Mercurial > genshi > mirror
annotate genshi/output.py @ 412:bd51adc20a67 trunk
Actually write xmlns declaratons for generated attribute namespace prefixes.
author | cmlenz |
---|---|
date | Mon, 26 Feb 2007 18:39:57 +0000 |
parents | d14d89995c29 |
children | 073640758a42 |
rev | line source |
---|---|
1 | 1 # -*- coding: utf-8 -*- |
2 # | |
408 | 3 # Copyright (C) 2006-2007 Edgewall Software |
1 | 4 # All rights reserved. |
5 # | |
6 # This software is licensed as described in the file COPYING, which | |
7 # you should have received as part of this distribution. The terms | |
230 | 8 # are also available at http://genshi.edgewall.org/wiki/License. |
1 | 9 # |
10 # This software consists of voluntary contributions made by many | |
11 # individuals. For the exact contribution history, see the revision | |
230 | 12 # history and logs, available at http://genshi.edgewall.org/log/. |
1 | 13 |
14 """This module provides different kinds of serialization methods for XML event | |
15 streams. | |
16 """ | |
17 | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
18 from itertools import chain |
1 | 19 try: |
20 frozenset | |
21 except NameError: | |
22 from sets import ImmutableSet as frozenset | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
23 import re |
1 | 24 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
25 from genshi.core import escape, Attrs, Markup, Namespace, QName, StreamEventKind |
402
c199e9b95884
Fix output of namespace declarations for namespace URLs appearing more than once in a stream. Thanks to Jeff Cutsinger for reporting the problem.
cmlenz
parents:
397
diff
changeset
|
26 from genshi.core import DOCTYPE, START, END, START_NS, END_NS, TEXT, \ |
c199e9b95884
Fix output of namespace declarations for namespace URLs appearing more than once in a stream. Thanks to Jeff Cutsinger for reporting the problem.
cmlenz
parents:
397
diff
changeset
|
27 START_CDATA, END_CDATA, PI, COMMENT, XML_NAMESPACE |
1 | 28 |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
29 __all__ = ['DocType', 'XMLSerializer', 'XHTMLSerializer', 'HTMLSerializer', |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
30 'TextSerializer'] |
1 | 31 |
32 | |
85 | 33 class DocType(object): |
34 """Defines a number of commonly used DOCTYPE declarations as constants.""" | |
35 | |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
36 HTML_STRICT = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
37 'html', '-//W3C//DTD HTML 4.01//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
38 'http://www.w3.org/TR/html4/strict.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
39 ) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
40 HTML_TRANSITIONAL = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
41 'html', '-//W3C//DTD HTML 4.01 Transitional//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
42 'http://www.w3.org/TR/html4/loose.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
43 ) |
85 | 44 HTML = HTML_STRICT |
45 | |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
46 XHTML_STRICT = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
47 'html', '-//W3C//DTD XHTML 1.0 Strict//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
48 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
49 ) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
50 XHTML_TRANSITIONAL = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
51 'html', '-//W3C//DTD XHTML 1.0 Transitional//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
52 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
53 ) |
85 | 54 XHTML = XHTML_STRICT |
55 | |
56 | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
57 class XMLSerializer(object): |
1 | 58 """Produces XML text from an event stream. |
59 | |
230 | 60 >>> from genshi.builder import tag |
20 | 61 >>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True)) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
62 >>> print ''.join(XMLSerializer()(elem.generate())) |
1 | 63 <div><a href="foo"/><br/><hr noshade="True"/></div> |
64 """ | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
65 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
66 _PRESERVE_SPACE = frozenset() |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
67 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
68 def __init__(self, doctype=None, strip_whitespace=True, |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
69 namespace_prefixes=None): |
85 | 70 """Initialize the XML serializer. |
71 | |
72 @param doctype: a `(name, pubid, sysid)` tuple that represents the | |
73 DOCTYPE declaration that should be included at the top of the | |
74 generated output | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
75 @param strip_whitespace: whether extraneous whitespace should be |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
76 stripped from the output |
85 | 77 """ |
78 self.preamble = [] | |
79 if doctype: | |
80 self.preamble.append((DOCTYPE, doctype, (None, -1, -1))) | |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
81 self.filters = [EmptyTagFilter()] |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
82 if strip_whitespace: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
83 self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
84 self.filters.append(NamespaceFlattener(prefixes=namespace_prefixes)) |
1 | 85 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
86 def __call__(self, stream): |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
87 have_doctype = False |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
88 in_cdata = False |
1 | 89 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
90 stream = chain(self.preamble, stream) |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
91 for filter_ in self.filters: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
92 stream = filter_(stream) |
1 | 93 for kind, data, pos in stream: |
94 | |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
95 if kind is START or kind is EMPTY: |
1 | 96 tag, attrib = data |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
97 buf = ['<', tag] |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
98 for attr, value in attrib: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
99 buf += [' ', attr, '="', escape(value), '"'] |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
100 buf.append(kind is EMPTY and '/>' or '>') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
101 yield Markup(u''.join(buf)) |
1 | 102 |
69 | 103 elif kind is END: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
104 yield Markup('</%s>' % data) |
1 | 105 |
69 | 106 elif kind is TEXT: |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
107 if in_cdata: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
108 yield data |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
109 else: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
110 yield escape(data, quotes=False) |
1 | 111 |
89
80386d62814f
Support comments in templates that are not included in the output, in the same way Kid does: if the comment text starts with a `!` character, it is stripped from the output.
