Mercurial > genshi > mirror
annotate genshi/output.py @ 448:1154f2aadb6c trunk
Add support for HTML5 doctype.
author | cmlenz |
---|---|
date | Fri, 13 Apr 2007 11:54:02 +0000 |
parents | 821fc97d3c0a |
children | 75425671b437 |
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'] |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
31 __docformat__ = 'restructuredtext en' |
1 | 32 |
33 | |
85 | 34 class DocType(object): |
35 """Defines a number of commonly used DOCTYPE declarations as constants.""" | |
36 | |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
37 HTML_STRICT = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
38 'html', '-//W3C//DTD HTML 4.01//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
39 'http://www.w3.org/TR/html4/strict.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
40 ) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
41 HTML_TRANSITIONAL = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
42 'html', '-//W3C//DTD HTML 4.01 Transitional//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
43 'http://www.w3.org/TR/html4/loose.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
44 ) |
85 | 45 HTML = HTML_STRICT |
46 | |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
47 XHTML_STRICT = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
48 'html', '-//W3C//DTD XHTML 1.0 Strict//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
49 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
50 ) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
51 XHTML_TRANSITIONAL = ( |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
52 'html', '-//W3C//DTD XHTML 1.0 Transitional//EN', |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
53 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
54 ) |
85 | 55 XHTML = XHTML_STRICT |
56 | |
448 | 57 HTML5 = ('html', None, None) |
58 | |
85 | 59 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
60 class XMLSerializer(object): |
1 | 61 """Produces XML text from an event stream. |
62 | |
230 | 63 >>> from genshi.builder import tag |
20 | 64 >>> 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
|
65 >>> print ''.join(XMLSerializer()(elem.generate())) |
1 | 66 <div><a href="foo"/><br/><hr noshade="True"/></div> |
67 """ | |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
68 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
69 _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
|
70 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
71 def __init__(self, doctype=None, strip_whitespace=True, |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
72 namespace_prefixes=None): |
85 | 73 """Initialize the XML serializer. |
74 | |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
75 :param doctype: a ``(name, pubid, sysid)`` tuple that represents the |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
76 DOCTYPE declaration that should be included at the top |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
77 of the generated output |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
78 :param strip_whitespace: whether extraneous whitespace should be |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
79 stripped from the output |
85 | 80 """ |
81 self.preamble = [] | |
82 if doctype: | |
83 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
|
84 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
|
85 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
|
86 self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
87 self.filters.append(NamespaceFlattener(prefixes=namespace_prefixes)) |
1 | 88 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
89 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
|
90 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
|
91 in_cdata = False |
1 | 92 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
93 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
|
94 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
|
95 stream = filter_(stream) |
1 | 96 for kind, data, pos in stream: |
97 | |
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
|
98 if kind is START or kind is EMPTY: |
1 | 99 tag, attrib = data |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
100 buf = ['<', tag] |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
101 for attr, value in attrib: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
102 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
|
103 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
|
104 yield Markup(u''.join(buf)) |
1 | 105 |
69 | 106 elif kind is END: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
107 yield Markup('</%s>' % data) |
1 | 108 |
69 | 109 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
|
110 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
|
111 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
|
112 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
|
113 yield escape(data, quotes=False) |
1 | 114 |
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
|
115 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
|
116 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
|
117 |
136 | 118 elif kind is DOCTYPE and not have_doctype: |
119 name, pubid, sysid = data | |
120 buf = ['<!DOCTYPE %s'] | |
121 if pubid: | |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
122 buf.append(' PUBLIC "%s"') |
136 | 123 elif sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
124 buf.append(' SYSTEM') |
136 | 125 if sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
126 buf.append(' "%s"') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
127 buf.append('>\n') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
128 yield Markup(u''.join(buf), *filter(None, data)) |
136 | 129 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
|
130 |
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
|
131 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
|
132 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
|
133 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
|
134 |
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 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
|
136 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
|
137 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
|
138 |
105
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
139 elif kind is PI: |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
140 yield Markup('<?%s %s?>' % data) |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
141 |
1 | 142 |
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
|
143 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
|
144 """Produces XHTML text from an event stream. |
1 | 145 |
230 | 146 >>> from genshi.builder import tag |
20 | 147 >>> 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
|
148 >>> 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
|
149 <div><a href="foo"></a><br /><hr noshade="noshade" /></div> |
