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
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
|
"""\
A library of useful helper classes to the SAX classes, for the
convenience of application and driver writers.
"""
import os, urlparse, urllib, types
import handler
import xmlreader
try:
_StringTypes = [types.StringType, types.UnicodeType]
except AttributeError:
_StringTypes = [types.StringType]
# See whether the xmlcharrefreplace error handler is
# supported
try:
from codecs import xmlcharrefreplace_errors
_error_handling = "xmlcharrefreplace"
del xmlcharrefreplace_errors
except ImportError:
_error_handling = "strict"
def __dict_replace(s, d):
"""Replace substrings of a string using a dictionary."""
for key, value in d.items():
s = s.replace(key, value)
return s
def escape(data, entities={}):
"""Escape &, <, and > in a string of data.
You can escape other strings of data by passing a dictionary as
the optional entities parameter. The keys and values must all be
strings; each key will be replaced with its corresponding value.
"""
# must do ampersand first
data = data.replace("&", "&")
data = data.replace(">", ">")
data = data.replace("<", "<")
if entities:
data = __dict_replace(data, entities)
return data
def unescape(data, entities={}):
"""Unescape &, <, and > in a string of data.
You can unescape other strings of data by passing a dictionary as
the optional entities parameter. The keys and values must all be
strings; each key will be replaced with its corresponding value.
"""
data = data.replace("<", "<")
data = data.replace(">", ">")
if entities:
data = __dict_replace(data, entities)
# must do ampersand last
return data.replace("&", "&")
def quoteattr(data, entities={}):
"""Escape and quote an attribute value.
Escape &, <, and > in a string of data, then quote it for use as
an attribute value. The \" character will be escaped as well, if
necessary.
You can escape other strings of data by passing a dictionary as
the optional entities parameter. The keys and values must all be
strings; each key will be replaced with its corresponding value.
"""
data = escape(data, entities)
if '"' in data:
if "'" in data:
data = '"%s"' % data.replace('"', """)
else:
data = "'%s'" % data
else:
data = '"%s"' % data
return data
class XMLGenerator(handler.ContentHandler):
def __init__(self, out=None, encoding="iso-8859-1"):
if out is None:
import sys
out = sys.stdout
handler.ContentHandler.__init__(self)
self._out = out
self._ns_contexts = [{}] # contains uri -> prefix dicts
self._current_context = self._ns_contexts[-1]
self._undeclared_ns_maps = []
self._encoding = encoding
def _write(self, text):
if isinstance(text, str):
self._out.write(text)
else:
self._out.write(text.encode(self._encoding, _error_handling))
# ContentHandler methods
def startDocument(self):
self._write('<?xml version="1.0" encoding="%s"?>\n' %
self._encoding)
def startPrefixMapping(self, prefix, uri):
self._ns_contexts.append(self._current_context.copy())
self._current_context[uri] = prefix
self._undeclared_ns_maps.append((prefix, uri))
def endPrefixMapping(self, prefix):
self._current_context = self._ns_contexts[-1]
del self._ns_contexts[-1]
def startElement(self, name, attrs):
self._write('<' + name)
for (name, value) in attrs.items():
self._write(' %s=%s' % (name, quoteattr(value)))
self._write('>')
def endElement(self, name):
self._write('</%s>' % name)
def startElementNS(self, name, qname, attrs):
if name[0] is None:
# if the name was not namespace-scoped, use the unqualified part
name = name[1]
else:
# else try to restore the original prefix from the namespace
name = self._current_context[name[0]] + ":" + name[1]
self._write('<' + name)
for pair in self._undeclared_ns_maps:
self._write(' xmlns:%s="%s"' % pair)
self._undeclared_ns_maps = []
for (name, value) in attrs.items():
name = self._current_context[name[0]] + ":" + name[1]
self._write(' %s=%s' % (name, quoteattr(value)))
self._write('>')
def endElementNS(self, name, qname):
if name[0] is None:
name = name[1]
else:
name = self._current_context[name[0]] + ":" + name[1]
self._write('</%s>' % name)
def characters(self, content):
self._write(escape(content))
def ignorableWhitespace(self, content):
self._write(content)
def processingInstruction(self, target, data):
self._write('<?%s %s?>' % (target, data))
class XMLFilterBase(xmlreader.XMLReader):
"""This class is designed to sit between an XMLReader and the
client application's event handlers. By default, it does nothing
but pass requests up to the reader and events on to the handlers
unmodified, but subclasses can override specific methods to modify
the event stream or the configuration requests as they pass
through."""