cmlenz
parents:
85
diff
changeset
|
112 elif kind is COMMENT: |
80386d62814f
Support comments in templates that are not included in the output, in the same way Kid does: if the comment text starts with a `!` character, it is stripped from the output.
cmlenz
parents:
85
diff
changeset
|
113 yield Markup('<!--%s-->' % data) |
80386d62814f
Support comments in templates that are not included in the output, in the same way Kid does: if the comment text starts with a `!` character, it is stripped from the output.
cmlenz
parents:
85
diff
changeset
|
114 |
136 | 115 elif kind is DOCTYPE and not have_doctype: |
116 name, pubid, sysid = data | |
117 buf = ['<!DOCTYPE %s'] | |
118 if pubid: | |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
119 buf.append(' PUBLIC "%s"') |
136 | 120 elif sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
121 buf.append(' SYSTEM') |
136 | 122 if sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
123 buf.append(' "%s"') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
124 buf.append('>\n') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
125 yield Markup(u''.join(buf), *filter(None, data)) |
136 | 126 have_doctype = True |
109
230ee6a2c6b2
Reorder the conditional branches in the serializers so that the more common event kinds are on top.
cmlenz
parents:
105
diff
changeset
|
127 |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
128 elif kind is START_CDATA: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
129 yield Markup('<![CDATA[') |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
130 in_cdata = True |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
131 |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
132 elif kind is END_CDATA: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
133 yield Markup(']]>') |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
134 in_cdata = False |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
135 |
105
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
136 elif kind is PI: |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
137 yield Markup('<?%s %s?>' % data) |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
138 |
1 | 139 |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
140 class XHTMLSerializer(XMLSerializer): |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
141 """Produces XHTML text from an event stream. |
1 | 142 |
230 | 143 >>> from genshi.builder import tag |
20 | 144 >>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True)) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
145 >>> print ''.join(XHTMLSerializer()(elem.generate())) |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
146 <div><a href="foo"></a><br /><hr noshade="noshade" /></div> |
1 | 147 """ |
148 | |
149 _EMPTY_ELEMS = frozenset(['area', 'base', 'basefont', 'br', 'col', 'frame', | |
150 'hr', 'img', 'input', 'isindex', 'link', 'meta', | |
151 'param']) | |
152 _BOOLEAN_ATTRS = frozenset(['selected', 'checked', 'compact', 'declare', | |
153 'defer', 'disabled', 'ismap', 'multiple', | |
154 'nohref', 'noresize', 'noshade', 'nowrap']) | |
346
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
155 _PRESERVE_SPACE = frozenset([ |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
156 QName('pre'), QName('http://www.w3.org/1999/xhtml}pre'), |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
157 QName('textarea'), QName('http://www.w3.org/1999/xhtml}textarea') |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
158 ]) |
1 | 159 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
160 def __init__(self, doctype=None, strip_whitespace=True, |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
161 namespace_prefixes=None): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
162 super(XHTMLSerializer, self).__init__(doctype, False) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
163 self.filters = [EmptyTagFilter()] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
164 if strip_whitespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
165 self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
166 namespace_prefixes = namespace_prefixes or {} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
167 namespace_prefixes['http://www.w3.org/1999/xhtml'] = '' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
168 self.filters.append(NamespaceFlattener(prefixes=namespace_prefixes)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
169 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
170 def __call__(self, stream): |
136 | 171 boolean_attrs = self._BOOLEAN_ATTRS |
172 empty_elems = self._EMPTY_ELEMS | |
85 | 173 have_doctype = False |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
174 in_cdata = False |
1 | 175 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
176 stream = chain(self.preamble, stream) |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
177 for filter_ in self.filters: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
178 stream = filter_(stream) |
1 | 179 for kind, data, pos in stream: |
180 | |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
181 if kind is START or kind is EMPTY: |
1 | 182 tag, attrib = data |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
183 buf = ['<', tag] |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
184 for attr, value in attrib: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
185 if attr in boolean_attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
186 value = attr |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
187 buf += [' ', attr, '="', escape(value), '"'] |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
188 if kind is EMPTY: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
189 if tag in empty_elems: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
190 buf.append(' />') |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
191 else: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
192 buf.append('></%s>' % tag) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
193 else: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
194 buf.append('>') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
195 yield Markup(u''.join(buf)) |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
196 |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