1 | 150 """ |
151 | |
152 _EMPTY_ELEMS = frozenset(['area', 'base', 'basefont', 'br', 'col', 'frame', | |
153 'hr', 'img', 'input', 'isindex', 'link', 'meta', | |
154 'param']) | |
155 _BOOLEAN_ATTRS = frozenset(['selected', 'checked', 'compact', 'declare', | |
156 'defer', 'disabled', 'ismap', 'multiple', | |
157 '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
|
158 _PRESERVE_SPACE = frozenset([ |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
159 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
|
160 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
|
161 ]) |
1 | 162 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
163 def __init__(self, doctype=None, strip_whitespace=True, |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
164 namespace_prefixes=None): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
165 super(XHTMLSerializer, self).__init__(doctype, False) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
166 self.filters = [EmptyTagFilter()] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
167 if strip_whitespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
168 self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
169 namespace_prefixes = namespace_prefixes or {} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
170 namespace_prefixes['http://www.w3.org/1999/xhtml'] = '' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
171 self.filters.append(NamespaceFlattener(prefixes=namespace_prefixes)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
172 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
173 def __call__(self, stream): |
136 | 174 boolean_attrs = self._BOOLEAN_ATTRS |
175 empty_elems = self._EMPTY_ELEMS | |
85 | 176 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
|
177 in_cdata = False |
1 | 178 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
179 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
|
180 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
|
181 stream = filter_(stream) |
1 | 182 for kind, data, pos in stream: |
183 | |
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
|
184 if kind is START or kind is EMPTY: |
1 | 185 tag, attrib = data |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
186 buf = ['<', tag] |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
187 for attr, value in attrib: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
188 if attr in boolean_attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
189 value = attr |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
190 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
|
191 if kind is EMPTY: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
192 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
|
193 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
|
194 else: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
195 buf.append('></%s>' % tag) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
196 else: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
197 buf.append('>') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
198 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
|
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 END: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
201 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
|
202 |
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
|
203 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
|
204 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
|
205 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
|
206 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
|
207 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
|
208 |
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
|
209 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
|
210 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
|
211 |
136 | 212 elif kind is DOCTYPE and not have_doctype: |
213 name, pubid, sysid = data | |
214 buf = ['<!DOCTYPE %s'] | |
215 if pubid: | |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
216 buf.append(' PUBLIC "%s"') |
136 | 217 elif sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
218 buf.append(' SYSTEM') |
136 | 219 if sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
220 buf.append(' "%s"') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
221 buf.append('>\n') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
222 yield Markup(u''.join(buf), *filter(None, data)) |
136 | 223 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
|
224 |
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
|
225 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
|
226 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
|
227 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
|
228 |
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 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
|
230 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
|
231 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
|
232 |
105
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
233 elif kind is PI: |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
234 yield Markup('<?%s %s?>' % data) |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
235 |
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
|
236 |
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
|
237 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
|
238 """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
|
239 |
230 | 240 >>> 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
|
241 >>> 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
|
242 >>> 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
|
243 <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
|
244 """ |
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
|
245 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
246 _NOESCAPE_ELEMS = frozenset([ |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
247 QName('script'), QName('http://www.w3.org/1999/xhtml}script'), |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
248 QName('style'), QName('http://www.w3.org/1999/xhtml}style') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
249 ]) |
141
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 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
|
252 """Initialize the HTML serializer. |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
253 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
254 :param doctype: a ``(name, pubid, sysid)`` tuple that represents the |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
255 DOCTYPE declaration that should be included at the top |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
256 of the generated output |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
257 :param strip_whitespace: whether extraneous whitespace should be |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
