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
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
|
require 'rexml/namespace'
require 'rexml/xmltokens'
require 'rexml/parsers/xpathparser'
module REXML
# You don't want to use this class. Really. Use XPath, which is a wrapper
# for this class. Believe me. You don't want to poke around in here.
# There is strange, dark magic at work in this code. Beware. Go back! Go
# back while you still can!
class XPathParser
include XMLTokens
LITERAL = /^'([^']*)'|^"([^"]*)"/u
def initialize( )
@parser = REXML::Parsers::XPathParser.new
@namespaces = {}
@variables = {}
end
def namespaces=( namespaces={} )
Functions::namespace_context = namespaces
@namespaces = namespaces
end
def variables=( vars={} )
Functions::variables = vars
@variables = vars
end
def parse path, nodeset
path_stack = @parser.parse( path )
#puts "PARSE: #{path} => #{path_stack.inspect}"
match( path_stack, nodeset )
end
def predicate path, nodeset
path_stack = @parser.predicate( path )
return Predicate( path_stack, nodeset )
end
def []=( variable_name, value )
@variables[ variable_name ] = value
end
private
def match( path_stack, nodeset )
while ( path_stack.size > 0 and nodeset.size > 0 )
#puts "PARSE: #{path_stack.inspect} '#{nodeset.collect{|n|n.type}.inspect}'"
nodeset = internal_parse( path_stack, nodeset )
#puts "NODESET: #{nodeset.size}"
#puts "PATH_STACK: #{path_stack.inspect}"
end
nodeset
end
def internal_parse path_stack, nodeset
return nodeset if nodeset.size == 0 or path_stack.size == 0
#puts "INTERNAL_PARSE: #{path_stack.inspect}, #{nodeset.collect{|n| n.type}.inspect}"
case path_stack.shift
when :document
return [ nodeset[0].root.parent ]
when :qname
prefix = path_stack.shift
name = path_stack.shift
#puts "QNAME #{prefix}#{prefix.size>0?':':''}#{name}"
n = nodeset.clone
ns = @namespaces[prefix]
ns = ns ? ns : ''
n.delete_if do |node|
# FIXME: This DOUBLES the time XPath searches take
ns = node.namespace( prefix ) if node.node_type == :element and ns == ''
#puts "NODE: '#{node.to_s}'; node.has_name?( #{name.inspect}, #{ns.inspect} ): #{ node.has_name?( name, ns )}; node.namespace() = #{node.namespace().inspect}; node.prefix = #{node.prefix().inspect}" if node.node_type == :element
!(node.node_type == :element and node.name == name and node.namespace == ns )
end
return n
when :any
n = nodeset.clone
n.delete_if { |node| node.node_type != :element }
return n
when :self
# THIS SPACE LEFT INTENTIONALLY BLANK
when :processing_instruction
target = path_stack.shift
n = nodeset.clone
n.delete_if do |node|
(node.node_type != :processing_instruction) or
( !target.nil? and ( node.target != target ) )
end
return n
when :text
#puts ":TEXT"
n = nodeset.clone
n.delete_if do |node|
#puts "#{node} :: #{node.node_type}"