197 elif kind is END: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
198 yield Markup('</%s>' % data) |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
199 |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
200 elif kind is TEXT: |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
201 if in_cdata: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
202 yield data |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
203 else: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
204 yield escape(data, quotes=False) |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
205 |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
206 elif kind is COMMENT: |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
207 yield Markup('<!--%s-->' % data) |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
208 |
136 | 209 elif kind is DOCTYPE and not have_doctype: |
210 name, pubid, sysid = data | |
211 buf = ['<!DOCTYPE %s'] | |
212 if pubid: | |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
213 buf.append(' PUBLIC "%s"') |
136 | 214 elif sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
215 buf.append(' SYSTEM') |
136 | 216 if sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
217 buf.append(' "%s"') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
218 buf.append('>\n') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
219 yield Markup(u''.join(buf), *filter(None, data)) |
136 | 220 have_doctype = True |
109
230ee6a2c6b2
Reorder the conditional branches in the serializers so that the more common event kinds are on top.
cmlenz
parents:
105
diff
changeset
|
221 |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
222 elif kind is START_CDATA: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
223 yield Markup('<![CDATA[') |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
224 in_cdata = True |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
225 |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
226 elif kind is END_CDATA: |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
227 yield Markup(']]>') |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
228 in_cdata = False |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
229 |
105
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
230 elif kind is PI: |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
231 yield Markup('<?%s %s?>' % data) |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
232 |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
233 |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
234 class HTMLSerializer(XHTMLSerializer): |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
235 """Produces HTML text from an event stream. |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
236 |
230 | 237 >>> from genshi.builder import tag |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
238 >>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True)) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
239 >>> print ''.join(HTMLSerializer()(elem.generate())) |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
240 <div><a href="foo"></a><br><hr noshade></div> |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
241 """ |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
242 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
243 _NOESCAPE_ELEMS = frozenset([ |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
244 QName('script'), QName('http://www.w3.org/1999/xhtml}script'), |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
245 QName('style'), QName('http://www.w3.org/1999/xhtml}style') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
246 ]) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
247 |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
248 def __init__(self, doctype=None, strip_whitespace=True): |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
249 """Initialize the HTML serializer. |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
250 |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
251 @param doctype: a `(name, pubid, sysid)` tuple that represents the |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
252 DOCTYPE declaration that should be included at the top of the |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
253 generated output |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
254 @param strip_whitespace: whether extraneous whitespace should be |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
255 stripped from the output |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
256 """ |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
257 super(HTMLSerializer, self).__init__(doctype, False) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
258 self.filters = [EmptyTagFilter()] |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
259 if strip_whitespace: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
260 self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE, |
305 | 261 self._NOESCAPE_ELEMS)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
262 self.filters.append(NamespaceStripper('http://www.w3.org/1999/xhtml')) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
263 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
264 def __call__(self, stream): |
136 | 265 boolean_attrs = self._BOOLEAN_ATTRS |
266 empty_elems = self._EMPTY_ELEMS | |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
267 noescape_elems = self._NOESCAPE_ELEMS |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
268 have_doctype = False |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
269 noescape = False |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
270 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
271 stream = chain(self.preamble, stream) |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
272 for filter_ in self.filters: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
273 stream = filter_(stream) |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
274 for kind, data, pos in stream: |
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
275 |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
276 if kind is START or kind is EMPTY: |
96
fa08aef181a2
Add an XHTML serialization method. Now really need to get rid of some code duplication in the `markup.output` module.
