multi_xml 0.2.2 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
Potentially problematic release.
This version of multi_xml might be problematic. Click here for more details.
- data/.autotest +1 -0
- data/.travis.yml +7 -0
- data/.yardopts +1 -1
- data/Gemfile +3 -3
- data/{LICENSE.mkd → LICENSE.md} +0 -0
- data/{README.mkd → README.md} +37 -7
- data/Rakefile +3 -1
- data/lib/multi_xml.rb +53 -44
- data/lib/multi_xml/parsers/libxml.rb +13 -62
- data/lib/multi_xml/parsers/libxml2_parser.rb +66 -0
- data/lib/multi_xml/parsers/nokogiri.rb +16 -63
- data/lib/multi_xml/parsers/rexml.rb +8 -20
- data/lib/multi_xml/version.rb +1 -1
- data/multi_xml.gemspec +20 -22
- data/spec/helper.rb +0 -1
- data/spec/multi_xml_spec.rb +14 -551
- data/spec/parser_shared_example.rb +550 -0
- metadata +80 -94
- data/lib/multi_xml/core_extensions.rb +0 -108
@@ -0,0 +1,550 @@
|
|
1
|
+
shared_examples_for "a parser" do |parser|
|
2
|
+
|
3
|
+
before do
|
4
|
+
begin
|
5
|
+
MultiXml.parser = parser
|
6
|
+
rescue LoadError
|
7
|
+
pending "Parser #{parser} couldn't be loaded"
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
describe ".parse" do
|
12
|
+
context "a blank string" do
|
13
|
+
before do
|
14
|
+
@xml = ''
|
15
|
+
end
|
16
|
+
|
17
|
+
it "should return an empty Hash" do
|
18
|
+
MultiXml.parse(@xml).should == {}
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
context "a whitespace string" do
|
23
|
+
before do
|
24
|
+
@xml = ' '
|
25
|
+
end
|
26
|
+
|
27
|
+
it "should return an empty Hash" do
|
28
|
+
MultiXml.parse(@xml).should == {}
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
context "an invalid XML document" do
|
33
|
+
before do
|
34
|
+
@xml = '<open></close>'
|
35
|
+
end
|
36
|
+
|
37
|
+
it "should raise MultiXml::ParseError" do
|
38
|
+
lambda do
|
39
|
+
MultiXml.parse(@xml)
|
40
|
+
end.should raise_error(MultiXml::ParseError)
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
context "a valid XML document" do
|
45
|
+
before do
|
46
|
+
@xml = '<user/>'
|
47
|
+
end
|
48
|
+
|
49
|
+
it "should parse correctly" do
|
50
|
+
MultiXml.parse(@xml).should == {'user' => nil}
|
51
|
+
end
|
52
|
+
|
53
|
+
context "with CDATA" do
|
54
|
+
before do
|
55
|
+
@xml = '<user><![CDATA[Erik Michaels-Ober]]></user>'
|
56
|
+
end
|
57
|
+
|
58
|
+
it "should return the correct CDATA" do
|
59
|
+
MultiXml.parse(@xml)['user'].should == "Erik Michaels-Ober"
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
context "with content" do
|
64
|
+
before do
|
65
|
+
@xml = '<user>Erik Michaels-Ober</user>'
|
66
|
+
end
|
67
|
+
|
68
|
+
it "should return the correct content" do
|
69
|
+
MultiXml.parse(@xml)['user'].should == "Erik Michaels-Ober"
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
context "with an attribute" do
|
74
|
+
before do
|
75
|
+
@xml = '<user name="Erik Michaels-Ober"/>'
|
76
|
+
end
|
77
|
+
|
78
|
+
it "should return the correct attribute" do
|
79
|
+