258 stripped from the output |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
259 """ |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
260 super(HTMLSerializer, self).__init__(doctype, False) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
261 self.filters = [EmptyTagFilter()] |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
262 if strip_whitespace: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
263 self.filters.append(WhitespaceFilter(self._PRESERVE_SPACE, |
305 | 264 self._NOESCAPE_ELEMS)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
265 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
|
266 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
267 def __call__(self, stream): |
136 | 268 boolean_attrs = self._BOOLEAN_ATTRS |
269 empty_elems = self._EMPTY_ELEMS | |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
270 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
|
271 have_doctype = False |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
272 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
|
273 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
274 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
|
275 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
|
276 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
|
277 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
|
278 |
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
|
279 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
|
280 tag, attrib = data |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
281 buf = ['<', tag] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
282 for attr, value in attrib: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
283 if attr in boolean_attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
284 if value: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
285 buf += [' ', attr] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
286 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
287 buf += [' ', attr, '="', escape(value), '"'] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
288 buf.append('>') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
289 if kind is EMPTY: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
290 if tag not in empty_elems: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
291 buf.append('</%s>' % tag) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
292 yield Markup(u''.join(buf)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
293 if tag in noescape_elems: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
294 noescape = True |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
295 |
69 | 296 elif kind is END: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
297 yield Markup('</%s>' % data) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
298 noescape = False |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
299 |
69 | 300 elif kind is TEXT: |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
301 if noescape: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
302 yield data |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
303 else: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
304 yield escape(data, quotes=False) |
1 | 305 |
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
|
306 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
|
307 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
|
308 |
136 | 309 elif kind is DOCTYPE and not have_doctype: |
310 name, pubid, sysid = data | |
311 buf = ['<!DOCTYPE %s'] | |
312 if pubid: | |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
313 buf.append(' PUBLIC "%s"') |
136 | 314 elif sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
315 buf.append(' SYSTEM') |
136 | 316 if sysid: |
397
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
317 buf.append(' "%s"') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
318 buf.append('>\n') |
31742fe6d47e
* Moved some utility functions from `genshi.core` to `genshi.util` (backwards compatibility preserved via imports)
cmlenz
parents:
346
diff
changeset
|
319 yield Markup(u''.join(buf), *filter(None, data)) |
136 | 320 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
|
321 |
105
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
322 elif kind is PI: |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
323 yield Markup('<?%s %s?>' % data) |
71f3db26eecb
Include processing instructions in serialized streams.
cmlenz
parents:
96
diff
changeset
|
324 |
1 | 325 |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
326 class TextSerializer(object): |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
327 """Produces plain text from an event stream. |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
328 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
329 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
|
330 special XML characters are not escaped: |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
331 |
230 | 332 >>> from genshi.builder import tag |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
333 >>> 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
|
334 >>> print elem |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
335 <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
|
336 >>> print ''.join(TextSerializer()(elem.generate())) |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
337 <Hello!> |
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 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
|
340 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
|
341 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
342 >>> 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
|
343 >>> print elem |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
344 <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
|
345 >>> print ''.join(TextSerializer()(elem.generate())) |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
346 Hello! |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
347 """ |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
348 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
349 def __call__(self, stream): |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
350 for event in stream: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
351 if event[0] is TEXT: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
352 data = event[1] |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
353 if type(data) is Markup: |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
354 data = data.striptags().stripentities() |
201
c5e0a1c86173
The `TextSerializer` should produce `unicode` objects, not `Markup` objects.
cmlenz
parents:
200
diff
changeset
|
355 yield unicode(data) |
200
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
356 |
5861f4446c26
Add serialization to plain text, based on cboos' patch. Closes #41.