cmlenz
parents:
89
diff
changeset
|
277 tag, attrib = data |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
278 buf = ['<', tag] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
279 for attr, value in attrib: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
280 if attr in boolean_attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
281 if value: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
282 buf += [' ', attr] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
283 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
284 buf += [' ', attr, '="', escape(value), '"'] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
285 buf.append('>') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
286 if kind is EMPTY: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
287 if tag not in empty_elems: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
288 buf.append('</%s>' % tag) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
289 yield Markup(u''.join(buf)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
290 if tag in noescape_elems: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
291 noescape = True |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
292 |
69 | 293 elif kind is END: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
294 yield Markup('</%s>' % data) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
295 noescape = False |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
296 |
69 | 297 elif kind is TEXT: |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
298 if noescape: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
299 yield data |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
300 else: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
301 yield escape(data, quotes=False) |
1 | 302 |
89
80386d62814f
Support comments in templates that are not included in the output, in the same way Kid does: if the comment text starts with a `!` character, it is stripped from the output.
cmlenz
parents:
85
diff
changeset
|
303 elif kind is COMMENT: |
80386d62814f
Support comments in templates that are not included in the output, in the same way Kid does: if the comment text starts with a `!` character, it is stripped from the output.
cmlenz
parents:
85
diff
changeset
|
304 yield Markup('<!--%s-->' % data) |
80386d62814f
Support comments in templates that are not included in the output, in the same way Kid does: if the comment text starts with a `!` character, it is stripped from the output.
cmlenz
parents:
85
diff
changeset
|
305 |
136 | 306 elif kind is DOCTYPE and not have_doctype: |
307 name, pubid, sysid = data | |
308 buf = ['<!DOCTYPE %s'] | |
309 if pubid: | |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
310 buf.append(' PUBLIC "%s"') |
136 | 311 elif sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
312 buf.append(' SYSTEM') |
136 | 313 if sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
314 buf.append(' "%s"') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
315 buf.append('>\n') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
316 yield Markup(u''.join(buf), *filter(None, data)) |
136 | 317 have_doctype = True |
109
230ee6a2c6b2
Reorder the conditional branches in the serializers so that the more common event kinds are on top.
cmlenz
parents:
105
diff
changeset
|
318 |
105
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
319 elif kind is PI: |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
320 yield Markup('<?%s %s?>' % data) |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
321 |
1 | 322 |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
323 class TextSerializer(object): |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
324 """Produces plain text from an event stream. |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
325 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
326 Only text events are included in the output. Unlike the other serializer, |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
327 special XML characters are not escaped: |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
328 |
230 | 329 >>> from genshi.builder import tag |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
330 >>> elem = tag.div(tag.a('<Hello!>', href='foo'), tag.br) |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
331 >>> print elem |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
332 <div><a href="foo"><Hello!></a><br/></div> |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
333 >>> print ''.join(TextSerializer()(elem.generate())) |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
334 <Hello!> |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
335 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
336 If text events contain literal markup (instances of the `Markup` class), |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
337 tags or entities are stripped from the output: |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
338 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
339 >>> elem = tag.div(Markup('<a href="foo">Hello!</a><br/>')) |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
340 >>> print elem |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
341 <div><a href="foo">Hello!</a><br/></div> |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
342 >>> print ''.join(TextSerializer()(elem.generate())) |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
343 Hello! |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
344 """ |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
345 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
346 def __call__(self, stream): |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
347 for event in stream: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
348 if event[0] is TEXT: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
349 data = event[1] |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
350 if type(data) is Markup: |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
351 data = data.striptags().stripentities() |
201
c5e0a1c86173
The `TextSerializer` should produce `unicode` objects, not `Markup` objects.
cmlenz
parents:
200
diff
changeset
|
352 yield unicode(data) |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
353 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
354 |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
355 class EmptyTagFilter(object): |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
356 """Combines `START` and `STOP` events into `EMPTY` events for elements that |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
357 have no contents. |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
358 """ |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
359 |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
360 EMPTY = StreamEventKind('EMPTY') |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
361 |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
362 def __call__(self, stream): |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
363 prev = (None, None, None) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
364 for ev in stream: |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
365 if prev[0] is START: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
366 if ev[0] is END: |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
367 prev = EMPTY, prev[1], prev[2] |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
368 yield prev |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
369 continue |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
370 else: |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
371 yield prev |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
372 if ev[0] is not START: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
373 yield ev |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
374 prev = ev |
212
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
375 |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
376 |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
377 EMPTY = EmptyTagFilter.EMPTY |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
378 |
0141f45c18e1
Refactored the handling of empty tags in the serializer: use an `EmptyTagFilter` that combines adjacent start/end events, instead of the generic pushback-iterator.