node.node_type != :text
end
return n
when :comment
n = nodeset.clone
n.delete_if do |node|
node.node_type != :comment
end
return n
when :node
return nodeset
#n = nodeset.clone
#n.delete_if do |node|
# !node.node?
#end
#return n
# FIXME: I suspect the following XPath will fail:
# /a/*/*[1]
when :child
#puts "CHILD"
new_nodeset = []
nt = nil
for node in nodeset
nt = node.node_type
new_nodeset += node.children if nt == :element or nt == :document
end
#path_stack[0,(path_stack.size-ps_clone.size)] = []
return new_nodeset
when :literal
literal = path_stack.shift
if literal =~ /^\d+(\.\d+)?$/
return ($1 ? literal.to_f : literal.to_i)
end
#puts "RETURNING '#{literal}'"
return literal
when :attribute
#puts ":ATTRIBUTE"
new_nodeset = []
case path_stack.shift
when :qname
prefix = path_stack.shift
name = path_stack.shift
for element in nodeset
if element.node_type == :element
#puts element.name
#puts "looking for attribute #{name} in '#{@namespaces[prefix]}'"
attr = element.attribute( name, @namespaces[prefix] )
#puts ":ATTRIBUTE: attr => #{attr}"
new_nodeset << attr if attr
end
end
when :any
for element in nodeset
if element.node_type == :element
attr = element.attributes
end
end
end
#puts "RETURNING #{new_nodeset.collect{|n|n.to_s}.inspect}"
return new_nodeset
when :parent
return internal_parse( path_stack, nodeset.collect{|n| n.parent}.compact )
when :ancestor
#puts "ANCESTOR"
new_nodeset = []
for node in nodeset
while node.parent
node = node.parent
new_nodeset << node unless new_nodeset.include? node
end
end
#nodeset = new_nodeset.uniq
return new_nodeset
when :ancestor_or_self
new_nodeset = []
for node in nodeset
if node.node_type == :element
new_nodeset << node
while ( node.parent )
node = node.parent
new_nodeset << node unless new_nodeset.includes? node
end
end
end
#nodeset = new_nodeset.uniq
return new_nodeset
when :predicate
#puts "@"*80
#puts "NODESET = #{nodeset.collect{|n|n.to_s}.inspect}"
predicate = path_stack.shift
new_nodeset = []
Functions::size = nodeset.size
nodeset.size.times do |index|
node = nodeset[index]
Functions::node = node
Functions::index = index+1
#puts "Node #{node} and index=#{index+1}"
result = Predicate( predicate, node )
#puts "Predicate returned #{result} (#{result.type}) for #{node.type}"
if result.kind_of? Numeric
#puts "#{result} == #{index} => #{result == index}"
new_nodeset << node if result == (index+1)
elsif result.instance_of? Array
new_nodeset << node if result.size > 0
else
new_nodeset << node if result
end
end
#puts "Nodeset after predicate #{predicate.inspect} has #{new_nodeset.size} nodes"
#puts "NODESET: #{new_nodeset.collect{|n|n.to_s}.inspect}"
return new_nodeset
when :descendant_or_self
rv = descendant_or_self( path_stack, nodeset )
path_stack.clear
return rv
when :descendant
#puts ":DESCENDANT"
results = []
nt = nil
for node in nodeset
nt = node.node_type
results += internal_parse( path_stack.clone.unshift( :descendant_or_self ),
node.children ) if nt == :element or nt == :document
end
return results
when :following_sibling
results = []
for node in nodeset
all_siblings = node.parent.children
current_index = all_siblings.index( node )
following_siblings = all_siblings[ current_index+1 .. -1 ]
results += internal_parse( path_stack.clone, following_siblings )
end
return results
when :preceding_sibling
results = []
for node in nodeset
all_siblings = node.parent.children
current_index = all_siblings.index( node )
preceding_siblings = all_siblings[ 0 .. current_index-1 ]
results += internal_parse( path_stack.clone, preceding_siblings )
end
return results
when :preceding
new_nodeset = []
for node in nodeset
new_nodeset += preceding( node )
end
return new_nodeset
when :following
new_nodeset = []
for node in nodeset
new_nodeset += following( node )
end
return new_nodeset
when :namespace
new_set = []
for node in nodeset
new_nodeset << node.namespace if node.node_type == :element or node.node_type == :attribute
end
return new_nodeset
when :variable
var_name = path_stack.shift
return @variables[ var_name ]
end
nodeset
end
##########################################################
# The next two methods are BAD MOJO!
# This is my achilles heel. If anybody thinks of a better
# way of doing this, be my guest. This really sucks, but
# it took me three days to get it to work at all.
# ########################################################
def descendant_or_self( path_stack, nodeset )
rs = []
d_o_s( path_stack, nodeset, rs )
#puts "RS = #{rs.collect{|n|n.to_s}.inspect}"
rs.flatten.compact
end
def d_o_s( p, ns, r )
#puts r.collect{|n|n.to_s}.inspect
#puts ns.collect{|n|n.to_s}.inspect
nt = nil
ns.each_index do |i|
n = ns[i]
x = match( p.clone, [ n ] )
#puts "Got a match on #{p.inspect} for #{ns.collect{|n|n.to_s+"("+n.type.to_s+")"}.inspect}"
nt = n.node_type
d_o_s( p, n.children, x ) if nt == :element or nt == :document
r[i,0] = [x] if x.size > 0
end
end
def recurse( nodeset, &block )