cmlenz
parents:
178
diff
changeset
|
357 |
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
|
358 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
|
359 """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
|
360 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
|
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 |
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 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
|
364 |
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 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
|
366 prev = (None, None, None) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
367 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
|
368 if prev[0] is START: |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
369 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
|
370 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
|
371 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
|
372 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
|
373 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
|
374 yield prev |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
375 if ev[0] is not START: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
376 yield ev |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
377 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
|
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 |
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
|
380 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
|
381 |
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
|
382 |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
383 class NamespaceFlattener(object): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
384 r"""Output stream filter that removes namespace information from the stream, |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
385 instead adding namespace attributes and prefixes as needed. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
386 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
387 :param prefixes: optional mapping of namespace URIs to prefixes |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
388 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
389 >>> from genshi.input import XML |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
390 >>> xml = XML('''<doc xmlns="NS1" xmlns:two="NS2"> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
391 ... <two:item/> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
392 ... </doc>''') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
393 >>> for kind, data, pos in NamespaceFlattener()(xml): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
394 ... print kind, repr(data) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
395 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
|
396 TEXT u'\n ' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
397 START (u'two:item', Attrs()) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
398 END u'two:item' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
399 TEXT u'\n' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
400 END u'doc' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
401 """ |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
402 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
403 def __init__(self, prefixes=None): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
404 self.prefixes = {XML_NAMESPACE.uri: 'xml'} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
405 if prefixes is not None: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
406 self.prefixes.update(prefixes) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
407 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
408 def __call__(self, stream): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
409 prefixes = dict([(v, [k]) for k, v in self.prefixes.items()]) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
410 namespaces = {XML_NAMESPACE.uri: ['xml']} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
411 def _push_ns(prefix, uri): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
412 namespaces.setdefault(uri, []).append(prefix) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
413 prefixes.setdefault(prefix, []).append(uri) |
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 ns_attrs = [] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
416 _push_ns_attr = ns_attrs.append |
437 | 417 def _make_ns_attr(prefix, uri): |
418 return u'xmlns%s' % (prefix and ':%s' % prefix or ''), uri | |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
419 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
420 def _gen_prefix(): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
421 val = 0 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
422 while 1: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
423 val += 1 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
424 yield 'ns%d' % val |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
425 _gen_prefix = _gen_prefix().next |
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 for kind, data, pos in stream: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
428 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
429 if kind is START or kind is EMPTY: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
430 tag, attrs = data |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
431 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
432 tagname = tag.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
433 tagns = tag.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
434 if tagns: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
435 if tagns in namespaces: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
436 prefix = namespaces[tagns][-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
437 if prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
438 tagname = u'%s:%s' % (prefix, tagname) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
439 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
440 _push_ns_attr((u'xmlns', tagns)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
441 _push_ns('', tagns) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
442 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
443 new_attrs = [] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
444 for attr, value in attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
445 attrname = attr.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
446 attrns = attr.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
447 if attrns: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
448 if attrns not in namespaces: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
449 prefix = _gen_prefix() |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
450 _push_ns(prefix, attrns) |
412
bd51adc20a67
Actually write xmlns declaratons for generated attribute namespace prefixes.
cmlenz
parents:
410
diff
changeset
|
451 _push_ns_attr(('xmlns:%s' % prefix, attrns)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
452 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
453 prefix = namespaces[attrns][-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
454 if prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
455 attrname = u'%s:%s' % (prefix, attrname) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
456 new_attrs.append((attrname, value)) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
457 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
458 yield kind, (tagname, Attrs(ns_attrs + new_attrs)), pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
459 del ns_attrs[:] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
460 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
461 elif kind is END: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
462 tagname = data.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
463 tagns = data.namespace |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
464 if tagns: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
465 prefix = namespaces[tagns][-1] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
466 if prefix: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
467 tagname = u'%s:%s' % (prefix, tagname) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
468 yield kind, tagname, pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
469 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
470 elif kind is START_NS: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
471 prefix, uri = data |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
472 if uri not in namespaces: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
473 prefix = prefixes.get(uri, [prefix])[-1] |
437 | 474 _push_ns_attr(_make_ns_attr(prefix, uri)) |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
475 _push_ns(prefix, uri) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
476 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
477 elif kind is END_NS: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
478 if data in prefixes: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
479 uris = prefixes.get(data) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
480 uri = uris.pop() |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
481 if not uris: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
482 del prefixes[data] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
483 if uri not in uris or uri != uris[-1]: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
484 uri_prefixes = namespaces[uri] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
485 uri_prefixes.pop() |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
486 if not uri_prefixes: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
