Mercurial > genshi > mirror
annotate genshi/core.py @ 958:6fc92535c888 experimental-performance-improvement-exploration
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
author | hodgestar |
---|---|
date | Tue, 13 Mar 2012 03:03:02 +0000 |
parents | 417787b9b9a7 |
children |
rev | line source |
---|---|
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
1 # -*- coding: utf-8 -*- |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
2 # |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
3 # Copyright (C) 2006-2009 Edgewall Software |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
4 # All rights reserved. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
5 # |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
6 # This software is licensed as described in the file COPYING, which |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
7 # you should have received as part of this distribution. The terms |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
8 # are also available at http://genshi.edgewall.org/wiki/License. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
9 # |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
10 # This software consists of voluntary contributions made by many |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
11 # individuals. For the exact contribution history, see the revision |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
12 # history and logs, available at http://genshi.edgewall.org/log/. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
13 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
14 """Core classes for markup processing.""" |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
15 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
16 try: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
17 reduce # builtin in Python < 3 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
18 except NameError: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
19 from functools import reduce |
932 | 20 import sys |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
21 from itertools import chain |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
22 import operator |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
23 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
24 from genshi.util import plaintext, stripentities, striptags, stringrepr |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
25 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
26 __all__ = ['Stream', 'Markup', 'escape', 'unescape', 'Attrs', 'Namespace', |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
27 'QName'] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
28 __docformat__ = 'restructuredtext en' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
29 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
30 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
31 class StreamEventKind(str): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
32 """A kind of event on a markup stream.""" |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
33 __slots__ = [] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
34 _instances = {} |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
35 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
36 def __new__(cls, val): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
37 return cls._instances.setdefault(val, str.__new__(cls, val)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
38 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
39 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
40 class Stream(object): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
41 """Represents a stream of markup events. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
42 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
43 This class is basically an iterator over the events. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
44 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
45 Stream events are tuples of the form:: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
46 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
47 (kind, data, position) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
48 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
49 where ``kind`` is the event kind (such as `START`, `END`, `TEXT`, etc), |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
50 ``data`` depends on the kind of event, and ``position`` is a |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
51 ``(filename, line, offset)`` tuple that contains the location of the |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
52 original element or text in the input. If the original location is unknown, |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
53 ``position`` is ``(None, -1, -1)``. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
54 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
55 Also provided are ways to serialize the stream to text. The `serialize()` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
56 method will return an iterator over generated strings, while `render()` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
57 returns the complete generated text at once. Both accept various parameters |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
58 that impact the way the stream is serialized. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
59 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
60 __slots__ = ['events', 'serializer'] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
61 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
62 START = StreamEventKind('START') #: a start tag |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
63 END = StreamEventKind('END') #: an end tag |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
64 TEXT = StreamEventKind('TEXT') #: literal text |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
65 XML_DECL = StreamEventKind('XML_DECL') #: XML declaration |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
66 DOCTYPE = StreamEventKind('DOCTYPE') #: doctype declaration |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
67 START_NS = StreamEventKind('START_NS') #: start namespace mapping |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
68 END_NS = StreamEventKind('END_NS') #: end namespace mapping |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
69 START_CDATA = StreamEventKind('START_CDATA') #: start CDATA section |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
70 END_CDATA = StreamEventKind('END_CDATA') #: end CDATA section |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
71 PI = StreamEventKind('PI') #: processing instruction |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
72 COMMENT = StreamEventKind('COMMENT') #: comment |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
73 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
74 def __init__(self, events, serializer=None): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
75 """Initialize the stream with a sequence of markup events. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
76 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
77 :param events: a sequence or iterable providing the events |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
78 :param serializer: the default serialization method to use for this |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
79 stream |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
80 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
81 :note: Changed in 0.5: added the `serializer` argument |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
82 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
83 self.events = events #: The underlying iterable producing the events |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
84 self.serializer = serializer #: The default serializion method |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
85 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
86 def __iter__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
87 return iter(self.events) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
88 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
89 def __or__(self, function): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
90 """Override the "bitwise or" operator to apply filters or serializers |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
91 to the stream, providing a syntax similar to pipes on Unix shells. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
92 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
93 Assume the following stream produced by the `HTML` function: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
94 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
95 >>> from genshi.input import HTML |
932 | 96 >>> html = HTML('''<p onclick="alert('Whoa')">Hello, world!</p>''', encoding='utf-8') |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
97 >>> print(html) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
98 <p onclick="alert('Whoa')">Hello, world!</p> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
99 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
100 A filter such as the HTML sanitizer can be applied to that stream using |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
101 the pipe notation as follows: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
102 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