MultiXml.parse(@xml)['user']['name'].should == "Erik Michaels-Ober"
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
context "with multiple attributes" do
|
84
|
+
before do
|
85
|
+
@xml = '<user name="Erik Michaels-Ober" screen_name="sferik"/>'
|
86
|
+
end
|
87
|
+
|
88
|
+
it "should return the correct attributes" do
|
89
|
+
MultiXml.parse(@xml)['user']['name'].should be == "Erik Michaels-Ober"
|
90
|
+
MultiXml.parse(@xml)['user']['screen_name'].should be == "sferik"
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
context "with :symbolize_keys => true" do
|
95
|
+
before do
|
96
|
+
@xml = '<user><name>Erik Michaels-Ober</name></user>'
|
97
|
+
end
|
98
|
+
|
99
|
+
it "should symbolize keys" do
|
100
|
+
MultiXml.parse(@xml, :symbolize_keys => true).should == {:user => {:name => "Erik Michaels-Ober"}}
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
context "when value is true" do
|
105
|
+
before do
|
106
|
+
pending
|
107
|
+
@xml = '<tag>true</tag>'
|
108
|
+
end
|
109
|
+
|
110
|
+
it "should return true" do
|
111
|
+
MultiXml.parse(@xml)['tag'].should be_true
|
112
|
+
end
|
113
|
+
end
|
114
|
+
|
115
|
+
context "when value is false" do
|
116
|
+
before do
|
117
|
+
pending
|
118
|
+
@xml = '<tag>false</tag>'
|
119
|
+
end
|
120
|
+
|
121
|
+
it "should return false" do
|
122
|
+
MultiXml.parse(@xml)['tag'].should be_false
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
context "when key is id" do
|
127
|
+
before do
|
128
|
+
pending
|
129
|
+
@xml = '<id>1</id>'
|
130
|
+
end
|
131
|
+
|
132
|
+
it "should return a Fixnum" do
|
133
|
+
MultiXml.parse(@xml)['id'].should be_a(Fixnum)
|
134
|
+
end
|
135
|
+
|
136
|
+
it "should return the correct number" do
|
137
|
+
MultiXml.parse(@xml)['id'].should == 1
|
138
|
+
end
|
139
|
+
end
|
140
|
+
|
141
|
+
context "when key contains _id" do
|
142
|
+
before do
|
143
|
+
pending
|
144
|
+
@xml = '<tag_id>1</tag_id>'
|
145
|
+
end
|
146
|
+
|
147
|
+
it "should return a Fixnum" do
|
148
|
+
MultiXml.parse(@xml)['tag_id'].should be_a(Fixnum)
|
149
|
+
end
|
150
|
+
|
151
|
+
it "should return the correct number" do
|
152
|
+
MultiXml.parse(@xml)['tag_id'].should == 1
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
context "with an attribute type=\"boolean\"" do
|
157
|
+
%w(true false).each do |boolean|
|
158
|
+
context "when #{boolean}" do
|
159
|
+
it "should return #{boolean}" do
|
160
|
+
xml = "<tag type=\"boolean\">#{boolean}</tag>"
|
161
|
+
MultiXml.parse(xml)['tag'].should instance_eval("be_#{boolean}")
|
162
|
+
end
|
163
|
+
end
|
164
|
+
end
|
165
|
+
|
166
|
+
context "when 1" do
|
167
|
+
before do
|
168
|
+
@xml = '<tag type="boolean">1</tag>'
|
169
|
+
end
|
170
|
+
|
171
|
+
it "should return true" do
|
172
|
+
MultiXml.parse(@xml)['tag'].should be_true
|
173
|
+
end
|
174
|
+
end
|
175
|
+
|
176
|
+
context "when 0" do
|
177
|
+
before do
|
178
|
+
@xml = '<tag type="boolean">0</tag>'
|
179
