Class: XmlCanonicalizer

Inherits:
Object
  • Object
show all
Defined in:
lib/xmlcanonicalizer.rb

Overview

From the IBM DeveloperWorks website:

XML is careful to separate details of a file or other data source, bit-by-bit, from the abstract model of an XML document. This can be an inconvenience when comparing two XML documents for equality – either directly (for instance, as part of a test suite) or by comparing digital signatures for security purposes – to determine whether an XML document has been tampered with in some way. The W3C addresses this problem with the XML Canonicalization spec (c14n), which defines a standard form for an XML document that is guaranteed to provide proper bit-wise comparisons and thus consistent digital signatures.

Constant Summary collapse

BEFORE_DOC_ELEMENT = 
0
INSIDE_DOC_ELEMENT = 
1
AFTER_DOC_ELEMENT = 
2
NODE_TYPE_ATTRIBUTE = 
3
NODE_TYPE_WHITESPACE = 
4
NODE_TYPE_COMMENT = 
5
NODE_TYPE_PI = 
6
NODE_TYPE_TEXT = 
7

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(with_comments, excl_c14n) ⇒ XmlCanonicalizer

Returns a new instance of XmlCanonicalizer.



101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
 
# File 'lib/xmlcanonicalizer.rb', line 101

def initialize(with_comments, excl_c14n)
  @with_comments = with_comments
  @exclusive = excl_c14n
  @res = ""
  @state = BEFORE_DOC_ELEMENT
  @xnl = Array.new()
  @prevVisibleNamespacesStart = 0
  @prevVisibleNamespacesEnd = 0
  @visibleNamespaces = Array.new()
  @inclusive_namespaces = Array.new()
  @prefix_list = nil
  @rendered_prefixes = Array.new()
  @logger = Logger.new("xmlcanonicalizer.log")
  @logger.level = Logger::DEBUG
end

Instance Attribute Details

#logger ⇒ Object

Returns the value of attribute logger.



88
89
90
 
# File 'lib/xmlcanonicalizer.rb', line 88

def logger
  @logger
end

#prefix_list ⇒ Object

Returns the value of attribute prefix_list.



88
89
90
 
# File 'lib/xmlcanonicalizer.rb', line 88

def prefix_list
  @prefix_list
end

Instance Method Details

#add_inclusive_namespaces(prefix_list, element, visible_namespaces) ⇒ Object 



117
118
119
120
121
122
123
124
125
126
127
128
129
 
# File 'lib/xmlcanonicalizer.rb', line 117

def add_inclusive_namespaces(prefix_list, element, visible_namespaces)
  namespaces = element.attributes()
  namespaces.each_attribute{|ns|
    if (ns.prefix=="xmlns")
      if (prefix_list.include?(ns.local_name()))
        visible_namespaces.push(NamespaceNode.new("xmlns:"+ns.local_name(), ns.value()))
      end
    end
  }
  parent = element.parent()
  add_inclusive_namespaces(prefix_list, parent, visible_namespaces) if (parent)
  visible_namespaces
end

#canonicalize(document) ⇒ Object 



131
132
133
134
135
 
# File 'lib/xmlcanonicalizer.rb', line 131

def canonicalize(document)
  write_document_node(document)
  @logger.debug("\nCanonicalized result\n" + @res.to_s()) if @logger
  @res
end

#canonicalize_element(element, logging = true) ⇒ Object 



137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
 
# File 'lib/xmlcanonicalizer.rb', line 137

def canonicalize_element(element, logging = true)
  @logger.debug("Canonicalize element:\n" + element.to_s()) if @logger
  @inclusive_namespaces = add_inclusive_namespaces(@prefix_list, element, @inclusive_namespaces) if (@prefix_list)
  @preserve_document = element.document()
  tmp_parent = element.parent()
  body_string = remove_whitespace(element.to_s().gsub("\n","").gsub("\t","").gsub("\r",""))
  document = Document.new(body_string)
  tmp_parent.delete_element(element)
  element = tmp_parent.add_element(document.root())
  @preserve_element = element
  document = Document.new(element.to_s())
  ns = element.namespace(element.prefix())
  document.root().add_namespace(element.prefix(), ns)
  write_document_node(document)
  @logger.debug("Canonicalized result:\n" + @res.to_s()) if @logger
  @res
end

#is_namespace_decl(attribute) ⇒ Object 



374
375
376
377
378
 
# File 'lib/xmlcanonicalizer.rb', line 374

def is_namespace_decl(attribute)
  #return true if (attribute.name() == "xmlns")
  return true if (attribute.prefix().index("xmlns") == 0)
  return false
end

#is_namespace_node(namespace_uri) ⇒ Object 



301
302
303
 
# File 'lib/xmlcanonicalizer.rb', line 301

def is_namespace_node(namespace_uri)
  return (namespace_uri == "http://www.w3.org/2000/xmlns/")
end