103 >>> from genshi.filters import HTMLSanitizer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
104 >>> sanitizer = HTMLSanitizer() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
105 >>> print(html | sanitizer) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
106 <p>Hello, world!</p> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
107 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
108 Filters can be any function that accepts and produces a stream (where |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
109 a stream is anything that iterates over events): |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
110 |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
111 >>> def uppercase(stream): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
112 ... for kind, data, pos in stream: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
113 ... if kind is TEXT: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
114 ... data = data.upper() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
115 ... yield kind, data, pos |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
116 >>> print(html | sanitizer | uppercase) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
117 <p>HELLO, WORLD!</p> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
118 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
119 Serializers can also be used with this notation: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
120 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
121 >>> from genshi.output import TextSerializer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
122 >>> output = TextSerializer() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
123 >>> print(html | sanitizer | uppercase | output) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
124 HELLO, WORLD! |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
125 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
126 Commonly, serializers should be used at the end of the "pipeline"; |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
127 using them somewhere in the middle may produce unexpected results. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
128 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
129 :param function: the callable object that should be applied as a filter |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
130 :return: the filtered stream |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
131 :rtype: `Stream` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
132 """ |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
133 # TODO: this is horribly slow because is has to guess whether |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
134 # the function passed in is something that produces stream |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
135 # events or something that produces a sequence of strings. |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
136 # Sequences of strings are converted back to a sequence of |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
137 # stream events (and then back to text when rendered). |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
138 events = _possible_text_iterator_to_stream(function(self)) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
139 return Stream(events, serializer=self.serializer) |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
140 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
141 def filter(self, *filters): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
142 """Apply filters to the stream. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
143 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
144 This method returns a new stream with the given filters applied. The |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
145 filters must be callables that accept the stream object as parameter, |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
146 and return the filtered stream. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
147 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
148 The call:: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
149 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
150 stream.filter(filter1, filter2) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
151 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
152 is equivalent to:: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
153 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
154 stream | filter1 | filter2 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
155 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
156 :param filters: one or more callable objects that should be applied as |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
157 filters |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
158 :return: the filtered stream |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
159 :rtype: `Stream` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
160 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
161 return reduce(operator.or_, (self,) + filters) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
162 |
932 | 163 def render(self, method=None, encoding=None, out=None, **kwargs): |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
164 """Return a string representation of the stream. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
165 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
166 Any additional keyword arguments are passed to the serializer, and thus |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
167 depend on the `method` parameter value. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
168 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
169 :param method: determines how the stream is serialized; can be either |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
170 "xml", "xhtml", "html", "text", or a custom serializer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
171 class; if `None`, the default serialization method of |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
172 the stream is used |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
173 :param encoding: how the output string should be encoded; if set to |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
174 `None`, this method returns a `unicode` object |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
175 :param out: a file-like object that the output should be written to |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
176 instead of being returned as one big string; note that if |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
177 this is a file or socket (or similar), the `encoding` must |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
178 not be `None` (that is, the output must be encoded) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
179 :return: a `str` or `unicode` object (depending on the `encoding` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
180 parameter), or `None` if the `out` parameter is provided |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
181 :rtype: `basestring` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
182 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
183 :see: XMLSerializer, XHTMLSerializer, HTMLSerializer, TextSerializer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
184 :note: Changed in 0.5: added the `out` parameter |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
185 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
186 from genshi.output import encode |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
187 if method is None: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
188 method = self.serializer or 'xml' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
189 generator = self.serialize(method=method, **kwargs) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
190 return encode(generator, method=method, encoding=encoding, out=out) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
191 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
192 def select(self, path, namespaces=None, variables=None): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
193 """Return a new stream that contains the events matching the given |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
194 XPath expression. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
195 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
196 >>> from genshi import HTML |
932 | 197 >>> stream = HTML('<doc><elem>foo</elem><elem>bar</elem></doc>', encoding='utf-8') |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
198 >>> print(stream.select('elem')) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
199 <elem>foo</elem><elem>bar</elem> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
200 >>> print(stream.select('elem/text()')) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
201 foobar |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
202 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
203 Note that the outermost element of the stream becomes the *context |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
204 node* for the XPath test. That means that the expression "doc" would |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
205 not match anything in the example above, because it only tests against |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
206 child elements of the outermost element: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