487 del namespaces[uri] |
437 | 488 if ns_attrs: |
489 attr = _make_ns_attr(data, uri) | |
490 if attr in ns_attrs: | |
491 ns_attrs.remove(attr) | |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
492 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
493 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
494 yield kind, data, pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
495 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
496 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
497 class NamespaceStripper(object): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
498 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
|
499 optionally strips out all tags not in a given namespace. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
500 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
501 :param namespace: the URI of the namespace that should not be stripped. If |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
502 not set, only elements with no namespace are included in |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
503 the output. |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
504 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
505 >>> from genshi.input import XML |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
506 >>> xml = XML('''<doc xmlns="NS1" xmlns:two="NS2"> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
507 ... <two:item/> |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
508 ... </doc>''') |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
509 >>> for kind, data, pos in NamespaceStripper(Namespace('NS1'))(xml): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
510 ... print kind, repr(data) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
511 START (u'doc', Attrs()) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
512 TEXT u'\n ' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
513 TEXT u'\n' |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
514 END u'doc' |
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 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
517 def __init__(self, namespace=None): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
518 if namespace is not None: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
519 self.namespace = Namespace(namespace) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
520 else: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
521 self.namespace = {} |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
522 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
523 def __call__(self, stream): |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
524 namespace = self.namespace |
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 for kind, data, pos in stream: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
527 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
528 if kind is START or kind is EMPTY: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
529 tag, attrs = data |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
530 if tag.namespace and tag not in namespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
531 continue |
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 new_attrs = [] |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
534 for attr, value in attrs: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
535 if not attr.namespace or attr in namespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
536 new_attrs.append((attr, value)) |
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 data = tag.localname, Attrs(new_attrs) |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
539 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
540 elif kind is END: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
541 if data.namespace and data not in namespace: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
542 continue |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
543 data = data.localname |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
544 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
545 elif kind is START_NS or kind is END_NS: |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
546 continue |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
547 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
548 yield kind, data, pos |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
549 |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
550 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
551 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
|
552 """A filter that removes extraneous ignorable white space from the |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
553 stream. |
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
554 """ |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
555 |
305 | 556 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
|
557 """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
|
558 |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
559 :param preserve: a set or sequence of tag names for which white-space |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
560 should be preserved |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
561 :param noescape: a set or sequence of tag names for which text content |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
562 should not be escaped |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
563 |
346
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
564 The `noescape` set is expected to refer to elements that cannot contain |
425
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
565 further child elements (such as ``<style>`` or ``<script>`` in HTML |
073640758a42
Try to use proper reStructuredText for docstrings throughout.
cmlenz
parents:
412
diff
changeset
|
566 documents). |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
567 """ |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
568 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
|
569 preserve = [] |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
570 self.preserve = frozenset(preserve) |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
571 if noescape is None: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
572 noescape = [] |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
573 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
|
574 |
219 | 575 def __call__(self, stream, ctxt=None, space=XML_NAMESPACE['space'], |
576 trim_trailing_space=re.compile('[ \t]+(?=\n)').sub, | |
577 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
|
578 mjoin = Markup('').join |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
579 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
|
580 preserve = 0 |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
581 noescape_elems = self.noescape |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
582 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
|
583 |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
584 textbuf = [] |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
585 push_text = textbuf.append |
136 | 586 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
|
587 for kind, data, pos in chain(stream, [(None, None, None)]): |
410
d14d89995c29
Improve the handling of namespaces in serialization.
cmlenz
parents:
408
diff
changeset
|
588 |
123
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
589 if kind is TEXT: |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
590 if noescape: |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
591 data = Markup(data) |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
592 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
|
593 else: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
594 if textbuf: |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
595 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
|
596 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
|
597 del textbuf[:] |
10279d2eeec9
Fix for #18: whitespace in space-sensitive elements such as `<pre>` and `<textarea>` is now preserved.
cmlenz
parents:
109
diff
changeset
|
598 else: |
136 | 599 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
|
600 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
|
601 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
|
602 yield TEXT, Markup(text), pos |
141
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 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
|
605 tag, attrs = data |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
606 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
|
607 attrs.get(space) == 'preserve'): |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
608 preserve += 1 |
219 | 609 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
|
610 noescape = True |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
611 |
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
612 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
|
613 noescape = False |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
614 if preserve: |
96882a191686
Whitespace was not getting preserved in HTML `<pre>` elements that contained other HTML elements.
cmlenz
parents:
345
diff
changeset
|
615 preserve -= 1 |
141
520a5b7dd6d2
* No escaping of `<script>` or `<style>` tags in HTML output (see #24)
cmlenz
parents:
140
diff
changeset
|
616 |
305 | 617 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
|
618 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
|
619 |
305 | 620 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
|
621 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
|
622 |
136 | 623 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
|
624 yield kind, data, pos |