#is_namespace_rendered(prefix, uri) ⇒ Object 



305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
 
# File 'lib/xmlcanonicalizer.rb', line 305

def is_namespace_rendered(prefix, uri)
  is_empty_ns = prefix == nil && uri == nil
  if (is_empty_ns)
    start = 0
  else
    start = @prevVisibleNamespacesStart
  end
  @visibleNamespaces.each{|ns|
    if (ns.prefix() == "xmlns:"+prefix.to_s() && ns.uri() == uri)
      return true
    end
  }
  return is_empty_ns
  #(@visibleNamespaces.size()-1).downto(start) {|i|
  #   ns = @visibleNamespaces[i]
  #	return true if (ns.prefix() == "xmlns:"+prefix.to_s() && ns.uri() == uri)
  #	#p = ns.prefix() if (ns.prefix().index("xmlns") == 0) 
  #	#return ns.uri() == uri if (p == prefix) 
  #}
  #return is_empty_ns
end

#is_node_visible(node) ⇒ Object 



327
328
329
330
331
332
333
 
# File 'lib/xmlcanonicalizer.rb', line 327

def is_node_visible(node)
  return true if (@xnl.size() == 0)
  @xnl.each{|element|
    return true if (element == node)
  }
  return false
end

#is_text_node(type) ⇒ Object 



380
381
382
383
 
# File 'lib/xmlcanonicalizer.rb', line 380

def is_text_node(type)
  return true if (type == NODE_TYPE_TEXT || type == NODE_TYPE_CDATA || type == NODE_TYPE_WHITESPACE)
  return false
end

#normalize_string(input, type) ⇒ Object 



335
336
337
338
 
# File 'lib/xmlcanonicalizer.rb', line 335

def normalize_string(input, type)
  sb = ""
  return input
end

#remove_whitespace(string) ⇒ Object 



385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
 
# File 'lib/xmlcanonicalizer.rb', line 385

def remove_whitespace(string)
  new_string = ""
  in_white = false
  string.each_byte{|b|
    #if (in_white && b == 32)
    #else
    if !(in_white && b == 32)
      new_string = new_string + b.chr()
    end
    if (b == 62) #>
      in_white = true
    end
    if (b == 60) #<
      in_white = false
    end
  }
  new_string
end

#white_text?(text) ⇒ Boolean

Returns:

  • (Boolean) 


369
370
371
372
 
# File 'lib/xmlcanonicalizer.rb', line 369

def white_text?(text)
  return true if ((text.strip() == "") || (text.strip() == nil))
  return false
end

#write_attribute_axis(node) ⇒ Object 



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
 
# File 'lib/xmlcanonicalizer.rb', line 264

def write_attribute_axis(node)
  list = Array.new()
  node.attributes().sort.each{|key, attr|
    list.push(attr) if (!is_namespace_node(attr.value()) && !is_namespace_decl(attr)) # && is_node_visible(
  }
  if (!@exclusive && node.parent() != nil && node.parent().parent() != nil)
    cur = node.parent()
    while (cur != nil)
      #next if (cur.attributes() == nil)
      cur.each_attribute{|attribute|
        next if (attribute.prefix() != "xml")
        next if (attribute.prefix().index("xmlns") == 0)
        next if (node.namespace(attribute.prefix()) == attribute.value())
        found = true
        list.each{|n|
          if (n.prefix() == "xml" && n.value() == attritbute.value())
            found = true
            break
          end
        }
        next if (found)
        list.push(attribute)
      }
    end
  end
  list.each{|attribute|
    if (attribute != nil)
      if (attribute.name() != "xmlns")
        @res = @res + " " + normalize_string(attribute.to_string(), NODE_TYPE_ATTRIBUTE).gsub("'",'"')
      end
      #	else
      #	@res = @res + " " + normalize_string(attribute.name()+'="'+attribute.to_s()+'"', NODE_TYPE_ATTRIBUTE).gsub("'",'"')
      #end
    end
  }
end

#write_document_node(document) ⇒ Object 



155
156
157
158
159
160
161
162
163
164
165
 
# File 'lib/xmlcanonicalizer.rb', line 155

def write_document_node(document)
  @state = BEFORE_DOC_ELEMENT
  if (document.class().to_s() == "REXML::Element")
    write_node(document)
  else
    document.each_child{|child|
      write_node(child)
    }
  end
  @res
end

#write_element_node(node, visible) ⇒ Object 



192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
 
# File 'lib/xmlcanonicalizer.rb', line 192

def write_element_node(node, visible)
  savedPrevVisibleNamespacesStart = @prevVisibleNamespacesStart
  savedPrevVisibleNamespacesEnd = @prevVisibleNamespacesEnd
  savedVisibleNamespacesSize = @visibleNamespaces.size()
  state = @state
  state = INSIDE_DOC_ELEMENT if (visible && state == BEFORE_DOC_ELEMENT)
  @res = @res + "<" + node.expanded_name() if (visible)
  write_namespace_axis(node, visible)
  write_attribute_axis(node)
  @res = @res + ">" if (visible)
  node.each_child{|child|
	 	write_node(child)
	}
  @res = @res + "</" +node.expanded_name() + ">" if (visible)
  @state = AFTER_DOC_ELEMENT if (visible && state == BEFORE_DOC_ELEMENT)
  @prevVisibleNamespacesStart = savedPrevVisibleNamespacesStart
  @prevVisibleNamespacesEnd = savedPrevVisibleNamespacesEnd
  @visibleNamespaces.slice!(savedVisibleNamespacesSize, @visibleNamespaces.size() - savedVisibleNamespacesSize) 		if (@visibleNamespaces.size() > savedVisibleNamespacesSize)
end