207 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
208 >>> print(stream.select('doc')) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
209 <BLANKLINE> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
210 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
211 You can use the "." expression to match the context node itself |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
212 (although that usually makes little sense): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
213 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
214 >>> print(stream.select('.')) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
215 <doc><elem>foo</elem><elem>bar</elem></doc> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
216 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
217 :param path: a string containing the XPath expression |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
218 :param namespaces: mapping of namespace prefixes used in the path |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
219 :param variables: mapping of variable names to values |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
220 :return: the selected substream |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
221 :rtype: `Stream` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
222 :raises PathSyntaxError: if the given path expression is invalid or not |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
223 supported |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
224 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
225 from genshi.path import Path |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
226 return Path(path).select(self, namespaces, variables) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
227 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
228 def serialize(self, method='xml', **kwargs): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
229 """Generate strings corresponding to a specific serialization of the |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
230 stream. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
231 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
232 Unlike the `render()` method, this method is a generator that returns |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
233 the serialized output incrementally, as opposed to returning a single |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
234 string. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
235 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
236 Any additional keyword arguments are passed to the serializer, and thus |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
237 depend on the `method` parameter value. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
238 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
239 :param method: determines how the stream is serialized; can be either |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
240 "xml", "xhtml", "html", "text", or a custom serializer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
241 class; if `None`, the default serialization method of |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
242 the stream is used |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
243 :return: an iterator over the serialization results (`Markup` or |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
244 `unicode` objects, depending on the serialization method) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
245 :rtype: ``iterator`` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
246 :see: XMLSerializer, XHTMLSerializer, HTMLSerializer, TextSerializer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
247 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
248 from genshi.output import get_serializer |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
249 if method is None: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
250 method = self.serializer or 'xml' |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
251 return get_serializer(method, **kwargs)(self) |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
252 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
253 def __str__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
254 return self.render() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
255 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
256 def __unicode__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
257 return self.render(encoding=None) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
258 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
259 def __html__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
260 return self |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
261 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
262 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
263 START = Stream.START |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
264 END = Stream.END |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
265 TEXT = Stream.TEXT |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
266 XML_DECL = Stream.XML_DECL |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
267 DOCTYPE = Stream.DOCTYPE |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
268 START_NS = Stream.START_NS |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
269 END_NS = Stream.END_NS |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
270 START_CDATA = Stream.START_CDATA |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
271 END_CDATA = Stream.END_CDATA |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
272 PI = Stream.PI |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
273 COMMENT = Stream.COMMENT |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
274 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
275 |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
276 def _text_event(text): |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
277 return (TEXT, unicode(text), (None, -1, -1)) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
278 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
279 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
280 def _text_to_stream(text): |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
281 yield _text_event(text) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
282 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
283 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
284 def _possible_text_iterator_to_stream(textiter_or_stream): |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
285 it = iter(textiter_or_stream) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
286 event = it.next() |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
287 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
288 # Check whether the iterable is a real markup event stream by examining the |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
289 # first item it yields; if it's not we'll need to do some conversion |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
290 if type(event) is not tuple: |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
291 yield TEXT, unicode(event), (None, -1, -1) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
292 for event in it: |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
293 yield TEXT, unicode(event), (None, -1, -1) |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
294 return |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
295 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
296 # This looks like a markup event stream, so we'll just pass it through |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
297 # unchanged |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
298 yield event |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
299 for event in it: |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
300 yield event |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
301 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
302 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
303 class Attrs(tuple): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
304 """Immutable sequence type that stores the attributes of an element. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
305 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
306 Ordering of the attributes is preserved, while access by name is also |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
307 supported. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
308 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
309 >>> attrs = Attrs([('href', '#'), ('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
310 >>> attrs |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
311 Attrs([('href', '#'), ('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
312 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
313 >>> 'href' in attrs |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
314 True |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
315 >>> 'tabindex' in attrs |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
316 False |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
317 >>> attrs.get('title') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
318 'Foo' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
319 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
320 Instances may not be manipulated directly. Instead, the operators ``|`` and |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