|
+
end
|
180
|
+
|
181
|
+
it "should return false" do
|
182
|
+
MultiXml.parse(@xml)['tag'].should be_false
|
183
|
+
end
|
184
|
+
end
|
185
|
+
end
|
186
|
+
|
187
|
+
context "with an attribute type=\"integer\"" do
|
188
|
+
context "with a positive integer" do
|
189
|
+
before do
|
190
|
+
@xml = '<tag type="integer">1</tag>'
|
191
|
+
end
|
192
|
+
|
193
|
+
it "should return a Fixnum" do
|
194
|
+
MultiXml.parse(@xml)['tag'].should be_a(Fixnum)
|
195
|
+
end
|
196
|
+
|
197
|
+
it "should return a positive number" do
|
198
|
+
MultiXml.parse(@xml)['tag'].should > 0
|
199
|
+
end
|
200
|
+
|
201
|
+
it "should return the correct number" do
|
202
|
+
MultiXml.parse(@xml)['tag'].should == 1
|
203
|
+
end
|
204
|
+
end
|
205
|
+
|
206
|
+
context "with a negative integer" do
|
207
|
+
before do
|
208
|
+
@xml = '<tag type="integer">-1</tag>'
|
209
|
+
end
|
210
|
+
|
211
|
+
it "should return a Fixnum" do
|
212
|
+
MultiXml.parse(@xml)['tag'].should be_a(Fixnum)
|
213
|
+
end
|
214
|
+
|
215
|
+
it "should return a negative number" do
|
216
|
+
MultiXml.parse(@xml)['tag'].should < 0
|
217
|
+
end
|
218
|
+
|
219
|
+
it "should return the correct number" do
|
220
|
+
MultiXml.parse(@xml)['tag'].should == -1
|
221
|
+
end
|
222
|
+
end
|
223
|
+
end
|
224
|
+
|
225
|
+
context "with an attribute type=\"string\"" do
|
226
|
+
before do
|
227
|
+
@xml = '<tag type="string"></tag>'
|
228
|
+
end
|
229
|
+
|
230
|
+
it "should return a String" do
|
231
|
+
MultiXml.parse(@xml)['tag'].should be_a(String)
|
232
|
+
end
|
233
|
+
|
234
|
+
it "should return the correct string" do
|
235
|
+
MultiXml.parse(@xml)['tag'].should == ""
|
236
|
+
end
|
237
|
+
end
|
238
|
+
|
239
|
+
context "with an attribute type=\"date\"" do
|
240
|
+
before do
|
241
|
+
@xml = '<tag type="date">1970-01-01</tag>'
|
242
|
+
end
|
243
|
+
|
244
|
+
it "should return a Date" do
|
245
|
+
MultiXml.parse(@xml)['tag'].should be_a(Date)
|
246
|
+
end
|
247
|
+
|
248
|
+
it "should return the correct date" do
|
249
|
+
MultiXml.parse(@xml)['tag'].should == Date.parse('1970-01-01')
|
250
|
+
end
|
251
|
+
end
|
252
|
+
|
253
|
+
context "with an attribute type=\"datetime\"" do
|
254
|
+
before do
|
255
|
+
@xml = '<tag type="datetime">1970-01-01 00:00</tag>'
|
256
|
+
end
|
257
|
+
|
258
|
+
it "should return a Time" do
|
259
|
+
MultiXml.parse(@xml)['tag'].should be_a(Time)
|
260
|
+
end
|
261
|
+
|
262
|
+
it "should return the correct time" do
|
263
|
+
MultiXml.parse(@xml)['tag'].should == Time.parse('1970-01-01 00:00')
|
264
|
+
end
|
265
|
+
end
|
266
|
+
|
267
|
+
context "with an attribute type=\"dateTime\"" do
|
268
|
+
before do
|
269
|
+
@xml = '<tag type="datetime">1970-01-01 00:00</tag>'
|
270
|
+
end
|
271
|
+
|
272
|
+
it "should return a Time" do
|
273
|
+
MultiXml.parse(@xml)['tag'].should be_a(Time)
|
274
|
+
end
|
275
|
+
|
276
|
+
it "should return the correct time" do
|
277
|
+
