This file is indexed.

/usr/lib/python2.7/dist-packages/wstools/c14n.py is in python-wstools 0.4.3-3.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
#! /usr/bin/env python
'''XML Canonicalization

Patches Applied to xml.dom.ext.c14n:
    http://sourceforge.net/projects/pyxml/

    [ 1444526 ] c14n.py: http://www.w3.org/TR/xml-exc-c14n/ fix
        -- includes [ 829905 ] c14n.py fix for bug #825115,
           Date Submitted: 2003-10-24 23:43
        -- include dependent namespace declarations declared in ancestor nodes
           (checking attributes and tags),
        -- handle InclusiveNamespaces PrefixList parameter

This module generates canonical XML of a document or element.
    http://www.w3.org/TR/2001/REC-xml-c14n-20010315
and includes a prototype of exclusive canonicalization
    http://www.w3.org/Signature/Drafts/xml-exc-c14n

Requires PyXML 0.7.0 or later.

Known issues if using Ft.Lib.pDomlette:
    1. Unicode
    2. does not white space normalize attributes of type NMTOKEN and ID?
    3. seems to be include "\n" after importing external entities?

Note, this version processes a DOM tree, and consequently it processes
namespace nodes as attributes, not from a node's namespace axis. This
permits simple document and element canonicalization without
XPath. When XPath is used, the XPath result node list is passed and used to
determine if the node is in the XPath result list, but little else.

Authors:
    "Joseph M. Reagle Jr." <reagle@w3.org>
    "Rich Salz" <rsalz@zolera.com>

$Date$ by $Author$
'''

_copyright = '''Copyright 2001, Zolera Systems Inc.  All Rights Reserved.
Copyright 2001, MIT. All Rights Reserved.

Distributed under the terms of:
  Python 2.0 License or later.
  http://www.python.org/2.0.1/license.html
or
  W3C Software License
  http://www.w3.org/Consortium/Legal/copyright-software-19980720
'''

import string
from xml.dom import Node
try:
    from xml.ns import XMLNS
except:
    class XMLNS:
        BASE = "http://www.w3.org/2000/xmlns/"
        XML = "http://www.w3.org/XML/1998/namespace"
try:
    import cStringIO
    StringIO = cStringIO
except ImportError:
    import StringIO

_attrs = lambda E: (E.attributes and E.attributes.values()) or []
_children = lambda E: E.childNodes or []
_IN_XML_NS = lambda n: n.name.startswith("xmlns")
_inclusive = lambda n: n.unsuppressedPrefixes is None


# Does a document/PI has lesser/greater document order than the
# first element?
_LesserElement, _Element, _GreaterElement = range(3)


def _sorter(n1, n2):
    '''_sorter(n1,n2) -> int
    Sorting predicate for non-NS attributes.'''

    i = cmp(n1.namespaceURI, n2.namespaceURI)
    if i:
        return i
    return cmp(n1.localName, n2.localName)


def _sorter_ns(n1, n2):
    '''_sorter_ns((n,v),(n,v)) -> int
    "(an empty namespace URI is lexicographically least)."'''

    if n1[0] == 'xmlns':
        return -1
    if n2[0] == 'xmlns':
        return 1
    return cmp(n1[0], n2[0])


def _utilized(n, node, other_attrs, unsuppressedPrefixes):
    '''_utilized(n, node, other_attrs, unsuppressedPrefixes) -> boolean
    Return true if that nodespace is utilized within the node'''
    if n.startswith('xmlns:'):
        n = n[6:]
    elif n.startswith('xmlns'):
        n = n[5:]
    if (n == "" and node.prefix in ["#default", None]) or \
        n == node.prefix or n in unsuppressedPrefixes:
            return 1
    for attr in other_attrs:
        if n == attr.prefix:
            return 1
    # For exclusive need to look at attributes
    if unsuppressedPrefixes is not None:
        for attr in _attrs(node):
            if n == attr.prefix:
                return 1