321 ``-`` can be used to produce new instances that have specific attributes |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
322 added, replaced or removed. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
323 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
324 To remove an attribute, use the ``-`` operator. The right hand side can be |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
325 either a string or a set/sequence of strings, identifying the name(s) of |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
326 the attribute(s) to remove: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
327 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
328 >>> attrs - 'title' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
329 Attrs([('href', '#')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
330 >>> attrs - ('title', 'href') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
331 Attrs() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
332 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
333 The original instance is not modified, but the operator can of course be |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
334 used with an assignment: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
335 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
336 >>> attrs |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
337 Attrs([('href', '#'), ('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
338 >>> attrs -= 'title' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
339 >>> attrs |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
340 Attrs([('href', '#')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
341 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
342 To add a new attribute, use the ``|`` operator, where the right hand value |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
343 is a sequence of ``(name, value)`` tuples (which includes `Attrs` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
344 instances): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
345 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
346 >>> attrs | [('title', 'Bar')] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
347 Attrs([('href', '#'), ('title', 'Bar')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
348 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
349 If the attributes already contain an attribute with a given name, the value |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
350 of that attribute is replaced: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
351 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
352 >>> attrs | [('href', 'http://example.org/')] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
353 Attrs([('href', 'http://example.org/')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
354 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
355 __slots__ = [] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
356 |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
357 ATTRS = StreamEventKind('ATTRS') |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
358 |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
359 def __contains__(self, name): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
360 """Return whether the list includes an attribute with the specified |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
361 name. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
362 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
363 :return: `True` if the list includes the attribute |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
364 :rtype: `bool` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
365 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
366 for attr, _ in self: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
367 if attr == name: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
368 return True |
941
417787b9b9a7
Fix genshi.core.Attrs.__contains__ so that it returns False instead of None if an attribute is not found (CPython translates this to False automatically but PyPy does not).
hodgestar
parents:
932
diff
changeset
|
369 return False |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
370 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
371 def __getitem__(self, i): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
372 """Return an item or slice of the attributes list. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
373 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
374 >>> attrs = Attrs([('href', '#'), ('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
375 >>> attrs[1] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
376 ('title', 'Foo') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
377 >>> attrs[1:] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
378 Attrs([('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
379 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
380 items = tuple.__getitem__(self, i) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
381 if type(i) is slice: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
382 return Attrs(items) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
383 return items |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
384 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
385 def __getslice__(self, i, j): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
386 """Return a slice of the attributes list. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
387 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
388 >>> attrs = Attrs([('href', '#'), ('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
389 >>> attrs[1:] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
390 Attrs([('title', 'Foo')]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
391 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
392 return Attrs(tuple.__getslice__(self, i, j)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
393 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
394 def __or__(self, attrs): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
395 """Return a new instance that contains the attributes in `attrs` in |
904
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
396 addition to any already existing attributes. Any attributes in the new |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
397 set that have a value of `None` are removed. |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
398 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
399 :return: a new instance with the merged attributes |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
400 :rtype: `Attrs` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
401 """ |
904
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
402 remove = set([an for an, av in attrs if av is None]) |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
403 replace = dict([(an, av) for an, av in attrs |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
404 if an in self and av is not None]) |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
405 return Attrs([(sn, replace.get(sn, sv)) for sn, sv in self |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
406 if sn not in remove] + |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
407 [(an, av) for an, av in attrs |
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
408 if an not in self and an not in remove]) |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
409 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
410 def __repr__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
411 if not self: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
412 return 'Attrs()' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
413 return 'Attrs([%s])' % ', '.join([repr(item) for item in self]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
414 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
415 def __sub__(self, names): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
416 """Return a new instance with all attributes with a name in `names` are |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
417 removed. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
418 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
419 :param names: the names of the attributes to remove |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
420 :return: a new instance with the attribute removed |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
421 :rtype: `Attrs` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
422 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
423 if isinstance(names, basestring): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
424 names = (names,) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
425 return Attrs([(name, val) for name, val in self if name not in names]) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
426 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
427 def get(self, name, default=None): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
428 """Return the value of the attribute with the specified name, or the |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
429 value of the `default` parameter if no such attribute is found. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
430 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
431 :param name: the name of the attribute |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
