body.namespace |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
390 u'http://www.w3.org/1999/xhtml' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
391 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
392 The same works using item access notation, which is useful for element or |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
393 attribute names that are not valid Python identifiers: |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
394 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
395 >>> html['body'] |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
396 u'{http://www.w3.org/1999/xhtml}body' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
397 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
398 A `Namespace` object can also be used to test whether a specific `QName` |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
399 belongs to that namespace using the `in` operator: |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
400 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
401 >>> qname = html.body |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
402 >>> qname in html |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
403 True |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
404 >>> qname in Namespace('http://www.w3.org/2002/06/xhtml2') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
405 False |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
406 """ |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
407 def __init__(self, uri): |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
408 self.uri = unicode(uri) |
1 | 409 |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
410 def __contains__(self, qname): |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
411 return qname.namespace == self.uri |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
412 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
413 def __eq__(self, other): |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
414 if isinstance(other, Namespace): |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
415 return self.uri == other.uri |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
416 return self.uri == other |
1 | 417 |
418 def __getitem__(self, name): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
419 return QName(self.uri + u'}' + name) |
1 | 420 __getattr__ = __getitem__ |
421 | |
422 def __repr__(self): | |
423 return '<Namespace "%s">' % self.uri | |
424 | |
425 def __str__(self): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
426 return self.uri.encode('utf-8') |
1 | 427 |
428 def __unicode__(self): | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
429 return self.uri |
1 | 430 |
431 | |
432 class QName(unicode): | |
433 """A qualified element or attribute name. | |
434 | |
435 The unicode value of instances of this class contains the qualified name of | |
436 the element or attribute, in the form `{namespace}localname`. The namespace | |
437 URI can be obtained through the additional `namespace` attribute, while the | |
438 local name can be accessed through the `localname` attribute. | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
439 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
440 >>> qname = QName('foo') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
441 >>> qname |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
442 u'foo' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
443 >>> qname.localname |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
444 u'foo' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
445 >>> qname.namespace |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
446 |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
447 >>> qname = QName('http://www.w3.org/1999/xhtml}body') |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
448 >>> qname |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
449 u'{http://www.w3.org/1999/xhtml}body' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
450 >>> qname.localname |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
451 u'body' |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
452 >>> qname.namespace |
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
453 u'http://www.w3.org/1999/xhtml' |
1 | 454 """ |
455 __slots__ = ['namespace', 'localname'] | |
456 | |
457 def __new__(cls, qname): | |
100 | 458 if type(qname) is cls: |
1 | 459 return qname |
460 | |
18
4cbebb15a834
Actually make use of the `markup.core.Namespace` class, and add a couple of doctests.
cmlenz
parents:
17
diff
changeset
|
461 parts = qname.split(u'}', 1) |
100 | 462 if len(parts) > 1: |
136 | 463 self = unicode.__new__(cls, u'{%s' % qname) |
464 self.namespace, self.localname = map(unicode, parts) | |
1 | 465 else: |
466 self = unicode.__new__(cls, qname) | |
136 | 467 self.namespace, self.localname = None, unicode(qname) |
1 | 468 return self |