    return 0


def _inclusiveNamespacePrefixes(node, context, unsuppressedPrefixes):
    '''http://www.w3.org/TR/xml-exc-c14n/
    InclusiveNamespaces PrefixList parameter, which lists namespace prefixes that
    are handled in the manner described by the Canonical XML Recommendation'''
    inclusive = []
    if node.prefix:
        usedPrefixes = ['xmlns:%s' % node.prefix]
    else:
        usedPrefixes = ['xmlns']

    for a in _attrs(node):
        if a.nodeName.startswith('xmlns') or not a.prefix:
            continue
        usedPrefixes.append('xmlns:%s' % a.prefix)

    unused_namespace_dict = {}
    for attr in context:
        n = attr.nodeName
        if n in unsuppressedPrefixes:
            inclusive.append(attr)
        elif n.startswith('xmlns:') and n[6:] in unsuppressedPrefixes:
            inclusive.append(attr)
        elif n.startswith('xmlns') and n[5:] in unsuppressedPrefixes:
            inclusive.append(attr)
        elif attr.nodeName in usedPrefixes:
            inclusive.append(attr)
        elif n.startswith('xmlns:'):
            unused_namespace_dict[n] = attr.value

    return inclusive, unused_namespace_dict

#_in_subset = lambda subset, node: not subset or node in subset
_in_subset = lambda subset, node: subset is None or node in subset  # rich's tweak


class _implementation:
    '''Implementation class for C14N. This accompanies a node during it's
    processing and includes the parameters and processing state.'''

    # Handler for each node type; populated during module instantiation.
    handlers = {}

    def __init__(self, node, write, **kw):
        '''Create and run the implementation.'''
        self.write = write
        self.subset = kw.get('subset')
        self.comments = kw.get('comments', 0)
        self.unsuppressedPrefixes = kw.get('unsuppressedPrefixes')
        nsdict = kw.get('nsdict', {'xml': XMLNS.XML, 'xmlns': XMLNS.BASE})

        # Processing state.
        self.state = (nsdict, {'xml': ''}, {}, {})  # 0422

        if node.nodeType == Node.DOCUMENT_NODE:
            self._do_document(node)
        elif node.nodeType == Node.ELEMENT_NODE:
            self.documentOrder = _Element        # At document element
            if not _inclusive(self):
                inherited, unused = _inclusiveNamespacePrefixes(node, self._inherit_context(node),
                                self.unsuppressedPrefixes)
                self._do_element(node, inherited, unused=unused)
            else:
                inherited = self._inherit_context(node)
                self._do_element(node, inherited)
        elif node.nodeType == Node.DOCUMENT_TYPE_NODE:
            pass
        else:
            raise TypeError(str(node))

    def _inherit_context(self, node):
        '''_inherit_context(self, node) -> list
        Scan ancestors of attribute and namespace context.  Used only
        for single element node canonicalization, not for subset
        canonicalization.'''

        # Collect the initial list of xml:foo attributes.
        xmlattrs = filter(_IN_XML_NS, _attrs(node))

        # Walk up and get all xml:XXX attributes we inherit.
        inherited, parent = [], node.parentNode
        while parent and parent.nodeType == Node.ELEMENT_NODE:
            for a in filter(_IN_XML_NS, _attrs(parent)):
                n = a.localName
                if n not in xmlattrs:
                    xmlattrs.append(n)
                    inherited.append(a)
            parent = parent.parentNode
        return inherited

    def _do_document(self, node):
        '''_do_document(self, node) -> None
        Process a document node. documentOrder holds whether the document
        element has been encountered such that PIs/comments can be written
        as specified.'''