432 :param default: the value to return when the attribute does not exist |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
433 :return: the attribute value, or the `default` value if that attribute |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
434 does not exist |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
435 :rtype: `object` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
436 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
437 for attr, value in self: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
438 if attr == name: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
439 return value |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
440 return default |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
441 |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
442 def toevent(self): |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
443 """Return the attributes as a markup event. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
444 |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
445 The returned event is an `ATTRS` event, the data is the Attr object. |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
446 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
447 >>> a = Attrs([('href', '#'), ('title', 'Foo')]) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
448 >>> a.toevent() |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
449 ('ATTRS', Attrs([('href', '#'), ('title', 'Foo')]), (None, -1, -1)) |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
450 |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
451 :return: an `ATTR` event |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
452 :rtype: `tuple` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
453 """ |
958
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
454 return self.ATTRS, self, (None, -1, -1) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
455 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
456 def concatenate_values(self): |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
457 """Return the values of the attributes concatenated into a string. |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
458 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
459 >>> a = Attrs([('href', '#'), ('title', 'Foo')]) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
460 >>> a.concatenate_values() |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
461 '#Foo' |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
462 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
463 :return: the concatenated attribute values |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
464 :rtype: `str` |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
465 """ |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
466 return ''.join([x[1] for x in self]) |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
467 |
6fc92535c888
Be more careful about what is passed into streams as events and remove many uses of _ensure as a result. An ATTRS event is added for handling Attributes returned by gensh.path.select().
hodgestar
parents:
941
diff
changeset
|
468 ATTRS = Attrs.ATTRS |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
469 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
470 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
471 class Markup(unicode): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
472 """Marks a string as being safe for inclusion in HTML/XML output without |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
473 needing to be escaped. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
474 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
475 __slots__ = [] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
476 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
477 def __add__(self, other): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
478 return Markup(unicode.__add__(self, escape(other))) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
479 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
480 def __radd__(self, other): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
481 return Markup(unicode.__add__(escape(other), self)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
482 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
483 def __mod__(self, args): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
484 if isinstance(args, dict): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
485 args = dict(zip(args.keys(), map(escape, args.values()))) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
486 elif isinstance(args, (list, tuple)): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
487 args = tuple(map(escape, args)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
488 else: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
489 args = escape(args) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
490 return Markup(unicode.__mod__(self, args)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
491 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
492 def __mul__(self, num): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
493 return Markup(unicode.__mul__(self, num)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
494 __rmul__ = __mul__ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
495 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
496 def __repr__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
497 return "<%s %s>" % (type(self).__name__, unicode.__repr__(self)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
498 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
499 def join(self, seq, escape_quotes=True): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
500 """Return a `Markup` object which is the concatenation of the strings |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
501 in the given sequence, where this `Markup` object is the separator |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
502 between the joined elements. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
503 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
504 Any element in the sequence that is not a `Markup` instance is |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
505 automatically escaped. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
506 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
507 :param seq: the sequence of strings to join |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
508 :param escape_quotes: whether double quote characters in the elements |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
509 should be escaped |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
510 :return: the joined `Markup` object |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
511 :rtype: `Markup` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
512 :see: `escape` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
513 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
514 return Markup(unicode.join(self, [escape(item, quotes=escape_quotes) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
515 for item in seq])) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
516 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
517 @classmethod |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
518 def escape(cls, text, quotes=True): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
519 """Create a Markup instance from a string and escape special characters |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
520 it may contain (<, >, & and \"). |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
521 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
522 >>> escape('"1 < 2"') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
523 <Markup u'"1 < 2"'> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
524 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
525 If the `quotes` parameter is set to `False`, the \" character is left |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
526 as is. Escaping quotes is generally only required for strings that are |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
527 to be used in attribute values. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
528 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
529 >>> escape('"1 < 2"', quotes=False) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
530 <Markup u'"1 < 2"'> |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
531 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
532 :param text: the text to escape |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
533 :param quotes: if ``True``, double quote characters are escaped in |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
534 addition to the other special characters |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
535 :return: the escaped `Markup` string |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
536 :rtype: `Markup` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
537 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
538 if not text: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
539 return cls() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
540 if type(text) is cls: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
541 return text |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
542 if hasattr(text, '__html__'): |
904
82b9b3afe0b8
The `|` operator on `Attrs` objects now removes any existing attributes if the value is `None`.