MultiXml.parse(@xml)['tag'].should == Time.parse('1970-01-01 00:00')
|
278
|
+
end
|
279
|
+
end
|
280
|
+
|
281
|
+
context "with an attribute type=\"double\"" do
|
282
|
+
before do
|
283
|
+
@xml = '<tag type="double">3.14159265358979</tag>'
|
284
|
+
end
|
285
|
+
|
286
|
+
it "should return a Float" do
|
287
|
+
MultiXml.parse(@xml)['tag'].should be_a(Float)
|
288
|
+
end
|
289
|
+
|
290
|
+
it "should return the correct number" do
|
291
|
+
MultiXml.parse(@xml)['tag'].should == 3.14159265358979
|
292
|
+
end
|
293
|
+
end
|
294
|
+
|
295
|
+
context "with an attribute type=\"decimal\"" do
|
296
|
+
before do
|
297
|
+
@xml = '<tag type="decimal">3.14159265358979323846264338327950288419716939937510</tag>'
|
298
|
+
end
|
299
|
+
|
300
|
+
it "should return a BigDecimal" do
|
301
|
+
MultiXml.parse(@xml)['tag'].should be_a(BigDecimal)
|
302
|
+
end
|
303
|
+
|
304
|
+
it "should return the correct number" do
|
305
|
+
MultiXml.parse(@xml)['tag'].should == 3.14159265358979323846264338327950288419716939937510
|
306
|
+
end
|
307
|
+
end
|
308
|
+
|
309
|
+
context "with an attribute type=\"base64Binary\"" do
|
310
|
+
before do
|
311
|
+
@xml = '<tag type="base64Binary">aW1hZ2UucG5n</tag>'
|
312
|
+
end
|
313
|
+
|
314
|
+
it "should return a String" do
|
315
|
+
MultiXml.parse(@xml)['tag'].should be_a(String)
|
316
|
+
end
|
317
|
+
|
318
|
+
it "should return the correct string" do
|
319
|
+
MultiXml.parse(@xml)['tag'].should == "image.png"
|
320
|
+
end
|
321
|
+
end
|
322
|
+
|
323
|
+
context "with an attribute type=\"yaml\"" do
|
324
|
+
before do
|
325
|
+
@xml = "<tag type=\"yaml\">--- \n1: should return an integer\n:message: Have a nice day\narray: \n- should-have-dashes: true\n should_have_underscores: true\n</tag>"
|
326
|
+
end
|
327
|
+
|
328
|
+
it "should return a Hash" do
|
329
|
+
MultiXml.parse(@xml)['tag'].should be_a(Hash)
|
330
|
+
end
|
331
|
+
|
332
|
+
it "should return the correctly parsed YAML" do
|
333
|
+
MultiXml.parse(@xml)['tag'].should == {:message => "Have a nice day", 1 => "should return an integer", "array" => [{"should-have-dashes" => true, "should_have_underscores" => true}]}
|
334
|
+
end
|
335
|
+
end
|
336
|
+
|
337
|
+
context "with an attribute type=\"file\"" do
|
338
|
+
before do
|
339
|
+
@xml = '<tag type="file" name="data.txt" content_type="text/plain">ZGF0YQ==</tag>'
|
340
|
+
end
|
341
|
+
|
342
|
+
it "should return a StringIO" do
|
343
|
+
MultiXml.parse(@xml)['tag'].should be_a(StringIO)
|
344
|
+
end
|
345
|
+
|
346
|
+
it "should be decoded correctly" do
|
347
|
+
MultiXml.parse(@xml)['tag'].string.should == 'data'
|
348
|
+
end
|
349
|
+
|
350
|
+
it "should have the correct file name" do
|
351
|
+
MultiXml.parse(@xml)['tag'].original_filename.should == 'data.txt'
|
352
|
+
end
|
353
|
+
|
354
|
+
it "should have the correct content type" do
|
355
|
+
MultiXml.parse(@xml)['tag'].content_type.should == 'text/plain'
|
356
|
+
end
|
357
|
+
|
358
|
+