for node in nodeset
yield node
recurse( node, &block ) if node.node_type == :element
end
end
# Given a predicate, a node, and a context, evaluates to true or false.
def Predicate( predicate, node )
predicate = predicate.clone
#puts "#"*20
#puts "Predicate( #{predicate.inspect}, #{node.type} )"
results = []
case (predicate[0])
when :and, :or, :eq, :neq, :lt, :lteq, :gt, :gteq
eq = predicate.shift
left = Predicate( predicate.shift, node )
right = Predicate( predicate.shift, node )
return equality_relational_compare( left, eq, right )
when :div, :mod, :mult, :plus, :minus, :union
op = predicate.shift
left = Predicate( predicate.shift, node )
right = Predicate( predicate.shift, node )
left = Functions::number( left )
right = Functions::number( right )
case op
when :div
return left.to_f / right.to_f
when :mod
return left % right
when :mult
return left * right
when :plus
return left + right
when :minus
return left - right
when :union
return (left | right)
end
when :neg
predicate.shift
operand = Functions::number(Predicate( predicate, node ))
return -operand
when :not
predicate.shift
return !Predicate( predicate.shift, node )
when :function
predicate.shift
func_name = predicate.shift.tr('-', '_')
arguments = predicate.shift
#puts "\nFUNCTION: #{func_name}"
#puts "ARGUMENTS: #{arguments.inspect} #{node.to_s}"
args = arguments.collect { |arg| Predicate( arg, node ) }
#puts "FUNCTION: #{func_name}( #{args.collect{|n|n.to_s}.inspect} )"
result = Functions.send( func_name, *args )
#puts "RESULTS: #{result.inspect}"
return result
else
return match( predicate, [ node ] )
end
end
# Builds a nodeset of all of the following nodes of the supplied node,
# in document order
def following( node )
all_siblings = node.parent.children
current_index = all_siblings.index( node )
following_siblings = all_siblings[ current_index+1 .. -1 ]
following = []
recurse( following_siblings ) { |node| following << node }
following.shift
#puts "following is returning #{puta following}"
following
end
# Builds a nodeset of all of the preceding nodes of the supplied node,
# in reverse document order
def preceding( node )
all_siblings = node.parent.children
current_index = all_siblings.index( node )
preceding_siblings = all_siblings[ 0 .. current_index-1 ]
preceding_siblings.reverse!
preceding = []
recurse( preceding_siblings ) { |node| preceding << node }
preceding.reverse
end
def equality_relational_compare( set1, op, set2 )
#puts "EQ_REL_COMP: #{set1.to_s}, #{op}, #{set2.to_s}"
if set1.kind_of? Array and set2.kind_of? Array
if set1.size == 1 and set2.size == 1
set1 = set1[0]
set2 = set2[0]
else
set1.each do |i1|
i1 = i1.to_s
set2.each do |i2|
i2 = i2.to_s
return true if compare( i1, op, i2 )
end
end
return false
end
end
#puts "COMPARING VALUES"
# If one is nodeset and other is number, compare number to each item
# in nodeset s.t. number op number(string(item))
# If one is nodeset and other is string, compare string to each item
# in nodeset s.t. string op string(item)
# If one is nodeset and other is boolean, compare boolean to each item
# in nodeset s.t. boolean op boolean(item)
if set1.kind_of? Array or set2.kind_of? Array
#puts "ISA ARRAY"
if set1.kind_of? Array
a = set1
b = set2.to_s
else
a = set2
b = set1.to_s
end
case b
when 'true', 'false'
b = Functions::boolean( b )
for v in a
v = Functions::boolean(v)
return true if compare( v, op, b )
end
when /^\d+(\.\d+)?$/
b = Functions::number( b )
for v in a
v = Functions::number(v)
return true if compare( v, op, b )
end
else
b = Functions::string( b )
for v in a
v = Functions::string(v)
return true if compare( v, op, b )
end
end
else
# If neither is nodeset,
# If op is = or !=
# If either boolean, convert to boolean
# If either number, convert to number
# Else, convert to string
# Else
# Convert both to numbers and compare
s1 = set1.to_s
s2 = set2.to_s
#puts "EQ_REL_COMP: #{set1}=>#{s1}, #{set2}=>#{s2}"
if s1 == 'true' or s1 == 'false' or s2 == 'true' or s2 == 'false'
#puts "Functions::boolean(#{set1})=>#{Functions::boolean(set1)}"
#puts "Functions::boolean(#{set2})=>#{Functions::boolean(set2)}"
set1 = Functions::boolean( set1 )
set2 = Functions::boolean( set2 )
else
if op == :eq or op == :neq
if s1 =~ /^\d+(\.\d+)?$/ or s2 =~ /^\d+(\.\d+)?$/
set1 = Functions::number( s1 )
set2 = Functions::number( s2 )
else
set1 = Functions::string( set1 )
set2 = Functions::string( set2 )
end
else
set1 = Functions::number( set1 )
set2 = Functions::number( set2 )
end
end
#puts "EQ_REL_COMP: #{set1} #{op} #{set2}"
return compare( set1, op, set2 )
end
return false
end
def compare a, op, b
case op
when :eq
a == b
when :neq
a != b
when :lt
a < b
when :lteq
a <= b
when :gt
a > b
when :gteq
a >= b
when :and
a and b
when :or
a or b
else
false
end
end
end
end
|