cmlenz
parents:
862
diff
changeset
|
543 return cls(text.__html__()) |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
544 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
545 text = text.replace('&', '&') \ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
546 .replace('<', '<') \ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
547 .replace('>', '>') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
548 if quotes: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
549 text = text.replace('"', '"') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
550 return cls(text) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
551 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
552 def unescape(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
553 """Reverse-escapes &, <, >, and \" and returns a `unicode` object. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
554 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
555 >>> Markup('1 < 2').unescape() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
556 u'1 < 2' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
557 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
558 :return: the unescaped string |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
559 :rtype: `unicode` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
560 :see: `genshi.core.unescape` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
561 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
562 if not self: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
563 return '' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
564 return unicode(self).replace('"', '"') \ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
565 .replace('>', '>') \ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
566 .replace('<', '<') \ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
567 .replace('&', '&') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
568 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
569 def stripentities(self, keepxmlentities=False): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
570 """Return a copy of the text with any character or numeric entities |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
571 replaced by the equivalent UTF-8 characters. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
572 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
573 If the `keepxmlentities` parameter is provided and evaluates to `True`, |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
574 the core XML entities (``&``, ``'``, ``>``, ``<`` and |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
575 ``"``) are not stripped. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
576 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
577 :return: a `Markup` instance with entities removed |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
578 :rtype: `Markup` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
579 :see: `genshi.util.stripentities` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
580 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
581 return Markup(stripentities(self, keepxmlentities=keepxmlentities)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
582 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
583 def striptags(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
584 """Return a copy of the text with all XML/HTML tags removed. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
585 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
586 :return: a `Markup` instance with all tags removed |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
587 :rtype: `Markup` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
588 :see: `genshi.util.striptags` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
589 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
590 return Markup(striptags(self)) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
591 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
592 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
593 try: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
594 from genshi._speedups import Markup |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
595 except ImportError: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
596 pass # just use the Python implementation |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
597 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
598 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
599 escape = Markup.escape |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
600 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
601 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
602 def unescape(text): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
603 """Reverse-escapes &, <, >, and \" and returns a `unicode` object. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
604 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
605 >>> unescape(Markup('1 < 2')) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
606 u'1 < 2' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
607 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
608 If the provided `text` object is not a `Markup` instance, it is returned |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
609 unchanged. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
610 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
611 >>> unescape('1 < 2') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
612 '1 < 2' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
613 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
614 :param text: the text to unescape |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
615 :return: the unescsaped string |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
616 :rtype: `unicode` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
617 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
618 if not isinstance(text, Markup): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
619 return text |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
620 return text.unescape() |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
621 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
622 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
623 class Namespace(object): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
624 """Utility class creating and testing elements with a namespace. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
625 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
626 Internally, namespace URIs are encoded in the `QName` of any element or |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
627 attribute, the namespace URI being enclosed in curly braces. This class |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
628 helps create and test these strings. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
629 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
630 A `Namespace` object is instantiated with the namespace URI. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
631 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
632 >>> html = Namespace('http://www.w3.org/1999/xhtml') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
633 >>> html |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
634 Namespace('http://www.w3.org/1999/xhtml') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
635 >>> html.uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
636 u'http://www.w3.org/1999/xhtml' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
637 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
638 The `Namespace` object can than be used to generate `QName` objects with |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
639 that namespace: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
640 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
641 >>> html.body |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
642 QName('http://www.w3.org/1999/xhtml}body') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
643 >>> html.body.localname |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
644 u'body' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
645 >>> html.body.namespace |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
646 u'http://www.w3.org/1999/xhtml' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
647 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
648 The same works using item access notation, which is useful for element or |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
649 attribute names that are not valid Python identifiers: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
650 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
651 >>> html['body'] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