context "with missing name and content type" do
|
359
|
+
before do
|
360
|
+
@xml = '<tag type="file">ZGF0YQ==</tag>'
|
361
|
+
end
|
362
|
+
|
363
|
+
it "should return a StringIO" do
|
364
|
+
MultiXml.parse(@xml)['tag'].should be_a(StringIO)
|
365
|
+
end
|
366
|
+
|
367
|
+
it "should be decoded correctly" do
|
368
|
+
MultiXml.parse(@xml)['tag'].string.should == 'data'
|
369
|
+
end
|
370
|
+
|
371
|
+
it "should have the default file name" do
|
372
|
+
MultiXml.parse(@xml)['tag'].original_filename.should == 'untitled'
|
373
|
+
end
|
374
|
+
|
375
|
+
it "should have the default content type" do
|
376
|
+
MultiXml.parse(@xml)['tag'].content_type.should == 'application/octet-stream'
|
377
|
+
end
|
378
|
+
end
|
379
|
+
end
|
380
|
+
|
381
|
+
context "with an attribute type=\"array\"" do
|
382
|
+
before do
|
383
|
+
@xml = '<users type="array"><user>Erik Michaels-Ober</user><user>Wynn Netherland</user></users>'
|
384
|
+
end
|
385
|
+
|
386
|
+
it "should return an Array" do
|
387
|
+
MultiXml.parse(@xml)['users'].should be_a(Array)
|
388
|
+
end
|
389
|
+
|
390
|
+
it "should return the correct array" do
|
391
|
+
MultiXml.parse(@xml)['users'].should == ["Erik Michaels-Ober", "Wynn Netherland"]
|
392
|
+
end
|
393
|
+
end
|
394
|
+
|
395
|
+
%w(integer boolean date datetime yaml file).each do |type|
|
396
|
+
context "with an empty attribute type=\"#{type}\"" do
|
397
|
+
before do
|
398
|
+
@xml = "<tag type=\"#{type}\"/>"
|
399
|
+
end
|
400
|
+
|
401
|
+
it "should return nil" do
|
402
|
+
MultiXml.parse(@xml)['tag'].should be_nil
|
403
|
+
end
|
404
|
+
end
|
405
|
+
end
|
406
|
+
|
407
|
+
context "with an empty attribute type=\"array\"" do
|
408
|
+
before do
|
409
|
+
@xml = '<tag type="array"/>'
|
410
|
+
end
|
411
|
+
|
412
|
+
it "should return an empty Array" do
|
413
|
+
MultiXml.parse(@xml)['tag'].should == []
|
414
|
+
end
|
415
|
+
|
416
|
+
context "with whitespace" do
|
417
|
+
before do
|
418
|
+
@xml = '<tag type="array"> </tag>'
|
419
|
+
end
|
420
|
+
|
421
|
+
it "should return an empty Array" do
|
422
|
+
MultiXml.parse(@xml)['tag'].should == []
|
423
|
+
end
|
424
|
+
end
|
425
|
+
end
|
426
|
+
|
427
|
+
context "with XML entities" do
|
428
|
+
before do
|
429
|
+
@xml_entities = {
|
430
|
+
"<" => "<",
|
431
|
+
">" => ">",
|
432
|
+
'"' => """,
|
433
|
+
"'" => "'",
|
434
|
+
"&" => "&"
|
435
|
+
}
|
436
|
+
end
|
437
|
+
|
438
|
+
context "in content" do
|
439
|
+
it "should return unescaped XML entities" do
|
440
|
+
@xml_entities.each do |key, value|
|
441
|
+
xml = "<tag>#{value}</tag>"
|
442
|
+
MultiXml.parse(xml)['tag'].should == key
|
443
|
+
end
|
444
|
+
end
|
445
|
+
end
|
446
|
+
|
447
|
+
context "in attribute" do
|
448
|
+
it "should return unescaped XML entities" do
|
449
|
+
@xml_entities.each do |key, value|
|
450
|
+
xml = "<tag attribute=\"#{value}\"/>"
|
451
|
+
MultiXml.parse(xml)['tag']['attribute'].should == key
|
452
|
+
end
|
453
|
+
end
|
454
|
+
end
|
