1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
|
"""
module for generating and serializing xml and html structures
by using simple python objects.
(c) holger krekel, holger at merlinux eu. 2009
"""
import py
import sys, re
if sys.version_info >= (3,0):
def u(s):
return s
def unicode(x):
if hasattr(x, '__unicode__'):
return x.__unicode__()
return str(x)
else:
def u(s):
return unicode(s)
unicode = unicode
class NamespaceMetaclass(type):
def __getattr__(self, name):
if name[:1] == '_':
raise AttributeError(name)
if self == Namespace:
raise ValueError("Namespace class is abstract")
tagspec = self.__tagspec__
if tagspec is not None and name not in tagspec:
raise AttributeError(name)
classattr = {}
if self.__stickyname__:
classattr['xmlname'] = name
cls = type(name, (self.__tagclass__,), classattr)
setattr(self, name, cls)
return cls
class Tag(list):
class Attr(object):
def __init__(self, **kwargs):
self.__dict__.update(kwargs)
def __init__(self, *args, **kwargs):
super(Tag, self).__init__(args)
self.attr = self.Attr(**kwargs)
def __unicode__(self):
return self.unicode(indent=0)
__str__ = __unicode__
def unicode(self, indent=2):
l = []
SimpleUnicodeVisitor(l.append, indent).visit(self)
return u("").join(l)
def __repr__(self):
name = self.__class__.__name__
return "<%r tag object %d>" % (name, id(self))
Namespace = NamespaceMetaclass('Namespace', (object, ), {
'__tagspec__': None,
'__tagclass__': Tag,
'__stickyname__': False,
})
class HtmlTag(Tag):
def unicode(self, indent=2):
l = []
HtmlVisitor(l.append, indent, shortempty=False).visit(self)
return u("").join(l)
# exported plain html namespace
class html(Namespace):
__tagclass__ = HtmlTag
__stickyname__ = True
__tagspec__ = dict([(x,1) for x in (
'a,abbr,acronym,address,applet,area,b,bdo,big,blink,'
'blockquote,body,br,button,caption,center,cite,code,col,'
'colgroup,comment,dd,del,dfn,dir,div,dl,dt,em,embed,'
'fieldset,font,form,frameset,h1,h2,h3,h4,h5,h6,head,html,'
'i,iframe,img,input,ins,kbd,label,legend,li,link,listing,'
'map,marquee,menu,meta,multicol,nobr,noembed,noframes,'
'noscript,object,ol,optgroup,option,p,pre,q,s,script,'
'select,small,span,strike,strong,style,sub,sup,table,'
'tbody,td,textarea,tfoot,th,thead,title,tr,tt,u,ul,xmp,'
'base,basefont,frame,hr,isindex,param,samp,var'
).split(',') if x])
class Style(object):
def __init__(self, **kw):
for x, y in kw.items():
x = x.replace('_', '-')
setattr(self, x, y)
class raw(object):
"""just a box that can contain a unicode string that will be
included directly in the output"""
def __init__(self, uniobj):
self.uniobj = uniobj
class SimpleUnicodeVisitor(object):
""" recursive visitor to write unicode. """
def __init__(self, write, indent=0, curindent=0, shortempty=True):
self.write = write
self.cache = {}
self.visited = {} # for detection of recursion
self.indent = indent
self.curindent = curindent
self.parents = []
self.shortempty = shortempty # short empty tags or not
def visit(self, node):
""" dispatcher on node's class/bases name. """
cls = node.__class__
try:
visitmethod = self.cache[cls]
except KeyError:
for subclass in cls.__mro__:
visitmethod = getattr(self, subclass.__name__, None)
if visitmethod is not None:
break
else:
visitmethod = self.__object
self.cache[cls] = visitmethod
visitmethod(node)
# the default fallback handler is marked private
# to avoid clashes with the tag name object
def __object(self, obj):
#self.write(obj)
self.write(escape(unicode(obj)))
def raw(self, obj):
self.write(obj.uniobj)
def list(self, obj):
assert id(obj) not in self.visited
self.visited[id(obj)] = 1
for elem in obj:
self.visit(elem)
def Tag(self, tag):
assert id(tag) not in self.visited
try:
tag.parent = self.parents[-1]
except IndexError:
tag.parent = None
self.visited[id(tag)] = 1
tagname = getattr(tag, 'xmlname', tag.__class__.__name__)
if self.curindent and not self._isinline(tagname):
self.write("\n" + u(' ') * self.curindent)
if tag:
self.curindent += self.indent
self.write(u('<%s%s>') % (tagname, self.attributes(tag)))
self.parents.append(tag)
for x in tag:
self.visit(x)
self.parents.pop()
self.write(u('</%s>') % tagname)
self.curindent -= self.indent
else:
nameattr = tagname+self.attributes(tag)
if self._issingleton(tagname):
self.write(u('<%s/>') % (nameattr,))
else:
self.write(u('<%s></%s>') % (nameattr, tagname))
def attributes(self, tag):
# serialize attributes
attrlist = dir(tag.attr)
attrlist.sort()
l = []
for name in attrlist:
res = self.repr_attribute(tag.attr, name)
if res is not None:
l.append(res)
l.extend(self.getstyle(tag))
return u("").join(l)
def repr_attribute(self, attrs, name):
if name[:2] != '__':
value = getattr(attrs, name)
if name.endswith('_'):
name = name[:-1]
if isinstance(value, raw):
insert = value.uniobj
else:
insert = escape(unicode(value))
return ' %s="%s"' % (name, insert)
def getstyle(self, tag):
""" return attribute list suitable for styling. """
try:
styledict = tag.style.__dict__
except AttributeError:
return []
else:
stylelist = [x+': ' + y for x,y in styledict.items()]
return [u(' style="%s"') % u('; ').join(stylelist)]
def _issingleton(self, tagname):
"""can (and will) be overridden in subclasses"""
return self.shortempty
def _isinline(self, tagname):
"""can (and will) be overridden in subclasses"""
return False
class HtmlVisitor(SimpleUnicodeVisitor):
single = dict([(x, 1) for x in
('br,img,area,param,col,hr,meta,link,base,'
'input,frame').split(',')])
inline = dict([(x, 1) for x in
('a abbr acronym b basefont bdo big br cite code dfn em font '
'i img input kbd label q s samp select small span strike '
'strong sub sup textarea tt u var'.split(' '))])
def repr_attribute(self, attrs, name):
if name == 'class_':
value = getattr(attrs, name)
if value is None:
return
return super(HtmlVisitor, self).repr_attribute(attrs, name)
def _issingleton(self, tagname):
return tagname in self.single
def _isinline(self, tagname):
return tagname in self.inline
class _escape:
def __init__(self):
self.escape = {
u('"') : u('"'), u('<') : u('<'), u('>') : u('>'),
u('&') : u('&'), u("'") : u('''),
}
self.charef_rex = re.compile(u("|").join(self.escape.keys()))
def _replacer(self, match):
return self.escape[match.group(0)]
def __call__(self, ustring):
""" xml-escape the given unicode string. """
ustring = unicode(ustring)
return self.charef_rex.sub(self._replacer, ustring)
escape = _escape()
|