652 QName('http://www.w3.org/1999/xhtml}body') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
653 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
654 A `Namespace` object can also be used to test whether a specific `QName` |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
655 belongs to that namespace using the ``in`` operator: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
656 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
657 >>> qname = html.body |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
658 >>> qname in html |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
659 True |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
660 >>> qname in Namespace('http://www.w3.org/2002/06/xhtml2') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
661 False |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
662 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
663 def __new__(cls, uri): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
664 if type(uri) is cls: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
665 return uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
666 return object.__new__(cls) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
667 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
668 def __getnewargs__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
669 return (self.uri,) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
670 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
671 def __getstate__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
672 return self.uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
673 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
674 def __setstate__(self, uri): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
675 self.uri = uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
676 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
677 def __init__(self, uri): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
678 self.uri = unicode(uri) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
679 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
680 def __contains__(self, qname): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
681 return qname.namespace == self.uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
682 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
683 def __ne__(self, other): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
684 return not self == other |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
685 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
686 def __eq__(self, other): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
687 if isinstance(other, Namespace): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
688 return self.uri == other.uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
689 return self.uri == other |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
690 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
691 def __getitem__(self, name): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
692 return QName(self.uri + '}' + name) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
693 __getattr__ = __getitem__ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
694 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
695 def __hash__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
696 return hash(self.uri) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
697 |
932 | 698 if sys.version_info[0] == 2: |
699 # Only use stringrepr in python 2 | |
700 def __repr__(self): | |
701 return '%s(%s)' % (type(self).__name__, stringrepr(self.uri)) | |
702 else: | |
703 def __repr__(self): | |
704 return '%s(%r)' % (type(self).__name__, self.uri) | |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
705 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
706 def __str__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
707 return self.uri.encode('utf-8') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
708 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
709 def __unicode__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
710 return self.uri |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
711 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
712 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
713 # The namespace used by attributes such as xml:lang and xml:space |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
714 XML_NAMESPACE = Namespace('http://www.w3.org/XML/1998/namespace') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
715 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
716 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
717 class QName(unicode): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
718 """A qualified element or attribute name. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
719 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
720 The unicode value of instances of this class contains the qualified name of |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
721 the element or attribute, in the form ``{namespace-uri}local-name``. The |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
722 namespace URI can be obtained through the additional `namespace` attribute, |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
723 while the local name can be accessed through the `localname` attribute. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
724 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
725 >>> qname = QName('foo') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
726 >>> qname |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
727 QName('foo') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
728 >>> qname.localname |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
729 u'foo' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
730 >>> qname.namespace |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
731 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
732 >>> qname = QName('http://www.w3.org/1999/xhtml}body') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
733 >>> qname |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
734 QName('http://www.w3.org/1999/xhtml}body') |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
735 >>> qname.localname |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
736 u'body' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
737 >>> qname.namespace |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
738 u'http://www.w3.org/1999/xhtml' |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
739 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
740 __slots__ = ['namespace', 'localname'] |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
741 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
742 def __new__(cls, qname): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
743 """Create the `QName` instance. |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
744 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
745 :param qname: the qualified name as a string of the form |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
746 ``{namespace-uri}local-name``, where the leading curly |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
747 brace is optional |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
748 """ |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
749 if type(qname) is cls: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
750 return qname |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
751 |
923 | 752 qname = qname.lstrip('{') |
753 parts = qname.split('}', 1) | |
860
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
754 if len(parts) > 1: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
755 self = unicode.__new__(cls, '{%s' % qname) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
756 self.namespace, self.localname = map(unicode, parts) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
757 else: |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
758 self = unicode.__new__(cls, qname) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
759 self.namespace, self.localname = None, unicode(qname) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
760 return self |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
761 |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
762 def __getnewargs__(self): |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
763 return (self.lstrip('{'),) |
16d55698006a
A bit of cleanup of the `Markup` Python implementation.
cmlenz
parents:
857
diff
changeset
|
764 |
932 | 765 if sys.version_info[0] == 2: |
766 # Only use stringrepr in python 2 | |
767 def __repr__(self): | |
768 return '%s(%s)' % (type(self).__name__, stringrepr(self.lstrip('{'))) | |
769 else: | |
770 def __repr__(self): | |
771 return '%s(%r)' % (type(self).__name__, self.lstrip('{')) |