455
|
+
end
|
456
|
+
|
457
|
+
context "with dasherized tag" do
|
458
|
+
before do
|
459
|
+
@xml = '<tag-1/>'
|
460
|
+
end
|
461
|
+
|
462
|
+
it "should return undasherize tag" do
|
463
|
+
MultiXml.parse(@xml).keys.should include('tag_1')
|
464
|
+
end
|
465
|
+
end
|
466
|
+
|
467
|
+
context "with dasherized attribute" do
|
468
|
+
before do
|
469
|
+
@xml = '<tag attribute-1="1"></tag>'
|
470
|
+
end
|
471
|
+
|
472
|
+
it "should return undasherize attribute" do
|
473
|
+
MultiXml.parse(@xml)['tag'].keys.should include('attribute_1')
|
474
|
+
end
|
475
|
+
end
|
476
|
+
|
477
|
+
context "with children" do
|
478
|
+
context "with attributes" do
|
479
|
+
before do
|
480
|
+
@xml = '<users><user name="Erik Michaels-Ober"/></users>'
|
481
|
+
end
|
482
|
+
|
483
|
+
it "should return the correct attributes" do
|
484
|
+
MultiXml.parse(@xml)['users']['user']['name'].should == "Erik Michaels-Ober"
|
485
|
+
end
|
486
|
+
end
|
487
|
+
|
488
|
+
context "with text" do
|
489
|
+
before do
|
490
|
+
@xml = '<user><name>Erik Michaels-Ober</name></user>'
|
491
|
+
end
|
492
|
+
|
493
|
+
it "should return the correct text" do
|
494
|
+
MultiXml.parse(@xml)['user']['name'].should == "Erik Michaels-Ober"
|
495
|
+
end
|
496
|
+
end
|
497
|
+
|
498
|
+
context "with an unrecognized attribute type" do
|
499
|
+
before do
|
500
|
+
@xml = '<user type="admin"><name>Erik Michaels-Ober</name></user>'
|
501
|
+
end
|
502
|
+
|
503
|
+
it "should pass through the type" do
|
504
|
+
MultiXml.parse(@xml)['user']['type'].should == 'admin'
|
505
|
+
end
|
506
|
+
end
|
507
|
+
|
508
|
+
context "with newlines and whitespace" do
|
509
|
+
before do
|
510
|
+
@xml = <<-XML
|
511
|
+
<user>
|
512
|
+
<name>Erik Michaels-Ober</name>
|
513
|
+
</user>
|
514
|
+
XML
|
515
|
+
end
|
516
|
+
|
517
|
+
it "should parse correctly" do
|
518
|
+
MultiXml.parse(@xml).should == {"user" => {"name" => "Erik Michaels-Ober"}}
|
519
|
+
end
|
520
|
+
end
|
521
|
+
|
522
|
+
# Babies having babies
|
523
|
+
context "with children" do
|
524
|
+
before do
|
525
|
+
@xml = '<users><user name="Erik Michaels-Ober"><status text="Hello"/></user></users>'
|
526
|
+
end
|
527
|
+
|
528
|
+
it "should parse correctly" do
|
529
|
+
MultiXml.parse(@xml).should == {"users" => {"user" => {"name" => "Erik Michaels-Ober", "status" => {"text" => "Hello"}}}}
|
530
|
+
end
|
531
|
+
end
|
532
|
+
end
|
533
|
+
|
534
|
+
context "with sibling children" do
|
535
|
+
before do
|
536
|
+
@xml = '<users><user>Erik Michaels-Ober</user><user>Wynn Netherland</user></users>'
|
537
|
+
end
|
538
|
+
|
539
|
+
it "should return an Array" do
|
540
|
+
MultiXml.parse(@xml)['users']['user'].should be_a(Array)
|
541
|
+
end
|
542
|
+
|
543
|
+
it "should parse correctly" do
|
544
|
+
MultiXml.parse(@xml).should == {"users" => {"user" => ["Erik Michaels-Ober", "Wynn Netherland"]}}
|
545
|
+
end
|
546
|
+
end
|
547
|
+
end
|
548
|
+
end
|
549
|
+
|
550
|
+
end
|