cmlenz
parents:
201
diff
changeset
|
379 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
380 class NamespaceFlattener(object): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
381 r"""Output stream filter that removes namespace information from the stream, |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
382 instead adding namespace attributes and prefixes as needed. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
383 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
384 @param prefixes: optional mapping of namespace URIs to prefixes |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
385 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
386 >>> from genshi.input import XML |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
387 >>> xml = XML('''<doc xmlns="NS1" xmlns:two="NS2"> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
388 ... <two:item/> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
389 ... </doc>''') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
390 >>> for kind, data, pos in NamespaceFlattener()(xml): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
391 ... print kind, repr(data) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
392 START (u'doc', Attrs([(u'xmlns', u'NS1'), (u'xmlns:two', u'NS2')])) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
393 TEXT u'\n ' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
394 START (u'two:item', Attrs()) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
395 END u'two:item' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
396 TEXT u'\n' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
397 END u'doc' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
398 """ |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
399 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
400 def __init__(self, prefixes=None): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
401 self.prefixes = {XML_NAMESPACE.uri: 'xml'} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
402 if prefixes is not None: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
403 self.prefixes.update(prefixes) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
404 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
405 def __call__(self, stream): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
406 prefixes = dict([(v, [k]) for k, v in self.prefixes.items()]) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
407 namespaces = {XML_NAMESPACE.uri: ['xml']} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
408 def _push_ns(prefix, uri): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
409 namespaces.setdefault(uri, []).append(prefix) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
410 prefixes.setdefault(prefix, []).append(uri) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
411 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
412 ns_attrs = [] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
413 _push_ns_attr = ns_attrs.append |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
414 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
415 def _gen_prefix(): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
416 val = 0 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
417 while 1: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
418 val += 1 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
419 yield 'ns%d' % val |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
420 _gen_prefix = _gen_prefix().next |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
421 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
422 for kind, data, pos in stream: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
423 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
424 if kind is START or kind is EMPTY: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
425 tag, attrs = data |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
426 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
427 tagname = tag.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
428 tagns = tag.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
429 if tagns: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
430 if tagns in namespaces: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
431 prefix = namespaces[tagns][-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
432 if prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
433 tagname = u'%s:%s' % (prefix, tagname) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
434 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
435 _push_ns_attr((u'xmlns', tagns)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
436 _push_ns('', tagns) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
437 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
438 new_attrs = [] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
439 for attr, value in attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
440 attrname = attr.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
441 attrns = attr.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
442 if attrns: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
443 if attrns not in namespaces: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
444 prefix = _gen_prefix() |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
445 _push_ns(prefix, attrns) |
412
bd51adc20a67
Actually write xmlns declaratons for generated attribute namespace prefixes.
cmlenz
parents:
410
diff
changeset
|
446 _push_ns_attr(('xmlns:%s' % prefix, attrns)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
447 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
448 prefix = namespaces[attrns][-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
449 if prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
450 attrname = u'%s:%s' % (prefix, attrname) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
451 new_attrs.append((attrname, value)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
452 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
453 yield kind, (tagname, Attrs(ns_attrs + new_attrs)), pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
454 del ns_attrs[:] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
455 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
456 elif kind is END: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
457 tagname = data.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
458 tagns = data.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
459 if tagns: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
460 prefix = namespaces[tagns][-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
461 if prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
462 tagname = u'%s:%s' % (prefix, tagname) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
463 yield kind, tagname, pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
464 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
465 elif kind is START_NS: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
466 prefix, uri = data |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
467 if uri not in namespaces: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
468 prefix = prefixes.get(uri, [prefix])[-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
469 if not prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
470 _push_ns_attr((u'xmlns', uri)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
471 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
472 _push_ns_attr((u'xmlns:%s' % prefix, uri)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
473 _push_ns(prefix, uri) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
474 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
475 elif kind is END_NS: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
476 if data in prefixes: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
477 uris = prefixes.get(data) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
478 uri = uris.pop() |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
479 if not uris: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
480 del prefixes[data] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
481 if uri not in uris or uri != uris[-1]: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
482 uri_prefixes = namespaces[uri] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
483 uri_prefixes.pop() |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
484 if not uri_prefixes: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
485 del namespaces[uri] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
486 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
487 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
488 yield kind, data, pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
489 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
490 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
491 class NamespaceStripper(object): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
492 r"""Stream filter that removes all namespace information from a stream, and |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
493 optionally strips out all tags not in a given namespace. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
494 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
495 @param namespace: the URI of the namespace that should not be stripped. If |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