        self.documentOrder = _LesserElement
        for child in node.childNodes:
            if child.nodeType == Node.ELEMENT_NODE:
                self.documentOrder = _Element        # At document element
                self._do_element(child)
                self.documentOrder = _GreaterElement  # After document element
            elif child.nodeType == Node.PROCESSING_INSTRUCTION_NODE:
                self._do_pi(child)
            elif child.nodeType == Node.COMMENT_NODE:
                self._do_comment(child)
            elif child.nodeType == Node.DOCUMENT_TYPE_NODE:
                pass
            else:
                raise TypeError(str(child))
    handlers[Node.DOCUMENT_NODE] = _do_document

    def _do_text(self, node):
        '''_do_text(self, node) -> None
        Process a text or CDATA node.  Render various special characters
        as their C14N entity representations.'''
        if not _in_subset(self.subset, node):
            return
        s = string.replace(node.data, "&", "&amp;")
        s = string.replace(s, "<", "&lt;")
        s = string.replace(s, ">", "&gt;")
        s = string.replace(s, "\015", "&#xD;")
        if s:
            self.write(s)
    handlers[Node.TEXT_NODE] = _do_text
    handlers[Node.CDATA_SECTION_NODE] = _do_text

    def _do_pi(self, node):
        '''_do_pi(self, node) -> None
        Process a PI node. Render a leading or trailing #xA if the
        document order of the PI is greater or lesser (respectively)
        than the document element.
        '''
        if not _in_subset(self.subset, node):
            return
        W = self.write
        if self.documentOrder == _GreaterElement:
            W('\n')
        W('<?')
        W(node.nodeName)
        s = node.data
        if s:
            W(' ')
            W(s)
        W('?>')
        if self.documentOrder == _LesserElement:
            W('\n')
    handlers[Node.PROCESSING_INSTRUCTION_NODE] = _do_pi

    def _do_comment(self, node):
        '''_do_comment(self, node) -> None
        Process a comment node. Render a leading or trailing #xA if the
        document order of the comment is greater or lesser (respectively)
        than the document element.
        '''
        if not _in_subset(self.subset, node):
            return
        if self.comments:
            W = self.write
            if self.documentOrder == _GreaterElement:
                W('\n')
            W('<!--')
            W(node.data)
            W('-->')
            if self.documentOrder == _LesserElement:
                W('\n')
    handlers[Node.COMMENT_NODE] = _do_comment

    def _do_attr(self, n, value):
        ''''_do_attr(self, node) -> None
        Process an attribute.'''

        W = self.write
        W(' ')
        W(n)
        W('="')
        s = string.replace(value, "&", "&amp;")
        s = string.replace(s, "<", "&lt;")
        s = string.replace(s, '"', '&quot;')
        s = string.replace(s, '\011', '&#x9')
        s = string.replace(s, '\012', '&#xA')
        s = string.replace(s, '\015', '&#xD')
        W(s)
        W('"')

    def _do_element(self, node, initial_other_attrs=[], unused=None):
        '''_do_element(self, node, initial_other_attrs = [], unused = {}) -> None
        Process an element (and its children).'''

        # Get state (from the stack) make local copies.
        #   ns_parent -- NS declarations in parent
        #   ns_rendered -- NS nodes rendered by ancestors
        #        ns_local -- NS declarations relevant to this element
        #   xml_attrs -- Attributes in XML namespace from parent
        #       xml_attrs_local -- Local attributes in XML namespace.
        #   ns_unused_inherited -- not rendered namespaces, used for exclusive
        ns_parent, ns_rendered, xml_attrs = \
                self.state[0], self.state[1].copy(), self.state[2].copy()  # 0422

        ns_unused_inherited = unused
        if unused is None:
            ns_unused_inherited = self.state[3].copy()

        ns_local = ns_parent.copy()
        inclusive = _inclusive(self)
        xml_attrs_local = {}

        # Divide attributes into NS, XML, and others.
        other_attrs = []
        in_subset = _in_subset(self.subset, node)
        for a in initial_other_attrs + _attrs(node):
            if a.namespaceURI == XMLNS.BASE:
                n = a.nodeName
                if n == "xmlns:":
                    n = "xmlns"        # DOM bug workaround
                ns_local[n] = a.nodeValue
            elif a.namespaceURI == XMLNS.XML:
                if inclusive or (in_subset and _in_subset(self.subset, a)):  # 020925 Test to see if attribute node in subset
                    xml_attrs_local[a.nodeName] = a  # 0426
            else:
                if _in_subset(self.subset, a):  # 020925 Test to see if attribute node in subset
                    other_attrs.append(a)

#                # TODO: exclusive, might need to define xmlns:prefix here
#                if not inclusive and a.prefix is not None and not ns_rendered.has_key('xmlns:%s' %a.prefix):
#                    ns_local['xmlns:%s' %a.prefix] = ??