def __init__(self, parent = None):
xmlreader.XMLReader.__init__(self)
self._parent = parent
# ErrorHandler methods
def error(self, exception):
self._err_handler.error(exception)
def fatalError(self, exception):
self._err_handler.fatalError(exception)
def warning(self, exception):
self._err_handler.warning(exception)
# ContentHandler methods
def setDocumentLocator(self, locator):
self._cont_handler.setDocumentLocator(locator)
def startDocument(self):
self._cont_handler.startDocument()
def endDocument(self):
self._cont_handler.endDocument()
def startPrefixMapping(self, prefix, uri):
self._cont_handler.startPrefixMapping(prefix, uri)
def endPrefixMapping(self, prefix):
self._cont_handler.endPrefixMapping(prefix)
def startElement(self, name, attrs):
self._cont_handler.startElement(name, attrs)
def endElement(self, name):
self._cont_handler.endElement(name)
def startElementNS(self, name, qname, attrs):
self._cont_handler.startElementNS(name, qname, attrs)
def endElementNS(self, name, qname):
self._cont_handler.endElementNS(name, qname)
def characters(self, content):
self._cont_handler.characters(content)
def ignorableWhitespace(self, chars):
self._cont_handler.ignorableWhitespace(chars)
def processingInstruction(self, target, data):
self._cont_handler.processingInstruction(target, data)
def skippedEntity(self, name):
self._cont_handler.skippedEntity(name)
# DTDHandler methods
def notationDecl(self, name, publicId, systemId):
self._dtd_handler.notationDecl(name, publicId, systemId)
def unparsedEntityDecl(self, name, publicId, systemId, ndata):
self._dtd_handler.unparsedEntityDecl(name, publicId, systemId, ndata)
# EntityResolver methods
def resolveEntity(self, publicId, systemId):
self._ent_handler.resolveEntity(publicId, systemId)
# XMLReader methods
def parse(self, source):
self._parent.setContentHandler(self)
self._parent.setErrorHandler(self)
self._parent.setEntityResolver(self)
self._parent.setDTDHandler(self)
self._parent.parse(source)
def setLocale(self, locale):
self._parent.setLocale(locale)
def getFeature(self, name):
return self._parent.getFeature(name)
def setFeature(self, name, state):
self._parent.setFeature(name, state)
def getProperty(self, name):
return self._parent.getProperty(name)
def setProperty(self, name, value):
self._parent.setProperty(name, value)
# XMLFilter methods
def getParent(self):
return self._parent
def setParent(self, parent):
self._parent = parent
# --- Utility functions
def prepare_input_source(source, base = ""):
"""This function takes an InputSource and an optional base URL and
returns a fully resolved InputSource object ready for reading."""
if type(source) in _StringTypes:
source = xmlreader.InputSource(source)
elif hasattr(source, "read"):
f = source
source = xmlreader.InputSource()
source.setByteStream(f)
if hasattr(f, "name"):
source.setSystemId(f.name)
if source.getByteStream() is None:
sysid = source.getSystemId()
if os.path.isfile(sysid):
basehead = os.path.split(os.path.normpath(base))[0]
source.setSystemId(os.path.join(basehead, sysid))
f = open(sysid, "rb")
else:
source.setSystemId(urlparse.urljoin(base, sysid))
f = urllib.urlopen(source.getSystemId())
source.setByteStream(f)
return source
|