496 not set, only elements with no namespace are included in the output. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
497 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
498 >>> from genshi.input import XML |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
499 >>> xml = XML('''<doc xmlns="NS1" xmlns:two="NS2"> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
500 ... <two:item/> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
501 ... </doc>''') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
502 >>> for kind, data, pos in NamespaceStripper(Namespace('NS1'))(xml): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
503 ... print kind, repr(data) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
504 START (u'doc', Attrs()) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
505 TEXT u'\n ' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
506 TEXT u'\n' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
507 END u'doc' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
508 """ |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
509 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
510 def __init__(self, namespace=None): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
511 if namespace is not None: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
512 self.namespace = Namespace(namespace) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
513 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
514 self.namespace = {} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
515 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
516 def __call__(self, stream): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
517 namespace = self.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
518 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
519 for kind, data, pos in stream: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
520 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
521 if kind is START or kind is EMPTY: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
522 tag, attrs = data |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
523 if tag.namespace and tag not in namespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
524 continue |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
525 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
526 new_attrs = [] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
527 for attr, value in attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
528 if not attr.namespace or attr in namespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
529 new_attrs.append((attr, value)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
530 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
531 data = tag.localname, Attrs(new_attrs) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
532 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
533 elif kind is END: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
534 if data.namespace and data not in namespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
535 continue |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
536 data = data.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
537 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
538 elif kind is START_NS or kind is END_NS: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
539 continue |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
540 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
541 yield kind, data, pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
542 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
543 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
544 class WhitespaceFilter(object): |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
545 """A filter that removes extraneous ignorable white space from the |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
546 stream. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
547 """ |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
548 |
305 | 549 def __init__(self, preserve=None, noescape=None): |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
550 """Initialize the filter. |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
551 |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
552 @param preserve: a set or sequence of tag names for which white-space |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
553 should be preserved |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
554 @param noescape: a set or sequence of tag names for which text content |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
555 should not be escaped |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
556 |
346
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
557 The `noescape` set is expected to refer to elements that cannot contain |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
558 further child elements (such as <style> or <script> in HTML documents). |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
559 """ |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
560 if preserve is None: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
561 preserve = [] |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
562 self.preserve = frozenset(preserve) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
563 if noescape is None: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
564 noescape = [] |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
565 self.noescape = frozenset(noescape) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
566 |
219 | 567 def __call__(self, stream, ctxt=None, space=XML_NAMESPACE['space'], |
568 trim_trailing_space=re.compile('[ \t]+(?=\n)').sub, | |
569 collapse_lines=re.compile('\n{2,}').sub): | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
570 mjoin = Markup('').join |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
571 preserve_elems = self.preserve |
346
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
572 preserve = 0 |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
573 noescape_elems = self.noescape |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
574 noescape = False |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
575 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
576 textbuf = [] |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
577 push_text = textbuf.append |
136 | 578 pop_text = textbuf.pop |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
579 for kind, data, pos in chain(stream, [(None, None, None)]): |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
580 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
581 if kind is TEXT: |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
582 if noescape: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
583 data = Markup(data) |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
584 push_text(data) |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
585 else: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
586 if textbuf: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
587 if len(textbuf) > 1: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
588 text = mjoin(textbuf, escape_quotes=False) |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
589 del textbuf[:] |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
590 else: |
136 | 591 text = escape(pop_text(), quotes=False) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
592 if not preserve: |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
593 text = collapse_lines('\n', trim_trailing_space('', text)) |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
594 yield TEXT, Markup(text), pos |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
595 |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
596 if kind is START: |
346
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
597 tag, attrs = data |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
598 if preserve or (tag in preserve_elems or |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
599 attrs.get(space) == 'preserve'): |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
600 preserve += 1 |
219 | 601 if not noescape and tag in noescape_elems: |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
602 noescape = True |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
603 |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
604 elif kind is END: |
346
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
605 noescape = False |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
606 if preserve: |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
607 preserve -= 1 |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
608 |
305 | 609 elif kind is START_CDATA: |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
610 noescape = True |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
611 |
305 | 612 elif kind is END_CDATA: |
143
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
613 noescape = False |
3d4c214c979a
CDATA sections in XML input now appear as CDATA sections in the output. This should address the problem with escaping the contents of `<style>` and `<script>` elements, which would only get interpreted correctly if the output was served as `application/xhtml+xml`. Closes #24.
cmlenz
parents:
141
diff
changeset
|
614 |
136 | 615 if kind: |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
616 yield kind, data, pos |