            #add local xml:foo attributes to ancestor's xml:foo attributes
            xml_attrs.update(xml_attrs_local)

        # Render the node
        W, name = self.write, None
        if in_subset:
            name = node.nodeName
            if not inclusive:
                if node.prefix is not None:
                    prefix = 'xmlns:%s' % node.prefix
                else:
                    prefix = 'xmlns'

                if prefix not in ns_rendered and prefix not in ns_local:
                    if not prefix in ns_unused_inherited:
                        raise RuntimeError('For exclusive c14n, unable to map prefix "%s" in %s' % (
                            prefix, node))

                    ns_local[prefix] = ns_unused_inherited[prefix]
                    del ns_unused_inherited[prefix]

            W('<')
            W(name)

            # Create list of NS attributes to render.
            ns_to_render = []
            for n, v in ns_local.items():

                # If default namespace is XMLNS.BASE or empty,
                # and if an ancestor was the same
                if n == "xmlns" and v in [XMLNS.BASE, ''] \
                    and ns_rendered.get('xmlns') in [XMLNS.BASE, '', None]:
                    continue

                # "omit namespace node with local name xml, which defines
                # the xml prefix, if its string value is
                # http://www.w3.org/XML/1998/namespace."
                if n in ["xmlns:xml", "xml"] \
                    and v in ['http://www.w3.org/XML/1998/namespace']:
                    continue

                # If not previously rendered
                # and it's inclusive  or utilized
                if (n, v) not in ns_rendered.items():
                    if inclusive or _utilized(n, node, other_attrs, self.unsuppressedPrefixes):
                        ns_to_render.append((n, v))
                    elif not inclusive:
                        ns_unused_inherited[n] = v

            # Sort and render the ns, marking what was rendered.
            ns_to_render.sort(_sorter_ns)
            for n, v in ns_to_render:
                self._do_attr(n, v)
                ns_rendered[n] = v  # 0417

            # If exclusive or the parent is in the subset, add the local xml attributes
            # Else, add all local and ancestor xml attributes
            # Sort and render the attributes.
            if not inclusive or _in_subset(self.subset, node.parentNode):  # 0426
                other_attrs.extend(xml_attrs_local.values())
            else:
                other_attrs.extend(xml_attrs.values())
            other_attrs.sort(_sorter)
            for a in other_attrs:
                self._do_attr(a.nodeName, a.value)
            W('>')

        # Push state, recurse, pop state.
        state, self.state = self.state, (ns_local, ns_rendered, xml_attrs, ns_unused_inherited)
        for c in _children(node):
            _implementation.handlers[c.nodeType](self, c)
        self.state = state

        if name:
            W('</%s>' % name)
    handlers[Node.ELEMENT_NODE] = _do_element


def Canonicalize(node, output=None, **kw):
    '''Canonicalize(node, output=None, **kw) -> UTF-8

    Canonicalize a DOM document/element node and all descendents.
    Return the text; if output is specified then output.write will
    be called to output the text and None will be returned
    Keyword parameters:
        nsdict: a dictionary of prefix:uri namespace entries
                assumed to exist in the surrounding context
        comments: keep comments if non-zero (default is 0)
        subset: Canonical XML subsetting resulting from XPath
                (default is [])
        unsuppressedPrefixes: do exclusive C14N, and this specifies the
                prefixes that should be inherited.
    '''
    if output:
        apply(_implementation, (node, output.write), kw)
    else:
        s = StringIO.StringIO()
        apply(_implementation, (node, s.write), kw)
        return s.getvalue()