#write_namespace_axis(node, visible) ⇒ Object 



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
 
# File 'lib/xmlcanonicalizer.rb', line 212

def write_namespace_axis(node, visible)
  doc = node.document()
  has_empty_namespace = false
  list = Array.new()
  cur = node
  #while ((cur != nil) && (cur != doc) && (cur.node_type() != :document)) 
  namespaces = cur.node_namespaces()
  namespaces.each{|prefix|
    next if ((prefix == "xmlns") && (node.namespace(prefix) == "")) 
    namespace = cur.namespace(prefix)
    next if (is_namespace_node(namespace))
    next if (node.namespace(prefix) != cur.namespace(prefix))
    next if (prefix == "xml" && namespace == "http://www.w3.org/XML/1998/namespace")
    next if (!is_node_visible(cur))
    rendered = is_namespace_rendered(prefix, namespace)
    @visibleNamespaces.push(NamespaceNode.new("xmlns:"+prefix,namespace)) if (visible)
    if ((!rendered) && !list.include?(prefix))
      list.push(prefix)
    end
    has_empty_namespace = true if (prefix == nil)
  }
  if (visible && !has_empty_namespace && !is_namespace_rendered(nil, nil)) 
    @res = @res + ' xmlns=""'
  end
  #TODO: ns of inclusive_list
#=begin
  if ((@prefix_list) && (node.to_s() == node.parent().to_s()))
    #list.push(node.prefix())
    @inclusive_namespaces.each{|ns|
      prefix = ns.prefix().split(":")[1]
      list.push(prefix) if (!list.include?(prefix) && (!node.attributes.prefixes.include?(prefix))) 
    }
		@prefix_list = nil
  end
#=end
  list.sort!()
  list.insert(0, "xmlns") unless list.delete("xmlns").nil?
  list.each{|prefix|
    next if (prefix == "")
		next if (@rendered_prefixes.include?(prefix))
		@rendered_prefixes.push(prefix)
    ns = node.namespace(prefix)
    ns = @preserve_element.namespace(prefix) if (ns == nil)
    @res = @res + normalize_string(" " + prefix + '="' + ns + '"', NODE_TYPE_TEXT) if (prefix == "xmlns")
    @res = @res + normalize_string(" xmlns:" + prefix + '="' + ns + '"', NODE_TYPE_TEXT) if (prefix != nil && prefix != "xmlns")
  }
  if (visible)
    @prevVisibleNamespacesStart = @prevVisibleNamespacesEnd
    @prevVisibleNamespacesEnd = @visibleNamespaces.size()	
  end
end

#write_node(node) ⇒ Object 



167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
 
# File 'lib/xmlcanonicalizer.rb', line 167

def write_node(node)
  visible = is_node_visible(node)
  if ((node.node_type() == :text) && white_text?(node.value()))
    res = node.value()
    res.gsub("\r\n","\n")
    #res = res.delete(" ").delete("\t")
    res.delete("\r")
    @res = @res + res
    #write_text_node(node,visible) if (@state == INSIDE_DOC_ELEMENT)
    return
  end
  if (node.node_type() == :text)
    write_text_node(node, visible)
    return
  end		
  if (node.node_type() == :element)
    write_element_node(node, visible) if (!node.rendered?())
  node.rendered=(true)
  end
  if (node.node_type() == :processing_instruction)
  end
  if (node.node_type() == :comment)
  end
end

#write_text_node(node, visible) ⇒ Object

input.each_byte{|b| if (b ==60 && (type == NODE_TYPE_ATTRIBUTE || is_text_node(type))) sb = sb + “&lt;” elsif (b == 62 && is_text_node(type)) sb = sb + “&gt;” elsif (b == 38 && (is_text_node(type) || is_text_node(type))) #Ampersand sb = sb + “&amp;” elsif (b == 34 && is_text_node(type)) #Quote sb = sb + “&quot;” elsif (b == 9 && is_text_node(type)) #Tabulator sb = sb + “&#x9;” elsif (b == 11 && is_text_node(type)) #CR sb = sb + “&#xA;” elsif (b == 13 && (type == NODE_TYPE_ATTRIBUTE || (is_text_node(type) && type != NODE_TYPE_WHITESPACE) || type == NODE_TYPE_COMMENT || type == NODE_TYPE_PI)) sb = sb + “&#xD;” elsif (b == 13) next else sb = sb.concat(b) end } sb end



363
364
365
366
367
 
# File 'lib/xmlcanonicalizer.rb', line 363

def write_text_node(node, visible)
  if (visible)
    @res = @res + normalize_string(node.value(), node.node_type())
  end
end